Self-learning grating interference spectrum analysis technology for motor fault early warning

Abstract

The invention discloses a self-learning grating interference spectrum analysis technology for motor fault early warning in the technical field of motor fault detection, and the technology comprises the steps: determining a wavelet basis function according to the parameters of a motor and an environment, training a judgment model through the data of the motor during normal operation, deducing fault features based on the model, and carrying out the early warning of the motor fault; a signal frequency band with abnormal energy can be more accurately determined as a frequency band where a fault feature is located, so that a fault feature frequency is further identified by utilizing wavelet packet node reconstruction, and a fault type is judged by utilizing machine learning; only two signals of the vibration sensor and the temperature sensor are fused, and the two signals are optical fiber sensors, so that the influence of electromagnetic interference can be completely avoided.

Description

technical field [0001] The invention relates to the technical field of motor fault detection, in particular to a self-learning grating interference spectrum analysis technology for motor fault early warning. Background technique [0002] Electric motors are widely used in production, life and scientific research. In the modern industrial process, the motor, as an important driving device, has the characteristics of harsh working environment and many components. When the motor operates under complex and harsh conditions, its performance will decline, resulting in various failures of the motor and damage to the core components of the motor, thereby affecting the normal operation of the entire production and living systems, causing serious catastrophic accidents, adverse social impacts and Huge economic loss. It is of great significance to detect the parameters representing the fault state of the motor in time and improve the fault detection technology of the motor to avoid m...

AI Technical Summary

Problems solved by technology

[0004] (1) In a complex electromagnetic environment, the sensor will generate interference signals due to electromagnetic induction, which will affect the judgment: multi-sensor technology can effectively extract the motor fault characteristic signal through signal fusion. The problem is that the sensors contained in the multi-sensor have power Links susceptible to electromagnetic interference such as power supply and conductive lines

During the detection process of the vibration acceleration sensor, there is a problem of spectrum leakage. The characteristic signal of the fault is relatively small, and its characteristic spectrum is easily submerged by the fundamental component and difficult to identify.

[0005] (2) The vibration characteristics of the motor are affected by many factors, not only related to the process of the motor itself, but also related to the operating environment. When detecting the vibration signal, this part of the content has a lot of interference in judging the motor fault. Use The fixed model judges the running state of the motor, which has great limitations and is not very applicable

Images