Open set fault diagnosis method for bearing of high-speed motor train unit

Abstract

The invention discloses an open set fault diagnosis method for a bearing of a high-speed motor train unit. The open set fault diagnosis method comprises the steps of collecting a vibration signal of the bearing of the high-speed motor train unit in operation through an acceleration sensor; aiming at an open set diagnosis scene of a constant working condition, inputting training data with a label to train a one-dimensional convolutional neural network; inputting labeled source domain data and unlabeled target domain data to train the bilateral weighted adversarial network according to an open set diagnosis scene with working condition changes; establishing an extreme value theoretical model by utilizing the characteristics of the training data or the source domain data, inputting the characteristics of the test sample or the target domain sample into the established extreme value theoretical model, outputting the probability that the test sample or the target domain sample belongs to an unknown fault type, and if the probability is greater than a threshold value, determining that the test sample or the target domain sample belongs to the unknown fault type, and if not, determining that the test sample or the target domain sample belongs to the known fault type. The type of the test sample or the target domain sample is determined according to the label predicted value so as to realize the fault diagnosis of the bearing of the high-speed motor train unit.

Description

technical field [0001] The disclosure belongs to the field of mechanical fault diagnosis, and in particular relates to an open-collector fault diagnosis method for bearings of high-speed EMUs. Background technique [0002] Due to the ability of deep learning to automatically extract useful features, deep learning has been widely used in many mechanical fault diagnosis tasks. However, there are two problems in the existing fault diagnosis methods based on deep learning. On the one hand, it is assumed that the labeled data used for training and the unlabeled data used for testing have the same label set, which is difficult to satisfy in practical applications. The types of faults during the test phase are unpredictable, i.e. the label set of the test data may only contain part of the known fault categories and may contain unknown faults. On the other hand, the prerequisite for deep learning to have good performance is that the training samples and test samples have the same d...

AI Technical Summary

Problems solved by technology

However, there are two problems in the existing fault diagnosis methods based on deep learning. On the one hand, it is assumed that the labeled data used for training and the unlabeled data used for testing have the same label set, which is difficult to satisfy in practical applications. The type of faults during the test phase is unpredictable, that is, the label set of the test data may only contain part of the known fault categories and may contain unknown faults

On the other hand, the prerequisite for deep learning to have good performance is that the training samples and test samples have the same distribution. However, the working conditions of high-speed EMUs will change, so there are differences in the distribution of training samples and test samples, resulting in a significant decline in diagnostic performance.

Images