https://www.mdu.se/

There is an increasing interest from manufacturing industry and academia to improve operational efficiency with advanced AI systems. One such innovation is the Retrieval-Augmented Generation (RAG) system, which integrates a Large Language Model (LLM) to deliver customized recommendations and question-answering based on historical maintenance data and machine operational manuals. Previous studies highlight the effectiveness of LLMs in processing unstructured text, but limited research exists on their application within RAG frameworks for industrial maintenance use cases. The key challenge is efficiently retrieving relevant quality data and providing recommendations that are both contextually appropriate and implementable by maintenance repairmen and technicians. This paper presents a case study where a RAG system, trained on data from a Computerized Maintenance Management System and one operational manual provide recommendations/question-answers to support decision-making on the factory floor. The methodology involves embedding all the data using LLM, followed by conducting a similarity search to identify relevant information. Recommendations are then generated using the LLM and subsequently validated through expert review by subject matter experts. The results indicate that the RAG system facilitates faster and more streamlined decision-making in maintenance tasks by efficiently retrieving and contextualizing contextual maintenance records. This approach not only makes it easier for operators, repairmen and technicians to access expert knowledge, but it also shows how RAG systems can help simplify operations in industries that depend on complicated maintenance processes. The study highlights how RAG-based LLM systems can improve maintenance work by using AI to provide helpful insights.

This paper presents a usability test of a chatbot designed for the operational manual of a machining center within a manufacturing industry context as well as a survey of maintenance repairmen, focusing on information retrieval. The usability test was conducted with maintenance professionals experienced in working with similar machines and operational manuals. The test is divided into two parts. The first part evaluates how quickly participants can retrieve information using three different media—a printed version, a PDF file, and the developed chatbot. The second part covers a follow-up interview with the test participants. Twelve test participants with varying levels of experience in generative artificial intelligence (most with little or no experience) were involved in the study. Despite the limited familiarity with AI tools, the results favor the chatbot in terms of average information retrieval time. On average, participants took 40 s to find the requested information using the chatbot, compared to 1 min and 35 s with a searchable PDF file, and 2 min and 27 s with a printed manual. While participants generally expressed a positive attitude towards the use of the chatbot, they also raised concerns regarding its future applicability and potential limitations. These concerns will be discussed in detail in the paper. The survey shows that there is much efficiency to gain as the average maintenance repairman at the case company spend almost 2.5 h per week retrieving this type of information.

Purpose The maintenance function is crucial for maintaining competitiveness, safety and environmental responsibility. As demands for quality and production efficiency increase, optimized maintenance becomes more essential. Industry 4.0 and 5.0 introduce new generations of maintenance, highlighting technical and human-centered approaches. However, manufacturing companies still face many challenges in implementation and use. Prior research lacks studies that support the manufacturing industry and have not been practically connected to it. This research explores the implementation and use of smart maintenance technologies in large Swedish manufacturing companies, offering practical recommendations for industry practitioners and contributing to the field of smart maintenance research.Design/methodology/approach The research is based on 12 semi-structured interviews with respondents from 11 large manufacturing companies representing varying levels of experience and maturity in smart maintenance technologies. The empirical data were analyzed qualitatively to identify themes associated with such technologies.Findings This research identifies and describes three themes associated with smart maintenance technologies in large manufacturing companies: organizational, human and technical. These themes do not outline an implementation process, but rather synthesize the practical experiences of participating companies, increasing the understanding of how smart maintenance technologies are implemented and used in industrial practice.Originality/value This research highlights developments in maintenance for both practitioners and researchers. It compiles insights from participating companies using smart maintenance technologies to improve understanding of their practical application in industry.

This paper presents a retrospective case study comparing a life cycle cost analysis performed ten years ago with the actual cost outcome between 2014–2023. It does so to exemplify and problematize the notion of uncertainty. Through an industrial case it gives recommendations to practitioners how to reduce it. By a quantitative cost follow-up and a qualitative focus group study with key representatives of the case company the paper sets out to code sources of uncertainties, and to categorize these into either epistemic/aleatoric and into internal/external. The paper contribution is a suggested framework on management of uncertainties in industrial LCC.

Research within smart maintenance has become a popular research topic largely focused on how the nine technologies of Industry 4.0, such as Industrial Internet of Things (IIoT) and Augmented Reality (AR), as well as Artificial Intelligence (AI) and Cyber Physical System (CPS), can be used for, e.g., condition monitoring of equipment, remote services, modelling wear of components, calculating Remaining Useful Life (RUL) and prediction of failure. Due to the new generation of maintenance, new skills are required regarding the interaction between humans and technologies. Human-technology interaction in smart maintenance research is not highlighted in a structured way and according to any type of socio-technical system. The aim of the paper is to study the challenges and their associated theoretically grounded enablers regarding the implementation of and use of smart maintenance technologies, through the interplay between humans, technologies and organizations. The paper is based on empirical data from seven large manufacturing companies in Sweden as well as a literature review.

