A Motor Fault Diagnosis Method Based on Current and Voltage Signals

Abstract

The invention relates to a motor fault diagnosis method based on current and voltage signals, which divides working conditions according to power, builds a Bayesian classifier for each working condition, and trains the Bayesian classifier for motor fault diagnosis; collects the current and voltage of the motor , calculate the power of the motor based on the current and voltage, determine the current working condition according to the power; extract the feature vector based on the collected current; select the corresponding Bayesian classifier according to the current working condition, and calculate each Probability of failure type. The fault diagnosis of various fault factors is realized, and the accuracy of the obtained fault diagnosis results is high. The invention divides the operating conditions of the motor into five layers, collects data in different working conditions, establishes a fault diagnosis model, and more comprehensively considers the differences of various faults in different working conditions, thereby obtaining more accurate diagnosis results. At the same time, the steady state and transient operation of the motor are considered, and the diagnostic results obtained are more in line with the real operating state of the motor.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis, in particular to a motor fault diagnosis method based on current and voltage signals. Background technique [0002] With the rapid development of science and technology and industrial level, motors, as a kind of rotating equipment, are more and more applied to various fields of industrial and agricultural production. However, due to the complex operating environment of the motor and the long-term overload operation, accidents caused by the failure of the motor equipment occur from time to time, causing serious personal and economic losses. Therefore, it is necessary to carry out fault diagnosis on the motor to prevent accidents, which is also an important measure to ensure the safe and stable operation of industrial and agricultural production. [0003] Existing fault diagnosis methods mainly include the following: [0004] 1. Judgment of motor failure by analyzing noise, temperature an...

AI Technical Summary

Problems solved by technology

[0007] In actual production, due to defects such as inconvenient sensor installation and susceptibility to background noise interference, it is difficult to implement traditional vibration analysis and noise analysis methods. In addition, many methods are still limited to fault diagnosis related to the steady-state operation of the motor. The diagnosis under transient conditions such as acceleration and acceleration is still insufficient, and the steady state and transient signals are not combined for comprehensive evaluation. Only considering the steady state or transient state will lead to the lack of fault information, which will eventually lead to motor fault diagnosis. The accuracy is low; in addition, in the actual operation of the motor, with the change of the load, the actual operating condition of the motor is also constantly changing. The current method basically does not consider whether the fault characteristics of the motor will change under different operating conditions. Instead of filtering the working conditions, the same treatment is performed on various working conditions, ignoring the factor that the degree of fault characteristics will be different under different working conditions, which finally leads to low accuracy of motor fault diagnosis

Images