Motor thermal fault diagnosis method and device based on deep neural network

Abstract

The invention relates to the technical field of fault detection, in particular to a motor thermal fault diagnosis method and device based on a deep neural network. The method comprises the steps: firstly, detecting the environment temperature in real time, and detecting whether the motor temperature exceeds the rated temperature of a motor or not in real time when the environment temperature is ina reasonable range; if the motor temperature exceeds the rated temperature of the motor, detecting whether the working voltage of the motor exceeds the rated voltage of the motor in real time to obtain whether the motor has a power failure; if the power supply of the motor is normal, detecting the vibration signal of the motor in real time, preprocessing the vibration signal detected in real timeto obtain vibration data, and performing fault diagnosis on the vibration data by using the trained neural network model to generate a diagnosis result of the motor state. The motor thermal fault detection technical mode provided by the invention is more diversified, and the diagnosis conclusion is more accurate and clearer.

Description

technical field [0001] The invention relates to the technical field of fault detection, in particular to a method and device for diagnosing motor thermal faults based on a deep neural network. Background technique [0002] With the rapid improvement of industrial modernization level, electrical equipment is increasingly developing towards high speed, precision, automation and integration. The working environment of motor equipment is complex and changeable, and it is often prone to various failures due to its heavy workload, variable load and the influence of external extreme working environment. If the failure cannot be diagnosed and eliminated in a timely and effective manner, it will bring about major safety hazards and cause major economic losses. [0003] When the motor is converting energy, a small part of the loss is always converted into heat, which is a normal phenomenon and can continue to be used. Disconnection of motor windings, shorting of motor windings, impr...

AI Technical Summary

Problems solved by technology

[0004] There are many disadvantages in the traditional motor thermal fault detection method of the motor temperature. For example, an early warning is issued only when the motor temperature is too high; it is impossible to judge the cause of the motor overheating, specifically whether the external temperature is too high or The motor is faulty, and no conclusion can be given

Therefore, the existing motor thermal fault detection technology has a single method, the diagnostic conclusion is not precise enough, the auxiliary effect of fault diagnosis is not great, and it cannot meet the requirements of advanced productivity

Images