Assessment of contamination condition of insulator based on PSO-SVM

Contamination grades assessment is the important content for the online monitoring system of insulator leakage current (LC). The difficult of assessment is the nonlinear relationship between the electric character variables of the LC, the environment factors and the contamination condition of insulator surface. In this paper, based on laboratory simulation experiments and field data, the parameters of support vector machine (SVM) is optimized by using particle swarm optimization (PSO) arithmetic, then the SVM pattern recognition model of assessment of the contamination grades is constructed. The method takes advantages of the minimum structure risk of SVM and the quickly globally optimizing ability of particle swarm, and the mapping relation between the root mean square (R.M.S.) of LC, the peak value of the LC, the amplitude and times of the pulses of the LC, temperature and humidity of environment and contamination grades may be setup quickly by learning from sample data. Experiment results show that the contamination condition assessment method is effective. Then the insulator contamination condition online detection system is developed based on the assessment model.