RISK ASSESSMENT OF SEWER CONDITION USING ARTIFICIAL INTELLIGENCE TOOLS - PowerPoint Presentation

Slide1

RISK ASSESSMENT OF SEWER CONDITION USING ARTIFICIAL INTELLIGENCE TOOLS Application to the SANEST sewer system

Vitor SousaIST, UTLJosé Pedro MatosIST, UTLNuno Marques AlmeidaIST, UTLJosé Saldanha MatosIST, UTL

http://www.toledoblade.com/Police-Fire/2013/07/06/Sewer-repairs-start-after-intersection-collapse-Copy.html

OUTLINE

IntroductionSewer condition modellingSANEST sewer systemData collectionModel designArtificial Neural NetworksSupport Vector MachinesDiscriminant analysis

Conclusions

1. INTRODUCTION

Wastewater drainage systems asset management strategiesReactiveProactive:prevention-based (or based on age); inspection-based (or based on condition);

prediction-based

(or based on reliability

)

;

The concept of risk has also been used in managing wastewater drainage assets, either:

Indirectly – by indentifying critical sewers (managed proactively) and non-critical sewers (managed reactively

)

Directly – through the development of multicriteria tools accounting also for the consequences of the sewers failures

(

MARESS - Reyna 1993; RERAUVIS - RERAU 1998; CARE-S - CARE‑S 2005)

2. SEWER CONDITION MODELLING

CATEGORYCLASSTYPEREFERENCES

Function-based

Deterministic

Linear regression

Chughtay and Zayed (2007a, 2007b, 2008)

Non-linear regression

Newton and Vanier (2006); Wirahadikusumah et al. (2001)

Stochastic

Survival function

Hörold and Baur (1999); Baur and Herz (2002); Baur et al. (2004); Ana (2009)

Ordinal regression

Yang (1999); Davies et al. (2001b);

Ariaratnam

et al.

(2001); Pohls (2001); Ana (2009)

Markov chains

Wirahadikusumah

et al. (2001);

Micevski

et al. (2002);

Coombes

et al. (2002);

Baik

et al.

(2006); Koo and Ariaratnam (2006); Newton and Vanier (2006); Tran (2007); Le Gat (2008)

Semi-Markov chains

Kleiner

(2001); Dirksen and Clemens (2008); Ana (2009)

Discriminant analysis

Tran (2007); Ana (2009)

Data-based

Artificial inteligence

Artificial Neural Networks – ANNs

Najafi

and

Kulandaivel

(2005); Tran et al. (2006); Tran (2007); Ana (2009); Khan et al.

(2010)

Fuzzy Set

Yan and

Vairavamoorthy

(2003);

Kleiner

et al. (2004a, 2004b, 2006)

Case Based Reasoning – CBR

Fenner et al. (2007)

Support Vector Machines – SVMs

Mashford et al. (2011)

Genetic programing

Evolutionary Polynomial Regression – EPR

Savic

et al. (2006);

Ugarelli

et al.

(2008); Savic et al. (2009)

3. SANEST SEWER SYSTEM

http://www.sanest.pt/artigo.aspx?sid=e73adb75-e84d-46ae-b578-50a5ee934cc2&cntx=d00N%2Fz8yc6LPuMNx72xjzkHnWQg%2Bm23akSu576zxbEk%3D

Material / Diameter

Sewers [nº]Total length [m]

Average age [years]

Average depth [m]

Average slope [%]

Average length [m]

VC (1)

134

4370.50

54.55

2.52

2.14

32.62

2007186.1345.002.681.3226.5925015389.4158.132.411.0925.96300381232.8549.741.982.9532.44350692484.6858.172.821.8336.01400142.2339.002.311.1142.23PC (2)531408.7029.852.472.0826.58315151.2630.002.732.0951.26500521357.4429.852.472.0826.10PVC (3)34812682.2011.532.881.7236.44200380.448.002.197.2226.81250592291.4610.372.344.1438.8431538957.0312.392.460.9025.194001124347.9011.592.981.7538.82500732868.8112.263.030.8739.30630271132.6410.373.120.8141.9570030915.3812.003.470.5330.51800688.5412.003.470.3414.76HDPE (4)1224102.049.843.531.2333.62360381206.4710.003.700.9631.754004111.039.753.311.6827.764504217.339.002.071.2654.33500662154.489.923.761.5032.6460010412.739.002.080.2741.27C-PP (5)601771.999.653.021.5129.5331526908.069.964.422.8334.934004122.8912.003.230.2630.7250029713.709.031.720.4624.61630127.3410.003.402.7127.34C-PVC (6)281033.744.423.871.2439.763507165.006.202.832.7133.0040021868.744.004.120.8941.37Total74525369.1719.922.941.7134.14

4

. DATA COLLECTION

5. MODEL DESIGN

The sewer operational and structural condition classes were determined from the CCTV inspection results using the WRc (2001) rating protocol.Two alternative approaches were used to reduce number of condition classes used as outputs:ALT A – the sewers were classified into three categories representing reaches that are in good condition and are expected to endure a long period before the next inspection (category 0 – sewers in condition 1 and 2), sewers that require a shorter period of time until the next inspection (category 1 – sewers in condition 3) and sewers that are failing and should be intervened in the short term (category 2 –sewers in condition 4 and 5)

ALT B – the sewers were divided into those that require intervention (category 2 – sewers in condition 4 and 5) and those which do not require intervention (category 1 – sewers in condition 1, 2 and 3

).

6. ARTIFICIAL NEURAL NETWORKS

ANNsFor the classification case of the sewers' structural condition according to ALT B, the corresponding ANN presented was used to evaluate the effect of the initial weights of the neuron connections.

Randomly varying the initial weights of the neuron connections in 100 ANNs resulted in correlations ranging from 67% to 79%, for the train data (average=73%), and from 72% to 84%, for the test data (average=76%).

Classification Case

Train Algorithm

Error Function

Correlation

Number of neurons

Activation function

Train

Test

Hidden Layer

Output Layer

Hidden LayerOutput LayerOperational – ALT ABFGSCE61.8066.67153Hiperbolic TangentSoftmaxStructural – ALT ABFGSSOS68.5271.85293Hiperbolic TangentSigmoid LogisticOperational – ALT BBFGSCE80.0082.96192Sigmoid LogisticSoftmaxStructural – ALT BBFGSSOS75.7482.22182Sigmoid LogisticSigmoid Logistic

6. ARTIFICIAL NEURAL NETWORKS

ALT AALT B

OBSERVED

PREDICTED (Operational)

Correct / Incorrect

PREDICTED (Structural)

Correct / Incorrect

Category

0

1

2

0

1

2072358.3% / 41.7%51083.3% / 16.7%11149476.6% / 23.4%7551175.3% / 24.7%212133457.6% / 42.4%5143766.1% / 33.9%Correct / Incorrect23.3% / 76.7%76.6% / 23.4%82.9% / 17.1%66.7% / 33.3%29.4% / 70.6%78.6% / 21.4%77.1% / 22.9%71.9% / 28.1%OBSERVEDPREDICTED (Operational)Correct / IncorrectPREDICTED (Structural)Correct / IncorrectCategory12121851485.9% / 14.1%751286.2% / 13.8%292775.0% / 25.0%123575.0% / 25.0%Correct / Incorrect90.4% / 9.6%65.9% / 34.1%83.0% / 17.0%86.2% / 18.8%75.0% / 25.0%82.2% / 17.8%

7. SUPPORT VECTOR MACHINES

ALT AALT B

OBSERVED

PREDICTED (Operational)

Correct / Incorrect

PREDICTED (Structural)

Correct / Incorrect

Category

0

1

2

0

1

201701750% / 50%1461046.7% / 53.3%17064645.7% / 54.3%17371057.8% / 42.2%248163233.3% / 66.7%1202970.7% / 29.3%Correct / Incorrect12.6% / 87.4%80.0% / 20.0%58.2% / 41.8%41.9% / 58.1%32.6% / 67.4%86.0% / 14.0%59.2% / 40.8%59.3% / 40.7%OBSERVEDPREDICTED (Operational)Correct / IncorrectPREDICTED (Structural)Correct / IncorrectCategory12121831188.3% / 11.7%80792.0% / 8.0%2182356.1% / 43.9%321633.3% / 66.7%Correct / Incorrect82.2% / 17.8%67.6% / 32.4%78.5% / 21.5%71.4% / 28.6%69.6% / 30.4%71.1% / 28.9%

