Gear contact fatigue life prediction method based on GA-BP neural network

Abstract

The invention discloses a GA-BP neural network-based gear contact fatigue life prediction method. The method comprises the following steps of 1, collecting gear contact fatigue test data and normalizing the gear contact fatigue test data as sample data of a BP neural network model; 2, constructing a structure of a BP neural network; 3, optimizing the weight and threshold of the BP neural network by using a genetic algorithm, and training the BP neural network; 4, calculating a prediction precision evaluation parameter determination coefficient, and obtaining an optimization weight and a threshold when the prediction precision evaluation parameter determination coefficient meets a set value; and 5, testing the established GA-BP neural network by using the test sample set. Compared with an existing gear contact fatigue life prediction method based on a physical model, the gear contact fatigue life prediction method is low in cost and high in prediction precision, does not need to be derived according to a failure mechanism, achieves prediction of the gear fatigue life, improves the prediction accuracy, is easy to use, and provides a new technical means for design and manufacturing ofgears.

Description

technical field [0001] The invention belongs to the technical field of intelligent manufacturing, and in particular relates to a method for predicting the contact fatigue life of gears. Background technique [0002] Gear is an important mechanical basic part, which is widely used in various industrial fields for motion and power transmission, and its fatigue life directly determines the service performance of the whole machine. With the development of major equipment such as wind power, high-speed rail, and aviation in the direction of high reliability, long life, and intelligence, higher requirements are placed on the life and reliability of gears. If the gear is fatigued and damaged during the service stage, it will not only cause equipment shutdown and affect production, but also endanger personal and property safety. Accurately predicting the fatigue life of gears can avoid sudden and vicious equipment accidents and ensure long-term safe and reliable operation of mechan...

AI Technical Summary

Problems solved by technology

[0003] Existing gear fatigue life prediction methods mainly include fatigue cumulative damage theory, mathematical models, etc. The fatigue cumulative damage theory believes that when a part acts on a constant stress amplitude, its maximum life is N times, that is, when the part is running N times, its danger point will produce fatigue damage; the mathematical model predicts the fatigue life of the gear by establishing the relationship between the gear parameters and the fatigue life; although it can predict the fatigue life and achieve a certain accuracy, there are still many defects. These methods are time-consuming and costly, and the results often have large deviations from the test values.

Images