Dynamic Modeling of Failure Events in Preventative Pipe Maintenance

Urban water supply network is ubiquitous and indispensable to city dwellers, especially in the era of global urbanization. Preventative maintenance of water pipes, especially in urban-scale networks, thus becomes a vital importance. To achieve this goal, failure prediction that aims to pro-actively pinpoint those “most-risky-to-fail” pipes becomes critical and has been attracting wide attention from government, academia, and industry. Different from classification-, regression-, or ranking-based methods, this paper adopts a point process-based framework that incorporates both the past failure event data and individual pipe-specific profile including physical, environmental, and operational covariants. In particular, based on a common wisdom of previous work that the failure event sequences typically exhibit temporal clustering distribution, we use mutual-exciting point process to model such triggering effects for different failure types. Our system is deployed as a platform commissioned by the water agency in a metropolitan city in Asia, and achieves state-of-the-art performance on an urban-scale pipe network. Our model is generic and thus can be applied to other industrial scenarios for event prediction.

[1]  Haimonti Dutta,et al.  Machine Learning for the New York City Power Grid , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  P. Diggle,et al.  Monte Carlo Methods of Inference for Implicit Statistical Models , 1984 .

[3]  Wenzhong Shi,et al.  Spatial analysis of water mains failure clusters and factors: a Hong Kong case study , 2013, Ann. GIS.

[4]  A. Hawkes,et al.  A cluster process representation of a self-exciting process , 1974, Journal of Applied Probability.

[5]  Ana Debón,et al.  Comparing risk of failure models in water supply networks using ROC curves , 2010, Reliab. Eng. Syst. Saf..

[6]  C. Rudin,et al.  Reactive point processes: A new approach to predicting power failures in underground electrical systems , 2015, 1505.07661.

[7]  A. Dassios,et al.  Exact Simulation of Hawkes Process with Exponentially Decaying Intensity , 2013 .

[8]  Le Song,et al.  Learning Triggering Kernels for Multi-dimensional Hawkes Processes , 2013, ICML.

[9]  Xin Yao,et al.  Pipe failure prediction: A data mining method , 2013, 2013 IEEE 29th International Conference on Data Engineering (ICDE).

[10]  Uri Shamir,et al.  An Analytic Approach to Scheduling Pipe Replacement , 1979 .

[11]  A. Stomakhin,et al.  Reconstruction of missing data in social networks based on temporal patterns of interactions , 2011 .

[12]  Hongyuan Zha,et al.  Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence Towards Effective Prioritizing Water Pipe Replacement and Rehabilitation ∗ , 2022 .

[13]  Abdelwahab M. Bubtiena,et al.  Application of Artificial Neural networks in modeling water networks , 2011, 2011 IEEE 7th International Colloquium on Signal Processing and its Applications.

[14]  Changsheng Li,et al.  Modeling Contagious Merger and Acquisition via Point Processes with a Profile Regression Prior , 2016, IJCAI.

[15]  I. C. Goulter,et al.  Spatial and temporal groupings of water main pipe breakage in Winnipeg , 1988 .

[16]  Alison M. St. Clair,et al.  State-of-the-technology review on water pipe condition, deterioration and failure rate prediction models! , 2012 .

[17]  James H. Garrett,et al.  Detection of Patterns in Water Distribution Pipe Breakage Using Spatial Scan Statistics for Point Events in a Physical Network , 2011, J. Comput. Civ. Eng..

[18]  Visakan Kadirkamanathan,et al.  Point process modelling of the Afghan War Diary , 2012, Proceedings of the National Academy of Sciences.

[19]  Yoram Singer,et al.  An Efficient Boosting Algorithm for Combining Preferences by , 2013 .

[20]  Hongyuan Zha,et al.  Energy Usage Behavior Modeling in Energy Disaggregation via Marked Hawkes Process , 2015, AAAI.

[21]  Thomas Hofmann,et al.  Support vector machine learning for interdependent and structured output spaces , 2004, ICML.

[22]  Balvant Rajani,et al.  Using limited data to assess future needs , 1999 .

[23]  S. Xanthos,et al.  Urban Water Distribution Network Asset Management Using Spatio-Temporal Analysis of Pipe-Failure Data , 2012 .

[24]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[25]  Seth D. Guikema,et al.  Statistical models for the analysis of water distribution system pipe break data , 2009, Reliab. Eng. Syst. Saf..

[26]  Jing Xiao,et al.  Pipe failure prediction , 2011, Proceedings of 2011 IEEE International Conference on Service Operations, Logistics and Informatics.

[27]  Hongyuan Zha,et al.  On Machine Learning towards Predictive Sales Pipeline Analytics , 2015, AAAI.

[28]  Y. Ogata.  Space-Time Point-Process Models for Earthquake Occurrences , 1998 .

[29]  Hongbo Deng,et al.  Identifying and labeling search tasks via query-based hawkes processes , 2014, KDD.

[30]  Le Song,et al.  Learning Social Infectivity in Sparse Low-rank Networks Using Multi-dimensional Hawkes Processes , 2013, AISTATS.

[31]  Thomas Josef Liniger,et al.  Multivariate Hawkes processes , 2009 .

[32]  Yosihiko Ogata,et al.  Statistical Models for Earthquake Occurrences and Residual Analysis for Point Processes , 1988 .

[33]  Haimonti Dutta,et al.  A process for predicting manhole events in Manhattan , 2009, Machine Learning.

[34]  Mark Goadrich,et al.  The relationship between Precision-Recall and ROC curves , 2006, ICML.

[35]  A. Hawkes.  Spectra of some self-exciting and mutually exciting point processes , 1971 .

[36]  Jean-Pierre Villeneuve,et al.  Modeling Water Pipe Breaks—Three Case Studies , 2003 .

[37]  Ya Zhang,et al.  Multi-touch Attribution in Online Advertising with Survival Theory , 2014, 2014 IEEE International Conference on Data Mining.

[38]  B. Kingdom,et al.  The challenge of reducing non-revenue water (NRW) in developing countries - how the private sector can help : a look at performance-based service contracting , 2006 .