Low-Cost and low-Redundancy Fault Diagnosis in Complex Pneumatic Systems: Case Study of a Pick-and-Place System

Authors

  • Lingchao Yu Department of Mechanical Engineering, Dalian Maritime University, Dalian 116026, Liaoning, China
  • Zhiwen Wang Department of Mechanical Engineering, Dalian Maritime University, Dalian 116026, Liaoning, China https://orcid.org/0000-0002-5644-0545
  • Chunpu Zhang Department of Mechanical Engineering, Dalian Maritime University, Dalian 116026, Liaoning, China
  • Zheng Zhao College of Artificial Intelligence, Dalian Maritime University, Dalian 116026, Liaoning, China
  • Duo Li Department of Mechanical Engineering, Dalian Maritime University, Dalian 116026, Liaoning, China
  • Rupp Carriveau Turbulence and Energy Laboratory, Ed Lumley Centre for Engineering Innovation, University of Windsor, Windsor N9B 3P4, Ontario, Canada
  • David S.-K. Ting Turbulence and Energy Laboratory, Ed Lumley Centre for Engineering Innovation, University of Windsor, Windsor N9B 3P4, Ontario, Canada https://orcid.org/0000-0002-0919-6156
  • Wei Xiong Department of Mechanical Engineering, Dalian Maritime University, Dalian 116026, Liaoning, China

DOI:

https://doi.org/10.13052/ijfp1439-9776.2723

Keywords:

Pneumatic systems, Fault diagnosis, Low redundancy, Machine learning

Abstract

Low-cost fault diagnosis of pneumatic systems has been highly demanded by the industrial community in recent years. In this study, the feasibility of low-cost and low-redundancy fault diagnosis in complex pneumatic systems is investigated by using a minimal number of mature flow and pressure sensors. A pick-and-place demonstration system with 17 pneumatic actuators is taken as the experimental platform. Only one pressure sensor and one flow sensor are utilized to diagnose 132 leakage faults with the help of a one-dimensional convolutional neural network (1D CNN). The average accuracies of leakage fault diagnosis with pressure, flow rate, and exergy data are 89.5%, 96.8%, and 98.9%, respectively. The results are interpreted with Class Activation Mapping (CAM) and Occlusion Sensitivity Analysis (OSA). Overall, it reveals that it is feasible to diagnose multiple faults in complex pneumatic systems with a minimal number of commonly used sensors.

Downloads

Download data is not yet available.

Author Biographies

Lingchao Yu, Department of Mechanical Engineering, Dalian Maritime University, Dalian 116026, Liaoning, China

Lingchao Yu received his bachelor’s degree in Mechanical Engineering from Qingdao University of Science and Technology in 2023. Currently, he is pursuing his master’s degree in Mechanical Engineering at Dalian Maritime University. His research interests include pneumatic fault diagnosis and machine learning.

Zhiwen Wang, Department of Mechanical Engineering, Dalian Maritime University, Dalian 116026, Liaoning, China

Zhiwen Wang received the bachelor’s degree of Marine Engineering from Dalian Maritime University in 2012 and the philosophy of doctorate degree in Marine Engineering from Dalian Maritime University in 2018, respectively. He is currently working as an Associate Professor at the Department of Mechanical Engineering, Dalian Maritime University. His research areas include energy saving and FDD of pneumatics, thermodynamics, and energy storage.

Chunpu Zhang, Department of Mechanical Engineering, Dalian Maritime University, Dalian 116026, Liaoning, China

Chunpu Zhang received his bachelor’s degree in Mechanical Engineering from Dezhou University in 2022. He is currently pursuing a master’s degree in Mechanical Engineering at Dalian Maritime University. His research areas include data-driven modeling.

Zheng Zhao, College of Artificial Intelligence, Dalian Maritime University, Dalian 116026, Liaoning, China

Zheng Zhao received his B.D., M.D. and Ph.D. degrees of information science and technology in 2010, 2013, and 2017, respectively. He is currently a lecturer in the College of Artificial Intelligence, Dalian Maritime University, Dalian, China. His research interests include next-generation internet, data security, and artificial intelligence.

Duo Li, Department of Mechanical Engineering, Dalian Maritime University, Dalian 116026, Liaoning, China

Duo Li received his bachelor’s degree in Mechanical Engineering from Shenyang Jianzhu University and Technology in 2023. Currently, he is pursuing his master’s degree in Mechanical Engineering at Dalian Maritime University. His research interests include pneumatic fault diagnosis and machine learning.

Rupp Carriveau, Turbulence and Energy Laboratory, Ed Lumley Centre for Engineering Innovation, University of Windsor, Windsor N9B 3P4, Ontario, Canada

Rupp Carriveau is a Professor of Mechanical, Automotive & Materials Engineering, University of Windsor, Canada. He received his BSc in Civil Structural Engineering from University of Windsor. He obtained his MSc and PhD in Fluids Engineering from Western University, Canada. His research interests cover energy storage, renewable energy, and systems optimization etc.

David S.-K. Ting, Turbulence and Energy Laboratory, Ed Lumley Centre for Engineering Innovation, University of Windsor, Windsor N9B 3P4, Ontario, Canada

David S.-K. Ting is a Professor of Mechanical, Automotive & Materials Engineering, University of Windsor, Canada. He received his BSc in 1989 from University of Manitoba. He obtained his MSc and PhD in 1992 and 1995 from University of Alberta, Canada. His major research interests are turbulence, heat transfer, energy & thermal systems, renewable energy, and aerodynamics.

