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

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.