Machine learning applications for sustainable manufacturing: a bibliometric-based review for future research

Abstract

PurposeThe role of data analytics is significantly important in manufacturing industries as it holds the key to address sustainability challenges and handle the large amount of data generated from different types of manufacturing operations. The present study, therefore, aims to conduct a systematic and bibliometric-based review in the applications of machine learning (ML) techniques for sustainable manufacturing (SM).Design/methodology/approachIn the present study, the authors use a bibliometric review approach that is focused on the statistical analysis of published scientific documents with an unbiased objective of the current status and future research potential of ML applications in sustainable manufacturing.FindingsThe present study highlights how manufacturing industries can benefit from ML techniques when applied to address SM issues. Based on the findings, a ML-SM framework is proposed. The framework will be helpful to researchers, policymakers and practitioners to provide guidelines on the successful management of SM practices.Originality/valueA comprehensive and bibliometric review of opportunities for ML techniques in SM with a framework is still limited in the available literature. This study addresses the bibliometric analysis of ML applications in SM, which further adds to the originality.

Implementing Industry 4.0 through Cleaner Production and Social Stakeholders: Holistic and Sustainable Model

“…The objective of this study is to present an implementation model of Industry 4.0. A holistic model for implementing Industry 4.0 was proposed, based on cleaner production as a fundamental tool for the development of production systems that meet the Sustainable Development Goals (SDGs) and social stakeholders considered pillars for this implementation process, helping to develop sustainable infrastructure [74][75][76][77][78][79], processes [18,80] and technologies [16][17][18][19][20]47,[74][75][76]79,84] to increase the sustainable transformation of these companies towards Industry 4.0. The model was evaluated and improved by specialists through the Delphi technique.…”

“…It is expected that the implementation of the concepts of Industry 4.0 will bring great opportunities, such as: (1) Provide better production and planning control, through the integration of technologies and communication between customers, suppliers, production and other relevant stakeholders, (2) Increase the company's global competitiveness, (3) Become or be seen as a modern company, (4) Improve the quality of the production lines, (5) Become or be seen as a company that provides products with superior performance, (6) Reach a better customer/business interaction (pre-sales/sales/after-sales), (7) Increase market share, (8) Deliver products in less time than competitors, (9) Become or be seen as a trustworthy company, (10) Delivery within the initial forecast [18,[74][75][76][77][78].…”

“…(4) Adequate infrastructure is necessary to support the complexity of the changes, requiring that companies can be guided in this implementation process. It is expected that the implementation of Industry 4.0 will bring unemployment [74][75][76][77][78][79] to the less qualified workforce, so these companies should be oriented towards alternatives to preserve the income and/or employment of this less favored workforce, reducing inequalities [74][75][76][77][78][79]. It is suggested that social stakeholders such as: Government [95,96], unions (employers and workers), banks, academic institutions, other organizations and institutions, as well as private companies [18,47,72] can join efforts to assist in this process.…”

Examining the impact of deep learning technology capability on manufacturing firms: moderating roles of technology turbulence and top management support

“…Deep learning helps improve the quality control tasks of a manufacturing unit, as it helps to detect quality-related issues. Deep learning can optimize quality processes (Kannan & Garad, 2021 ) and detect problems in quality with high levels of precision, which is difficult to achieve through traditional quality control mechanisms (Jamwal et al, 2021 ; Naoui et al, 2021 ). One of the main impacts of deep learning technology is to improve the QCC of a manufacturing unit (Hassan, 2017 ).…”

New Business and Operating Models. Optimization of a Blast Furnace in the Steel Industry. Machine Learning as a Process Optimization

“…ML develop accurate models for a variety of complex problems [18]. In the case of the Blast Furnace, very complex chemical and thermodynamic issues arise.…”