Detection and Interactive Isolation of Faults in Steam Turbines To

download Detection and Interactive Isolation of Faults in Steam Turbines To

of 15

Transcript of Detection and Interactive Isolation of Faults in Steam Turbines To

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    1/15

    Detection and interactive isolation of faults in steam turbines to

    support maintenance decisions

    Christer Karlsson a,*, Jaime Arriagada b, Magnus Genrup b

    a Mälardalen University, Department of Public Technology, Process Diagnostics Group, P.O. Box 883, 721 23 Västerås, Swedenb Lund University – Lund Institute of Technology, Department of Heat and Power Engineering, Division of Thermal Power Engineering,

    P.O. Box 118, 221 00 Lund, Sweden

    a r t i c l e i n f o

     Article history:

    Received 30 January 2007

    Received in revised form 30 June 2008

    Accepted 21 August 2008

    Available online 9 September 2008

    Keywords:

    Steam turbine maintenance

    Artificial neural network fault detection

    Bayesian network fault isolation

    Decision support

    a b s t r a c t

    The maintenance of steam turbines is expensive, particularly if dismantling is required. A

    concept for the provision of support for the maintenance engineer in determining steam

    turbine status in relation to the recommended maintenance interval is presented here.

    The concept embodies an artificial neural network which is conditioned to recognise pat-

    terns known to be related to faults. The faults simulated are not known to be recognized

    on-line and the concept is in an early stage of development. An example of a Bayesian net-

    work structure containing expert knowledge is proposed to be used, in a dialogue with the

    operator, to isolate the root causes of a number of fault types. The aim is to be well

    informed about the statue of the turbine in order to take earlier and better informed main-

    tenance actions. The detection procedure has been validated in a simulation environment.

     2008 Elsevier B.V. All rights reserved.

    1. Introduction

    Most of the productive equipment in heat and power generating plants is subject to degradation and requires mainte-

    nance. Advice on when to carry out major overhauls and other maintenance operations is usually provided by the manufac-

    turers of the equipment. The intervals between these procedures are usually based on a periodic maintenance schedule. The

    single largest cost of keeping a steam turbine in operation is related to these activities [19], with dismantling being one of the

    most expensive procedures [3]. The dismantling itself introduces the risk of creating problems such as vibration and leakage.

    Monitoring and fault diagnostic systems for steam turbines are efficient means of preventing avoidable and costly turbine

    maintenance. There are examples of steam turbines operating for up to 17 years without dismantling [3]. This is only pos-

    sible with efficient monitoring of the turbine.

    If a steam turbine owner wishes to change from periodic maintenance to condition-based maintenance, on-line monitor-

    ing of the turbine performance is required to provide sufficient information to evaluate the risks of continued operation.

    Methods of determining steam turbine condition include thermodynamic calculations to determine turbine efficiency and

    leakage [7], and vibration analysis [13]. Methods that address detection and isolation have been reviewed from a risk assess-

    ment perspective [8], and research and methods aimed at solving the whole chain of tasks for diagnostics (including detec-

    tion and isolation) are presented by [18].

    In steam turbine engineering, the steps involved in determining the need for maintenance action include fault detection,

    isolation and identification. Faults are detected by observing abnormal patterns in data. Artificial neural networks (ANNs) are

    one means by which such patterns can be recognized [5]. ANNs ‘learn’ patterns from input provided either from plant data or

    1569-190X/$ - see front matter    2008 Elsevier B.V. All rights reserved.doi:10.1016/j.simpat.2008.08.013

    *   Corresponding author. Tel.: +46 21 101356; fax: +46 21 101370.

    E-mail address: [email protected] (C. Karlsson).

    Simulation Modelling Practice and Theory 16 (2008) 1689–1703

    Contents lists available at  ScienceDirect

    Simulation Modelling Practice and Theory

    j o u r n a l h o m e p a g e :   w w w . e l s e v i e r . c o m / l o c a t e/ s i m p a t

    mailto:[email protected]://www.sciencedirect.com/science/journal/1569190Xhttp://www.elsevier.com/locate/simpathttp://www.elsevier.com/locate/simpathttp://www.sciencedirect.com/science/journal/1569190Xmailto:[email protected]

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    2/15

    from extensive simulations and are therefore data-driven. Fault isolation can be performed by ANNs, but they do not fully

    explain the domain and human interaction is needed to compensate for the incomplete system domain knowledge. Isolation

    is a difficult task but among the possible methods for solving this kind of problem, Bayesian networks (BNs) have been found

    to be suitable [20]. The operator feeds evidence into a BN that handles uncertainties in variables. The structure of the BN

    makes it easy to monitor the effect of new evidence on the probability of a certain root cause.

    The operator of a heat and power plant solves most operational problems in co-operation with the maintenance staff, but

    there are some tasks that require additional support. The identification and isolation of faults that develop slowly is one such

    task. Our proposed concept for on-line decision support uses ANNs for fault detection and BNs for fault isolation. ANNs auto-

    mate the detection of faults, and BNs automate the isolation of faults to some degree. In order to be cost effective, this system

    is applied to only a small part of the domain in a heat and power plant – that which has the greatest impact on maintenance

    costs. The system is kept simple and focused on detection and decision support associated with the most expensive main-

    tenance. The system is demonstrated here in an application that only addresses problems that can be determined by ther-

    modynamic models and have impact on turbine efficiency.

    The concept is evaluated by detecting and isolating seven fault types introduced in a simulation of a steam turbine and

    surrounding equipment. Training data is from simulations of plant operation at 100% turbine load with the fault types pres-

    ent. An ANN is trained to detect patterns of several fault types. For one of the seven fault types, an expert network has been

    developed for a dialogue with the operator. The BNs for fault isolation are constructed from empirical knowledge of turbine

    faults [4,12,17] and faults in surrounding equipment [9]. The parts of the concept considered here are the fault detection and

    the fault isolation. Sensors in addition to those proposed here can increase the number of detectable faults and enhance per-

    formance of detection and isolation. The concept of using a combination of ANNs and a BN to provide a decision support

    structure to the operator is presented in the following text, along with a case study and description of fault types used to

    demonstrate the concept. Issues related to the selection of methods for each task and the division of the work between these

    methods are discussed. Finally we discuss the results and the structure and draw conclusions from the study.

    2. Concept of the fault diagnosis system

    Previous work by this joint research group, has demonstrated that ANNs have excellent capabilities for detecting faults in

    thermal power systems. This includes the important capacity to detect incipient faults to permit the generation of early

    warnings [1]. However, we have not achieved a satisfactory ANN approach to the performance of root cause analysis. On

    the other hand, attempted solution of similar tasks through the application of BNs has revealed their inherent ability to per-

    form root cause analysis [11,22]. Discussion of the pros and cons of both tools has led to the basic idea presented in this

    work: the combination of ANN and BNs, both derived from the artificial intelligence field.

