Transformer fault diagnosis method based on weighted and selective naive Bayes

Abstract

A transformer fault diagnosis method based on weighting and selective naive Bayes is characterized in that an attribute selection method based on x2 statistics removes a part of redundant attributes and constructs an attribute learning classifier better for a classification result, and comprises the following steps: 1) collecting historical fault data of a main transformer, including attribute data and fault types, discretizing conditional attribute data; wherein the fault type is a decision attribute, and dividing the data into a training set and a test set; 2) selecting an optimal reduction subset RAS by using an attribute selection method based on x2 statistics; 3) learning prior probability: calculating prior probabilities of all decision attributes and conditional probabilities of attributes in RAS by the training set, and respectively storing results into a CP table and a CPT table; 4) establishing a weight table of the attribute data by using a correlation probability method; calculating all weights of the attributes in the RAS table under different categories, and storing the weights in a weight table AW; using the test set to test model performance; and accessing model accuracy according to the actual category of the test data.

Description

technical field [0001] The invention belongs to the technical field of fault diagnosis of main transformers in substation equipment, and in particular relates to a transformer fault diagnosis method based on weighted and selective Naive Bayes. Background technique [0002] The latest mission of the State Grid clearly requires that all efforts are made to ensure the safe and stable operation of the power grid, and power transformers are responsible for voltage transformation, power distribution and transfer in the power system. ensure. However, in actual operation, faults and accidents cannot be completely avoided, and early detection and treatment of transformer faults is of great significance. At present, there are many transformer fault diagnosis methods, such as neural network, ensemble learning, support vector machine and other methods are effectively used, among which Naive Bayes is recognized for its advantages of short diagnosis time and high efficiency, but the cond...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, provide a transformer fault diagnosis method based on weighted and selective naive Bayesian, and solve the problem of long diagnosis time and low accuracy of the existing substation main transformer fault diagnosis method. Low and a single naive Bayesian improvement measure does not solve the problem of attribute weight setting and attribute selection

Images