Automatic detection system of secondary equipment in smart substation based on decision tree and support vector machine

Abstract Because the current method is not effective in detecting secondary equipment in smart substations, the actual loss value is unstable and the recall rate is low, and the expected detection effect cannot be achieved, an automatic detection system for secondary equipment in smart substation based on decision tree and support vector machine is designed. Firstly, the connection structure of the front-end detection circuit is designed, and the detection sensor is designed by combining the current sensor, voltage sensor, and power factor sensor. A decision tree is used to sample the detection data, and kernel function is introduced to convert nonlinear data into linear data under support vector machine, to realize the transformation of secondary equipment data in smart substation from low dimension to high dimension and complete the design of automatic detection system. The experimental results show that the detection effect of the designed system is closer to the actual loss value under some actual losses, which can improve the automatic detection effect. The designed system has the best performance in the recall rate, with little fluctuation and the most stable performance.