Cooperative Static and Dynamic Correlation-Aware Learning for Vehicle Maintenance Demand Prediction

Accurate prediction of vehicle maintenance demands is crucial for enhancing service longevity and minimizing costs. However, current methods are limited to predicting maintenance demands for individual vehicle components. They fail to offer a comprehensive prediction that encompasses diverse maintenance demands. Additionally, vehicle maintenance demand prediction must consider the interrelationships among various maintenance projects and maintenance project records. To address these issues, we propose a vehicle maintenance demand prediction method that employs a collaborative approach. This method utilizes both static and dynamic correlation-aware learning techniques. We design a static correlation-aware method for maintenance project representation learning by leveraging prior statistical data from various maintenance projects. To effectively capture the temporal correlations inherent in different maintenance project records, we propose an attention-based dynamic correlation-aware technique. Experiments conducted on real-world datasets demonstrate that the proposed model outperforms existing methods.