Ubi Comp2009 Hydro Sense Final

64
Infrastructure-Mediated Single-Point Sensing of Whole Home Water Activity desig n: use: build: univ. of washington computer science and engineering Jon Froehlich 1 , Eric Larson 2 , Tim Campbell 3 , Conor Haggerty 4 , James Fogarty 1 , Shwetak N. Patel 1,2 1 Computer Science & Engineering, 2 Electrical Engineering, 3 Mechanical Engineering, 4 Community, Environment, and Planning

description

A project I worked with Jon Froehlich on presented at UbiComp 2009

Transcript of Ubi Comp2009 Hydro Sense Final

Page 1: Ubi Comp2009 Hydro Sense Final

Infrastructure-Mediated Single-Point Sensing of Whole-Home Water Activity

design:use:build:

univ. of washington

computer scienceand engineering

Jon Froehlich1, Eric Larson2, Tim Campbell3, Conor Haggerty4, James Fogarty1, Shwetak N. Patel1,2

1Computer Science & Engineering, 2Electrical Engineering,3Mechanical Engineering, 4Community, Environment, and Planning

Page 2: Ubi Comp2009 Hydro Sense Final

water scarcity

Page 3: Ubi Comp2009 Hydro Sense Final

barcelona, spain

Page 4: Ubi Comp2009 Hydro Sense Final

lake mead, nevada

Page 5: Ubi Comp2009 Hydro Sense Final

average indoor household water usage per person/day (70 gpd)

Dishwasher

Baths

Other Domestic

Leaks

Faucets

Showers

Clothes Washer

Toilets

0% 5% 10% 15% 20% 25% 30%

what are the most consuming water activities in your home?

Vickers, 2001

Page 6: Ubi Comp2009 Hydro Sense Final

• single-point pressure-based sensor of water usage

• identifies water usage activity down to fixture level (e.g., toilet)

• provides estimates of flow at each fixture

hydrosense

Page 7: Ubi Comp2009 Hydro Sense Final

hydrosensetoilet

kitchen sink

shower

Page 8: Ubi Comp2009 Hydro Sense Final

Pressure Sensor

16-bit ADC20 MHz

Microcontroller

Class 1 Bluetooth

Radio

3D-Printed Enclosure

the hydrosensor prototype

Page 9: Ubi Comp2009 Hydro Sense Final

water tower

brief plumbing primer

Page 10: Ubi Comp2009 Hydro Sense Final

water tower

incoming cold water from supply line

40 psi

100 psi

1 psi = 6.89 kpabrief plumbing primer

Page 11: Ubi Comp2009 Hydro Sense Final

water tower

incoming cold water from supply line

pressure regulator

pipe layout

Page 12: Ubi Comp2009 Hydro Sense Final

water tower

incoming cold water from supply line

thermal expansion

tank

laundry

bathroom 1hose

spigot

hot water heater bathroom

2

kitchen

dishwasher

pressure regulator

closed pressure system

Page 13: Ubi Comp2009 Hydro Sense Final

incoming cold water from supply line

thermal expansion

tank

laundry

bathroom 1hose

spigot

hot water heater bathroom

2

kitchen

dishwasher

pressure regulator

water tower

hot water heater drain

valve

hot water heater

Page 14: Ubi Comp2009 Hydro Sense Final

water tower

incoming cold water from supply line

thermal expansion

tank

laundry

bathroom 1hose

spigot

bathroom 2

kitchen

dishwasher

pressure regulator

hot water heater

some possible installation points

Page 15: Ubi Comp2009 Hydro Sense Final
Page 16: Ubi Comp2009 Hydro Sense Final

raw bathroom sink signal

stabilized pressure drop

openvalve

closevalve

time (t)

Page 17: Ubi Comp2009 Hydro Sense Final

detecting water usage events

1. detect a water event

2. classify event as “open” or “close”

3. determine source of event (e.g., toilet, kitchen sink).

