A Blended Risk Index Modeling and Visualization Based on Hierarchical Fuzzy Logic for Water Supply Pipelines Assessment and Management

Critical infrastructure such as power and water delivery is growing rapidly in the developing world and there are developed assets that must be maintained in developed nations. One underground component that is difficult to inspect is water supply pipelines. Most of the water line accidents occur in buildings is due to pipeline damage. To minimize accidental loss, a risk assessment method is needed to continuously assess risk and report any abnormality for preventative maintenance. In this work, a blended hierarchical fuzzy logic model for water supply pipeline risk index assessment is proposed. Four important parameters are inputs to the proposed blended hierarchical fuzzy logic model. The blended hierarchical fuzzy logic model dramatically reduces the number of conditions in the rule base. Rule reduction is important because the transparency and interpretation are compromised by an overly large set. Further, it is challenging to accurately design a large number of rules because rule design requires expert knowledge and uncertainty in predictions can lead to unforeseen incidents. A blended hierarchical fuzzy model is designed with a structure that takes fewer rules as compared to conventional fuzzy logic. For the four parameters, the proposed model takes 85 rules and for the same four parameters, the conventional fuzzy logic approach requires 900 rules. In this paper, four parameters are considered because these are available measurements. The proposed reduction method is also applicable for systems with more parameters. The numbers of rules increase exponentially in the conventional fuzzy logic as new parameters enter into the system. The blended hierarchical fuzzy logic is deployed on a water distribution network to compute the risk index of supply pipelines. The results indicate improved performance of the blended hierarchical fuzzy logic. This approach is usable in practical applications where the calculated risk index values of the water supply pipeline are plotted on a geographic information system (GIS) map to provide a graphical interface for the caretaker. The risk index visualization is necessary to trace the risk index location and to take preemptive measures to avoid failures.