Dry clutch temperature prediction method based on dynamic neural network time series prediction

Abstract

The invention discloses a dry clutch temperature prediction method based on dynamic neural network time series prediction. The clutch temperature and time history sample data are used to model and predict the clutch temperature by using the dynamic neural network time series prediction method. First, data acquisition; then training data, establishing a dynamic neural network time series model; predicting the clutch temperature in the future time series, analyzing the error of the prediction result, and de-normalizing the predicted data; finally, the clutch temperature prediction model and time are obtained. Predicted values ​​on the series. Compared with the traditional test method and finite element numerical simulation method to obtain the clutch temperature, this method has the advantages of simple implementation, high precision and low cost. In addition, this method has a memory function, which is very suitable for processing time series data. Can predict all temperatures, including maximum temperatures, during a single clutch engagement or multiple engagements in a row.

Description

technical field [0001] The invention relates to a dry clutch temperature prediction method, in particular to a dry clutch temperature prediction method based on dynamic neural network time series prediction. Background technique [0002] The clutch is an important part in the drive train of the automobile chassis, which mainly realizes the smooth start and safe stop of the automobile. Diaphragm spring dry clutches use the friction between friction pairs to transmit torque, and have the advantages of strong mechanical reliability and high transmission efficiency, especially in heavy-duty vehicles, accounting for more than 90% of the market share. When the diaphragm spring clutch engages for a long time or has a high frequency of slipping, the temperature of the clutch will continue to rise rapidly, which will cause the clutch to slip easily. Slip faults cause clutch ablation, reduced transmission friction torque, and significantly reduced clutch life. The slip fault is clos...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the problem in the prior art that it is difficult to accurately obtain the temperature of dry clutches that cause frequent clutch slipping faults, the present invention provides a dry clutch temperature prediction method based on dynamic neural network time series prediction, which is especially suitable for predicting dry clutches. The temperature at which the clutch is engaged multiple times in succession

Images