Fernández Astudillo, Miguel
Energy intensive industries are responsible a large share of global greenhouse gas emissions (GHGe) and their decarbonization is an indispensable step to reach climate change mitigation targets. They are also large players in the economy and changes in their production lines have important social and economic implications. Digitalization of these industries, using machine learning and big data analytics has the potential to increase the efficiency, reducing their costs and environmental impact, and potentially affecting labour needs. In this context, cognitive manufacturing appears as a new manufacturing paradigm, where machines are increasingly interconnected, and their operation is optimized with smart algorithms. In this study we evaluate the impacts of the implementation of cognitive manufacturing technologies in three energy intensive industries: Portland cement production, steel, and rare-earth separation. The environmental, social and economic pillars of sustainability are addressed from a life-cycle perspective. The implementation is taking place in three plants, one of each industry. Embedding life-cycle sustainability indicators in cognitive manufacturing has the potential to account for these in the day-to-day decisions of the plant operation, using sensor data to calculate indicators “on the fly”. The project will analyse the status of the operations before and after the adoption of cognitive manufacturing solutions, in order to assess their effects. In this presentation we show the early LCA results of the digitalization process that is underway in three case studies, focusing on the status prior to the implementation of cognitive manufacturing systems.