给水管网故障智能诊断方法

针对传统的支持向量机(support vector machine,简称SVM)参数选择方法以人工试验为主,花费时间长且很难得到最优参数的问题,提出了一种基于遗传算法(genetic algoritlam,简称GA)的支持向量机参数自动寻优方法.利用GA的全局搜索能力对支持向量机的各项参数进行寻优预处理,找到最优的参数取值,建立基于遗传算法的支持向量机模型(GA-SVM).以某小型给水管网为研究对象,采用水力分析算法求得管网局部破坏状态下的各项数据,并用这些数据对预测模型进行故障诊断试验,结果表明,经遗传算法优化的支持向量机模型具有较高的预测精度,整体性能优于传统的BP神经网络模型.

Intelligent Fault Diagnosis of Water Supply Network

The traditional parameter selection method using support vector mach in e (SVM) is time consuming and difficult to obtain the optimal parameters becaus e it is based on artificial tests. So, this paper presents an automatic optimizat ion selection method based on genetic algorithm (GA). The global search capabil i ty of GA was adopted to obtain the optimum values automatically in the range of the SVM parameters. An SVM regression model was built to diagnose a small scale water supply network. The results show that the forecast accuracy of the model o ptimized by GA is higher than that of the BP network. In addition, the overall d iagnosis performance of the SVM regression model using GA is superior to that of the traditional BP network.