8. DISCRIMINANT ANALYSIS

ALT AALT B

OBSERVED

PREDICTED (Operational)

Correct / Incorrect

PREDICTED (Structural)

Correct / Incorrect

Category

0

1

2

0

1

201261240.0% / 60.0%411223.5% / 76.5%115371257.8% / 42.2%0561480.0% / 20.0%21202970.7% / 29.3%0272143.8% / 56.3%Correct / Incorrect30.8% / 69.2%86.0% / 14.0%54.7% / 45.3%57.8% / 42.2%100.0% / 0.0%59.6% / 40.4%56.8% / 43.2%60.0% / 40.0%OBSERVEDPREDICTED (Operational)Correct / IncorrectPREDICTED (Structural)Correct / IncorrectCategory12121841089.4% / 10.6%79890.8% / 9.2%2172458.5% / 41.5%301837.5% / 62.5%Correct / Incorrect83.2% / 16.8%70.6% / 29.4%80.0% / 20.0%72.5% / 72.5%69.2% / 30.8%71.9% / 28.1%

9. CONCLUSIONS

The different methods yielded very similar overall result. Since the main goal of modelling the condition of sewers is to identify the sewer reaches that may need intervention, the ANNs’ results provided better results given the approach adopted. However, contrarily to the SVMs and discriminant analysis, the ANNs’ results depend significantly in various factors.

The increase of the number of classes resulted in a decrease in the models accuracy.

REFERENCES

Ana, E. V. (2009). Sewer asset management - sewer structural deterioration modeling and multicriteria decision making in sewer rehabilitation projects prioritization. PhD Thesis, Faculty of Engineering, Vrije Universiteit Brussel, Brussels, Belgium. Ariaratnam, T. S.; Assaly, E. A.; Yuqing, Y. (2001). Assessment of infrastructure inspection needs using logistic models. Journal of Infrastructure Systems, 7(4):66-72. Baik

, H. S.; Jeong, H. S.; Abraham, D. M. (2006). Estimating transition probabilities in

markov

chain-based deterioration models for management of wastewater systems. Journal of Water Resources Planning and Management, 132(1):15-24.

Baur

, R.;

Herz

, R. (2002). Selective inspection planning with ageing forecast for sewer types. Water Science and Technology, 46(6-7):379-387.

Baur

, R.;

Zielichowski

-Haber, W.;

Kropp, I. (2004). Statistical analysis of inspection data for the asset management of sewer networks. In Proceedings 19th EJSW on Process Data and Integrated Urban Water Modeling, Lyon, France. Chughtai, F; Zayed, T. (2007a). Structural condition models for sewer pipeline. Pipelines 2007: Advances and Experiences with Trenchless Pipeline Projects, 8–11 July, Boston, USA. Chughtai, F; Zayed, T. (2007b). Sewer pipeline operational condition prediction using multiple regression. Pipelines 2007: Advances and Experiences with Trenchless Pipeline Projects, 8–11 July, Boston, USA. Chughtai, F; Zayed, T. (2008). Infrastructure condition prediction models for sustainable sewer pipelines. Journal of Performance of Constructed Facilities, 22(5):333-341.Davies, J.; Clarke, B.; Whiter, J.; Cunningham, R. (2001). The structural condition of rigid sewer pipes: a statistical investigation. Urban Water, 3:277-286. Dirksen, J.; Clemens, F. H. L. R. (2008). Probabilistic modeling of sewer deterioration using inspection data. Water Science & Technology, 57(10):1635-1641. Fenner, R. A.; McFarland, G.; Thorne, O. (2007). Case-based reasoning approach for managing sewerage assets. Proceedings of the Institution of Civil Engineers, Water Management, 160(WM1):15–24.

REFERENCES

Hörold, S.; Baur, R. (1999). Modeling sewer deterioration for selective inspection planning – case study Dresden. In Proceedings 13th EJSW on Service Life Management Strategies of Water Mains and Sewers, 8-12 September, Switzerland. Khan, Z.; Zayed, T.; Moselhi, O. (2010). Structural condition assessment of sewer pipelines. Journal of Performance of Constructed Facilities, 24(2):170-179. Kleiner, Y. (2001). Scheduling inspection and renewal of large infrastructure assets. Journal of Infrastructure Systems, 7(4):136-143.

