A digital life-cycle management framework for sustainable smart manufacturing in energy intensive industries

Abstract

Energy intensive industries can be classified into those that process metal, glass, ceramics, paper, cement, and bulk chemicals. They are associated with significantly high proportions of carbon emissions, consume a lot of energy and raw materials, and cause energy wastage as a result of heat escaping from furnaces, reheating of products, and rejection of parts. In alignment with UN sustainable development goals of industry, innovation, infrastructure and responsible consumption and production, it is important to ensure that the energy consumption of EIIs are monitored and reduced such that their energy efficiency can be improved. Towards this aim, it is possible to employ the concepts of digitalisation and smart manufacturing to identify the critical areas of improvement and establish enablers that can help improve the energy efficiency. The aim of this research is to review the current state of digitalisation in energy-intensive industries and propose a framework to support the realisation of sustainable smart manufacturing in Energy Intensive Industries (EIIs). The key objectives of the work are (i) the investigation of process mining and simulation modelling to support sustainability, (ii) embedding intelligence in EIIs to improve energy and material efficiency and (iii) proposing a framework to enable the digital transformation of EIIs. The proposed five-layer framework employs data acquisition, process management, simulation & modelling, artificial intelligence, and data visualisation to identify and forecast energy consumption. A detailed description of the various phases of the framework and how they can be used to support sustainability and smart manufacturing is demonstrated using business process data obtained from a machining industry. In the demonstrated case study, the process management layer utilises Disco for process mining, the simulation layer utilises Matlab SimEvent for discrete-event simulation, the artificial intelligence layer utilises Matlab for energy prediction and the visualisation layer utilises grafana to dashboard the e-KPIs. The findings of the research indicate that the proposed digital life-cyle framework helps EIIs realise sustainable smart manufacturing through better understanding of the energy-intensive processes. The study also provided a better understanding of the integration of process mining and simulation & modelling within the context of EIIs.