ABSTRACT
Pipe failure prediction in the water industry aims to prioritize the pipes that are at high risk of failure for proactive maintenance. However, existing statistical or machine learning models that rely on historical failures and asset attributes can hardly leverage the structure information of pipe networks. In this work, we develop a failure prediction framework for pipe networks by jointly considering the pipes' features, the network structure, the geographical neighboring effect, and the temporal failure series. We apply a multi-hop Graph Neural Network (GNN) to failure prediction. We propose a method of constructing a geographical graph structure depending on not only the physical connections but also geographical distances between pipes. To differentiate the pipes with diverse properties, we employ an attention mechanism in the neighborhood aggregation process of each GNN layer. Also, residual connections and layer-wise aggregation are used to avoid the over-smoothing issue in deep GNNs. The historical failures exhibit a strong temporal pattern. Inspired by point process, we develop a module to learn the pipes' evolutionary effect and the time-decayed excitement of historical failures on the current state of the pipe. The proposed framework is evaluated on two real-world large-scale pipe networks. It outperforms the existing statistical, machine learning, and state-of-the-art GNN baselines. Our framework provides the water utility with core data-driven support for proactive maintenance including regular pipe inspection, pipe renewal planning, and sensor system deployment. It can be extended to other infrastructure networks in the future.
Supplemental Material
- Sami Abu-El-Haija, Bryan Perozzi, Amol Kapoor, Nazanin Alipourfard, Kristina Lerman, Hrayr Harutyunyan, Greg Ver Steeg, and Aram Galstyan. 2019. Mixhop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixing. In Proceedings of the 36th International Conference on Machine Learning (Proceedings of Machine Learning Research, Vol. 97),, Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 21--29.Google Scholar
- André Altmann, Laura Tolocşi, Oliver Sander, and Thomas Lengauer. 2010. Permutation importance: a corrected feature importance measure. Bioinformatics, Vol. 26, 10 (2010), 1340--1347. Google ScholarDigital Library
- Lars Backstrom and Jure Leskovec. 2011. Supervised random walks: predicting and recommending links in social networks. In Proceedings of the fourth ACM international conference on Web search and data mining. 635--644. Google ScholarDigital Library
- Neal Andrew Barton, Timothy Stephen Farewell, Stephen Henry Hallett, and Timothy Francis Acland. 2019. Improving pipe failure predictions: Factors affecting pipe failure in drinking water networks. Water research, Vol. 164 (2019), 114926.Google Scholar
- Tianqi Chen and Carlos Guestrin. 2016. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 785--794. Google ScholarDigital Library
- Sophie Duchesne, Guillaume Beardsell, Jean-Pierre Villeneuve, Babacar Toumbou, and Kassandra Bouchard. 2013. A survival analysis model for sewer pipe structural deterioration. Computer-Aided Civil and Infrastructure Engineering, Vol. 28, 2 (2013), 146--160.Google ScholarCross Ref
- Vijay Prakash Dwivedi, Chaitanya K Joshi, Thomas Laurent, Yoshua Bengio, and Xavier Bresson. 2020. Benchmarking graph neural networks. arXiv preprint arXiv:2003.00982 (2020).Google Scholar
- Raziyeh Farmani, Konstantinos Kakoudakis, Kourosh Behzadian, and David Butler. 2017. Pipe failure prediction in water distribution systems considering static and dynamic factors. Procedia Engineering, Vol. 186 (2017), 117--126.Google ScholarCross Ref
- Mónica Marcela Giraldo-González and Juan Pablo Rodríguez. 2020. Comparison of statistical and machine learning models for pipe failure modeling in water distribution networks. Water, Vol. 12, 4 (2020), 1153.Google ScholarCross Ref
