Type Of Grid Fault Diagnosis Based On Bayesian Network

Short-circuit fault is one of the most frequent faults in the power grid How to diagnose the short-circuit fault in fast, accurate and intelligent way, deal with the fault and restore power to line quickly is an important research topic in the field of smart power system cinrently.First some common intelligent diagnosis methods, which were applied to the fault detection, were introduced and took a comparison among them. The Bayesian network, whose advantages were more obvious, was chosen to diagnose the fault lype. Then, the related basic knowledge of Bayesian network theory was introduced in the paper at length. Finally, the kinds of power fault types were analyzed, and extracted corresponding fault features. Using the Bayesian network model to analyze results as nodal variables, assign a network structure, and build power network fault diagnosis model based on Bayesian network. Based on the expert knowledge, sensitivity analysis of probabilistic reasoning and evidence of nodal variables of Bayesian network were shown in the paper. The system had the following characteristics:(1) Using the Bayesian network theory, constructing an simple and practical intelligent diagnosis model, and could correctly identify the fault types;(2) Based on the expert knowledge, according to the sensitivity analysis of probabilistic reasoning and evidence of nodal variables of the intelligent diagnosis model, and the value that each node variables affected the diagnosis result, increased the universality and practicability of the diagnosis model.In order to verify the effectiveness of the Bayesian network system model, a large number of fault samples are tested in the laboratory. The test results show that the Bayesian network fault diagnosis system can accurately judge the type of fault of power system through various fault characteristics, and achieve the expected goal.