    One of the key features of the concept is the dialogue with the operator. The dialogue gives the expert system access to

    the common sense of the operator, his eyes and ears, and his ability to quantify relative measures (if a motor is in good or badcondition, for example). The following paragraphs and Fig. 1 describe the working of the concept from detection to root cause

    isolation.

    When there is no sensor fault and the ANNs report a developing type 7 fault in the steam cycle, information about the

    detection of this fault type is sent to the operator. The fault types considered are those which do not require immediate ac-

    tions, like shutdown, so the operator has time to consider the appropriate course of action. His next task is to isolate the fault

    to one of causes of the type 7 fault. This task is carried out by collecting evidence in the form of observations such as manual

    temperature measurements, a check of the valve stem position, estimate of equipment status, etc. This evidence is important

    Fig. 1.   Fault diagnostic system.

    1690   C. Karlsson et al./ Simulation Modelling Practice and Theory 16 (2008) 1689–1703

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    3/15

    in distinguishing one root cause from another, but is not important enough to be monitored on-line for process operation

    under normal conditions. This is another example of the importance of the operator as a user of informed judgment in

    the context of the constraints on the system, particularly in isolating faults.

    Inputs to the BN from the operator via ‘Observations’ affect the probability of different root causes. When the operator

    decides that enough evidence has been collected, he can continue to interact with the system to test alternative hypotheses.

    An important issue here is that maintenance decisions are not solely influenced by the plant owner. The maintenance

    instructions of the equipment manufacturer are also important. The insurance company that insures the equipment and

    other stakeholders must be convinced of the benefits of the new maintenance strategy. Their requirements must also be ta-

    ken into account.

    In this study, the ANNs for fault detection and the BNs for fault isolation are applied in a steam turbine simulation. The

    concept is applied to a simulation of a steam turbine and its surrounding components (Fig. 2). The application in the example

    illustrates how maintenance decisions based on measurements can be supported. Additional measurements that provide

    information about the condition of the plant and steam turbine can be incorporated to increase the effectiveness of the fault

    detection and isolation. Performance of the detection and isolation tasks presented here usually requires special perfor-

    mance tests performed by experts. The detection levels of the faults are very low and are not achievable using thresholds

    on single measurement devices.

    We believe that this concept helps operators and plant owners to take appropriate maintenance actions both earlier and

    based on a better foundation. The concept does not aim to replace steam turbine experts, but to provide more relevant infor-

    mation to support improved decision-making. When the correct information about the turbine status is available, a steam

    turbine expert is probably consulted at an earlier stage than in the absence of the detection–isolation system.

    3. Case study and fault types

    The case study of the steam turbine and plant components is presented briefly in this section and the fault types are

    described.

     3.1. Steam turbine and steam cycle components

    The thermal process studied is a biomass-fuelled heat and power co-generation plant with a flue gas condenser and cat-

    alyst flue gas cleaning. The boiler was installed in 1994 and has steam data 540 C, 100 bar(a) and generates 80 MWth before

    losses. The steam powers a turbine that generates up to 23 MWe. The process model is illustrated in Fig. 2 [9]. District heat-

    ing is obtained from two condensers that output a total of 55 MWth. The flue gas condenser for district heating is not in-

    cluded in the model. The previously developed process model included high and low pressure turbines, turbine gear,

    generator, condensers, preheaters, leakage condenser and seals [9]. The components manipulated for simulation of the faulttypes in the process model are illustrated in  Fig. 2 and further described in the next section.

     3.2. Fault types

    Dismantling of the turbine is the largest single maintenance cost for a heat and power plant and considerable savings in

    maintenance costs are made with each year that passes without dismantling the turbine. The fault types and their causes,

    Fig. 2.   Steam turbine and steam cycle [9, p. 136]. Fault types 1–7 and the indicated manipulated process components in the simulations.

    C. Karlsson et al. / Simulation Modelling Practice and Theory 16 (2008) 1689–1703   1691

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    4/15

    effects and in some cases treatments are presented. Seven fault types were selected from the literature and from the expe-

    rience of the authors [4,9,17,12]. Faults in the steam turbine and surrounding equipment considered are: (1) solid particle

    erosion on turbine first stage; (2) leakage in overflow valve; (3) fouling and deposits in stages 2 and 3; (4) fouling and depos-

    its in stage 4; (5) damaged shell and rotor sealing; (6) ageing and wear; and (7) fouling and gassing in the condenser.

    The system proposed is intended for a subset of faults with increased emphasis on some examples of faults that are dif-

    ficult to detect and may potentially cause major economic costs. The fault types 1, 3, 4, 5, and 6 have been chosen as exam-

    ples of errors that require dismantling of the turbine for verification and correction. Fault types 2 and 7 do not require

    dismantling of the turbine but in common with faults 1, 3, 4, 5, and 6 are hard to detect and isolate and can cause plant shut-

    down or damage of the turbine. In this context hard to detect means that the installed sensors alone are insufficient to isolate

    the root cause of the fault. Dialogue with the operator is needed to isolate the fault.

     3.2.1. Solid particle erosion on turbine first stage (type 1)

    Solid particle erosion in the steam path is due to exfoliation of iron oxide and magnetite particles from the high temper-

    ature section of the boiler  [4]. The impact of the particles on the first turbine stage causes damage to the blades (Fig. 3),

    which increases the swallowing capacity of the turbine, and decreases the efficiency of the turbine stage. Solid particle ero-

    sion can to some extent be avoided by using a bypass valve that leads the steam to the condenser during start-up. Other

    counter-measures to reduce the effects of solid particle erosion include the chemical treatment of the steam system to re-

    duce exfoliation, and armouring the particle removal system and turbine with erosion-resistant coatings,  [15]. Recently the

    use of fewer and larger blades in the first stage has been identified as the most important factor in eliminating solid particle

    erosion [26].

     3.2.2. Leakage in overflow valve (fault type 2)

    Leakage in the overflow valve can be due to a broken spindle [6] or solid particle erosion [4]. Leakage in the overflow valve

    causes loss of turbine performance [9]. Steam of high quality bypasses the first turbine stage and is either lost as condensate

    in the leakage condenser or re-enters the turbine at a lower pressure. The leakage can be detected by measuring the steam

    temperature downstream of the valve and by checking the valve position.

