A leak detection method based on Bayesian theory and Fisher’s law was developed for water distribution systems. A hydraulic model was associated with the parameters of leaks (location, extent). The randomness of para...A leak detection method based on Bayesian theory and Fisher’s law was developed for water distribution systems. A hydraulic model was associated with the parameters of leaks (location, extent). The randomness of parameter values was quantified by probability density function and updated by Bayesian theory. Values of the parameters were estimated based on Fisher’s law. The amount of leaks was estimated by back propagation neural network. Based on flow characteristics in water distribution systems, the location of leaks can be estimated. The effectiveness of the proposed method was illustrated by simulated leak data of node pressure head and flow rate of pipelines in a test pipe network, and the leaks were spotted accurately and renovated on time.展开更多
基金国家自然科学基金(the National Natural Science Foundation of China under Grant No.60603053)教育部重点项目(teh Key Projects of the Ministry of Education of China under Grant No.106158)
基金Supported by National Natural Science Foundation of China (No. 50278062 and 50578108)Science and Technology Innovation Funds Project of Tianjin, China (No. 08FDZDSF03200)
文摘A leak detection method based on Bayesian theory and Fisher’s law was developed for water distribution systems. A hydraulic model was associated with the parameters of leaks (location, extent). The randomness of parameter values was quantified by probability density function and updated by Bayesian theory. Values of the parameters were estimated based on Fisher’s law. The amount of leaks was estimated by back propagation neural network. Based on flow characteristics in water distribution systems, the location of leaks can be estimated. The effectiveness of the proposed method was illustrated by simulated leak data of node pressure head and flow rate of pipelines in a test pipe network, and the leaks were spotted accurately and renovated on time.
