New pipeline automates industrial device configuration using LLMs and ontologies

Researchers have developed SysName, a pipeline designed to automate the configuration of industrial fieldbus devices. This system uses a hybrid retrieval index combined with an ontology graph derived from ECLASS, AAS, and SOSA/SSN standards. A local large language model then generates JSON-LD configurations, which are further validated by a two-stage abstention gate to prevent unsafe operations. SysName demonstrated high accuracy and efficiency in configuring various industrial protocols, including a case study involving a Universal Robots UR5e robot. AI

IMPACT Automates complex industrial device configuration, potentially reducing errors and speeding up deployment in manufacturing and robotics.

RANK_REASON The item is a research paper detailing a novel system for industrial device configuration. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• AAS
• BGE-M3
• CANopen
• H100 GPU
• JSON-LD
• Profibus DP
• SHACL
• SOSA/SSN
• SysName
• Universal Robots UR5e

• paper
• product
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →