Motor fault data enhancement method based on deep convolution generative adversarial network

Abstract

The invention discloses a motor fault data enhancement method based on a deep convolution generative adversarial network. A motor fault type data sample and random noise are provided, the random noisecan be integrated into a generation model, and the generation data and the motor fault type data are classified and integrated according to a discrimination model, so that the effect of expanding themotor fault type data is achieved. According to the motor fault data enhancement method based on the deep convolution generative adversarial network, various information is generated in a motor operation process, a learning model is generated, through continuous learning and training, whether the motor operates normally or abnormally is predicted, the fault type of the motor is identified, whether a fault exists or not and the reason of the fault position are judged through detection and analysis of state parameters of the motor when the motor operates with a load or under the condition thatthe motor is not disassembled, and the future state of the motor is predicted.

Description

technical field [0001] The invention relates to the technical field of fault diagnosis and deep learning, in particular to an enhancement method of motor fault data based on a deep convolutional generative confrontation network. Background technique [0002] Fault diagnosis technology based on deep learning is a comprehensive technology that has emerged in recent years and contains many new technological contents. It establishes a learning model based on various information generated during the operation of the motor. Through continuous learning and training, it can predict whether the motor is running normally or abnormally, and identify the type of motor failure. It can realize the detection and analysis of the state parameters of the motor when the motor is running with load or without disassembly, to determine whether there is a fault and the cause of the fault location, and to predict the future state of the motor. [0003] With the progress of modern science and techn...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for enhancing motor fault data based on a deep convolutional generative confrontation network, so as to solve the problem that the existing motor faults cannot be detected and prevented in advance in the above background technology, and sudden accidents may easily cause production shutdown losses. The threat to the safety of personnel and equipment has been increased, and the problem of not being able to create conditions for the realization of condition-based maintenance

Images