Deep learning for manufacturing sustainability: Models, applications in Industry 4.0 and implications

Abstract

Recent advancements and developments in artificial intelligence (AI) based approaches have shifted the manufacturing practices towards the fourth industrial revolution, considered as Industry 4.0 practices. A positive impact of AI-based techniques on sustainability can be seen in manufacturing organisations’ at the system, product and process levels. Adopting AI-based strategies in manufacturing improves decision making, productivity and system performance. Despite sustainability and other benefits, the adoption of AI-based approaches in manufacturing organisations is still limited due to employees’ knowledge and digital skills. In the present time, due to the digitalisation of manufacturing activities, intelligent sensors, and supply chain activities, industries are facing challenges with the generation of high volume, different variety and velocity of data. This data can be helpful for manufacturing organisations to enhance their performance and sustainability. However, managing this big data is still a significant challenge due to a lack of knowledge and limited literature. Deep learning (DL) based models can be a suitable choice to provide advanced analytics tools for manufacturing data processing and analysis. However, literature on the DL is still limited in the manufacturing context with its relationship to sustainability. The present study discusses the evolution of DL approaches in manufacturing and different DL-based models. This study also highlights how DL-based approaches can enhance the sustainability performance of industries. In the study, primary research areas, i.e., fault diagnosis, quality management, and predictive maintenance, have been discussed. Finally, a conceptual DL-based framework is proposed for the manufacturing industries to enhance their sustainability performance in manufacturing activities.