4. provide flow estimate

Page 18: Ubi Comp2009 Hydro Sense Final

-2

0

2

44

46

48

0 5 10 15 20 25 30 35 40 4542

44

46

48

50

raw pressure

(psi)

smoothed pressure

derivative

event detection

time (s)

Page 19: Ubi Comp2009 Hydro Sense Final

0 5 10 15 20 25 30 35 40 4542

44

46

48

50

44

46

48

-2

0

2

event detection

!

critical change in pressure

raw pressure

(psi)

smoothed pressure

derivative

time (s)

time(s)

Page 20: Ubi Comp2009 Hydro Sense Final

0 5 10 15 20 25 30 35 40 4542

44

46

48

50

44

46

48

-2

0

2

event detection

time(s)

!!

critical stabilization point

raw pressure

(psi)

smoothed pressure

derivative

time (s)

Page 21: Ubi Comp2009 Hydro Sense Final

0 5 10 15 20 25 30 35 40 4542

44

46

48

50

44

46

48

-2

0

2

event detection

time(s)

!!

raw pressure

(psi)

smoothed pressure

derivative = valve open event

pressure decreaseand

negative initial derivative

time (s)

automatically detected event

valve open event

Page 22: Ubi Comp2009 Hydro Sense Final

0 5 10 15 20 25 30 35 40 4542

44

46

48

50

44

46

48

-2

0

2

event detection

time(s)

raw pressure

(psi)

smoothed pressure

derivative

!!

valve open event

Page 23: Ubi Comp2009 Hydro Sense Final

0 5 10 15 20 25 30 35 40 4542

44

46

48

50

44

46

48

-2

0

2

event detection

time(s)

raw pressure

(psi)

smoothed pressure

derivative

!!