- Aric Hagberg, Pieter Swart, and Daniel S Chult. 2008. Exploring network structure, dynamics, and function using NetworkX. Technical Report. Los Alamos National Lab.(LANL), Los Alamos, NM (United States).Google Scholar
- Will Hamilton, Zhitao Ying, and Jure Leskovec. 2017. Inductive representation learning on large graphs. In Advances in neural information processing systems. 1024--1034. Google ScholarDigital Library
- Alan G Hawkes. 1971. Spectra of some self-exciting and mutually exciting point processes. Biometrika, Vol. 58, 1 (1971), 83--90.Google ScholarCross Ref
- Hemant Ishwaran, Udaya B Kogalur, Eugene H Blackstone, Michael S Lauer, et al. 2008. Random survival forests. Annals of Applied Statistics, Vol. 2, 3 (2008), 841--860.Google ScholarCross Ref
- Thomas N. Kipf and Max Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In International Conference on Learning Representations (ICLR).Google Scholar
- Avishek Kumar, Syed Ali Asad Rizvi, Benjamin Brooks, R Ali Vanderveld, Kevin H Wilson, Chad Kenney, Sam Edelstein, Adria Finch, Andrew Maxwell, Joe Zuckerbraun, et al. 2018. Using machine learning to assess the risk of and prevent water main breaks. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 472--480. Google ScholarDigital Library
- Guohao Li, Chenxin Xiong, Ali Thabet, and Bernard Ghanem. 2020 b. Deepergcn: All you need to train deeper gcns. arXiv preprint arXiv:2006.07739 (2020).Google Scholar
- Pan Li, Yanbang Wang, Hongwei Wang, and Jure Leskovec. 2020 a. Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning. arXiv preprint arXiv:2009.00142 (2020).Google Scholar
- Qimai Li, Zhichao Han, and Xiao-Ming Wu. 2018. Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, (AAAI-18), New Orleans, Louisiana, USA, February 2-7, 2018,, Sheila A. McIlraith and Kilian Q. Weinberger (Eds.). AAAI Press, 3538--3545.Google ScholarCross Ref
- Zhidong Li, Bang Zhang, Yang Wang, Fang Chen, Ronnie Taib, Vicky Whiffin, and Yi Wang. 2014. Water pipe condition assessment: a hierarchical beta process approach for sparse incident data. Machine learning, Vol. 95, 1 (2014), 11--26. Google ScholarDigital Library
- Bin Liang, Zhidong Li, Yang Wang, and Fang Chen. 2018. Long-term RNN: Predicting hazard function for proactive maintenance of water mains. In Proceedings of the 27th acm international conference on information and knowledge management. 1687--1690. Google ScholarDigital Library
- Peng Lin, Bang Zhang, Yi Wang, Zhidong Li, Bin Li, Yang Wang, and Fang Chen. 2015. Data driven water pipe failure prediction: A bayesian nonparametric approach. In Proceedings of the 24th ACM International on Conference on Information and Knowledge Management. 193--202. Google ScholarDigital Library
- Xuan Lin, Zhe Quan, Zhi-Jie Wang, Tengfei Ma, and Xiangxiang Zeng. 2020. Kgnn: Knowledge graph neural network for drug-drug interaction prediction. In Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20 (International Joint Conferences on Artificial Intelligence Organization). 2739--2745.Google ScholarCross Ref
- Charles X Ling, Jin Huang, and Harry Zhang. 2003. AUC: a better measure than accuracy in comparing learning algorithms. In Conference of the canadian society for computational studies of intelligence. Springer, 329--341. Google ScholarDigital Library
- Dino Obradović. 2017. The impact of tree root systems on wastewater pipes. Zbornik radova, Zajednivčki temelji (2017), 65--71.Google Scholar
- Suwan Park, Hwandon Jun, Newland Agbenowosi, Bong Jae Kim, and Kiyoung Lim. 2011. The proportional hazards modeling of water main failure data incorporating the time-dependent effects of covariates. Water resources management, Vol. 25, 1 (2011), 1--19.Google Scholar
- Katarzyna Pietrucha-Urbanik. 2015. Failure analysis and assessment on the exemplary water supply network. Engineering failure analysis, Vol. 57 (2015), 137--142.Google Scholar
- Thomas B Randrup, E Gregory McPherson, and Laurence R Costello. 2001. Tree root intrusion in sewer systems: review of extent and costs. Journal of Infrastructure Systems, Vol. 7, 1 (2001), 26--31.Google ScholarCross Ref
- Alicia Robles-Velasco, Pablo Cortés, Jesús Muñuzuri, and Luis Onieva. 2020. Prediction of pipe failures in water supply networks using logistic regression and support vector classification. Reliability Engineering & System Safety, Vol. 196 (2020), 106754.Google ScholarCross Ref
- C Schmitt, G Pluvinage, E Hadj-Taieb, and R Akid. 2006. Water pipeline failure due to water hammer effects. Fatigue & Fracture of Engineering Materials & Structures, Vol. 29, 12 (2006), 1075--1082.Google ScholarCross Ref
- Uri Shamir and Charles DD Howard. 1979. An analytic approach to scheduling pipe replacement. Journal-American Water Works Association, Vol. 71, 5 (1979), 248--258.Google ScholarCross Ref
- Brett Snider and Edward A McBean. 2020. Improving urban water security through pipe-break prediction models: Machine learning or survival analysis. Journal of Environmental Engineering, Vol. 146, 3 (2020), 04019129.Google ScholarCross Ref
- Kiran K Thekumparampil, Chong Wang, Sewoong Oh, and Li-Jia Li. 2018. Attention-based graph neural network for semi-supervised learning. arXiv preprint arXiv:1803.03735 (2018).Google Scholar
- Petar Veličković, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Liò, and Yoshua Bengio. 2018. Graph Attention Networks. In International Conference on Learning Representations.Google Scholar
- Keyulu Xu, Chengtao Li, Yonglong Tian, Tomohiro Sonobe, Ken-ichi Kawarabayashi, and Stefanie Jegelka. 2018. Representation learning on graphs with jumping knowledge networks. In International Conference on Machine Learning. PMLR, 5453--5462.Google Scholar
- Junchi Yan, Yu Wang, Ke Zhou, Jin Huang, Chunhua Tian, Hongyuan Zha, and Weishan Dong. 2013. Towards effective prioritizing water pipe replacement and rehabilitation. In Twenty-third international joint conference on artificial intelligence. Citeseer. Google ScholarDigital Library
- Rex Ying, Ruining He, Kaifeng Chen, Pong Eksombatchai, William L Hamilton, and Jure Leskovec. 2018. Graph convolutional neural networks for web-scale recommender systems. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 974--983. Google ScholarDigital Library
- Jiani Zhang, Xingjian Shi, Junyuan Xie, Hao Ma, Irwin King, and Dit Yan Yeung. 2018. GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs. In 34th Conference on Uncertainty in Artificial Intelligence 2018, UAI 2018.Google Scholar
Index Terms
- Failure Prediction for Large-scale Water Pipe Networks Using GNN and Temporal Failure Series
Recommendations
Data Driven Water Pipe Failure Prediction: A Bayesian Nonparametric Approach
CIKM '15: Proceedings of the 24th ACM International on Conference on Information and Knowledge ManagementWater pipe failures can cause significant economic and social costs, hence have become the primary challenge to water utilities. In this paper, we propose a Bayesian nonparametric approach, namely the Dirichlet process mixture of hierarchical beta ...
Pipe failure prediction: A data mining method
ICDE '13: Proceedings of the 2013 IEEE International Conference on Data Engineering (ICDE 2013)Pipe breaks in urban water distribution network lead to significant economical and social costs, putting the service quality as well as the profit of water utilities at risk. To cope with such a situation, scheduled preventive maintenance is desired, ...
Software failure time series prediction with RBF, GRNN, and LSTM neural networks
AbstractThe important task of software quality assurance is failure prediction. Time series forecasting methods can be successfully used for this purpose. This paper aims to study and compare the effectiveness of software failure prediction using ...
Comments