Mechanical Engineering Science

CNN-LSTM based on attention mechanism for brake pad remaining life prediction

WANGShuo, YUZhenliang, XUGuangchen, CHENSisi

Abstract


In order to predict the remaining service life of brake pads accurately and efficiently, and to achieve intelligent warning, this paper proposes a CNN-LSTM brake pad remaining life prediction model based on an attention mechanism. The model constructs a non-linear relationship between brake pad features such as brake temperature, brake oil pressure and brake speed and brake pad wear data through convolutional neural network (CNN) and long and short term memory network (LSTM), as well as capturing the time dependence that exists in the brake pad wear sequence. The attention mechanism is also introduced to assign different weight values to the features output from multiple historical moments, highlighting the features with high saliency and avoiding the influence of invalid features, so as to improve the prediction effect of the remaining brake pad life. The results show that the proposed CNN-LSTM-Attention model can effectively predict the remaining life of brake pads, with the mean absolute error MAE value of 0.0048, root mean square error RMSE value of 0.0059 and coefficient of determination R2 value of 0.9636; and compared with the BP model, CNN model, LSTM model and CNN-LSTM model, the coefficient of determination R2 values are closest to 1, with an improvement of 8.26%, 5.25%, 3.99% and 1.85% respectively, enabling more effective monitoring and intelligent warning of the remaining brake pad life.

Keywords


attention mechanism; CNN-LSTM; brake pads; life prediction

Full Text:

PDF

References


Deng Fengman. Analysis of hydraulic brake system fault diagnosis based on fuzzy ARX-RBQ method [J]. Hydraulic Pneumatics and Seals, 2020, 40(6): 51-54.

Hao Mingshu. Thermal-structural coupling analysis and life prediction of disc brakes [J]. Wuhan University of Technology, 2012(7):68-69.

T.Liao, N.Zhang. Wear prediction of brake pads in EMUs using a BP neural network. Advanced Science and Industry Research Center.Proceedings of 2014 Proceedings of 2014 International Conference on Artificial Intelligence and Industrial Application (AIIA2014) [J]. WIT Press, 2014(6):47-56.

Eker Muammer, Mutlu brahim, Aysal Faruk Emre, Atli Sinan, Yavuz brahim, Ergn Yelda Akin. The ANN Analysis and Taguchi Method Optimisation of the Brake Pad Composition [J]. Emerging Materials Research,2021(4):6-9.

Eltayb N. S. M., Hamdy Abeer. LS-SVM Approach for Predicting Frictional Performance of Industrial Brake Pad Materials [J]. International Journal of Mechanical Engineering and Robotics Research, 2016,7(2):87-88.

Changchang Che, Huawei Wang, Qiang Fu, Xiaomei Ni. Combining multiple deep learning algorithms for prognostic and health management of aircraft [J]. Aerospace Science and Technology, 2019,94(3):34-35.

Zheng S, Ristovski K, Farahat A, et al. Long short-term

memory network for remaining useful life estimation. Proceedings of the 2017 EEE International Conference on Prognostics and Health Management [J]. piscataway: EEE, 2017(7): 88-95.

Zhang J, Wang P, Yan R, et al. Long short-term memory formachine remaining life predictiion [J]. Jourmal of Manufacturing Systems, 2018, 48(Pt C):78-86.

Xu M., Wang Y. Kun. Remaining life prediction of DA40 aircraft carbon brake pads based on bidirectional long- and short-term memory networks [J]. computer Applications, 2021,41(05): 1527-1532.

Liu Muyuan, He Junyu, Huang Yuzhou, Tang Tao, Hu Jing, Xiao Xi. Algal bloom forecasting with time-frequency analysis: A hybrid deep learning approach [J]. Water Research, 2022(2),219.

Rremer M, Vempaty A, Calmonf P, et al. Correcting forecasts with multifactor neural attention [J]. International Conference on Machine Learning. 2016(3):3010-3019.

Qin Y, Song D J, Chen H F, et al. A dual-stage attention-based recurrent neural network for time series prediction [J].AAAI Press, 2017(1):2627- 2633.

P. K. Ambadekar, C. M. Choudhari. CNN based tool monitoring system to predict the life of cutting tool [J]. SN Applied Sciences, 2020,2(4):5-9.

Xiaoyang Zhang, Xin Lu, Weidong Li, Sheng Wang. Prediction of the remaining useful life of cutting tool using the Hurst exponent and CNN-LSTM [J]. The International Journal of Advanced Manufacturing Technology, 2021(112):357-366.

Lecun Y, Bottou L, Bengioy, et al. Gradient based learning applied to document recognition [J]. Proceedings of the IEEE, 1998,86(11) :2278-2324.

Hochreiter S, Schmidhuber J. Long short- term memory [J]. Neural Computation, 1997,9 (8) :1735 - 1780.

Chen HH, Wu G, Li JX et al. Advances in deep learning recommendation research based on attention mechanism [J]. Computer Engineering and Science, 2021, 43 (2) :370-380.

Yao Wang. Research on the wear life prediction and failure warning method of automotive brake pads [J]. China University of Mining and Technology, 2018(7):68-69.




DOI: https://doi.org/10.33142/mes.v4i2.9085

Refbacks

  • There are currently no refbacks.


Copyright (c) 2022 Shuo WANG, Zhenliang YU, Guangchen XU, Sisi CHEN

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.