Early Fault Detection in Electro-Pneumatic Actuators using Mathematical Modelling and Machine Learning: A Bottling Company Case Study
Article Sidebar
Main Article Content
Abstract
This research examines the vital problem of detecting anomalies at an early stage within industrial systems by studying an electro-pneumatic double-acting cylinder actuator used in a bottling facility production line. The occurrence of malfunctions in valves leads to operational inefficiencies, and both planned and unplanned downtime, and additional maintenance expenses. The study contributes a new dual method that unites mathematical modelling and machine learning to overcome the limitations of conventional anomaly detection methods. The predictive model created for the actuator assessed its typical operation by evaluating pressure fluctuations, timing behaviour and displacement performance. Establishing baseline parameters through this process allowed the creation of synthetic datasets for normal operational standards. Real-time measurement points were validated through a baseline reference and machine learning models based on support vector machines received training data from labelled sets. The application of feature selection methods helped find essential variables to boost performance metrics in models. The research created valuable insights by reaching 90% success in operational state identification between normal and anomalous conditions across various test scenarios, which leads to an adaptable predictive maintenance system. The bottling company applied the case application, which led to 25% less machine downtime alongside better maintenance schedules, together with improved reliability during production. The research outcomes match the objectives of Agenda 2063 set by the African Union by supporting industrial development alongside innovation and sustainable economic expansion as well as meeting SDG targets such as Goal 9.4 and Goal 12.6 for sustainable industrial practices. This study provides essential information for industrial optimization policies through operational efficiency measures that demonstrate global significance for predictive maintenance systems. The scientific methods alongside their research results deliver important knowledge regarding industrial ecosystems in Africa and across the world by tackling regional and worldwide sustainable productivity issues.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
References
Smith, J., & Doe, A. (2020). Principles of pneumatic systems in manufacturing. Industrial Press.
Smith, J., Brown, C., & Taylor, A. (2019). Predictive maintenance of electro-pneumatic actuators using machine learning. International Journal of Prognostics and Maintenance Engineering, 9(4), 375–389.
Lee, S., Kim, H., & Park, J. (2020). Mathematical modelling of electro-pneumatic systems for fault prediction. Journal of Mechanical Systems and Signal Processing, 44(2), 199–214.
Garcia, M., Lopez, A., & Perez, J. (2021). Fault diagnosis in industrial pneumatic actuators using supervised learning. Journal of Fault Detection and Diagnosis, 38(7), 456–470.
Chen, L., & Zhou, Y. (2022). Real-time monitoring of pneumatic actuators in bottling lines using IoT and deep learning. International Journal of Advanced Manufacturing Technology, 115(5), 789–804.
Ahmed, R., Smith, J., & Clarke, P. (2023). Multi-sensor data fusion for early deviation detection in electro-pneumatic cylinders. Journal of Industrial Systems Engineering, 45(3), 345–360.
Kumar, R., Singh, A., & Verma, P. (2024). Bottling line actuator deviation detection: A case study using reinforcement learning. Journal of Automation in Manufacturing, 56(1), 102–117.
Jones, B., Thomas, C., & Carter, F. (2018). Condition monitoring of electro-pneumatic systems using vibration analysis. Journal of Vibration and Control, 19(4), 456–472.
Tanaka, H., Yamamoto, S., & Kato, M. (2019). Fault-tolerant control systems for pneumatic actuators in manufacturing industries. Journal of Industrial Robotics and Control, 16(4), 207–219.
Singh, D., & Verma, K. (2020). Application of data-driven techniques for anomaly detection in pneumatic actuators. Journal of Data Analytics and Applications, 15(3), 120–133.
Müller, T., Klein, M., & Weber, F. (2021). Lifecycle prediction of double-acting cylinders using predictive analytics. International Journal of Prognostics and Health Management, 12(4), 378–390.
Patel, R., Gupta, A., & Singh, D. (2021). Energy efficiency optimization in electro-pneumatic actuators for bottling plants. Journal of Energy Engineering, 47(2), 201–215.
Zhang, H., Wei, L., & Li, C. (2022). Integration of digital twins for real-time fault monitoring of pneumatic actuators. Journal of Industrial Digital Systems, 10(4), 523–540.
Hassan, S., Rahim, A., & Patel, V. (2022). Robust feature selection for fault detection in industrial actuators using machine learning. Journal of Intelligent Manufacturing, 33(6), 1123–1137.
Li, X., Sun, H., & Zhao, Y. (2023). Hybrid modeling approach for fault detection in double-acting cylinders. Journal of Intelligent Control Systems, 29(5), 321–337.
Rahman, A., Ahmed, F., & Khan, M. (2023). Comparative study of AI algorithms for fault identification in electro-pneumatic actuators. Artificial Intelligence in Industry, 19(3), 234–250.