Wei Xiong, Department of Mechanical Engineering, Dalian Maritime University, Dalian 116026, Liaoning, China

Wei Xiong is a Professor of Mechanical Engineering, Dalian Maritime University. He is the director of Ship Electromechanical Equipment Institute. He received his PhD in the Faculty of Mechatronic Engineering from Harbin Institute of Technology, China. His major research interests are fluid power and control, marine rescue, and compressed air energy storage.

References

M. Borg, P. Refalo, and E. Francalanza. Failure Detection Techniques on the Demand Side of Smart and Sustainable Compressed Air Systems: A Systematic Review. Energies, 2023, 16(7): 3188. https://doi.org/10.3390/en16073188.

M. Demetgul, I. N. Tansel, and S. Taskin. Fault diagnosis of pneumatic systems with artificial neural network algorithms. Expert Syst. Appl., 2009, 36(7): 10512–10519. https://doi.org/10.1016/j.eswa.2009.01.028.

K. Zhang. Fault Detection and Diagnosis for Multi-Actuator Pneumatic Systems. Ph.D. dissertation, Stony Brook Univ., New York, NY, USA, 2011.

Z. Wang et al. Facilitating Energy Monitoring and Fault Diagnosis of Pneumatic Cylinders with Exergy and Machine Learning. Int. J. Fluid Power, 2023, 24(4): 643–682. DOI: 10.13052/ijfp1439-9776.2442.

M. Daigle, C. S. Kulkarni, and G. Gorospe. Application of model-based prognostics to a pneumatic valves testbed. 2014 IEEE Aerospace Conf., Big Sky, MT, USA, 2014, pp. 1–8. DOI: 10.1109/AERO.2014.6836319.

B. M. Rahman et al. Fault Diagnosis of Pneumatic Systems: Application of a Systematic Model-Based Methodology. IFAC-PapersOnLine, 2017, 50(1): 3294–3300. https://doi.org/10.1016/j.ifacol.2017.08.505.

W. Gauchel, T. Streichert, Y. Wilhelm. Predictive Maintenance with a Minimum of Sensors using Pneumatic Clamps as an Example. The 9th Int. Fluid Power Conf Dresden, Oct. 12–14, 2020. https://doi.org/10.25368/2020.81.

V. Boyko and J. Weber. Cycle Time-Based Fault Detection and Localization in Pneumatic Drive Systems. Actuators. 2024, 13(11):447. https://doi.org/10.3390/act13110447.

W. Ertel et al. Model Free Diagnosis of Pneumatic Systems using Machine Learning. The 9th Int. Fluid Power Conf., Aachen, Germany, Mar. 24–26, 2014.

T. Kovacs and A. Ko. Monitoring Pneumatic Actuators’ Behavior Using Real-World Data Set. SN Comput. Sci., 2020, 1: 196. https://doi.org/10.1007/s42979-020-00202-2.

Z. Ding et al. A Deep-Learning-Based Low-Cost Micro-Leakage Measurement System for Industrial Applications. IEEE-ASME Trans. Mechatron., 2024, 29(1): 119–130. DOI: 10.1109/TMECH.2023.3272797.

M. Tiboni and C. Remino. Condition Monitoring of Pneumatic Drive Systems Based on the AI Method Feed-Forward Backpropagation Neural Network. Sensors, 2024, 24(6): 1783. https://doi.org/10.3390/s24061783.

Y. Shi et al. Improved object detection network for pipeline leakage localization in the pneumatic system based on thermal images. Measurement, 2025, 242: 116225. https://doi.org/10.1016/j.measurement.2024.116225.

M. Borg, P. Refalo, and E. Francalanza. Fault Condition Indicators along the Demand Side of a Sustainable Compressed Air System. Procedia CIRP, 2024, 126: 283–288. https://doi.org/10.1016/j.procir.2024.08.340.

H. Zhu et al. Leakage Fault Diagnosis of Two Parallel Cylinders in Pneumatic System with a Minimal Number of Sensors. Electronics, 2023, 12(15): 3261. https://doi.org/10.3390/electronics12153261.

Z. Wang et al. Low-cost Fault Diagnosis of Pneumatic Systems with Exergy and Machine Learning: Concept, Verification, and Interpretation. JFPS Int. J. Fluid Power Syst., 2023, 16(2): 24–32. https://doi.org/10.5739/jfpsij.16.24.

Z. Tong et al. Accumulated and transient exergy analyses of pneumatic systems with isochoric and isobaric compressed air storage tanks. Energy Storage, 2021, 3(6): e269. https://doi.org/10.1002/est2.269.

A. Krizhevsky, I. Sutskever, and G. E. Hinton. ImageNet classification with deep convolutional neural networks. Commun. ACM, 2017, 60(6): 84–90. https://doi.org/10.1145/306538.

Downloads

Published

2026-04-19

How to Cite

Yu, L. ., Wang, Z. ., Zhang, C. ., Zhao, Z. ., Li, D. ., Carriveau, R. ., Ting, D. S.-K. ., & Xiong, W. . (2026). Low-Cost and low-Redundancy Fault Diagnosis in Complex Pneumatic Systems: Case Study of a Pick-and-Place System. International Journal of Fluid Power, 27(02), 327–358. https://doi.org/10.13052/ijfp1439-9776.2723

Issue

2026: Vol 27 Iss 2

Section

Original Article