Author(s)

Hui Du

Affiliation(s)

School of Computer and Artificial Intelligence, Beijing Technology and Business University, Beijing 102488, Beijing, China.

Corresponding Author

Hui Du

ABSTRACT

To overcome insufficient feature representation and limited status quantification in active braking systems (ABS), an end-to-end fault diagnosis method of ABS is constructed to combine a one-dimensional convolutional neural network (1D-CNN) and a multi-head attention mechanism (MHAM) under conditions of stronger noise interference and multi-source nonlinear coupling. Based on a 1D-CNN front-end encoder to directly decouple local high-frequency transient features from the original time-series waveform, the long-distance dependency topology within the sequence is deeply reconstructed to quantify the contribution weights of features at different time steps to the evolution of the system's health status. according to the joint constraints of the Adam adaptive optimization algorithm and regularization penalty term, the model effectively avoids the overfitting risk of deep networks and significantly enhances its generalization robustness under unknown and complex conditions. Empirical results strongly demonstrate the superiority of this method. The regression prediction determination coefficient R2 for the degree of failure reaches 0.9472, and the root mean square error (RMSE) is reduced by 1.56%, achieving high-precision quantitative perception of the system's health status.

KEYWORDS

MHAM; Fault diagnosis; Active braking system; 1D-CNN

CITE THIS PAPER

Hui Du. A fault diagnosis method of active braking systems based on 1D-CNN and MHAM. Journal of Computer Science and Electrical Engineering. 2026, 8(1): 41-47. DOI: https://doi.org/10.61784/jcsee3116.

REFERENCES

[1] Lei Y, Yang B, Jiang X, et al. Applications of machine learning to machine fault diagnosis: A review and comparison. Mechanical Systems and Signal Processing, 2020, 138: 106587.

[2] Zhao R, Yan R, Chen Z, et al. Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 2019, 115: 213-237.

[3] Li Y, Wang X, Zhang Z. A review on deep learning in fault analysis of complex systems. In: International Conference on Power and Energy Systems, 2023.

[4] Kiranyaz S, Avci O, Abdeljaber O, et al. 1D convolutional neural networks and applications: A survey. Mechanical Systems and Signal Processing, 2021, 151: 107398.

[5] Eldele E, Ragab M, Chen Z, et al. TSLANet: Rethinking Transformers for Time Series Representation Learning. arXiv preprint arXiv:2404.08472, 2024.

[6] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. Advances in Neural Information Processing Systems (NIPS), 2017: 5998-6008.

[7] Li X, Zhang M, Guo H. Dual-Path Fault Diagnosis of Small Sample for Mechanical Systems Based on Multiple Attention Mechanisms. IEEE Access, 2024, 12: 114538-114551.

[8] Jo T, Park I, Lee J, et al. A Fault Diagnosis and Fault-Tolerant Anti-Lock Brake System Control for Actuator Stuck Failures in Braking System in Autonomous Vehicles. IEEE Transactions on Transportation Electrification, 2025, 11(1): 188.

[9] Li Y, Cheng J, Zhang W. Transformer network enhanced by dual convolutional neural network and cross-attention for wheelset bearing fault diagnosis. Frontiers in Physics, 2025, 13: 1546620.

[10] Sifat M S I, Kabir M A, Islam M M M, et al. GAN-Based Data Augmentation for Fault Diagnosis and Prognosis of Rolling Bearings: A Literature Review. IEEE Access, 2025, 12: 1-21.

[11] Kiranyaz S, Avci O, Abdeljaber O, et al. 1D convolutional neural networks and applications: A survey. Mechanical Systems and Signal Processing, 2021, 151: 107398.