Papers for

software developers in industrial automation

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Automated systems compare nlp and ai for disassembly instructions

Automated Knowledge Acquisition Pipeline for Disassembly Instructions: A Comparison of NLP and Generative AI Frameworks

Abstract: The push towards circularity and Re-X principles presents a challenge to SMEs, particularly due to increasing product complexity that impedes the adoption of disassembly automation. This paper introduces and compares two frameworks for extracting disassembly instructions from unstructured information sources, such as disassembly manuals. Our goal is to transform natural language text into a structured, curated and machine-readable format. We implemented and tested a rule-based Natural Language Processing (NLP) framework against a generative AI framework leveraging LLMs. The performance of both approaches was compared using real-world disassembly manuals. This work provides the necessary data foundation for developing and automating future disassembly processes.

Mon 9 NovArtificial Intelligence
The gist
Disassembling complex products can be hard, especially for small companies aiming to recycle or repair items easily. The paper looks at two ways to turn written manuals into clear, organized steps that machines can understand — one using strict language rules, and the other using AI that generates text understanding. The authors tested both on real manuals to see which works better. This helps create smarter tools to automate taking products apart for reuse or recycling.
Open → 2611.12816v1

Plant engineering greatly sped up using code and artificial intelligence

Engineering process plants as code in the age of agentic AI

Abstract: Agentic artificial intelligence (AI) could one day shorten process plant engineering from years to weeks. Today, however, plant information is scattered across documents and tools and must be carried between them by hand, so an AI agent placed into current workflows inherits the same silos. In this Comment, we argue for Plant-as-Code: defining the engineering of a plant as a version-controlled collection of machine-readable files that follow, where possible, existing standards such as DEXPI and IFC. On this foundation, Design-Ops extends DevOps principles to plant engineering, linking every engineering item to the information it derives from and replacing manual checking with automated tests. Agents can then coordinate routine work across disciplines while deterministic tools perform the calculations. Verification sets the pace: agents propose, tools check, and engineers review and authorize every change. We outline the risks of this shift and the research, industry and policy actions it requires.

Thu 29 OctComputational Engineering, Finance, and Science
The gist
Designing big industrial plants usually takes many years because information is spread out and handled manually. The authors suggest treating the entire plant design as code—organized, machine-readable files that can be tracked and updated like software. This approach allows AI agents to coordinate tasks and run automated checks, making the process much faster and less error-prone. They also highlight challenges and actions needed to make this shift practical and safe.
Open → 2610.40239v1