Leakage Detection in Pneumatic Systems with Machine Learning and Upstream Single-Point Signals
DOI:
https://doi.org/10.13052/ijfp1439-9776.2611Keywords:
Pneumatic system, pneumatic cylinder, leakage, fault diagnosis, machine learningAbstract
Pneumatic systems are widely utilized in industrial manufacturing plants. Leakage is the most common fault and the dominating way of energy waste in pneumatic systems. Due to the low investment cost and high reliability of pneumatic systems, it is significant to detect leakage faults with a minimal number of cheap sensors. In this study, the feasibility of locating the leakages in 11 positions of a typical pneumatic system is verified with machine learning methods and the measured signal at a single point upstream. Both external and internal leakages of different pneumatic components are considered. Feature extraction is conducted using a one-dimensional convolutional neural network (1D CNN). Various machine learning classifiers, including GPC (Gaussian Process Classification), SVM (Support Vector Machine), KNN (k-Nearest Neighbour), CART (Classification and Regression Tree), MLP (Multi-Layer Perceptron), and RF (Random Forest) are used for fault classification and comparison. Class Activation Mapping (CAM) is calculated for the visualization of decision-making processes. The results show that it is feasible and convenient to detect and locate the multipoint leakages in a pneumatic system by analysing signal measured at a sole upstream point with the help of machine learning methods. The methodology can be extrapolated to and applied in more complex pneumatic systems.
Downloads
References
Borg M, Refalo P, Francalanza E. Failure Detection Techniques on the Demand Side of Smart and Sustainable Compressed Air Systems: A Systematic Review. Energies 2023; 16(7): 3188.
Wang Z, Yang B, Ma Q, Wang H, Carriveau R, Ting DSK, Xiong W. Facilitating Energy Monitoring and Fault Diagnosis of Pneumatic Cylinders with Exergy and Machine Learning. International Journal of Fluid Power 2023; 24(4): 643–682.
Li X. Intelligent fault detection and diagnosis of mechanical-pneumatic systems. PhD Thesis, Stony Brook University, 2005.
Zhang K. Fault Detection and Diagnosis for Multi-Actuator Pneumatic Systems. PhD Thesis, Stony Brook University, 2011.
Abela K, Refalo P, Francalanza E. Analysis of pneumatic parameters to identify leakages and faults on the demand side of a compressed air system. Cleaner Engineering and Technology 2022; 6: 100355.
Gauchel W, Streichert T, Wilhelm Y. Predictive maintenance with a minimum of sensors using pneumatic clamps as an example. The 12th International Fluid Power Conference, October 12–14, 2020, Dresden, Germany.
Kovacs T, Ko A. Monitoring Pneumatic Actuators’ Behavior Using Real-World Data Set. SN Computer Science 2020, 1: 196.
Britzger M, Beckmann N, Seehausen F. Machine Learning Driven Local Assignment of Compressed Air Consumption Anomalies. The 13th International Fluid Power Conference, June 13–15, 2022, Aachen, Germany.
Wang Z, Zhu H, Xiong W. Low-cost Fault Diagnosis of Pneumatic Systems with Exergy and Machine Learning: Concept, Verification, and Interpretation. JFPS International Journal of Fluid Power System 2023, 16(2): 24–32.
Wang T, Wang X, Hong M. Gas Leak Location Detection Based on Data Fusion with Time Difference of Arrival and Energy Decay Using an Ultrasonic Sensor Array. Sensors 2018, 18(9):2985.
