Rolling bearing-rotor system coupling performance solving method based on BP neural network

Abstract

The invention relates to a rolling bearing-rotor system coupling performance solving method based on a BP neural network, and belongs to the field of automation. According to the method, a Newton-Raphson method is utilized to iteratively solve the normal contact load and speed of each rolling body in the rolling bearing; a Jacobi linear iteration method, a chasing method and an FFT algorithm are adopted to accelerate calculation of pressure distribution and temperature distribution of a lubricating film in a rolling bearing; and a BP neural network (BPNN) is trained based on the rolling bearing lubrication result obtained by calculation, the BP neural network is cured to quickly predict the oil film force of the rolling bearing, and the tribology and dynamics coupling performance of the rolling bearing-rotor system are quickly solved by using a Simulink simulator in Matlab. The method provided by the invention can accurately and quickly analyze the tribology and dynamics performance of the rolling bearing-rotor system, and provides theoretical guidance for the design and use of the rolling bearing-rotor system in engineering practice.

Description

technical field [0001] The invention belongs to the field of automation and relates to a method for solving the coupling performance of a rolling bearing-rotor system based on a BP neural network. Background technique [0002] As an important part of rotating machinery, the rolling bearing-rotor system is widely used in mechanical transmission systems, and the performance of the system directly affects the operating efficiency and fatigue life of the entire machine. In the rolling bearing-rotor system, the rotor is supported by the rolling bearing, and the vibration generated by the rotor during operation (especially under high-speed and heavy-load conditions) will have an important impact on the lubrication performance of the rolling bearing; while the rolling bearing lubricated with oil or grease Lubrication performance, through the bearing capacity and frictional moment of the lubricating film of the bearing, will affect the dynamic (vibration) performance of the rotor. ...

AI Technical Summary

Problems solved by technology

Although the above two aspects of research can be used to analyze the tribological and dynamic performance of the rolling bearing-rotor system to a certain extent, it cannot accurately and truly reflect the lubrication and dynamic performance parameters of the rotor system, and thus cannot accurately predict the rolling bearing-rotor system. system fatigue life, etc.

In addition, considering the two-way coupling effect of tribology and dynamics of the rolling bearing-rotor system, when accurately analyzing the lubrication performance of the rolling bearing and the vibration performance of the rotor, the traditional calculation method not only has a huge amount of calculation, but also consumes a lot of calculation time and resources, and even fails. Solution

Therefore, the traditional tribological and dynamic performance analysis methods of rolling bearing-rotor systems are more statistically and empirically significant, and their accuracy is not accurate enough, and their efficiency is not efficient enough.

Images