= valve close event

automatically detected event

valve open event

pressure increase

andpositive initial derivative

Page 24: Ubi Comp2009 Hydro Sense Final

home 1 home 2 home 3

toile

tfa

ucet

show

er

example open events

signature dependent on:- fixture type- valve type- valve location in home

Page 25: Ubi Comp2009 Hydro Sense Final

bath

tub

bath

fauc

et

kitc

hen

fauc

et

dish

was

her

toile

tsh

owe

r

unclassified open event open event library

fixture classification

Page 26: Ubi Comp2009 Hydro Sense Final

detrendedunclassified

derivativeunclassified

cepstrumunclassified

bath

tub

bath

fauc

et

kitc

hen

fauc

et

dish

was

her

toile

t

unclassified open event

detrendedshower

derivativeshower

cepstrumshower

open event library

show

er

Page 27: Ubi Comp2009 Hydro Sense Final

bath

tub

bath

fauc

et

kitc

hen

fauc

et

dish

was

her

toile

t

unclassified open event open event library

detrendedunclassified

derivativeunclassified

cepstrumunclassified cepstrumshower

detrendedshower

derivativeshower

possible events

matched filter

matched filter

matched filter

show

er

test similarity

Page 28: Ubi Comp2009 Hydro Sense Final

bath

tub

bath

fauc

et

kitc

hen

fauc

et

dish

was

her

unclassified open event

detrendedunclassified

derivativeunclassified

cepstrumunclassified

possible eventscepstrumtoilet

detrendedtoilet

derivativetoilet

open event library

toile

t

Page 29: Ubi Comp2009 Hydro Sense Final

bath

tub

bath

fauc

et

kitc

hen

fauc

et

dish

was

her

unclassified open event open event library

detrendedunclassified

derivativeunclassified

cepstrumunclassified

possible eventscepstrumtoilet

detrendedtoilet

derivativetoilet

matched filter

matched filter

matched filter

toile

t

Page 30: Ubi Comp2009 Hydro Sense Final

possible events

unclassified open event open event library

detrendedunclassified

derivativeunclassified

cepstrumunclassified

bath

tub

bath

fauc

et

kitc

hen

fauc

et

dish

was

her

Page 31: Ubi Comp2009 Hydro Sense Final

kitc

hen

fauc

et

dish

was

her

show

er

unclassified open event open event library

detrendedunclassified

derivativeunclassified

cepstrumunclassified

possible events

Page 32: Ubi Comp2009 Hydro Sense Final

kitc

hen

fauc

et

dish

was

her

show

er

unclassified open event open event library

detrendedunclassified

derivativeunclassified

cepstrumunclassified

possible events

derivativeshower

derivativetoilet

show

er

dish

was

her

kitc

hen

fauc

et derivativekitchen faucet

Page 33: Ubi Comp2009 Hydro Sense Final

unclassified open event open event library

derivativeunclassified

possible events

derivativeshower

derivativetoilet

show

er

dish

was

her

kitc

hen

fauc

et derivativekitchen faucet

nearest neighbor match

Page 34: Ubi Comp2009 Hydro Sense Final

raw bathroom sink signal

stabilized pressure drop

open close

time (t)

this is ∆P

Page 35: Ubi Comp2009 Hydro Sense Final

using ∆pressure to estimate flow

r

L

pipe

𝑄= ∆𝑃 𝜋 𝑟4 8 𝜇 𝐿 ≡ ∆𝑃 𝑅𝑓 poiseuille’s law:

𝑅𝑓 = ∆𝑃𝑄 ≡ 8 𝜇 𝐿𝜋 𝑟4 fluid resistance formula:

∆P = change in pressureL = length of piper = radius of pipeμ = viscosity of liquidQ = volumetric flow rate

Page 36: Ubi Comp2009 Hydro Sense Final

using ∆pressure to estimate flow

r

L

pipe

∆P = change in pressureL = length of piper = radius of pipeμ = viscosity of liquidQ = volumetric flow rate𝑄= ∆𝑃 𝑅𝑓

Page 37: Ubi Comp2009 Hydro Sense Final

water tower

incoming cold water from supply line

thermal expansion

tank

laundry

bathroom 1hose

spigot

hot water heater bathroom

2

kitchen

dishwasher

pressure regulator

acquiring Rf

𝑅𝑓 = ∆𝑃 𝑄 𝑄= ∆𝑃 𝑅𝑓

Page 38: Ubi Comp2009 Hydro Sense Final

in-home data collection

Page 39: Ubi Comp2009 Hydro Sense Final

home profiles

ten locations- 8 houses- 1 apt / 1 cabin

size- avg: 2,300 sq ft- min: 750 sq ft- max: 4,000 sq ft

install point:- 8 hose bib- 1 water heater- 1 utility faucet

Page 40: Ubi Comp2009 Hydro Sense Final

experimental protocol

- controlled experiments- 2 researchers per site

- 5 trials per valve- e.g., 5 cold / 5 hot for bathroom sink

- for each trial, valve open for 5 seconds, then closed

Page 41: Ubi Comp2009 Hydro Sense Final

collecting flow data

- 4 / 10 homes gathered flow data

- measure time to fill 1 gallon in a calibrated bucket

- this provides Q, allowing us to solve for Rf - Rf = ∆P / Q

Page 42: Ubi Comp2009 Hydro Sense Final

data collection stats

- ten locations- 706 trials- 155 flow rate trials- 84 total fixtures tested

Page 43: Ubi Comp2009 Hydro Sense Final

• cross validation experiment• learn similarity thresholds from test data• classify each event per home using a leave-

one out method

classification results across homes

Page 44: Ubi Comp2009 Hydro Sense Final

fixture classification results across homes

H1 (12 valves)

H2 (8 valves)

H3 (6 valves)

H4 (5 valves)

H5 (9 valves)

H6 (8 valves)

H7 (8 valves)

H8 (6 valves)

H9 (7 valves)

H10 (7 valves)

Aggregate Overall

0%

20%

40%

60%

80%

100% 98.9% 97.9%96.8%

Open Events Close Events

Page 45: Ubi Comp2009 Hydro Sense Final

fixture classification results across homes

H1 (12 valves)

H2 (8 valves)

H3 (6 valves)

H4 (5 valves)

H5 (9 valves)

H6 (8 valves)

H7 (8 valves)

H8 (6 valves)

H9 (7 valves)

H10 (7 valves)

