Running state monitoring method, system and equipment of permanent magnet synchronous motor, and medium

By using fractal information dimension algorithm and wavelet transformation technology in the fault diagnosis of permanent magnet synchronous motors, combined with simulation and actual data for model training, the problem of ignoring prior information in the existing technology is solved, and the ability to extract and identify fault features is improved.

CN119716537AActive Publication Date: 2025-03-28LEI YUE MUN (TIANJIN) INTELLIGENT TECHNOLOGY CO LTD
3 Cites 0 Cited by

Patent Information

Application Number
CN202411570710.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-11-05
Publication Date
2025-03-28
Estimated Expiration
2044-11-05

AI Technical Summary

Technical Problem

The fault diagnosis method of permanent magnet synchronous motor based on data-driven in the prior art ignores prior information and cannot fully extract the complexity and diversity of fault data, resulting in the inability of the model to accurately extract and fault identification when facing new or complex faults.

Method used

A method for monitoring the operating status of a permanent magnet synchronous motor is proposed. By obtaining simulated three-phase current data and actual three-phase current data, continuous wavelet transformation and standardization processing are carried out, fractal information dimension algorithm is established, fault diagnosis model is constructed, and model pre-training and fine-tuning is performed through the fusion of simulation and actual data.

Benefits of technology

It improves the sensitivity of the fault diagnosis model to fault characteristics, enhances the model's ability to extract complex and diverse fault data, and improves the ability to identify new faults.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The embodiment of the invention provides a method for monitoring the running state of a permanent magnet synchronous motor, and the method comprises the steps: obtaining simulated and actual three-phase current data of the permanent magnet synchronous motor in a fault state, carrying out the continuous wavelet transformation of the three-phase current data, and obtaining simulated and actual three-phase current time-frequency diagrams; performing standardization processing and average fusion on the three-phase current time-frequency diagram to obtain a simulated and actual comprehensive time-frequency diagram; establishing a fractal information dimension algorithm, and constructing a fault diagnosis model based on the algorithm; training the fault diagnosis model based on the simulation comprehensive time-frequency diagram to obtain a pre-training model; performing fine-tuning training on the pre-training model based on the actual comprehensive time-frequency graph to obtain a fine-tuning pre-training model; the fine tuning pre-training model outputs a prediction result based on the actual comprehensive time-frequency graph; and the operation state of the motor is identified according to the result, so that the complexity and diversity of comprehensively extracting fault data are realized, and the sensitivity of a fault diagnosis model to fault features is improved.
Need to check novelty before this filing date? Find Prior Art