This work develops a concept of a natural language co-pilot for the creation of IEC 61499 applications to accelerate initial testing and development. The co-pilot addresses the challenge of generating the correct function blocks that can be opened in popular IEC 61499 IDEs. In our case study, we focus on the generation of the centralised controller that operates particular equipment to perform a defined process. In addition, we have developed a scheme for how the co-pilot will be integrated into the FBME IDE as an AI assistant in the next steps. In the discussion, we provide valuable information for future co-pilot developers on the possible problems they might face in this area and how to overcome them.

This paper introduces an innovative multiactor framework that harnesses the potential of LLMs to augment the functionalities of ICS. By integrating conversational AI technologies, this framework significantly improves human-machine interactions, enabling sophisticated analysis and visualization of intricate data sets. The core of the system comprises specialized LLM actors that interact through a LangGraph-based multiactor framework, addressing various aspects of IEC 61499 control systems including PLC code analysis, SQL query execution, and data visualization. This integration enables operators to interact with the control system using natural language, significantly reducing technical barriers and enhancing the accessibility and usability of complex industrial systems.

The ever-increasing complexity of industrial control systems generates a demand for reliable development methods. IEC 61499, a recent industrial standard, helps to develop complex distributed systems based on their positive characteristics, namely reusability, reconfigurability, interoperability, and portability. Formal verification techniques, such as model checking, have been proposed to ensure the correctness of these systems during the design time. However, they do not consider the presence of the environment that can impact the application behaviour at runtime. This work combines design time and runtime analyses to apply probabilistic model checking on an IEC-61499-based manufacturing application. We present several probabilistic properties to be checked. The results are visualised graphically to be analysed, which allows one to optimise the system's quantitative features, such as productivity.

Automation systems within nuclear laboratories are intended to work under harsh operating conditions. Selective Production of Exotic Species (SPES) is a nuclear research facility currently under construction by the Istituto Nazionale di Fisica Nucleare, dedicated to the production and study of radioactive ion beams. Isotopes are produced within the target ion source unit, a vacuum vessel that must be replaced on a regular basis. The highly radioactive environment necessitates the deployment of a set of automated systems dedicated to the unit's remote management. To meet high-level security standards, the design of such instrumentation and control systems must include extensive verification. Based on specific safety requirements, model checking can be used to assess the systems' correctness. This article describes how to employ an integrated toolchain to design, simulate, formally verify, and deploy the control software for the Horizontal Handling Machine, a safety-critical remote handling system in operation at SPES. The IEC 61499 standard's adoption led to a redesign of the control logic. Following a preliminary online simulation, the closed-loop system has been formally verified using the NuSMV symbolic model checker, with the help of the FB2SMV converter. In addition, the Function Blocks Modeling Environment tool was used for automating verification and analyzing counterexamples.

With increase in use formal verification tools and methods in distributed systems, it is becoming more challenging to analyse the execution traces generated by formal verification tools. This paper presents a method for unification of execution traces of industrial automation systems, based on IEC 61499 standard. Execution trace of a system is a sequence of events, where each event represents a change in the state of the system. Execution traces allow developers to explore safely behavior of control software. Execution traces can be obtained several ways, including monitoring of a real system (or its simulator), or as a counterexample build by model checker. In the paper we explore unification of execution traces for debug task in FBME - modular IDE for IEC 61499 applications. We present the formal model of the execution trace representation and show the working on a simple example.