Machine learning-assisted optimal schedule of underground water pipe inspection

Journal of Infrastructure Preservation and Resilience
Xudong Fan1, Xiong Yu1
1Department of Civil and Environmental Engineering, Case Western Reserve University, 2104 Adelbert Road, Bingham 206, Cleveland, OH, 44106-7201, USA

Tóm tắt

AbstractThere are over 2.2 million miles of underground water pipes serving the cities in the United States. Many are in poor conditions and deteriorate rapidly. Failures of these pipes could cause enormous financial losses to the customers and communities. Inspection provides crucial information for pipe condition assessment and maintenance plan; it, however, is very expensive for underground pipes due to accessibility issues. Therefore, water agencies commonly face the challenge to 1) decide whether it is worthwhile to schedule expensive water pipe inspections under financial constraints, and 2) if so, how to optimize the inspection schedule to maximize its value. This study leverages the physical model and data-based ML (ML) models for underground water pipe failure prediction to shed light on these two important questions for decision making. Analyses are firstly conducted to assess the value of water pipe inspection. Results by use of a physical-based failure model and Monte Carlo simulations indicate that by inspecting pipe’s condition, i.e., assessment of pipe’s erosion depth, the uncertainty of water pipe failure prediction can be narrowed down by 51%. For optimal inspection schedule, an artificial neural network (ANN) model, trained with historical inspection data, is evaluated for its performance in forecasting the future pipe failure probability. The results showed that a biased pipe failure prediction can occur under limited rounds of inspection. However, incorporating more rounds of inspection allows to predict the pipe failure conditions over its life cycle. From this, an optimal inspection plan can be proposed to achieve the maximum benefits of inspection in uncertainty reduction. A few salient results from the analyses include 1) the optimal schedule for inspection is not necessarily equal in the time interval, 2) by setting the goal of uncertainty reduction, an optimal inspection schedule can be obtained, where ML (ML) model augmented by continuously training with inspection data allows to reliably predict water pipe failure conditions over its life cycle. While this study focuses on underground pipe inspection, the general observations and methodology are applicable to optimize the inspection of other types of infrastructure as well.

Từ khóa


Tài liệu tham khảo

Abokifa AA, Haddad K, Lo C, Biswas P (2018) Real-time identification of cyber-physical attacks on water distribution systems via machine learning-based anomaly detection techniques. J Water Resour Plan Manag 145(1):04018089

Ahammed M, Melchers R (1994) Reliability of underground pipelines subject to corrosion. J Transp Eng 120(6):989–1002

Ahammed M, Melchers R (1997) Probabilistic analysis of underground pipelines subject to combined stresses and corrosion. Eng Struct 19(12):988–994

Apicella A, Donnarumma F, Isgrò F, Prevete R (2021) A survey on modern trainable activation functions. Neural Netw 138:14–32

ASCE (2021). 2021 Infrastructure report card. www.infrastructurereportcard.org

American Water Works Association (1967) USA standard for thickness design of cast-iron pipe. Standard H1-67. New York

American Water Works Association (2001) Dawn of the replacement era: reinvesting in drinking water infrastructure: an analysis of twenty utilities’ needs for repair and replacement of drinking water infrastructure. American Water Works Association, New York

Campanella K, Andreasen C, Diba A, Himmelberger H, Leighton J, Santini J, Vause K (2016) 2015 establishing the level of progress in utility asset management survey results. Proc Water Environ Fed 1:462–490

Davis P, Burn S, Moglia M, Gould S (2007) A physical probabilistic model to predict failure rates in buried PVC pipelines. Reliab Eng Syst Saf 92(9):1258–1266

Dawood T, Elwakil E, Novoa HM, Gárate Delgado JF (2020) Water pipe failure prediction and risk models: state-of-the-art review. Can J Civ Eng 47(10):1117–1127

De Silva D, Moglia M, Davis P, Burn S (2002) Condition assessment and probabilistic analysis to estimate failure rates in buried pipelines. In: Proceedings of ASTT 5th Conference

Denison I, Darnielle R (1939) Observations on the behavior of steel corroding under cathodic control in soils. Trans Electrochem Soc 76(1):199–214

Dey PK (2003) Analytic hierarchy process analyzes risk of operating cross-country petroleum pipelines in India. Nat Hazard Rev 4(4):213–221

Dey PK (2004) Decision support system for inspection and maintenance: a case study of oil pipelines. IEEE Trans Eng Manage 51(1):47–56

Doyle G, Seica MV, Grabinsky MW (2003) The role of soil in the external corrosion of cast iron water mains in Toronto, Canada. Can Geotech J 40(2):225–236

Ewing S (1932) Rough correlation between corrosiveness and resistivity for alkali soils. Oil Gas J 30:29

Fan X, Wang X, Zhang X, Yu, X. (2022) Machine learning based water pipe failure prediction: the effects of engineering, geology, climate and socio-economic factors. Reliab Eng Syst Saf 219:108185

Jain AK, Mao J, Mohiuddin KM (1996) Artificial neural networks: A tutorial. Computer 29(3):31–44

Kajiyama F, Koyama Y (1997) Statistical analyses of field corrosion data for ductile cast iron pipes buried in sandy marine sediments. Corrosion 53(2):156–162