     3.2.3. Fouling and carry-over in the turbine steam path (fault types 3 and 4)

    Fouling originates from impurities in the raw water entering the steam system and from additives used in water process-

    ing. These impurities are transported from the boiler to the superheated steam by three different mechanisms: Mechanical

    carry-over, vaporous carry-over and attemperators (i.e. spray in a superheater) [17]. The degree of fouling and depositing is

    dependent on the boiler drum pressure level, the separation efficiency, spraying in superheaters, and other factors [21]. Foul-

    ing in the turbine steam path causes degradation of turbine performance. Deposits change the blade profile and increase the

    surface roughness as shown in Fig. 4. Compounds deposit on different turbine parts, depending on the temperature in the

    steam path. Fault type 3 consists of fouling and deposits in stages 2 and 3, and fault type 4 consists of fouling and deposits

    in stage 4. With correctly located sensors it is possible to distinguish between these two faults. Fouling and deposits can be

    reduced by generally improving the quality of the processed water and by reducing spray in the superheaters.

     3.2.4. Damaged shell and rotor sealing (fault type 5)

    Internal leakage can be caused by factors such as the erosion of seal tips and the rubbing of seals. Vibrations and axial

    displacement beyond design limits result in contact and rubbing between the seals of rotor and shell which cause deforma-

    Fig. 3.   Solid particle erosion, picture from  [26].

    1692   C. Karlsson et al./ Simulation Modelling Practice and Theory 16 (2008) 1689–1703

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    5/15

    tion of the seals (Fig. 5). Flow patterns in the steam path can also cause erosion of the seals. Internal leakage through imper-

    fect seals causes inefficient passage of high value steam past a turbine stage, decreasing the turbine efficiency [12]. The seal

    tip geometry is very important for the efficiency of the turbine as even a small deformation can cause a considerable increase

    in internal leakage.

     3.2.5. Ageing and wear (fault type 6)

    Increased surface roughness (Fig. 6) and degradation of mechanical components decrease turbine performance. The

    causes of ageing and wear include effects of temperature gradients, steam quality, and particles in steam and the effects

    are reduced turbine stage efficiency. This fault is detected as a uniform degradation in performance of the turbine.

     3.2.6. Fouling and gassing in the condenser (fault type 7)

    Fouling stems from residues in district heating water that build up and insulate the condenser tubes from the inside andthereby reduce heat transfer between the district heating water and the steam. Gassing occurs when non-condensable atmo-

    spheric gases form an insulating film on the tubes. This has a considerable impact on heat transfer between the steam and

    the condenser tubes even at low volume fractions of non-condensable gases [14]. In the low pressure part of the steam tur-

    bine the working pressures are lower than atmospheric pressure. External air continuously leaks into the condenser through

    low pressure turbine seals. This air should be removed from the condenser by vacuum pumps to avoid reduced heat transfer.

    Another source of non-condensable gases in the condenser is the raw water. The treatment of raw water removes most of 

    these gases but some can reach the condenser, where they accumulate. Air can also leak into the condenser through seals

    Fig. 4.  Fouling on turbine blades, detail of picture from  [7].

    Fig. 5.   Damaged (bent) rotor sealing inside black circle, detail of picture from  [7].

    C. Karlsson et al. / Simulation Modelling Practice and Theory 16 (2008) 1689–1703   1693

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    6/15

    and joints. Fouling and gassing reduces the efficiency of the condenser and increases the temperature difference at the con-

    denser outlet.

     3.3. Simulation of fault types

    The fault types reported in the literature referred to in this work have occurred in different power plants, and have been

    investigated and documented [4,6,9,12,17,21,26]. The authors know of no data set from a real process where a plant has been

    subject to all the faults presented.

    Production of artificial data is preferred to full-scale testing with physical components because of the known relationships

    between model parameters and fault types that make it possible to induce the faults in the mass and heat balance model, the

    lack of risk to plant personnel and equipment, the low cost of experiments and output that is free from problems such as

    outliers and missing data.

    Generation of process data with the fault types present was conducted using a set of district heating loads and process

    plant set-points. The outgoing steam pressure and temperature from the boiler were set to fixed values corresponding to

    the full load. This mimics the goal of the operator to maintain high pressure and goal temperature at the outlet of the boiler

    to maximize power generated in the turbine.

    The simulation output was used to ‘‘train” the ANN to recognise and memorise and fault type patterns. A model of a steam

    cycle [9] that included a steam turbine was used in the simulation. The fault types were simulated by manipulating param-

    eters in the model as indicated in the description of the fault types. The parameters and the associated fault types are sum-

    marized in Table 1. For fault types 2, 5 and 7, some relationships between cause and effect which permit the isolation of the

    root cause of the fault are known. For fault type 7 a BN structure has been developed for operator interaction as an example

    of how to isolate the root cause of this fault.

    4. Fault detection by artificial neural networks

    This section will explain how ANNs can be used to detect faults. The basic idea is to make use of the pattern recognition

    ability of ANNs to interpret combinations of data that would be difficult for a human expert to interpret. It is not possible to

    set alarm thresholds on single measurement devices to detect the faults simulated because of strong interactions between

    measurements, part load operations, and subtle changes in correlations between measurements that are related to the sim-

    ulated faults.

    Although the ANN procedure is similar to the procedure that is often used by operators in the control room, ANNs are able

    to handle systems with high degrees of interaction and multiple inputs and outputs. After the patterns have been recognised

    Fig. 6.   Increased turbine blade roughness  [12].

     Table 1

    Manipulated parameters in the process model by fault type

    Fault type Description Manipulated parameters

    1 Solid particle erosion Increased swallowing capacity and decreased efficiency for first stage

    2 Leakage in overflow valve Leakage flow through overflow valve

    3 Carry-over and deposits on stages 2 and 3 Turbine parts 2 and 3 decreased swallowing capacity and efficiency

    4 Carry-over and deposits on stage 4 Stage 4 decreased swallowing capacity and efficiency

    5 Damaged shell and rotor sealing Increased mass flow through sealing

    6 Ageing and wear Decreased efficiency for all turbine stages

    7 Fouling and gassing in the condensers Reduced heat transfer coefficients for both condensors

    1694   C. Karlsson et al./ Simulation Modelling Practice and Theory 16 (2008) 1689–1703

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    7/15

    they can be classified into groups. In this way, different combinations of data representing several malfunctions can be sorted

    into different groups of pre-determined faults.

    4.1. Artificial neural networks – a short introduction

    An ANN is a mathematical construction that can be used for modelling multi-dimensional systems, i.e. mapping of many

    inputs onto many outputs [10]. Among their most common applications are pattern recognition and multi-dimensional non-

    linear regression [5]. ANNs are not programmed as regular codes, instead they learn from experience. This experience is rep-

    resented by data that is used to train the ANN. An ANN is therefore classified as a data-driven system.