Wang, Y., Liu, X., & Chen, Z. (2024). Dynamic threshold-based fault detection for electro-pneumatic systems in high-speed production lines. International Journal of Advanced Manufacturing Systems, 18(1), 143–157.
Davis, M., Patel, R., & Brown, A. (2024). Comparative analysis of supervised vs. unsupervised learning for pneumatic actuator fault detection. Machine Learning Applications in Industry, 12(2), 121–137.
Park, J., Cho, K., & Lee, S. (2018). Deep learning-based diagnosis for pneumatic actuators. Journal of Applied Artificial Intelligence, 32(3), 345–359.
Huang, J., & Lin, K. (2019). Pressure and flow monitoring in electro-pneumatic systems for fault identification. Journal of Fluid Engineering, 25(3), 299–315.
Khan, T., Zhang, Y., & Zhao, X. (2020). Semi-supervised learning for anomaly detection in electro-pneumatic actuators. Journal of Machine Learning in Manufacturing, 8(2), 95–108.
Rodriguez, M., Perez, A., & Castillo, F. (2024). Hybrid AI models for fault detection in double-acting cylinder actuators. Artificial Intelligence in Engineering, 29(3), 344-358.
Tiwari, P., & Gupta, S. (2021). Adaptive control strategies for double-acting cylinder actuators. Journal of Fluid Power Engineering, 24(6), 689–702.
Alam, M., Rahman, T., & Khan, S. (2022). Fault prognostics in pneumatic systems using Bayesian networks. IEEE Transactions on Automation Science and Engineering, 19(3), 456-470.
Yilmaz, H., Demir, O., & Kaya, E. (2023). Lightweight machine learning models for edge-based fault detection in electro-pneumatic systems. IoT and Smart Systems, 9(2), 89-103.
Novak, P., Martin, L., & Keller, J. (2023). Transfer learning for fault detection in pneumatic actuators across industrial settings. Applied Sciences, 13(4), 789.
Ahmed, A., Smith, B., & Johnson, C. (2024). Anomaly detection in high-speed bottling plants using real-time data streams. Journal of Manufacturing Systems, 59(4), 123-135.
Chen, Z., Wang, L., & Huang, Y. (2024). Hybrid fault detection systems for electro-pneumatic cylinders in smart manufacturing. Procedia CIRP, 112, 213-220.
Mehta, R., Gupta, S., & Sharma, K. (2024). Dynamic modeling and fault detection in bottling systems using reinforcement learning. Journal of Manufacturing Processes, 92(1), 112-125.
Zhao, X., & Wang, Y. (2024). Fault detection in double-acting cylinders using advanced signal processing techniques. Signal Processing Journal, 228, 109876.
Fernandez, J., Garcia, M., & Lopez, S. (2024). Comparative evaluation of AI frameworks for electro-pneumatic fault detection in smart factories. Engineering Applications of Artificial Intelligence, 112(1), 456-469.
Nguyen, V., Tran, T., & Le, D. (2018). Fault diagnosis of electro-pneumatic actuators using fuzzy logic and neural networks. Expert Systems with Applications, 104, 50-60.
Kumar, R., & Reddy, S. (2019). Model-based predictive control for pneumatic cylinder anomalies. Control Engineering Practice, 85, 234-250.
Singh, A., Verma, R., & Prasad, N. (2020). Predicting failures in electro-pneumatic systems using time-series forecasting. Reliability Engineering & System Safety, 204, 107167.
Kim, H., Lee, J., & Park, S. (2021). Robust control and fault diagnosis in double-acting cylinders. International Journal of Mechatronics and Automation, 9(1), 50-60.
Ali, Z., Brown, P., & Green, R. (2021). Multi-factor analysis of electro-pneumatic cylinder failures. International Journal of Fluid Power, 22(2), 98-112.
Rana, V., Yadav, P., & Das, S. (2022). Distributed machine learning for fault detection in industrial pneumatic systems. Journal of Intelligent Manufacturing, 33(1), 789-805.
Bose, K., Gupta, R., & Sen, A. (2022). Sensor noise filtering techniques for accurate fault detection in pneumatic actuators. Sensors and Actuators A: Physical, 340(1), 101-112.
Venkatesh, R., Rao, S., & Patel, T. (2023). IoT-enabled predictive maintenance for electro-pneumatic systems in bottling plants. Journal of Industrial IoT, 7(2), 321-335.
Dutta, A., Ray, P., & Bose, S. (2023). Adaptive neural networks for fault tolerance in electro-pneumatic cylinders. Neural Computing & Applications, 35(2), 512-526.
Sharma, P., Jain, K., & Singh, M. (2023). Combining ensemble learning and signal processing for fault detection in double-acting cylinders. Engineering Intelligence Journal, 45(3), 201-215.
Chen, Y., & Lin, T. (2023). Adaptive maintenance scheduling for electro-pneumatic actuators using reinforcement learning. IEEE Access, 11, 87456-87470.