Domain-Specific Manufacturing Analytics Framework: An Integrated Architecture with Retrieval-Augmented Generation and Ollama-Based Models for Manufacturing Execution Systems Environments

Gorde:

Xehetasun bibliografikoak
Argitaratua izan da:	Processes vol. 13, no. 3 (2025), p. 670
Egile nagusia:	Choi, Hangseo
Beste egile batzuk:	Jeong, Jongpil
Argitaratua:	MDPI AG
Gaiak:	Language Software Data processing Quality control Security Data storage Manufacturing Servers Distributed processing Natural language Data management User interface Manufacturing execution systems Large language models Knowledge Decision making Retrieval Problem solving Data collection Integrated approach Information processing Queries Real time Information retrieval
Sarrera elektronikoa:	Citation/Abstract Full Text + Graphics Full Text - PDF
Etiketak:	Etiketa erantsi Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!

Deskribapena
Laburpena:	To support data-driven decision-making in a Manufacturing Execution System (MES) environment, a system that can quickly and accurately analyze a wide range of production, quality, asset, and material information must be deployed. However, existing MES data management approaches rely on predefined queries or report templates that lack flexibility and limit real-time decision support. In this paper, we proposes a domain-specific Retrieval-Augmented Generation (RAG) architecture that extends LangChain’s capabilities with Manufacturing Execution System (MES)-specific components and the Ollama-based Local Large Language Model (LLM). The proposed architecture addresses unique MES requirements including real-time sensor data processing, complex manufacturing workflows, and domain-specific knowledge integration. It implements a three-layer structure: an application layer using FastAPI for high-performance asynchronous processing, an LLM layer for natural language understanding, and a data storage layer combining MariaDB, Redis, and Weaviate for efficient data management. The system effectively handles MES-specific challenges such as schema relationships, temporal data processing, and security concerns without exposing sensitive factory data. This is an industry-specific, customized approach focusing on problem-solving in manufacturing sites, going beyond simple text-based RAG. The proposed architecture considers the specificity of data sources, real-time and high-availability requirements, the reflection of domain knowledge and workflows, compliance with security and quality control regulations, and direct interoperability with MES systems. The architecture can be further enhanced through integration with various manufacturing systems, an advanced LLM, and distributed processing frameworks while maintaining its core focus on MES domain specialization.
ISSN:	2227-9717
DOI:	10.3390/pr13030670
Baliabidea:	Materials Science Database