Analysis of the efficiency of pneumatic actuator regulation in selected production processes using artificial intelligence, graph algorithms, and probabilistic methods, taking into account failure rates and return on investment costs
Piotr SKUDLIK, Andrzej WRÓBEL
Abstract. Modern production systems are characterized by a high degree of automation, where pneumatic actuators play a key role in assembly and transport processes. This paper presents an analysis of the performance of pneumatic actuator regulation using artificial intelligence (AI) algorithms and probabilistic methods in simulated production conditions. The study utilized LSTM neural networks for failure prediction, graph algorithms like Bayesian networks, and Monte Carlo simulations to assess the risk of downtime. The results show that AI models enable a significant reduction in unplanned downtimes and optimization of operational costs through dynamic regulation of actuator parameters. The simulation, based on real operational data, demonstrated that AI models outperform traditional control methods, such as PID controllers, in terms of efficiency and accuracy in failure prediction. However, the applied models have limitations, including high computational requirements and dependence on the quality of input data. The findings suggest that integrating AI algorithms into industrial automation systems can substantially improve production efficiency by reducing operational costs and failure risks. This study highlights the potential benefits of widespread AI adoption in industrial automation, particularly in ensuring long-term system reliability.
Keywords
Artificial Intelligence, Manufacturing, Mechanical Engineering, Automation, Robotic, Statistic, Neural Networks, Mathematical Algorithms, Management
Published online 12/10/2024, 8 pages
Copyright © 2024 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: Piotr SKUDLIK, Andrzej WRÓBEL, Analysis of the efficiency of pneumatic actuator regulation in selected production processes using artificial intelligence, graph algorithms, and probabilistic methods, taking into account failure rates and return on investment costs, Materials Research Proceedings, Vol. 46, pp 338-345, 2024
DOI: https://doi.org/10.21741/9781644903377-44
The article was published as article 44 of the book Innovative Manufacturing Engineering and Energy
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] A. Gupta. “Modeling and Simulation in Manufacturing Systems”, International Journal of Computer Integrated Manufacturing, 2003
[2] R. Merwe, “Simulation as a Tool in Manufacturing,” Journal of Manufacturing Science and Engineering, 2001
[3] T. Oliphant, “A guide to NumPy“, Trelgol Publishing, 2006
[4] J. Hunter, “Matplotlib: A 2D graphics environment”, Computing in Science & Engineering, 9(2007) 90-95. https://doi.org/10.1109/MCSE.2007.55
[5] J. Muellbauer, “Economics and Consumer Behavior”, Cambridge University Press, 1980
[6] F. Chollet, “Deep Learning with Python”, Manning Publications, 2017
[7] M. Abadi, et al., “TensorFlow: A System for Large-Scale Machine Learning”, OSDI, 2016
[8] A. Geron, „Hands-On Machine Learning with Scikit-Learn, Keras, and Tensorflow: Concepts, Tools, and Techniques to Build Intelligent“, O’Reilly, 2019
[9] W. McKinney, “Data Structures for Statistical Computing in Python”, Proceedings of the 9th Python in Science Conference, 2010. https://doi.org/10.25080/Majora-92bf1922-00a
[10] Information on https://numpy.org/
[11] Information on https://pandas.org/
[12] Information on https://www.python.org/
[13] Information on http://www.weld.labs.gov.cn
