Machine Learning

, Volume 95, Issue 1, pp 11–26 | Cite as

Water pipe condition assessment: a hierarchical beta process approach for sparse incident data

  • Zhidong Li
  • Bang Zhang
  • Yang Wang
  • Fang Chen
  • Ronnie Taib
  • Vicky Whiffin
  • Yi Wang
Article

Abstract

Prediction of water pipe condition through statistical modelling is an important element for the risk management strategy of water distribution systems. In this work a hierarchical nonparametric model has been used to enhance the performance of pipe condition assessment. The main aims of this work are three-fold: (1) For sparse incident data, develop an efficient approximate inference algorithm based on hierarchical beta process. (2) Apply the hierarchical beta process based method to water pipe condition assessment. (3) Interpret the outcomes in financial terms usable by the water utilities. The experimental results show superior performance of the proposed method compared to current best practice methods, leading to substantial savings on reactive repairs and maintenance, as well as improved prioritization for capital expenditure.

Keywords

Hierarchical beta process Bayesian nonparametric Water main Condition assessment Sparse data 

References

  1. Andreou, S. A., Marks, D. H., & Clark, R. M. (1987). A new methodology for modelling break failure patterns in deteriorating water distribution systems: theory. Advances in Water Resources, 10, 11–20. CrossRefGoogle Scholar
  2. Awumah, K., Goulter, I., & Bhatt, S. K. (1990). Assessment of reliability in water distribution networks using entropy based measures. Stochastic Hydrology and Hydraulics, 4, 309–320. CrossRefGoogle Scholar
  3. Chen, X., Zhou, M., & Carin, L. (2012). The contextual focused topic model. In 18th ACM SIGKDD international conference on knowledge discovery and data mining (pp. 96–104). CrossRefGoogle Scholar
  4. Cox, D. R. (1972). Regression models and life-tables. Journal of the Royal Statistical Society, Series B Methodological, 187–220. Google Scholar
  5. Fares, H., & Zayed, T. (2010). Hierarchical fuzzy expert system for risk of failure of water mains. Journal of Pipeline Systems Engineering and Practice, 1, 53–62. CrossRefGoogle Scholar
  6. Ferguson, P., Heathcote, M., Moore, G., & Russsell, D. (1996). Condition assessment of water mains using remote field technology. Journal - American Water Works Association, 23, 6–8. Google Scholar
  7. Griffiths, T. L., & Ghahramani, Z. (2011). The Indian Buffet process: an introduction and review. Journal of Machine Learning Research, 12, 1185–1224. MathSciNetMATHGoogle Scholar
  8. Hjort, N. L. (1990). Nonparametric Bayes estimators based on beta processes in models for life history data. The Annals of Statistics, 18(3), 1259–1294. MathSciNetCrossRefMATHGoogle Scholar
  9. Ibrahim, J., Chen, M.-H., & Sinha, D. (2001). Bayesian survival analysis. Berlin: Springer. CrossRefMATHGoogle Scholar
  10. Japkowicz, N., & Shah, M. (2011). Evaluating learning algorithms, a classification perspective. Cambridge: Cambridge University Press. CrossRefMATHGoogle Scholar
  11. Kettler, A. J., & Goulter, I. C. (1985). An analysis of pipe breakage in urban water distribution networks. Canadian Journal of Civil Engineering, 12, 286–293. CrossRefGoogle Scholar
  12. Klein, J. P., & Goel, P. K. (1992). Survival analysis: state of the art. Berlin: Springer. CrossRefMATHGoogle Scholar
  13. Kleiner, Y., & Rajani, B. B. (2001). Comprehensive review of structural deterioration of water mains: statistical models (Technical report NRCC–42586). National Research Council Canada. Google Scholar
  14. Marks, H. D., Andreou, S., Jeffrey, L., Park, C., & Zaslavski, A. (1987). Statistical models for water main failures. US Environmental Protection Agency (Co-operative Agreement CR8-1-0558) M.I.T. Office of Sponsored Projects No. 94211. Boston, MA. Google Scholar
