Learning Automata of PLCs in Production Lines Using LSTM

2025-03-01

AI Summary

Accurately modeling the PLC control logic of modern pneumatic conveying systems remains challenging due to its complex, event-driven behavior and lack of accessible internal specifications. Method: This paper proposes an end-to-end finite state automaton (FSA) learning method based on Long Short-Term Memory (LSTM) networks. It directly trains an LSTM on raw sensor time-series data and subsequently infers an equivalent FSA via state clustering and transition extraction—without requiring handcrafted rules or structural assumptions. Contribution/Results: To our knowledge, this is the first approach enabling interpretable, PLC-level behavioral modeling using LSTMs. Compared with state-of-the-art OTALA methods, the learned FSAs achieve significantly higher state coverage and transition accuracy. Moreover, the resulting models are lightweight, scalable, and empirically validated on real industrial production lines, demonstrating strong robustness and generalization across diverse operational conditions.

Technology Category

• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Search and Optimization: Learning to Search
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Production Lines and Conveying Systems are the staple of modern manufacturing processes. Manufacturing efficiency is directly related to the efficiency of the means of production and conveying. Modelling in the industrial context has always been a challenge due to the complexity that comes along with modern manufacturing standards. Long Short-Term Memory is a pattern recognition Recurrent Neural Network, that is utilised on a simple pneumatic conveying system which transports a wooden block around the system. Recurrent Neural Networks (RNNs) capture temporal dependencies through feedback loops, while Long Short-Term Memory (LSTM) networks enhance this capability by using gated mechanisms to effectively learn long-term dependencies. Conveying systems, representing a major component of production lines, are chosen as the target to model to present an approach applicable in large scale production lines in a simpler format. In this paper data from sensors are used to train the LSTM in order to output an Automaton that models the conveying system. The automaton obtained from the proposed LSTM approach is compared with the automaton obtained from OTALA. The resultant LSTM automaton proves to be a more accurate representation of the conveying system, unlike the one obtained from OTALA.

Problem

• Modeling complex production lines using LSTM for improved accuracy.
• Comparing LSTM-generated automata with OTALA for conveying systems.
• Enhancing manufacturing efficiency through advanced neural network modeling.

Innovation

• LSTM models pneumatic conveying system dynamics
• Sensors train LSTM to output system automaton
• LSTM automaton outperforms OTALA in accuracy