Kleiner, Y.;

Rajani

, B.;

Sadiq

, R. (2004a).

Modeling failure risk in buried pipes using fuzzy Markov deterioration process”, 4th International Conference on Decision Making in Urban and Civil Engineering, 28-30 October, Porto, Portugal, pp. 1-11.

Kleiner

, Y.;

Sadiq

, R.;

Rajani

, B. (2004b). Modeling failure risk in buried pipes using fuzzy Markov deterioration process. Pipelines 2004, Conference Proceedings, ASCE, San Diego, California, USA, pp. 7-16. Kleiner, Y.; Sadiq, R.; Rajani, B. B. (2006). Modelling the deterioration of buried infrastructure as a fuzzy Markov process. Journal of Water Supply Research and Technology: Aqua, 55(2):67-80. Koo, D.-H.; Ariaratnam, S. T. (2006). Innovative method for assessment of underground sewer pipe condition. Automation in Construction, 15:479-488. Le Gat, Y. (2008). Modelling the deterioration process of drainage pipelines. Urban Water, 5(2):97-106. Mashford, J.; Marlow, D.; Tran, T.; May, R. (2011). Prediction of Sewer Condition Grade Using Support Vector Machines. Journal of Computing in Civil Engineering, 25(4):283-290. Micevski, T.; Kuczera, G.; Coombes, P. (2002). Markov model for storm water pipe deterioration. Journal of Infrastructure Systems, 8(2):49–56. multi-objective data mining. Journal of Hydroinformatics, 11(3–4):211-224. Najafi, M.; Kulandaivel, G. (2005). Pipeline condition prediction using neural network models. Pipelines 2005, ASCE, Reston, VA, USA, pp. 767–775.

REFERENCES

Pohls, O. (2001). The analysis of tree root blockages in sewer lines & their prevention methods. MSc. Thesis, Institute of Land and Food Resources, University of Melbourne, Melbourne, Australia. Savic, D. A.; Giustolisi, O.; Laucelli, D. (2009). Asset deterioration analysis using multi-utility data and Savic, D.; Giustolisi

, O.; Berardi, L.; Shepherd, W.;

Djordjevic

, S.; Saul, A. (2006).

Modelling

sewer failure by evolutionary computing. Proceedings of the Institution of Civil Engineers, Water Management, 159(WM2):111-118.

Tran, D. H.; Ng, A. W. M.; Perera, B. J. C.; Davis, P. (2006).

Application of probabilistic neural networks in modeling structural deterioration of

stormwater

pipes. Urban Water Journal, 3(3):175–184.

Tran, H. (2007) Investigation of deterioration models for

stormwater

pipe systems. PhD Thesis, Victoria University, School of Architectural, Civil and Mechanical Engineering Faculty of Health, Engineering and Science, Victoria, Australia. Ugarelli, R.; Kristensin, S. M.; Røstum, J.; Sægrov, S.; Di Frederico; V. (2008). Statistical analysis and definition of blockages-prediction formulae for the wastewater network of Oslo by evolutionary computing. 11th International Conference in Urban Drainage, Edinburgh, Scotland, UK. Wirahadikusumah, R.; Abraham, D.; Iseley, T. (2001). Challenging issues in modeling deterioration of combined sewers. Journal of Infrastructure Systems, 7(2):77-84. Yan, J.; Vairavamoorthy, K. (2003). Fuzzy approach for pipe condition assessment. Proc., New Pipeline Technologies, Security, and Safety, ASCE, Reston, Va., pp. 466–476. Yang, Y. (1999). Statistical models for assessing sewer infrastructure inspection requirements. MSc. Thesis, Department of Civil and Environmental Engineering, University of Alberta, Edmonton, Alberta, Canada.

RISK ASSESSMENT OF SEWER CONDITION USING ARTIFICIAL INTELLIGENCE TOOLS Application to the SANEST sewer system

Vitor SousaIST, UTLJosé Pedro MatosIST, UTLNuno Marques AlmeidaIST, UTLJosé Saldanha MatosIST, UTL

http://www.toledoblade.com/Police-Fire/2013/07/06/Sewer-repairs-start-after-intersection-collapse-Copy.html