Monitoring and Analysis of Safe and Efficient Operation of Mobile Sewage Treatment Equipment in Substations Based on BP-SVM

The substation environment is complex, and the equipment is affected by various external factors such as humidity, temperature difference and vibration. On the basis of electrochemical wastewater treatment, a combined model based on BP neural network (BP) and support vector machine (SVM) is proposed. In this paper, a sensor array is designed to collect the real-time operation parameters of the equipment, and then a feature vector which can represent the operation state of the equipment is constructed. Next, BP algorithm is used to adjust the weights and deviations of SVM model, and RBF kernel function is introduced to enhance the nonlinear processing ability of the model, thus constructing BP-SVM model. The experimental results show that under different operating conditions, the failure rate of sewage treatment equipment under BP-SVM model is between 0.2% and 0.4%, the average service life is 1126 days, and the maximum single operation time is 120 hours, which is significantly better than the performance of KNN and Naive Bayesian model.