  15. Micevski, T., Kuczera, G., & Coombes, P. (2002). Markov model for storm water pipe deterioration. Journal of Infrastructure Systems, 8, 49–56. CrossRefGoogle Scholar
  16. Misiunas, D. (2005). Failure monitoring and asset condition assessment in water supply systems. Doctoral dissertation, Lund University, Sweden. Google Scholar
  17. Murray, J. F., Hughes, G. F., & Kreutz-Delgado, K. (2006). Machine learning methods for predicting failures in hard drives: a multiple-instance application. Journal of Machine Learning Research, 6, 783–816. MathSciNetMATHGoogle Scholar
  18. Paisley, J., & Carin, L. (2009). Nonparametric factor analysis with beta process priors. In 26th Annual international conference on machine learning (pp. 777–784). Google Scholar
  19. Pelletier, G., Mailhot, A., & Villeneuve, J. P. (2003). Modeling water pipe breaks-three case studies. Journal of Water Resources Planning and Management, 129(2), 115–123. CrossRefGoogle Scholar
  20. Rajani, B. B., & Kleiner, Y. (2001). Comprehensive review of structural deterioration of water mains: physically based models (Technical report NRCC-43722). National Research Council Canada. Google Scholar
  21. Rogers, P. D. (2011). Prioritizing water main renewals: case study of the Denver water system. Journal of Pipeline Systems Engineering and Practice, 2, 73–81. CrossRefGoogle Scholar
  22. Rogers, P. D., & Grigg, N. S. (2009). Failure assessment modeling to prioritize water pipe renewal: two case studies. Journal of Infrastructure Systems, 15, 162–171. CrossRefGoogle Scholar
  23. Shamir, U., & Howard, C. D. D. (1979). An analytic approach to scheduling pipe replacement. Journal - American Water Works Association, 71(5), 248–258. Google Scholar
  24. Tchórzewska-Cieślak, B. (2011). Fuzzy failure risk analysis in drinking water technical system. Reliability: Theory and Applications, 2, 138–148. Google Scholar
  25. Teh, Y. W., Jordan, M. I., Beal, M. J., & Blei, D. M. (2006). Hierarchical Dirichlet processes. Journal of the American Statistical Association, 101, 1566–1581. MathSciNetCrossRefMATHGoogle Scholar
  26. Thibaux, R., & Jordan, M. I. (2007). Hierarchical beta processes and the Indian Buffet process. In International conference on artificial intelligence and statistics (pp. 564–571). Google Scholar
  27. Tian, C. H., Xiao, J., Huang, J., & Albertao, F. (2011). Pipe failure prediction. In IEEE international conference on service operations, logistics, and informatics. Google Scholar
  28. Wang, Y., Li, Z., Wang, Y., & Chen, F. (2013). A Bayesian non-parametric viewpoint to visual tracking. In Workshop on the applications of computer vision (pp. 482–488). Google Scholar
  29. Yang, S. K. (2003). A condition-based failure-prediction and processing-scheme for preventive maintenance. IEEE Transactions on Reliability, 52, 373–383. CrossRefGoogle Scholar
  30. Zhou, M., Chen, H., Paisley, J., Lu, R., Sapiro, G., & Carin, L. (2009). Non-parametric Bayesian dictionary learning for sparse image representations. In Advances in neural information processing systems. Google Scholar
  31. Zhou, M., Yang, H., Sapiro, G., Dunson, D., & Carin, L. (2011). Dependent hierarchical beta process for image interpolation and de-noising. In International conference on artificial intelligence and statistics (pp. 883–891). Google Scholar

Copyright information

© The Author(s) 2013

Authors and Affiliations

  • Zhidong Li
    • 1
    • 2
  • Bang Zhang
    • 1
    • 2
  • Yang Wang
    • 1
  • Fang Chen
    • 1
    • 2
  • Ronnie Taib
    • 1
  • Vicky Whiffin
    • 3
  • Yi Wang
    • 1
    • 2
  1. 1.National ICT AustraliaSydneyAustralia
  2. 2.University of New South WalesSydneyAustralia
  3. 3.Sydney WaterSydneyAustralia

Personalised recommendations