Abstract
In recent years, drinking water contamination incidents happen frequently, which is a serious threat to social stability and security. By placing the sensors for real-time monitoring of water quality in urban water supply, it can greatly reduce the probability of incidents of contamination. But how to use the information collected by water quality sensors to identify the contaminant source is a challenging problem. In this paper, we formulated the contaminant source identification problem into an optimization problem, and used hybrid encoding method to code the problem according to the properties of a variable, so as to improve the convergence speed and accuracy. We used different size of pipe network data in experiment, which results finally verified the validity and robustness of the proposed method.