Pipe Break Rate Assessment While Considering Physical and Operational Factors: A Methodology Based on Global Positioning System and Data Driven Techniques

Abstract

Deterioration of urban Water Distribution Networks (WDNs) is one of the primary cases of water supply losses, leading to the huge expenditures on the replacement and rehabilitation of elements WDNs. An accurate prediction of pipes failure rate play a substantial role in the management of WDNs. In this study, a field study was conducted to register pipes break and relevant causes in the WDN of Yazd City, Iran. In this way, 851 water pipes were incepted and localized by the Global Positioning System (GPS) apparatus. Then, 1033 failure cases were reported in the eight zones of under study WDN during March-December 2014. Pipes break rate (BRP) was calculated using the depth of pipe installation (hP), number of failure (NP), pressure of water pipes in operation (P), and age of pipe (AP). After completing a pipe break database, robust Artificial Intelligence models, namely Multivariate Adaptive Regression Spline (MARS), Gene-Expression Programming (GEP), and M5 Model Tree were employed to extract precise formulation for the pipes break rate estimation. Results of the proposed relationships demonstrated that MARS model with Coefficient of Correlation (R) of 0.981 and Root Mean Square Error (RMSE) of 0.544 provided more satisfying efficiency than M5 model (R = 0.888 and RMSE = 1.096). Furthermore, statistical results indicated that MARS and GEP models had comparatively at the same accuracy level. Explicit equations by AI models were satisfactorily comparable with those obtained by literature review in terms of various conditions: physical, operational, and environmental factors and complexity of AI models. Through a probabilistic framework for the pipes break rate, the results of first-order reliability analysis that MARS technique had highly satisfying performance when MARS-extracted-equation was assigned as a limit state function.

Artificial intelligence‐based correlation: Process side heat transfer coefficient for helical coils in stirred tank reactors

“…However, for every leaf of every tree, take note of all observations ( ŷ t n ) in this leaf, not just their average. For a given significance level α, one can take the α /2 and 1 − α /2 quantiles of all observations ŷ t n for a given data point X and prediction interval for that point X can be given as [ ŷ ɑ /2 n , ŷ 1 − ɑ /2 n ] 24,25 . Prediction intervals for the prediction of HTC in the testing set are observed in Figure 8.…”

Sound Pressure Level at Terminals through Data Mining

“…Support vector machine (SVM), multivariate adaptive regression splines (MARS), and random forest (RF) techniques have been applied to estimate the densimetric Froude number approximation for the incipient movement of riprap stones [26]. Robust artifcial intelligence models, namely, multivariate adaptive regression spline (MARS), gene-expression programming (GEP), and M5 model tree were employed to extract precise formulation for the pipes break rate estimation [27]. In this study, standardized precipitation evaporation rate values are formulated for various climates using three robust artifcial intelligence models, namely, gene expression programming (GEP), model tree (MT), and multivariate adaptive regression spline (MARS) [28].…”