Aggregate

Overall50%

60%

70%

80%

90%

100%

Open Events Close Events97.9%

Page 46: Ubi Comp2009 Hydro Sense Final

Sinks Toilets Showers Bathtubs Clothes Washer

Dishwasher0%

20%

40%

60%

80%

100%98

%

99%

96%

100%

100%

100%

95%

98%

89% 10

0%

100%

Open Events Close Events

fixture classification results across fixtures

Page 47: Ubi Comp2009 Hydro Sense Final

flow estimation results

HomeAvg Error

(GPM)Stdev Error

(GPM)Avg Error

(%)Stdev

Error (%)H1

(7 valves)0.17 0.13 7.3 6.7

H4 (6 valves)

0.19 0.17 5.6 5.3

H5 (8 valves)

0.13 0.11 4.5 5.5

H7 (8 valves)

0.67 1.47 22.2 46.0

Page 48: Ubi Comp2009 Hydro Sense Final

flow estimation results

HomeAvg Error

(GPM)Stdev Error

(GPM)Avg Error

(%)Stdev

Error (%)H1

(7 valves)0.17 0.13 7.3 6.7

H4 (6 valves)

0.19 0.17 5.6 5.3

H5 (8 valves)

0.13 0.11 4.5 5.5

H7 (4 valves)

0.15 0.18 4.5 3.8

Page 49: Ubi Comp2009 Hydro Sense Final

water tower

incoming cold water from supply line

thermal expansion

tank

laundry

bathroom 1hose

spigot

hot water heater bathroom

2

kitchen

dishwasher

pressure regulator

acquiring Rf

𝑅𝑓 = ∆𝑃 𝑄 𝑄= ∆𝑃 𝑅𝑓

Page 50: Ubi Comp2009 Hydro Sense Final

water tower

incoming cold water from supply line

thermal expansion

tank

laundry

bathroom 1hose

spigot

hot water heater bathroom

2

kitchen

dishwasher

pressure regulator

acquiring Rf

𝑅𝑓 = ∆𝑃 𝑄 𝑄= ∆𝑃 𝑅𝑓

Page 51: Ubi Comp2009 Hydro Sense Final

0

0.5

1

1.5

2

2.5

H1 H4H5 H7

Number of Samples

Aver

age

Erro

r (G

PM)

flow estimation using interpolated Rf

After 5 Rf samples, average error is 0.27 GPM

Page 52: Ubi Comp2009 Hydro Sense Final

future work: hydrosense 2.0

Page 53: Ubi Comp2009 Hydro Sense Final

longitudinal data collection

Page 54: Ubi Comp2009 Hydro Sense Final
Page 55: Ubi Comp2009 Hydro Sense Final

water feedback interfaces

Page 56: Ubi Comp2009 Hydro Sense Final

Jon Froehlich Eric Larson Tim Campbell

Conor Haggerty James Fogarty Shwetak Patel

Page 57: Ubi Comp2009 Hydro Sense Final

Infrastructure-Mediated Single-Point Sensing of Whole-Home Water Activity

design:use:build:

univ. of washington

computer scienceand engineering

Jon Froehlich1, Eric Larson2, Tim Campbell3, Conor Haggerty4, James Fogarty1, Shwetak N. Patel1,2

1Computer Science & Engineering, 2Electrical Engineering,3Mechanical Engineering, 4Community, Environment, and Planning

[email protected]://sustain.cs.washington.edu/blog

Page 58: Ubi Comp2009 Hydro Sense Final
Page 59: Ubi Comp2009 Hydro Sense Final
Page 60: Ubi Comp2009 Hydro Sense Final

flow estimation

Page 61: Ubi Comp2009 Hydro Sense Final

traditional inline water meter

typical water meters

- only provide aggregate information on water usage

- require pipe modification for installation

Page 62: Ubi Comp2009 Hydro Sense Final

matched filtering

save maximumsimilaritysi

mila

rity

Page 63: Ubi Comp2009 Hydro Sense Final

matched filtering

new maximumsimilarity

sim

ilarit

y

Page 64: Ubi Comp2009 Hydro Sense Final