Gear residual life prediction method based on SAE and ON-LSTM

Abstract

The invention relates to a gear residual life prediction method based on SAE and ON-LSTM, and belongs to the field of big data and intelligent manufacturing. According to the invention, the method comprises the steps: employing SAE for extracting gear health indexes, and employing a novel ON-LSTM neural network for predicting the remaining life of a gear; dividing a hierarchical structure of inputdata and historical data through a hierarchical divider in ON-LSTM; defining the position of the maximum element in the output vectors of the main forgetting gate and the main input gate as a hierarchical position, so that the recurrent neural network is updated hierarchically. According to the method, the residual life of the gear is predicted through SAE feature extraction and the ON-LSTM neural network, so the network calculation amount is greatly reduced, the calculation time is shortened, and the prediction speed and accuracy are improved.

Description

technical field [0001] The invention belongs to the field of big data and intelligent manufacturing, and relates to a method for predicting the remaining life of a gear based on SAE and ON-LSTM. Background technique [0002] Gears are widely used in mechanical equipment and are one of the most widely used mechanical parts. Gears have unique advantages such as high transmission efficiency, compact structure, good transmission smoothness, large carrying capacity, and long service life, which make them have strong and lasting vitality. Under complex working conditions and environments, gears are prone to failure, which may lead to disasters in machine operation and even endanger personal safety. This is especially true for large or very large equipment, such as hydroelectric generators, mining conveying machinery, helicopter power transmission systems, heavy machine tools, etc. The life prediction of in-service gears can effectively determine the maintenance time of equipment...

AI Technical Summary

Problems solved by technology

However, the traditional LTSM network does not analyze the gear degradation data comprehensively enough, and does not mine the order information of the neural network, so the life prediction ability is not good.

Images