Power System Fault Classification and Prediction Based on a Three-Layer Data Mining Structure

Abstract

In traditional fault diagnosis methods in power systems, it is difficult to accurately classify and predict the types of faults. With the emergence of big data technology, the fault classification and prediction methods based on big data analysis and processing have been applied in power systems. To make the classification and prediction of the fault types more accurate, this paper proposes a hybrid data mining method for power system fault classification and prediction based on clustering, association rules and stochastic gradient descent. This method uses a three-layer data mining model: The first layer uses the K-means clustering algorithm to preprocess the original fault data source, and it proposes to use self-encoding to simplify the data form. The second layer effectively eliminates the data that have little impact on the prediction results by using association rules, and the highly correlated data are mined to become the regression training data. The third layer first uses the cross-validation method to obtain the optimal parameters of each fault model, and then, it uses stochastic gradient descent for data regression training to obtain a classification and prediction model for each fault type. Finally, a verification example shows that compared with a single data mining algorithm model, the proposed method is more comparative in terms of the data mining, and the established power system fault classification and prediction model has global optimality and higher prediction accuracy, which has a certain feasibility for real-time online power system fault classification and prediction. This method reduces the disturbances from low-impact or irrelevant data by mining the fault data three times, and it uses cross-validation to optimize the multiple regression parameters of the regression model to solve the problems of low accuracy, large errors and easily falling into a local optimum, given the conduct of fault classification and prediction.

Analysis of the Ultrasonic Signal in Polymeric Contaminated Insulators Through Ensemble Learning Methods

“…To improve the diagnosis of possible failures in electrical power components, an approach that has proven to be successful is the prediction of failures [14], which is the specific subject addressed in this paper. Among the techniques used to improve the predictive capacity of the model, the wavelet transform stands out for having the ability to reduce the noise in the signal without losing its characteristic [15].…”

Research on rapier loom fault system based on cloud-side collaboration

“…Fault diagnosis techniques for equipment have prominent applications in electric power systems [1,2], chemical process systems [3,4], photovoltaic systems [5][6][7][8][9], bearings [10,11], building energy systems [6], control systems [12,13], and automation equipment [14]. The electrical control system of rapier loom is susceptible to various disturbances during operation and is prone to malfunction.…”

“…Many popular fault diagnosis methods exist. Based on big data analysis and processing, [1] proposed a hybrid data mining method based on clustering, association rules and stochastic gradient descent for the classification and prediction of faults in power systems. However, [1] applied to looms lacks sufficient sample data and requires a large amount of computational resources [10].…”

“…Based on big data analysis and processing, [1] proposed a hybrid data mining method based on clustering, association rules and stochastic gradient descent for the classification and prediction of faults in power systems. However, [1] applied to looms lacks sufficient sample data and requires a large amount of computational resources [10]. proposed a cloud/edge collaborative fault diagnosis solution with real-time responsiveness to improve the accuracy of the algorithm and reduce the time cost by improving the transfer learning and edge collaboration of the convolutional neural network model with a small number of samples for deep learning.…”

“…The above fault diagnosis methods are limited by the process and electrical characteristics of the weaving machine and are deficient. The method of method [1] lacks sufficient sample data. The method of [10] is of value, but this fault diagnosis method for bearings is not applicable to diagnose electrical faults of weaving machines.…”