Deep learning-based asynchronous motor fault diagnosis method

Abstract

The invention discloses a deep learning-based asynchronous motor fault diagnosis method. The method comprises the following steps of A, building a simulation experiment platform for asynchronous motoroperation; B, carrying out current signal and vibration signal acquisition on a simulated motor fault state; C, extracting internal features of acquired data and carrying out corresponding labellingto complete the construction of a data set; D, building a stack type encoder-based fault diagnosis model and training a network and a classifier in sequence; and E, training a built deep neural network by utilizing the constructed data set, and verifying the fault diagnosis method by combining the simulation experiment platform. According to the method, a deep learning theory is imported to designa system which is capable of correctly, sensitively and effectively diagnosing complicated faults of asynchronous motors, so that the method can solve the problems existing in the fault diagnosis ofthe asynchronous motors and adapt to the requirements of constantly developing electric systems.

Description

technical field [0001] The invention relates to a computer, in particular to a deep learning-based fault diagnosis method for asynchronous motors. Background technique [0002] With the advancement of modern science and technology, the development of production systems and the improvement of equipment manufacturing level, motors, as the most commonly used and largest power supply equipment and power machinery in the world, have occupied almost all fields. Obviously, the normal operation of the motor is of great significance to ensure the safe, efficient, agile, high-quality and low-consumption operation in the manufacturing process. Among them, the asynchronous motor is the most widely used and the most demanded motor among various motors. In the total load of the power grid, the consumption of asynchronous motors accounts for more than 60%. It is the most important driving force and driving device in today's industrial production activities and daily life. [0003] At pr...

AI Technical Summary

Problems solved by technology

At present, for the common fault types of asynchronous motors, traditional fault diagnosis methods have been able to effectively solve them, but problems such as the difficulty in fault diagnosis of asynchronous motors caused by factors such as complex motor structures, unstable vibration signals, and mechanical big data are still not perfect. s solution

Images