Query Your Handbooks - Processing of Industrial Documentation with LLMs

  • Operation and maintenance tasks in an industrial context are complex and often time- consuming processes. The manufacturer-provided manuals form the foundation for these processes. However, finding the required information from manuals remains an arduous task. During a maintenance task, the relevant information from plant documentation should be directly available. Along the individual process steps, questions may arise that require information from documentation. To make plant documentation queryable, a Retrieval Augmented Generation (RAG) system was developed. This technique is ideal for cases with little training data, in which fine-tuning of large language models (LLM) is ill-advised. The plant documentation serves as an external knowledge base for answering incoming questions with links to the original documents. Before the RAG development, comprehensive pre-processing of documents takes place, which here is divided into three main blocks: (1) Bill of materials are recognized,Operation and maintenance tasks in an industrial context are complex and often time- consuming processes. The manufacturer-provided manuals form the foundation for these processes. However, finding the required information from manuals remains an arduous task. During a maintenance task, the relevant information from plant documentation should be directly available. Along the individual process steps, questions may arise that require information from documentation. To make plant documentation queryable, a Retrieval Augmented Generation (RAG) system was developed. This technique is ideal for cases with little training data, in which fine-tuning of large language models (LLM) is ill-advised. The plant documentation serves as an external knowledge base for answering incoming questions with links to the original documents. Before the RAG development, comprehensive pre-processing of documents takes place, which here is divided into three main blocks: (1) Bill of materials are recognized, page references are stored, and tables are extracted. (2) Technical drawings are also recognized, their page reference is saved, and then passed to a multi-modal LLM (MMLLM), which extracts title and drawing number. (3) The manual is divided into chapters so that each query can be thematically assigned to one or more chapters where appropriate answers are sought. To provide further context, the operation and maintenance tasks are modeled using Business Process Model and Notation (BPMN), an international standard for representation of business processes. As a case study, the maintenance of an industrial pump is used. Along the maintenance process, questions are passed to LLM and RAG to provide concise answers.zeige mehrzeige weniger

Volltext Dateien herunterladen

  • 2025-11-06 - BAM ML Symposium.pdf
    eng

Metadaten exportieren

Weitere Dienste

Suche bei Google Scholar Anzahl der Zugriffe auf dieses Dokument
Metadaten
Autor*innen:Sarah Karioui
Koautor*innen:Elyess Eleuch, Erik Esche, Jens-Uwe Repke, Markus Schichtel, Frauke Weichardt
Dokumenttyp:Vortrag
Veröffentlichungsform:Präsentation
Sprache:Englisch
Jahr der Erstveröffentlichung:2025
Organisationseinheit der BAM:2 Prozess- und Anlagensicherheit
2 Prozess- und Anlagensicherheit / 2.0 Abteilungsleitung und andere
Freie Schlagwörter:AI; BPMN; Maintenance
Themenfelder/Aktivitätsfelder der BAM:Chemie und Prozesstechnik
Chemie und Prozesstechnik / Anlagensicherheit und Prozesssimulation
Veranstaltung:AI/ML Symposium BAM
Veranstaltungsort:Berlin, Germany
Beginndatum der Veranstaltung:06.11.2025
Verfügbarkeit des Dokuments:Datei im Netzwerk der BAM verfügbar ("Closed Access")
Datum der Freischaltung:13.01.2026
Referierte Publikation:Nein
Eingeladener Vortrag (wissenschaftliche Konferenzen):Nein
Einverstanden
Diese Webseite verwendet technisch erforderliche Session-Cookies. Durch die weitere Nutzung der Webseite stimmen Sie diesem zu. Unsere Datenschutzerklärung finden Sie hier.