Deep Learning Based Prediction of Automotive Maintenance Projects
Year: 2025
Type: book-chapter
Abstract: With the rapid increase in global automobile ownership, automobile maintenance has become increasingly important as a critical service industry. Effective automobile maintenance services are not only related to people’s quality of life but are also essential for ensuring road safety. In the context of rapid technological development, the advancements in deep learning have shown revolutionary results across many fields, particularly in the automotive maintenance industry, garnering significant attention for its potential applications. In this paper, we propose a hybrid learning model that combines Long Short-Term Memory Network (LSTM) with an Attention Mechanism to predict automobile maintenance projects. The model captures long-term dependencies within maintenance records via LSTM and emphasizes crucial historical information through the attention mechanism. It incorporates the Dropout technique and customized activation functions to enhance the model’s generalization ability and robustness. Experimental results demonstrate that the proposed method effectively predicts automotive maintenance projects and outperforms traditional models.
DOI: 10.3233/atde250419
Authors: Fanghua Chen, Gang Zhou, Wu Guofang, Liu Fujia, Chen Chaozhou, Jinrui Zhang
Institutions: Ministry of Transport, Research Institute of Highway
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4412919768