Kamran M, Ullah B, Ahmad M, Sabri MMS (2022) Application of KNN-based isometric mapping and fuzzy c-means algorithm to predict short-term rockburst risk in deep underground projects

Katano Y, Miyata K, Shimizu H, Isogai T (2003) Predictive model for pit growth on underground pipes. Corrosion 59(2):155–161

Kleiner Y, Rajani B (2001) Comprehensive review of structural deterioration of water mains: statistical models. Urban Water 3(3):131–150

Lehman M (2022) The American Society of Civil Engineers’ report card on America’s infrastructure. In: Women in infrastructure. Springer, p 5–21

Logan K, Koenig E (1939) A comparison of methods for estimation of the corrosivity of soils. Oil Gas J 38:130

Najjaran H, Sadiq R, Rajani B (2004) Modeling pipe deterioration using soil properties-an application of fuzzy logic expert system. In: Pipeline engineering and construction: what’s on the horizon? p 1–10

Nicholas D, Ferguson P (2005) Accurate prediction of cast iron watermain performance using linear polarisation resistance (LPR) methodology. In: NZWWA 2005 Conference, Auckland, NZ

O’Day DK, Weiss R, Chiavari S, Blair D, Clark RM, Association AWW (1988) Water main evaluation for rehabilitation/replacement, EPA

Pandey MD (1998) Probabilistic models for condition assessment of oil and gas pipelines. NDT E Int 31(5):349–358

Peng X-Y, Zhang P, Chen L-Q (2009) Long-distance oil/gas pipeline failure rate prediction based on fuzzy neural network model. In: Computer Science and Information Engineering, 2009 WRI World Congress on, IEEE

Rajani B (2000) Investigation of grey cast iron water mains to develop a methodology for estimating service life. American Water Works Association

Rajani B, Kleiner Y (2001) Comprehensive review of structural deterioration of water mains: physically based models. Urban Water 3(3):151–164

Rajani B, Makar J (2000) A methodology to estimate remaining service life of grey cast iron water mains. Can J Civ Eng 27(6):1259–1272

Ren C-Y, Qiao W, Tian X (2012) Natural gas pipeline corrosion rate prediction model based on BP neural network. In: Fuzzy engineering and operations research. Springer, p 449-455

Rossum JR (1969) Prediction of pitting rates in ferrous metals from soil parameters. J Am Water Works Assoc 61(6):305–310

Sadiq R, Kleiner Y, Rajani B (2004) Fuzzy cognitive maps for decision support to maintain water quality in ageing water mains. In: 4th international conference on decision-making in urban and civil engineering, Porto, Portugal

Sadiq R, Rajani B, Kleiner Y (2004) Probabilistic risk analysis of corrosion associated failures in cast iron water mains. Reliab Eng Syst Saf 86(1):1–10

Sawhney A, Mund A (2002) Adaptive probabilistic neural network-based crane type selection system. J Constr Eng Manag 128(3):265–273

Schlick W (1940) Supporting strength of cast iron pipe for gas and water services. Bulletin 146

Shahani NM, Kamran M, Zheng X, Liu C (2022) Predictive modeling of drilling rate index using machine learning approaches: LSTM, simple RNN, and RFA. Pet Sci Technol 40(5):534–555

Snider B, McBean EA (2020) Improving urban water security through pipe-break prediction models: machine learning or survival analysis. J Environ Eng 146(3):04019129

Spangler MG, Handy RL (1973) Soil engineering

Tabesh M, Soltani J, Farmani R, Savic D (2009) Assessing pipe failure rate and mechanical reliability of water distribution networks using data-driven modeling. J Hydroinf 11(1):1–17

Thomas L (2000) Fundamentals of decision making and priority theory. RWS Publications, Pittsburgh, p 21

Tsai CW, Franceschini S (2005) Evaluation of probabilistic point estimate methods in uncertainty analysis for environmental engineering applications. J Environ Eng 131(3):387–395

Ullah B, Kamran M, Rui Y (2022) Predictive modeling of short-term rockburst for the stability of subsurface structures using machine learning approaches: T-SNE, K-Means clustering and XGBoost. Mathematics 10(3):449

Valor A, Caleyo F, Hallen JM, Velázquez JC (2013) Reliability assessment of buried pipelines based on different corrosion rate models. Corros Sci 66:78–87

Vanaei H, Eslami A, Egbewande A (2017) A review on pipeline corrosion, in-line inspection (ILI), and corrosion growth rate models. Int J Press Vessels Pip 149:43–54

Wang X, Mazumder RK, Salarieh B, Salman AM, Shafieezadeh A, Li Y (2022) Machine learning for risk and resilience assessment in structural engineering: progress and future trends. J Struct Eng 148(8):03122003

Wilson D, Filion Y, Moore I (2017) State-of-the-art review of water pipe failure prediction models and applicability to large-diameter mains. Urban Water J 14(2):173–184

Yamijala S, Guikema SD, Brumbelow K (2009) Statistical models for the analysis of water distribution system pipe break data. Reliab Eng Syst Saf 94(2):282–293

Yang L, Shami A (2020) On hyperparameter optimization of machine learning algorithms: theory and practice. Neurocomputing 415:295–316

Young OC, Trott J (2014) Buried rigid pipes. CRC Press

Thông tin
Thông tin xuất bản

Journal of Infrastructure Preservation and Resilience

Thông tin tác giả