A novel approach for predicting Lockout/Tagout safety procedures for smart maintenance strategies

Abstract

This article presents an approach for predicting Lockout/Tagout (LOTO) procedure sheets, which are commonly used in the manufacturing industry to prevent premature equipment restart during maintenance. The prediction problem of energetic devices to lock from machine names is regarded as a multi-task classification problem. The dataset was obtained by processing LOTO sheets in Portable Document Format (PDF). The K-Nearest Neighbours (KNN), Random Forest (RF), and Deep Neural Network (DNN) algorithms were compared for this problem. The best prediction performance was achieved with the DNN method, with top-1 accuracies exceeding 63% and top-2 accuracies exceeding 90% for all devices. The sensitivity analysis conducted on the results indicates that the approach is robust and reliable, regardless of the industrial sector considered. In other words, the approach is not significantly affected by variations in the industry or its specific characteristics. These results suggest that the proposed approach can be used to assist workers in drafting LOTO sheets, and offers strong potential for concrete applications in safety management in the era of smart manufacturing.

KEYWORDS:

• Environment, health and safety (EHS)
• maintenance safety
• Lockout/Tagout
• text mining
• neural network
• smart manufacturing

Disclosure statement

No potential conflict of interest was reported by the author(s).

Data availability statement

The data that support the findings of this study are available from the corresponding author, LAH, upon reasonable request.

Additional information

Funding

This work was supported by Mitacs: [Grant Number IT27391]; Natural Sciences and Engineering Research Council of Canada: [Grant Number RGPIN-2019-05973]; Natural Sciences and Engineering Research Council of Canada (NSERC): [Grant Number RGPIN-2018-05292]; CONFORMiT: [Grant Number IT27391 ].

Notes on contributors

Victor Delpla

Victor Delpla holds an Engineering Master's degree from Arts et Métiers ParisTech in France and a Master of Science degree in Mechanical Engineering from École de Technologie Supérieure in Montreal, Canada. Currently, he is pursuing a doctoral degree at École de Technologie Supérieure, where his thesis is focused on optimising the safety of industrial equipment, particularly in the context of lockout/tagout operations. His other research interests encompass operational management, production and maintenance planning, supply chain management, and smart manufacturing. He has published research articles in journals such as the International Journal of Production Economics and the International Journal of Advanced Manufacturing Technology.

Kevin Chapron

Kévin Chapron holding a Ph.D. in Information Technology with a specialisation in Internet of Things (IoT) and Artificial Intelligence (AI) from Université du Québec en Outaouais, à Chicoutimi (UQO/UQAC), is an industrial researcher at CONFORMiT, a leading technology firm collaborating with high-risk industries worldwide. Joining CONFORMiT in 2020 as a Data Scientist, he now spearheads multiple substantial research projects in areas such as Environment, Health, and Safety (EHS), AI, and Optimisation, worth several million dollars. Additionally, Kévin serves as a Team Leader overseeing experts in Natural Language Processing (NLP), AI, and Computer Vision, working toward sustainable research outcomes. He also shares his knowledge by teaching courses in computer sciences and AI at UQAC and has a publication record with over 15 papers in reputable journals and international conferences, showcasing his notable contributions to both academia and industry.

Jean-Pierre Kenné

Jean-Pierre Kenné is a Professor in the Mechanical Engineering Department at Ecole de Technologie Superieure, University of Quebec since 2000. He received his M.S.A and Ph.D in Mechanical Engineering both from Ecole Polytechnique de Montreal in 1991 and 1998 respectively. He was project manager in automation and control at GEBO Canada and Logitrol Inc. for two years, before joining Ecole de Technologie Supérieure. Professor Kenne's teaching activities include control of dynamic systems, optimisation and stochastic control, design and control of hydraulic systems. He has been working on the modelling of dynamic systems and the development of control policies for more than twenty years. He proposed different strategies for controlling and real time validation of such systems. Over the past three decades, Professor Kenné and his colleagues have developed expertise in integrating the basic concepts of optimal stochastic control theory with simulation-based optimisation models, experimental designs and response surface.

Lucas A. Hof

Lucas A. Hof, ing., Ph.D., is an Associate Professor in the Mechanical Engineering Department at École de technologie supérieure, University of Quebec, Canada, since 2018. He obtained his PhD in Mechanical Engineering at Concordia University and both his Masters and Bachelor in Mechanical Engineering at Delft University of Technology. His research evolves from the need of a transformation from linear to circular manufacturing practices and concentrates on developing smart remanufacturing technologies for ceramic, metallic and polymer composite materials. Prof. Hof has developed extensive experience on advanced manufacturing systems and processes with a specific focus on circular production methods using industry 4.0 technologies. In addition, he has accumulated over ten years of industrial project management experience and produced over 60 journal and conference papers and one patent and he is supervising or co-supervising more than 20 PhD and MASc graduate students. He has a diverse portfolio on industrial research collaborations, varying from small to medium and large sized (international and local) businesses.