Integrated Decision Support System for Prognostic and Diagnostic Analyses of Water Distribution System Failures

Abstract

This paper presents an innovative decision support system (DSS) for prognostic and diagnostic analyses of water distribution system (WDS) failures. The framework of the DSS is based on four novel models developed and published by the authors of this paper. The four models include reliability assessment model, leakage potential model, leakage detection model, and water quality failure potential model. Information obtained from these models together with external information such as customer complaints, lab test results (if any), and historical information are integrated using Dempster-Shafer (D-S) theory to evaluate prognostic and diagnostic capabilities of the DSS. The prognostic capabilities of the DSS provide hydraulic and water quality states of a WDS whereas the diagnostic capabilities of the DSS help to identify the failure location with minimal time after the occurrence and will help to reduce false positive and false negative predictions. The framework has 'unique' capacity to bring the modeling information (hydraulic and Quality), consumer complaints, historical failure data, and laboratory test information under a single platform to perform a prognostic and diagnostic investigation of WDS failures (hydraulic and Quality). The proof of concept of the DSS has been demonstrated using data used in published four articles. The outcomes of this research widely addressed the uncertainties associated with WDS which improves the efficiency and effectiveness of diagnosis and prognosis analyses of WDS. It is expected that the developed integrated framework will help municipalities to make informed decisions to increase the safety, reliability and the security of public health.

Anomaly Detection System for Water Networks in Northern Ethiopia Using Bayesian Inference

“…In particular, due to the diverse and complex nature of water distribution systems, various 'anomalies' may occur due to fundamentally different underlying causes, e.g., water leakage, pipe blockage, device condition, and energy efficiency are a few examples, cf. Duan and Lee [20], Duan et al [21], Islam et al [22]. Conducting anomaly detection along with meaningful root-cause analysis for such systems often times requires an appropriate combination of human domain knowledge, observational data, and accurate modeling techniques.…”

Simulation Model for Optimal Operation of Dokan Dam Reservoir Northern of Iraq

“…An ideal arrangement mostly comprises contradictory choices due to the supply framework guidelines plans. A repository framework guideline plan, working strategy, or discharge approach are of utmost important principles in deciding the amounts of water to be put away or discharged or pulled back from a supply [7,8], or arrangement of a few repositories, under different conditions [9][10][11]. The principal issue is to choose how much water must be put away and additionally discharged, particularly for moderately little stores, without making any water deficiency in the long haul because of crisis conditions in the midst of flood.…”

An improved conflicting-evidence combination method based on the redistribution of the basic probability assignment

“…As an important method for modelling and processing uncertain information fusion [1,2], Dempster-Shafer (D-S) evidence theory is an effective tool to fuse information from different sources [3][4][5], and it can be applied to situations of uncertainty without prior information, which is required for Bayesian theory [3,6]. Therefore, it has attracted considerable attention from many scholars and has been widely applied in many fields, such as risk and reliability analysis [7][8][9], decision making [10,11], fault diagnosis [12][13][14], pattern recognition [15,16].…”