Explainable Dynamic Graph Neural Networks for Predictive Maintenance in Vehicle Chassis Systems

Wu You, Junwei SU, Sirui ZHANG, Zhijian Li
Proceedings of the 17th Asian Conference on Machine Learning, PMLR 304:878-893, 2025.

Abstract

Predictive maintenance is essential for commercial vehicle fleets to reduce unexpected downtime and emergency repair costs. While standardized fault codes (SPN/FMI, representing Suspect Parameter Numbers and Failure Mode Indicators) assist in diagnosis, their temporal and spatial inconsistency limits the effectiveness of conventional time-series models in identifying high-cost failures. We propose a Hybrid Node-level Relationship-based Graph Convolutional Network with Random Forest (NRP-GCN-RF), which encodes fault interactions as graphs to capture non-temporal dependencies. Built on a real-world dataset from Dongfeng Motor Corporation, our study follows a dual-task design. (1) We construct a predictive model using graph neural networks (GCN) and random forests (RF) to forecast emergency repair costs and fault categories based on chassis-level fault sequences. (2) In parallel, we apply the Apriori algorithm to mine frequent co-occurring SPN-FMI pairs, revealing interpretable fault patterns and subsystem-level dependencies. This interpretable analysis complements the graph-based model by supporting feature design and failure diagnostics. Experiments show that our approach achieves 98.93% accuracy, raises high-cost failure precision from 60% to 95%, and improves recall by 25%, offering a robust and explainable solution for predictive maintenance in commercial fleets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v304-you25a, title = {Explainable Dynamic Graph Neural Networks for Predictive Maintenance in Vehicle Chassis Systems}, author = {You, Wu and SU, Junwei and ZHANG, Sirui and Li, Zhijian}, booktitle = {Proceedings of the 17th Asian Conference on Machine Learning}, pages = {878--893}, year = {2025}, editor = {Lee, Hung-yi and Liu, Tongliang}, volume = {304}, series = {Proceedings of Machine Learning Research}, month = {09--12 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v304/main/assets/you25a/you25a.pdf}, url = {https://proceedings.mlr.press/v304/you25a.html}, abstract = {Predictive maintenance is essential for commercial vehicle fleets to reduce unexpected downtime and emergency repair costs. While standardized fault codes (SPN/FMI, representing Suspect Parameter Numbers and Failure Mode Indicators) assist in diagnosis, their temporal and spatial inconsistency limits the effectiveness of conventional time-series models in identifying high-cost failures. We propose a Hybrid Node-level Relationship-based Graph Convolutional Network with Random Forest (NRP-GCN-RF), which encodes fault interactions as graphs to capture non-temporal dependencies. Built on a real-world dataset from Dongfeng Motor Corporation, our study follows a dual-task design. (1) We construct a predictive model using graph neural networks (GCN) and random forests (RF) to forecast emergency repair costs and fault categories based on chassis-level fault sequences. (2) In parallel, we apply the Apriori algorithm to mine frequent co-occurring SPN-FMI pairs, revealing interpretable fault patterns and subsystem-level dependencies. This interpretable analysis complements the graph-based model by supporting feature design and failure diagnostics. Experiments show that our approach achieves 98.93% accuracy, raises high-cost failure precision from 60% to 95%, and improves recall by 25%, offering a robust and explainable solution for predictive maintenance in commercial fleets.} }
Endnote
%0 Conference Paper %T Explainable Dynamic Graph Neural Networks for Predictive Maintenance in Vehicle Chassis Systems %A Wu You %A Junwei SU %A Sirui ZHANG %A Zhijian Li %B Proceedings of the 17th Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Hung-yi Lee %E Tongliang Liu %F pmlr-v304-you25a %I PMLR %P 878--893 %U https://proceedings.mlr.press/v304/you25a.html %V 304 %X Predictive maintenance is essential for commercial vehicle fleets to reduce unexpected downtime and emergency repair costs. While standardized fault codes (SPN/FMI, representing Suspect Parameter Numbers and Failure Mode Indicators) assist in diagnosis, their temporal and spatial inconsistency limits the effectiveness of conventional time-series models in identifying high-cost failures. We propose a Hybrid Node-level Relationship-based Graph Convolutional Network with Random Forest (NRP-GCN-RF), which encodes fault interactions as graphs to capture non-temporal dependencies. Built on a real-world dataset from Dongfeng Motor Corporation, our study follows a dual-task design. (1) We construct a predictive model using graph neural networks (GCN) and random forests (RF) to forecast emergency repair costs and fault categories based on chassis-level fault sequences. (2) In parallel, we apply the Apriori algorithm to mine frequent co-occurring SPN-FMI pairs, revealing interpretable fault patterns and subsystem-level dependencies. This interpretable analysis complements the graph-based model by supporting feature design and failure diagnostics. Experiments show that our approach achieves 98.93% accuracy, raises high-cost failure precision from 60% to 95%, and improves recall by 25%, offering a robust and explainable solution for predictive maintenance in commercial fleets.
APA
You, W., SU, J., ZHANG, S. & Li, Z.. (2025). Explainable Dynamic Graph Neural Networks for Predictive Maintenance in Vehicle Chassis Systems. Proceedings of the 17th Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 304:878-893 Available from https://proceedings.mlr.press/v304/you25a.html.

Related Material