Commissioning is a critical phase in the lifecycle of an industrial drive system, significantly affecting overall performance and reliability. It involves configuring drives and motors for specific applications—such as mixing, pumping, or operating conveyors—and often requires managing complex interdependencies. Traditionally, commissioning is performed manually by domain experts through multiple steps, requiring them to navigate various resources ranging from drive datasheets to vendor-specific tools for drive parameter adjustment. This manual process is time-consuming, and errors can cause significant delays, sometimes lasting several days. In this paper, we propose DriveAIAgent, a novel system architecture and methodology that integrates generative AI-powered multi-agent systems to automate and enhance the commissioning and troubleshooting of industrial drives. Our agentic system utilizes expert tools to interact with and respond to external environments, incorporating a human-in-the-loop approach. The evaluation shows that our system achieves 100% accuracy in identifying encoder parameters during the initial commissioning phase, as well as very high solution relevance (94.73%) and correctness (86.29%) for troubleshooting across different drive types. Overall, DriveAIAgent can streamline complex interactions and significantly reduce the time required for commissioning and troubleshooting industrial drive systems while maintaining the same level of quality as a human expert.

Large language models (LLMs) have gained significant attention for their success in natural language generation and their widespread adoption across various business sectors. In process automation (PA) engineering, LLMs can be utilized to assist with tasks such as PLC programming, software development, and data processing. Despite their advantages, LLMs face challenges like biased responses, non-deterministic outputs and model hallucinations. Therefore, it is essential to validate the responses generated by LLMs before relying on them. This work presents a novel workflow to automatically validate unstructured outputs generated by LLMs used in question answering (Q&A) applications based on the user-specified documents in the PA domain. The Domain of Validity (DoV) of these LLMs is first estimated based on the user-specified documents. The proposed workflow uses the estimated DoV to evaluate the relevance of the outputs generated by the LLM with respect to the user documents. A regular expression approach is included in the workflow to check whether the mentioned tag names in the LLM output, if any, exist in the user-specified documents. Furthermore, an LLM-as-a-judge approach is used then to cross-check the LLM generated outputs with the ground truth information. The proposed workflow enables users to automatically detect invalid LLM outputs. This allows the user to focus on cases that truly require human judgment and act accordingly by re-prompting the LLM, adding documents, or switching models. A fictitious PA example is employed to demonstrate the versatility and benefits of the developed workflow.

Automation Engineering of a process automation system is still a very manual effort due to limited support for the interpretation and processing of process design specification documents. Even though standards for digital data exchange between process and automation engineering do exist, those formats are rarely used and consequently the immense automation potential in automation engineering cannot be lifted. This contribution presents an AI -based approach and prototype - using an ontology-enhanced LLM -based agent and a mixture-of-experts system - to structure and formalize multimodal unstructured process design information as in PDF, Excel, and Word formats and make it available for state-of-the-art engineering tools for the long-known “Automation of Automation”.

Looking at Process and Automation Engineering (P&AE) today, there are many different tools available to support the engineer in his work from translating engineering intentions, via describing modules, to defining entire process plant setups, for export to a control system. As of today, the tools to support these steps are rarely linked to each other and hence do not allow to communicate with each other or exchange knowledge or data. Therefore, we came up with the idea of the Semantic Facilitation & Integration Layer, SemFIL, an ontology-based software system and architecture, to overcome tool, knowledge, and data silos, and to facilitate integration of and interoperability between applications, especially in P&AE. In this work, we present and evaluate the concept of SemFIL, and how it allows to connect and integrate all P&AE tools into a powerful, comprehensive, integrated workflow. We conclude with a discussion of the proposed SemFIL, and list required efforts for as well as advantages from its implementation. Lastly, we give an outlook on the most relevant future research questions and directions.

The modularization of process plants and their modular automation are innovative concepts to meet increasing demands for flexibility in plant operation. However, previous approaches to support the engineering of such modular plants do not focus on the early phases of requirements elicitation and concept design, although these early phases are crucial for the economic efficiency of the later plant. This paper presents a method for the formalized description of intentions in the early engineering phases of modular process plants. According to this method, plant operators create a formalized model of their intentions and provide it to the module manufacturers in a modularized form. This allows a reduction of effort in the planning and development of the plant. The approach is demonstrated using an oil, gas and water separation process performed by a modular process plant.

Modular industrial process plants build a production system by integrating a set of predesigned modules supplied by different vendors. The plant process engineers do not have access to the internals of these predesigned modules. Even when a predesigned module is well-tested, the composition of a set of modules can be vulnerable to many unforeseen scenarios, resulting in system-level failures. Debugging the cause of failure becomes extremely difficult since the implementation details are not available to the engineers. This paper proposes a technique by which it models the abstract functionality of each module as a state machine. We model the plant execution as a set of communicating state machines, making it possible to perform error propagation analysis and generate a set of test cases during the engineering phase.

The modularization of process plants represents an innovative approach to meet the increasing requirements regarding flexibility. The current research focuses on 100%modular process plants, which are characterized by high flexibility of the plant, but unlike monolithic process plants, they are not designed for a specific and optimized operating point. In addition, the flexibility provided by the modularity is not needed everywhere in the plant. Therefore, hybrid process plants, i.e. a combination of a monolithic plant and several modules, are expected to overcome this issue. This paper presents the key terms in the context of hybrid process plants as well as the requirements for the engineering and automation of such plants. Furthermore, a generic workflow model for the engineering of hybrid process plants is derived, with focus on the conceptual design.