    There are different types of neural networks. The type of network depends on factors such as their architecture, the par-

    adigm used to train them, and the direction in which the data flows through them, among others. When the data flows

    strictly forward within an ANN, this is referred to as a feed-forward network. If feedback connections are introduced, then

    the ANN is a feedback or recurrent network (which can be used to introduce time-dependency, for instance). Feed-forward

    networks are trained in a supervised manner, meaning that the ANN is trained using patterns for which the desired output is

    known beforehand.

    The simplest feed-forward ANN consists of a single processing unit (or neuron) in which several parallel input signals

    [ x1, x2, . . . , xM ] are summed after they have been multiplied by their respective synaptic connection, i.e., the weights

    [w1, w2, . . ., wM ]. The resulting weighted signal (s) is the effective input to an activation or transfer function, F , which produces

    an output signal, y. An additional input, x0, with the fixed value of +1, is added in order to introduce an off-set to F . Its weight

    – w0  – is called the bias. The output from this simple network can be represented as a generic function of the inputs:

     y ¼  F XM i¼0

    wi xi

    !  ð1Þ

    where x0 = +1.

    If  F  is a threshold function, then this network is called Perceptron (see Fig. 7), which was first presented by Rosenblatt in

    1958 [16], and if  F  is a linear function, then this is a linear classifier called ADALINE, introduced by Widrow and Hoff in 1960

    [27]. Fig. 8 shows the threshold and the linear transfer functions.

    This basic configuration can be expanded both in depth and length, i.e., units can be added in parallel to form a layer of 

    neurons, and more layers can be added after each other. In the latter case, the ANN is referred to as a multi-layer feed-for-

    ward network, which is formed by an input layer, an output layer, and one or more hidden layers, as shown in  Fig. 9. The

    input signals, the weights and the outputs can be arranged in vectors and matrices, in order to simplify the mathematical

    notation.

    The input layer collects but does not process the information from the environment (the system to be modeled or ana-

    lyzed). The hidden and the output layers are the processing layers of the network. The weight matrices store the informationabout the underlying governing relationships of the actual system. They are the long-term memory of the ANN [23]. The out-

    put vector sends the response of the ANN back out to the environment. Every input unit corresponds to an input parameter,

    and every output neuron corresponds to an output parameter. This kind of ANN is called multi-layer perceptron (MLP), be-

    cause of its kinship to the Perceptron.

    It has been shown that one hidden layer is sufficient to carry out non-linear mapping of a continuous function if the num-

    ber of hidden neurons may be increased [10]. Therefore, we only consider two-layered MLPs in this study (the input layer is

    not counted in the number of layers). The generic expression for a two-layered MLP with  M  input signals, H  neurons in the

    hidden layer and N  outputs has the following form:

    Fig. 7.  The Perceptron.

    C. Karlsson et al. / Simulation Modelling Practice and Theory 16 (2008) 1689–1703   1695

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    8/15

     yk  ¼  F oXH  j¼0

    wkj  F hXM i¼0

    w ji xi

    ! !  ð2Þ

    where k  = 1,. . ., N ; x0 = +1.

    Depending on the application, it may not be necessary for the hidden and output layers to have the same activation func-

    tions. For this reason Eq. 2 uses different indices for each layer. The training of the MLP requires supervised learning, i.e., that

    a data set for which the targets are known is available. The most popular training algorithm is the backpropagation method,which was popularized by Rumelhart et al. in 1986 [24]. The principle is to present an input to the ANN, compare the output

    generated with the target, and to adjust the weights if there is an error. The updating of the weights continues until a least

    mean square (LMS) error function reaches the training goal. The weight correction is assumed to be in the decreasing direc-

    tion of the gradient of the error function with respect to the weights. During the training, the MLP learns the internal rep-

    resentations for the training data, and once the training is over, it can make predictions for new input patterns. This method

    requires activation functions which are differentiable in their entire range, such as the sigmoidal activation functions, for

    example. The two most popular functions are the logistic sigmoid and the tanh sigmoid, which are shown in  Fig. 10.

    In practice, the available training data set is divided into two portions – one for training, and a second for cross validation

    during training. When the performance of the ANN using this cross validation data set is satisfactory, the training procedure

    is stopped and the weights remaining are kept unchanged. The ANN is then tested further on a third independent data set in

    order to determine if it has a generalization capability, i.e. if its performance is also satisfactory for previously unknown pat-

    terns that were not used during the training phase [2]. An ANN with generalization capability is expected to perform well in

    a real case application for the system for which it has been trained if the data used for training is representative of thesystem.

    Fig. 10.   Sigmoidal activation functions.

    Fig. 8.   Threshold and linear transfer function.

    Fig. 9.  Feed-forward multi-layer network.

    1696   C. Karlsson et al./ Simulation Modelling Practice and Theory 16 (2008) 1689–1703

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    9/15

    4.2. Structure of the artificial neural network system for fault detection and selection of the input parameters

    ANNs of the type described above constitute the fault detection module of the monitoring system. Sensor validation is not

    considered in this theoretical example, but is needed in an industrial application.

    Twenty-three parameters that were measured in the real system are selected as input parameters for training the ANN,

    based on empirical evidence. The input parameters for ANN#1 and ANN#2 as shown in Table 2 have been recognized to be

    related to the faults studied. Later on, the same parameters are fed to the fault detection (the trained ANNs) in order to iden-

    tify them during the operation of the plant.

    In total 29 data sets were generated with a heat and mass balance model of the plant. These included one for the Healthy

    condition (H), and one for each of four different levels (25%, 50%, 75% and 100%) of each fault. The data sets for the Healthy

    and for Faulty conditions at 100% fault level were used to train different ANNs by a trial-and-error procedure where the num-

    ber of neurons in the hidden layer of the network was varied. The ANN that showed the best overall recognition capacity the

    faults contained 24 hidden neurons, and is referred to as ANN#1. ANN#1 contains eight output neurons, corresponding to

    the number of conditions to be diagnosed, one Healthy, and seven Faulty. The architecture of ANN#1 is therefore 22–24–

    8 (22 input neurons, 24 hidden neurons and 8 output neurons).

    The eight outputs are defined as binary, i.e. either 1 or 0. When input data is presented to the ANN, the output is 1 at the

    position corresponding to the predicting condition (H, F1, F2, F3, F4, F5, F6 or F7) and the remaining positions are occupied by

    zeros. The ANN produces values between 0 and 1 for each output neuron. The detection was divided into three classes: de-

    tected, not detected and not classified. Using arbitrarily chosen threshold values the fault is considered detected for values

    P0.7, not detected for values 60.3, and values in between are defined as not classified.

