Application Of Support Vector Machine In Fault Diagnosis Of Power Generation Equipment

The electric power industry plays a very important role in the process of national economic development,it provides a steady power to all walks of life.The safe and reliable operation of power generation equipment is the basis of the production and operation of the power generation enterprises.The application of intelligent technology in fault diagnosis of power generation equipment is of great significance.It is conducive to the timely and accurate detection of failures,guidance and maintenance,to take measures to avoid failure to bring greater losses.In this paper,support vector machine is applied to fault diagnosis,the fault diagnosis model and fault trend prediction model are constructed by using support vector machine classification and regression method.To solve the problem that the model accuracy rate of the method of directly using support vector machine classification is not high enough.We use the method of combination classification.We select some of the training data to train the classification model of support vector machine randomly.When we classify the data of test set,we use the method of voting to determine the class label of each classifier.Experiments show that the combined classification method can effectively improve the classification performance.As a part of the fault diagnosis technology,the fault trend prediction can be found in the early detection of faults and reasonable maintenance and troubleshooting.In this paper,we use correlation analysis,support vector machine regression and grid search method to construct the fault trend prediction model based on support vector machine regression.To do regression analysis using data from production practice,the result of experiment shows that the fault trend prediction model proposed by this paper can better predict the future status of the equipment,and can help to realize the fault trend analysis.