Design of classification model on high-dimensional imbalance data of motor bearing fault

According to the characteristics of high-dimensional imbalance distribution of motor bearing fault data, a design scheme of classification model is proposed for the high-dimensional data reduction problem in the classification algorithm. For details: Combining standard particle swarm optimization algorithm and random forest algorithm, a new high-dimensional data reduction algorithm is proposed. Aiming at the imbalance problem of data categories in the classification algorithm, we proposes to use machine learning under the sum of squares of dynamic deviations criterion to divide the minority sample data set into mixed regions, high-purity minority sample regions and outlier regions, and then use smote algorithm to complete the data equalization processing, so as to make the sample data equalization processing more reasonable, Focusing on the task of motor bearing fault classification, a design scheme of using standard particle swarm optimization algorithm to improve the least squares support vector machine model is proposed.

Effect of unbalanced magnetic pull on the thermal characteristics of traction motor bearing

Purpose The purpose of this paper is to analyze the unbalanced magnetic pull (UMP) of the rotor of traction motor and the influence of the UMP on thermal characteristics of traction motor bearing. Design/methodology/approach The unbalanced magnetic pull on the rotor with different eccentricity was calculated by Fourier series expansion method. A bearing thermal analysis finite element model considering both the vibration of high-speed train caused by track irregularity and the UMP of traction motor rotor was established. The validity of the model is verified by experimental data obtained from a service high-speed train. Findings The results show that thermal failure of bearing subassemblies most likely occurs at contact area between the inner ring and rollers. The UMP of rotor of traction motor has a significant effect on the temperature of the inner ring and roller of the bearing. When the eccentricity is 10%, the temperature can even be increased by about 12°C. Therefore, the UMP of rotor of traction motor must be considered in thermal analysis of traction motor bearing. Originality/value In the thermal analysis of the bearing of the traction motor of high-speed train, the UMP of the rotor of the traction motor is considered for the first time

Application of Machine Learning to a Medium Gaussian Support Vector Machine in the Diagnosis of Motor Bearing Faults

In recent years, artificial intelligence technology has been widely used in fault prediction and health management (PHM). The machine learning algorithm is widely used in the condition monitoring of rotating machines, and normal and fault data can be obtained through the data acquisition and monitoring system. After analyzing the data and establishing a model, the system can automatically learn the features from the input data to predict the failure of the maintenance and diagnosis equipment, which is important for motor maintenance. This research proposes a medium Gaussian support vector machine (SVM) method for the application of machine learning and constructs a feature space by extracting the characteristics of the vibration signal collected on the spot based on experience. Different methods were used to cluster and classify features to classify motor health. The influence of different Gaussian kernel functions, such as fine, medium, and coarse, on the performance of the SVM algorithm was analyzed. The experimental data verify the performance of various models through the data set released by the Case Western Reserve University Motor Bearing Data Center. As the motor often has noise interference in the actual application environment, a simulated Gaussian white noise was added to the original vibration data in order to verify the performance of the research method in a noisy environment. The results summarize the classification results of related motor data sets derived recently from the use of motor fault detection and diagnosis using different machine learning algorithms. The results show that the medium Gaussian SVM method improves the reliability and accuracy of motor bearing fault estimation, detection, and identification under variable crack-size and load conditions. This paper also provides a detailed discussion of the predictive analytical capabilities of machine learning algorithms, which can be used as a reference for the future motor predictive maintenance analysis of electric vehicles.