The performance degradation and safety risks associated with altered stiffness and damping in hydro-pneumatic suspensions are often caused by blockages. This paper presents an intelligent fault diagnosis method based on the Gramian Angular Summation Field (GASF) and a Convolutional Neural Network (CNN) for the precise identification and classification of blockage severity. Firstly, a single-wheel hydro-pneumatic suspension vibration test platform was developed for blockage-fault experiments. Then, by installing a throttle valve within the hose, five levels of partial blockage faults (30%-50%) were simulated. Subsequently, the body acceleration signals were acquired under sinusoidal excitations at various frequencies. To enable effective fault diagnosis, the one-dimensional time-series acceleration data were transformed into two-dimensional GASF images, which preserve critical temporal dependencies in the system's dynamic behavior. A CNN-based diagnostic model was then developed and trained on this GASF-image dataset for accurate blockage severity classification. The experimental results demonstrate that the proposed GASF-CNN approach achieves outstanding diagnostic accuracy across all tested conditions, with robustness confirmed under noisy conditions, demonstrating its potential for practical applications.

Yongchun Ding, Yun Zhu, Shuyi Yang. Research on Fault Diagnosis of Hydro-Pneumatic Suspension Blockage Based on GASF-CNN. Academic Journal of Engineering and Technology Science (2025), Vol. 8, Issue 5: 77-82. https://doi.org/10.25236/AJETS.2025.080511.

[1] Yang L, Wang R, Meng X, et al. Performance analysis of a new hydro-pneumatic inerter-based suspension system with semi-active control effect[J]. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, 2020, 234(7): 1883-1896. 

[2] Wu W, Tang H, Zhang S, et al. High‐Precision Dynamics Characteristic Modeling Method Research considering the Influence Factors of Hydro-pneumatic Suspension[J]. Shock and Vibration, 2020, 2020(1): 8886631.

[3] Hamed M, Tesfa B, Gu F, et al. A study of the suspension system for the diagnosis of dynamic characteristics[C]//2014 20th International Conference on Automation and Computing. IEEE, 2014: 152-157.

[4] Zhao G, Lyu J, Liu B, et al. Fault simulation of the hydro-pneumatic suspension system of a tracked vehicle[J]. Hydraulics Pneumatics & Seals, 2020, 40(11): 82–84, 87. 

[5] Yang C, Song P, Liu X, et al. Identification and prediction of gas-leakage faults in hydro-pneumatic springs for special vehicles[J]. Chinese Journal of Scientific Instrument, 2016, 37(11): 2536–2544.

[6] Yang C, Song P, Liu X. Failure prognostics of heavy vehicle hydro-pneumatic spring based on novel degradation feature and support vector regression[J]. Neural Computing and Applications, 2019, 31(1): 139-156.

[7] Wang Z, Oates T. Encoding time series as images for visual inspection and classification using tiled convolutional neural networks[C]//Workshops at the twenty-ninth AAAI conference on artificial intelligence. AAAI, 2015, 1: 000091-000096.

[8] Zhou Y, Long X, Sun M, et al. Bearing fault diagnosis based on Gramian angular field and DenseNet[J]. Math. Biosci. Eng, 2022, 19(12): 14086-14101.

[9] Li G, Ao J, Hu J, et al. Dual-source gramian angular field method and its application on fault diagnosis of drilling pump fluid end[J]. Expert Systems with Applications, 2024, 237: 121521.

[10] Li X, Zhang J, Xiao B, et al. Fault diagnosis of hydropower units based on Gramian angular summation field and parallel CNN[J]. Energies, 2024, 17(13): 3084.