Ontology development plays a vital role as it provides a structured way to represent and organize knowledge. It has the potential to connect and integrate data from different sources, enabling a new class of AI-based services and systems such as decision support systems and recommender systems. However, in large manufacturing industries, the development of such ontology can be challenging. This paper presents a use case of an application ontology development based on machine breakdown work orders coming from a Computerized Maintenance Management System (CMMS). Here, the ontology is developed using a Knowledge Meta Process: Methodology for Ontology-based Knowledge Management. This ontology development methodology involves steps such as feasibility study, requirement specification, identifying relevant concepts and relationships, selecting appropriate ontology languages and tools, and evaluating the resulting ontology. Additionally, this ontology is developed using an iterative process and in close collaboration with domain experts, which can help to ensure that the resulting ontology is accurate, complete, and useful for the intended application. The developed ontology can be shared and reused across different AI systems within the organization, facilitating interoperability and collaboration between them. Overall, having a well-defined ontology is critical for enabling AI systems to effectively process and understand information.

Industry 4.0 is usually presented as usage of technologies. Some of these play an important role in the development of smart maintenance technologies. However, although the subject of smart maintenance has been discussed for more than 10 years, the manufacturing industry still finds it challenging to implement smart maintenance technologies to add benefits to maintenance organizations in line with company’s goals. This study presents a conceptual process for implementing smart maintenance technologies, challenges and enablers to consider when implementing, and benefits. This article is based on an analysis of empirical findings from seven large manufacturing companies in Sweden, previous maintenance research, and authors’ three previous smart maintenance research articles. In the first article, the authors explored perspectives on smart maintenance technologies from 11 large companies within the manufacturing industry, while in the second one, perspectives on smart maintenance technologies from 15 manufacturing Small and medium-sized enterprises (SMEs) were presented. In the third and final one, the authors developed and presented a testbed for smart maintenance technologies.

Industry 4.0 presents nine technologies including Industrial Internet of Things (IIoT), Big Data and Analytics, Augmented Reality (AR), etc. Some of the technologies play an important role in the development of smart maintenance technologies. Previous research presents several technologies for smart maintenance. However, one problem is that the manufacturing industry still finds it challenging to implement smart maintenance technologies in a value-adding way. Open questionnaires and interviews have been used to collect information about the current needs of the manufacturing industry. Both the empirical findings of this paper, as well as previous research, show that knowledge is the most common challenge when implementing new technologies. Therefore, in this paper, we develop and present a testbed for how to approach smart maintenance technologies and to share technical knowledge to the manufacturing industry.

Manufacturing maintenance has always undergone change and development. With Industry 4.0-related technological development, increasingly more complex machining equipment, and an increased focus on sustainability, maybe more so today than ever. This has led to an increased difficulty in finding competent maintenance employees to recruit. Simultaneously, it increases the need for continuous competence development to retain the existing work force up to date with the challenges of future development. The introduction of these new technologies and demands does not reduce the need of competence in basic maintenance skills though, but rather adds new areas of needed competence, making the maintenance profession increasingly more complex. This paper will, through an interview study of maintenance managers in an international manufacturing company located in nine countries, delve into the issues and present both challenges and enablers in how to work with recruitment and competence development within maintenance.

Companies must enhance total maintenance effectiveness to stay competitive, focusing on both digitalization and basic maintenance procedures. Digitalization offers technologies for data-driven decision-making, but many maintenance decisions still lack a factual basis. Prioritizing efficiency and effectiveness require analyzing equipment history, facilitated by using Computerized Maintenance Management Systems (CMMS). However, CMMS data often contains unstructured free-text, leading to manual analysis, which is resource-intensive and reactive, focusing on short time periods and specific equipment. Two approaches are available to solve the issue: minimizing free-text entries or using advanced methods for processing them. Free-text allows detailed descriptions but may lack completeness, while structured reporting aids automated analysis but may limit fault description richness. As knowledge and experience are vital assets for companies this research uses a hybrid approach by combining Natural Language Processing with domain specific ontology and Large Language Models to extract information from free-text entries, enabling the possibility of real-time analysis e.g., identifying recurring failure and knowledge sharing across global sites.