    When testing ANN#1 with independent data (including data at lower Fault Levels) it is capable of recognizing most of the

    faults that have been considered in this study. However, ANN#1 is not fully successful in distinguishing a healthy (H) steam

    turbine from a steam turbine with fault type 5 (F5). Therefore, a second ANN (called ANN#2) has been trained for this specific

    purpose. ANN#1 and ANN#2 are shown in  Fig. 11. As previously stated, the inputs to ANN#1 are parameters that are mea-

    sured in the real plant. ANN#2 is supplemented with an extra input parameter not previously measured in the facility but

    that was discovered to be necessary for ANN#2 to work well. The extra input is a pressure measurement between turbine

    stages inside the steam turbine and provides the extra information needed in order to better detect F5. Thus ANN#2 has one

    more neuron in its input layer, making a total of 23. The trained ANN#2 delivered good results when 30 neurons were uti-

    lized in its hidden layer. Using the same binary classification method as in ANN#1, ANN#2 has only two outputs. The result-

    ing architecture for ANN#2 is 23–30–2.

    Fig. 11 shows how the module capacity can be subsequently expanded to include the detection of new faults. It also

    shows how ANNs can be utilized to present an analysis indicating which measurement values should be added in order

    to improve the detection capability of the module. By adding the new measurement value to the second network in series

    with the first, a dramatically improved performance was obtained for fault type 5.

     Table 2

    List of input data to ANNs

    1. Load on steam turbine

    2. Flow principal steam before HP-Turbine

    3. Outlet temperature LP-Turbine

    4. Pressure at condenser 1

    5. Temperature at condenser 1

    6. Pressure at condenser 2

    7. Temperature feed-water

    8. Flow feed-water9. Pressure in deaerator

    10. Temperature in deaerator

    11. Temperature outgoing district heating water

    12. Temperature water after condenser 1

    13. Temperature district heating water after condenser 2

    14. Temperature district heating water after gland steam condenser

    15. Flow condensate to deaerator

    16. Active power

    17. Position control valve group 1

    18. Position control valve group 2

    19. Position turbine overflow valve

    20. Temperature of condensate after condenser

    21. Flow condensate after condenser 1

    22. Pressure in the turbine between two stages, also called steam flow in turbine

    Additional parameter for ANN #2 is

    23. Temperature at low pressure turbine extraction A0

    C. Karlsson et al. / Simulation Modelling Practice and Theory 16 (2008) 1689–1703   1697

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    10/15

    4.3. Results of the detection

    Table 3 shows the performance of ANN#1 when used alone in comparison to the performance of ANN#1 in combination

    with ANN#2, as shown in Fig. 11. The table only shows their performance on 100% fault level ability to recognise all the faults

    is improved in the second case.

    Table 4 shows the results of using ANN#1 and ANN#2 in combination for all Fault levels, i.e. for fully developed faults

    (fault level 100%) and developing faults (fault level 75%, 50% and 25%, respectively). It is apparent that the system finds it

    difficult to recognise Fault number 7 when it is not fully developed. However, around half of the faults can be discovered

    at quite an early stage of their development.

    5. Fault isolation by Bayesian network 

    An important part of the concept of combining ANN and BN is operator interaction. The operator uses the BN as an advisor

    on what information is needed to discern root causes. The system structure contains expert knowledge – (stored as acyclic

    Fig. 11.   Structure of the neural networks for the fault detection module.

     Table 3

    Target ratio for ANN#1 and the combination of ANN#1 & ANN#2

    Target ratio in % Fault level 100 %

    Fault type ANN#1 ANN#1 & ANN#2

    H 80.7 94.6

    Fl 100 –

    F2 99.7 –

    F3 100 –

    F4 100 –

    F5 75 98.9

    F6 100 –

    F7 100 –

     Table 4

    Target ratio for the combination ANN#1 & ANN#2 for different fault levels

    Target ratio in % Fault level (%)

    0 25 50 75 100

    H 94.6 – – – –

    Fl – 4.3 41.8 75.9 100

    F2 – 0 6.8 62.6 99.7

    F3 – 84 100 99.7 100

    F4 – 0 85 97.8 100

    F5 – 6 22 97.6 98.9

    F6 – 0 100 100 100

    F7 – 0 7.6 12.2 100

    1698   C. Karlsson et al./ Simulation Modelling Practice and Theory 16 (2008) 1689–1703

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    11/15

    graph and condition-probability tables (CPTs) – of some faults and degeneration mechanisms that do not often appear but

    may cause turbine breakdown or plant malfunction if not detected. Here the interaction and use of the expert knowledge

    takes place through a BN, where the operator inputs information in observation nodes. The fault isolation begins with the

    ANN recognising a pattern in sensor readings and classifying it as a fault type. For each fault type a separate BN is required

    for root cause isolation. The BN observation node connected to the ANN has two states (0 and 1). To allow for the possibility

    of false alarms and missed detection (type I and II errors), the ANN-node (ANN_F7) should show a probability for classifica-

    tion error derived from evaluation of the power of detection.

    To compute probabilities for root causes the operator information and ANN information are used and communicated to

    the BN through observation nodes. The ANN observation node is the only information that is passed on to the BN from the

    ANN, the other information needed to isolate a root cause being provided by the operator and the maintenance staff. The size

    of the BN is kept small by only considering the most important root causes to follow the concept idea. The combination of 

    ANN pattern recognition for classification and BN isolation of root cause has the feature of accepting the ANN classification (0

    or 1) as absolute evidence.

    5.1. Bayesian networks summarized

    A BN consists of a combination of directed acyclic graph and condition-probability distributions. The graph structure is

    where the causal structure of the domain is visualized [11]. A directed acyclic graph is not necessarily causal, but the directed

    acyclic graphs used here are all causal. The second part of a BN is the condition-probability distributions that can be esti-

    mated from historic data. If data are not available, an expert may estimate the distributions and create conditional proba-

    bility tables. The conditional probability table and the directed acyclic graph together form the BN for decision support.

    Isolation is the task of finding a unique root cause of a detected symptom pattern. For some of these patterns, it is not

    possible to distinguish a single root cause. For instance, we have built a BN fault type 7. The BN structure supports the oper-

    ator in isolating a root cause. The BN requires additional evidence beyond the information from ANN detection of fault type

    to isolate root causes. New evidence is collected manually by the operator and entered by dialogue into the BN to help dis-

    tinguish the different root causes. If the same symptom has several potential causes, a constraint in the BN can simplify the

    analysis [20]. The BN only considers the most important, but not all of the possible root causes. The transparency of the BN to

    the operator and the interaction with the operator in collecting evidence are of great importance in this application.

