article · The International Journal of Advanced Manufacturing Technology
Mitigating equipment downtime remains a primary objective for manufacturing facilities. While traditional human machine interfaces and predictive maintenance tools provide alerts, their effectiveness relies heavily on how quickly human operators understand and resolve reported faults. An experimental hybrid artificial intelligence and generative artificial intelligence chatbot interface addresses this challenge by retrieving factory equipment status to support troubleshooting and predictive maintenance. Built using a Langchain agent connected to the OpenAI GPT-3.5 language model and a Streamlit front end, the system accepts monitored factory data and communicates through natural English. In addition to data retrieval, the generative model augments existing operational data formats to build larger datasets for machine learning applications. Experimental results indicate that the interface delivers accurate information based on specific prompts and reduces troubleshooting downtime compared to conventional factory practices that require frequent supervisory intervention.
Industrial downtime causes significant productivity losses when machine operators struggle to interpret complex equipment alarms. By replacing difficult technical interfaces with conversational artificial intelligence, frontline factory workers can independently diagnose machinery issues much faster. This approach supports the transition toward human-centric Industry 5.0 manufacturing environments, reducing reliance on senior supervisors and making operational maintenance data directly accessible in everyday language.
This prototype tool is designed for factory operators and plant maintenance teams seeking faster machinery troubleshooting and reduced downtime. Developed using existing frameworks including OpenAI APIs, Langchain, and Streamlit, the system represents an applied and experimentally tested proof of concept. Broader adoption would require integrating the software directly with live operational factory control systems and evaluating its performance across diverse industrial environments beyond the reported experimental trials.
AI-generated from the published abstract. Always read the original work before citing.
Abstract Throughout industrial revolutions, equipment downtime mitigations have been one of the ultimate goals of most factories. Several tools, such as human machine interface (HMI) alarming systems or predictive maintenance schedules, assist in reducing system downtime but still depend on the operators’ ability to swiftly retrieve, understand, and efficiently act upon reported failures. We propose the design of a hybrid experimental artificial intelligence (AI) and generative AI chatbot HMI that effectively extracts factory equipment conditions that are useful for troubleshooting and predictive maintenance analysis. We achieve these functions by feeding experimental factory-monitored data to the customized chatbot application tool running in its back-end, a Langchain agent linked to the OpenAI GPT $$-$$ <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML"> <mml:mo>-</mml:mo> </mml:math> 3.5 language model (LM) via OpenAI APIs. We design our chatbot front-end with Streamlit, an open-source web app. In the context of I5.0, our chatbot HMI uses personalized natural language, English, to interact with the operator, making the information extraction more understandable. We also integrate the generative AI capability of the GPT 3.5 LM that augments the factory data based on the loaded format to create a larger dataset for additional tasks like machine learning modelling. The experimental results show the accuracy of our customized chatbot HMI when retrieving data based on specific prompts and the advantages of a reduced troubleshooting time compared to operations in traditional factories, which are highly dependent on supervisors’ interventions. Our study provides a valuable example of upgrading standard factory HMIs to I5.0-capable ones by implementing customized AI and generative AI chatbots within operational industrial environments.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1007/s00170-024-13492-0
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