    5.2. Structure of Bayesian network for fault isolation

    A BN consists of nodes and conditional probability tables assembled to model relationships between fault types. For each

    fault type, there is a BN which models the relationship between the root cause and symptoms. The purpose of the BN is to

    help the operator find a single root cause for detected fault types. It may also help eliminate specific faults as the cause of a

    symptom. Fig. 12 shows an example of a BN that considers the root causes of fault type 7, demonstrating the principle of the

    concept.

    BN structures contain a layer of observations (also called inputs) of different types. In Fig. 12 observations are indicated by

    the dashed circles. Examples of observations converted to inputs include the ANN signal, the operator estimate of current

    conditions such as fouling of condenser tubes, direct observations of valve stem position, manual measurement of temper-

    ature, etc. All of these observations constitute evidence which enables the BN to help the operator isolate the fault. To reduce

    the number of possible states to be estimated in the BN, auxiliary nodes that include constraints for a single fault root cause

    called Constraint in Fig. 12 and the symptom nodes are in the middle layer (condFouling, pumpStatus, condHerm). These

    nodes indicate the status of a physical component or the function of a component.

    Fig. 12.   Bayesian network of root causes for fouling and gassing in the condenser.

    C. Karlsson et al. / Simulation Modelling Practice and Theory 16 (2008) 1689–1703   1699

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    12/15

    5.2.1. Example of operator dialogue using the Bayesian network for fault type 7 

    In the example in Fig. 12 we have used the Software Hugin Researcher 6.6 to construct and simulate a BN. When F7 is not

    indicated by the ANN, the value for o_F7_ANN is set to ‘not F7’ by the ANN. The Constraint node is set to ‘fault’ for single fault

    assumption. The results are shown in Fig. 13a.

    The operator may prepare the BNs with information about the process before a fault is detected. Prior data input is re-

    stricted to the parameters that do not change without maintenance action or due to degeneration. The root cause may be

    isolated directly using BN based on prior input data. The BN may even detect a fault type before the ANN does. This is pos-

    sible because the ANN and BN receive information from different sources. In addition, prior information may indicate if there

    is conflict in input data. If this occurs the operator has time to consult an expert to resolve the conflict in observations that

    may have been overlooked in a more urgent situation, which could result in faulty diagnosis and wrong action being taken.

    When the fault F7 is detected by the ANN, o_F7_ANN is set to ‘F7’ and the Constraint node is set to ‘fault’ for single fault

    assumption. Without any input in the top layer of observation nodes the BN indicates the most probable root cause

    (Fig. 13b), given prior probabilities. The operator sets the states of the observation nodes he has information about in order

    to isolate the root cause to the most probable root cause and receives updated probabilities (Fig. 13c). After the operator has

    input information about the states of the observation nodes, there are three possible results:

    1. Based on the information he sees, the operator decides that the BN   can isolate   the root cause with acceptably high

    probability.

    2. The observations create conflict   in the BN, meaning that the evidence is pointing in more than one direction. The operator

    needs to check the states again and if this does not resolve the conflict, expert help is needed.

    3. Based on the information the operator decides the BN cannot isolate the root cause with acceptably high probability. More

    observations of node states or further inspection using methods outside of the BN are needed.

    The BN cannot cover the entire domain and therefore only represents a subset of the faults and root causes. The operator

    also needs to consider the possibility that the ANN is reporting a false alarm. The BN supports the operator in a structured

    search for a root cause and makes a faster judgement on when to gather more information and when to call for expert help.

    Hypotheses proposed by experts about the root cause may be falsified using the BN. Feedback data is also used to update the

    BN to improve performance.

    Fig. 13a.  Result in BN for F7 when no fault is detected (F7_ANN set to not F7, and Constraint set to fault).

    Fig. 13b.  Result in BN for F7 when fault is detected (F7_ANN set to F7 and Constraint set to fault).

    Fig. 13c.  Result in BN for F7 after input of collected evidence.

    1700   C. Karlsson et al./ Simulation Modelling Practice and Theory 16 (2008) 1689–1703

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    13/15

    5.3. Resulting BN for isolation

    A BN was developed for isolation of root causes related to power loss of condenser heat power, denoted as fault type F7.

    The BN for F7 – shown in Fig. 12 – indicated two possible symptoms: fouling of condenser tubes (condFouling), and degas-

    sing. Degassing may be due to one of two causes: reduced vacuum pump function (PumpStatus), or air leaking into the con-

    denser (condHerm).

    The interaction between operator and BN is conducted by manual entry of observations that provide putative evidence for

    each root cause. The observation connected to each root cause is the manual estimate or manual reading of the observations

    at each node. These observations are: the pressure drop over the condenser (dpCondenser), prior fouling of the condenser

    that may affect the current state of fouling (priorFouling), the mechanical status of the pump (mechParts), the mechanical

    status of the pump motor (pumpMotor), the hermetic status of the manhole cover (manhole), the general state of the con-

    denser shell (shell), and the presence of water on the backpressure lid (waterBack). As the node Constraint assumes a single

    fault, it forces the network to choose one of the above fault symptoms at a time. The CPT for the BN is constructed from esti-

    mated probabilities. This work has resulted in rough estimates of the probabilities and needs further development before

    implementation in a specific plant. The F7_ANN probability is a product of training the BN for detection.

    6. Division of detection and isolation tasks between ANN, BN and operator 

    Various types of information are used by the operator to conduct maintenance decisions. The data may be collected man-

    ually or automatically and may be qualitative or quantitative. A sensor reading that is automatically collected by DCS and

    stored in a data base is considered quantitative. Manually collected data used by the BN may be either quantitative or qual-

    itative. The ANN is limited to processing patterns from automatically collected data. Pattern recognition (used here for detec-

    tion) is a task ANNs are well suited for, especially when there are databases available containing long time series of collected

    data. ANNs may also be trained on artificial data when no real data is available for one or more fault types. In these cases

    there is a need for a detailed simulator, such as the used in this project. Human operators are not proficient at detecting

    slowly developing faults. The ANN supports the operator in early detection of fault types related to correlations in several

    variables.

    The ANN is essentially used for pattern recognition and classification. A pattern in the data is recognized (detected) and a

    corresponding fault type is selected. Input from the BN or the operator is unlikely to enhance the performance of this task for

    slowly developing faults, therefore our concept does not support the transfer of information in this direction. The ANN de-

    tects and classifies the fault and passes on this information to the BN and the operator. The fault type is described beforehand

    by experts and may be presented to the operator through a written manual or a pop-up window on a screen. The ANN is a

    black box with inputs and outputs and the operator does not require knowledge of the processing between input and output

    to use it. This structure does not support explanation of the relationships between fault types and root causes. BN on the

    other hand may be represented by objects and links between them illustrating the relationship between fault type and root

    cause. Once the ANN detection threshold of a fault is reached, the dialogue between the BN and the operator is a powerful

    tool for rationalizing and isolating the fault.

    6.1. Drawing the line between ANN and BN 

    Developing ANNs from time series data in a database has been found to be less time consuming than developing BNs,

    which require expert input. The argument for separating ANNs and BNs is to make it possible to explain cause-effect rela-

    tionships by building BNs for specific faults and using the representational power of ANNs to build the model and to detect

    developing faults efficiently. This line of thought was promoted in a recent work treating a comparison of neural networks

    and BNs [25].

    ANNs differ from BNs for this particular case in that they are able to detect faults but may not be able to determine the

    root causes of the faults using sensor readings collected by the distributed control system. If further isolation of the faults is

    required, a BN is constructed and extended as far as the plant owner finds economical arguments for. The output node of the

    ANN is the connection to the BN and same as the observation node (F7_ANN) in the BN example in  Fig. 12.

    6.1.1. Dialogue between operator and BN 

    Humans tend to forget and distort memories over time, but a BN structure remains intact and does not forget or distort

    the correlations. Once the fault is detected and classified by the ANN the corresponding BN observation node for that fault

    type is set to 1. The detection and classification is still prone to false alarms and missed alarms (type I and type II errors). The

    BN can be used in at least two ways by the operator. The first is to help to discern between root causes when a fault is de-

    tected, and the second is to provide support in deciding whether a detected fault by the ANN is a false alarm. To discern be-

    tween root causes additional data is input into the observation nodes in the BN and the most probable root cause is updated.

    If the observed data support a single root cause the probability for that cause increases as data is added. If the observed data

    that is entered is not consistent with one fault type, the probability of the root causes is less defined or may point in more

    than one direction, causing conflicting results. At this point, the limitation of the BN reached – it can only say that the pro-

    C. Karlsson et al. / Simulation Modelling Practice and Theory 16 (2008) 1689–1703   1701

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    14/15

    vided data does not point to a root cause that is part of the BN structure or that it points to two or more root causes. At this

    point the decision on the course of action is down to the operator. The BN can no longer assist, and a turbine expert may need

    to be called in.

    7. Discussion and conclusions

    The ANNs used here can detect all the fault types introduced into the simulator environment. The detection part of the

    system has been validated against simulated data (Tables 3 and 4). The BN part of the system provides the operator withsupport for fault isolation. The system is intended to work as a decision support function for maintenance actions such as

    dismantling the turbine through operator dialogue using BNs. As well as the plant owner, the costly maintenance decision

    to dismantle the turbine relies on input from the steam turbine manufacturer and the insurance company.

    An ANN has been trained to detect seven fault types in a steam turbine. An approach using a network of ANNs is seen to

    be a powerful aid in reducing the number of mismatches at lower fault levels (75%, 50%, etc.). This is because ANN#2 focuses

    on a much smaller amount of data and classifies it in only 2 classes, i.e. H or F5, this being easier than the original task per-

    formed by ANN#1 (classification in eight different classes). The addition of the extra input parameter also helps when dis-

    tinguishing between these two conditions. Empirical evidence indicates that this parameter is related to fault 5 only, and its

    inclusion in ANN#1 could lead to an incorrect classification of other faults. The approach presented here does not indicate

    the extent of the developed fault, but only indicates whether they are present. However, incipient faults can be determined

    in an earlier stage, as shown in Table 4. A possible approach to detecting developing faults at an early stage can be to use a

    graphical approach such as that discussed in [2]. It should also be mentioned that the simulated levels of the faults are small

    in order to test the ANN for early fault detection. Failures in the steam turbine and surrounding equipment are normally de-tected by alarm thresholds set in the distributed control system. The detection threshold of the ANN is normally much lower

    than these alarm thresholds.

    The very good detection power for low fault levels is probably partly due to the absence of noise and errors in data that

    would be expected to appear in a dataset from a real process. The number of unclassified data was also very low compared

    to those previously seen by the authors. This system does not allow conclusions to be drawn from data that produce out-

    put that indicates more than one fault. Though it may be tempting to regard the highest neuron output value as the most

    probable and therefore ‘‘detected”, all the possibilities should be considered, including the presence of more than one fault

    at a time. The ANN must be trained on datasets generated for multiple faults if it is to be able to detect multiple faults

    reliably.

    The ANN may be trained on datasets prepared to resemble real data by introducing small errors and noise in measure-

    ment data to improve its performance when working with data generated by a real system. Mesbahi et al.  [23]  proposed

    gradual identification of fault types using a graphical display (5 by 8 pixels). With this system, as the certainty of a detected

    fault type increases, it is accompanied by a gradual increase in the resolution of the figure representing the number of thefault type.

    Using the combination of a BN and ANN together is a result of an effort to maintain a compact structure and to make use

    of easily checked variables. We believe that making use of the operator’s knowledge of the process and judgment as an ex-

    pert input helps to minimize the extent and therefore development cost of the BN and speeds up the isolation of a fault. We

    also believe that the BN provides more information for the operator to use himself or to pass on to an external expert if re-

    quired. The ability of the concept to estimate turbine condition by detecting a healthy state from on-line measurements and

    to combine this with operator knowledge through a BN is valuable for making earlier maintenance decisions to reduce dam-

    age and to avoid making maintenance decisions that consume resources and capital unnecessarily.

    Economic evaluations of indirect costs of maintenance actions rely on estimation of numerous parameters and limitations

    such as current and future electricity and fuel prices, signed contracts, insurance, maintenance intervals and random events

    affecting prices. Here the improvisation and experience of an operator is needed. The direct costs of a maintenance operation

    may be integrated in the BN through influence diagrams  [11]. The calculation of indirect costs should be done in a spread-

    sheet application in order to minimize the size of the influence diagram and for easy communication with other data used by

    the decision-maker.

    The action sequence of classification using the ANN followed by isolation performed by the interaction of operator and BN

    is straightforward. The ANN is a black box and the classification cannot therefore be evaluated as in the case of BN cause-

    effect graphs. The ANN output becomes the sole criterion for selection of a certain BN. However, the operator is free to

    set the ANN observation node to another state in order to test faults other than the one indicated by the ANN if the ANN

    is believed to be providing faulty information.

    It is the authors’ opinion that work on integrating economics in the decision-making process using influence diagrams

    should be taken further. Summarizing the estimation of direct cost of maintenance action through influence diagrams

    and the indirect costs estimated by the operator may be calculated in a spreadsheet. An alternative approach to using the

    ANN for fault classification is to use a BN. This is potentially interesting as its application would likely simplify the training

    of the BN as. A library of BN structures for different graphs from observation to root cause is a requirement to achieve com-

    ponent-based detection and decision-making support. We believe that such a system would be of value to heat and power

    plants that are less able to invest in fault detection and isolation systems of the size presented in  [18].

    1702   C. Karlsson et al./ Simulation Modelling Practice and Theory 16 (2008) 1689–1703

  • 8/18/2019 Detection and Interactive Isolation of Faults in Steam Turbines To

    15/15

    Power plants are subject to design changes and the ANN–BN may need to be updated with changes in the plant. Degra-

    dation of the plant over time also affects the performance of the ANN–BN. These models mimic a specific data set and

    changes in the plant over time may cause problems if the ANN–BN is not kept up to date. A brief discussion on how this

    challenge may be met follows. If the real process is drifting slowly (e.g. through fouling, decreasing heat transfer coefficients)

    the error in the ANN increases over time. The BN part of the system is almost unaffected by degeneration, because it is

    uncoupled from measurements affected by degeneration of the plant. The states in the BN are relative and not directly cou-

    pled to absolute figures measured in the plant. The ANN training dataset is generated from a set of mass and heat balance

    model parameters for the ‘Healthy condition’ and datasets for the faults F1–F7. If the original model parameters change, the

    performance of the ANN will decrease. The ANN must be adapted to the changes to maintain its accuracy. This will be the

    subject to further work. Our preferred approach relies on updating the first principles model. Updated ANNs may be auto-

    matically generated from the updated model and the system performance (detection threshold, low errors Types I and II) can

    be maintained over time in this way. In addition the parameter estimation results provide valuable data on how parameter

    changes can be used to inform maintenance decisions.

    References

    [1] J. Arriagada, On the Analysis and Fault-Diagnosis Tools for Small-Scale Heat and Power Plants, Ph.D. Thesis, Lund University, 2003.

    [2] J. Arriagada, M. Genrup, A Loberg, M. Assadi, Fault diagnosis system for an industrial gas turbine by means of neural networks, in: Proceedings of the

    International Gas Turbine Congress, Tokyo, 2003.

    [3] R. Beebe, Condition monitoring of steam turbine by performance analysis, Journal of Quality in Maintenance Engineering 9 (2003) 102–112.

    [4] C.P. Bellanca, Diagnostic monitoring of solid particle erosion in steam turbines, IEEE Transactions on Energy Conversion 3 (1988) 249–253.

    [5] C.M. Bishop, Neural Networks for Pattern Recognition, Oxford University Press, USA, 1995.

    [6] J.H. Bulloch, A.G. Callagy, Malfunctions of a steam turbine mechanical control system, Engineering Failure Analysis 5 (1995) 235–240.[7] K.C. Cotton, Evaluating and Improving Steam Turbine Performance, Cotton Fact Inc., 1988.

    [8] M.H. Faber, M.G. Stewart, Risk assessment for civil engineering facilities: critical overviewand discussion, Reliability Engineering andSystem Safety 80

    (2003) 173–184.

    [9] M. Genrup, On Degradation and Monitoring Tools for Gas and Steam Turbines, Ph.D. Thesis, Lund University, 2005.

    [10] S. Haykin, Neural Networks: A Comprehensive Foundation, Prentice-Hall, UK, 1995.

    [11] F.V. Jensen, Bayesian Networks and Decision Graphs, Springer Verlag, New York, 2001.

    [12] J. Kubiak, A. Garcı́a-Gutiérrez, B. Urquiza, The diagnosis of turbine component degradation – case stories, Applied Thermal Engineering 22 (2002)

    1955–1963.

    [13] A.Sh. Leyzerovich, Large Power Steam Turbines, PennWell Publishing Company, USA, 1997.

    [14] O. Lyle, The Efficient Use of Steam, Her Majesty’s Stationery Office, UK, 1958. ISBN: B0000CKCTV.

    [15] T.H. McCloskey, C. Bellanca, Minimizing solid particle erosion in power plant steam turbines, Power Engineering 8 (1989) 35–38.

    [16] F. Rosenblatt, The Perceptron: A probabilistic model for information storage and organization in the brain, Psychological Review 65 (1958) 386–408.

    [17] R. Svoboda, M. Bodmer, Deposits andcorrosion in steam turbines, ABB Power Generation TEZ87-20, paperpresented at Ringhals, Sweden, March 1987.

    [18] V. Uraikul, C.W. Chan, P. Tontiwachwuthikul, Artificial intelligence for monitoring and supervisory control of process systems, Engineering

    Applications of Artificial Intelligence 20 (2007) 115–131.

    [19] G. Waltenberger, Betriebskosten, VGB-Kraftverkstechnik 68 (1988) 244–248.

    [20] G. Weidl, Root Cause Analysis and Decision support on Process Operation, Ph.D. Thesis, Mälardalen University, 2002.[21] A. Whitehead, K.T. Sullivan, Carryover and its effects on efficiency, operation and maintenance of industrial steam turbines, Pulp and Paper Canada 11

    (1983) 309–313.

    [22] B. Widarsson, C. Karlsson, E. Dahlquist, Bayesian Network for Decision Support on Soot Blowing Superheaters in a Biomass Fuelled Boiler, International

    Conference on Probabilistic Methods Applied Power Systems 1 (2004) 212–217.

    [23] E. Mesbahi, Artificial Neural Networks for Fault Diagnosis, Modelling and Control of Diesel Engines, Ph.D. Thesis, Department of Marine Technology,

    University of Newcastle Upon Tyne, UK, 2000.

    [24] D. Rumelhart, G. Hinton, R. Williams, Learning internal representations by error propagation, in: Parallel Distributed Processing: Explorations in the

    Microstructure of Cognition, vol. 1: Foundations, 1986, pp. 318–362.

    [25] R. Zhang, A. Bivens, Comparing the use of Bayesian networks and neural networks in response time modeling for service-oriented systems, in:

    Proceedings of the 2007 Workshop on Service-Oriented Computing Performance: Aspects, Issues, and Approaches. Monterey, California, USA, pp. 67–

    74.

    [26] A. Holmes, A European OEM’s Experience, Presented at San Francisco Steam Turbine Retrofit Conference, San Francisco, USA, 16–17th September 2003.

    [27] B. Widrow, M. Hoff, Adaptive switching circuits, IRE WESCON Convention Record, pt. 4, 1960, pp. 96–104.

    C. Karlsson et al. / Simulation Modelling Practice and Theory 16 (2008) 1689–1703   1703