Smart manufacturing is considered as one of the most important means for manufacturing enterprises to achieve sustainable production and improve their sustainable competitive advantage. However, implementation of the smart manufacturing strategy is facing barriers, such as the lack of complete data and valuable knowledge that can be employed to provide better support on decision-making of coordination and optimization on the product lifecycle management (PLM) and the whole manufacturing process. Fortunately, with the widespread deployment of smart sensors and internet-of-things (IoT), a large amount of real-time and multi-source lifecycle data can now be collected. To make better manufacturing and management decisions based on these data, we have developed an innovative analytics approach for smart manufacturing and maintenance processes, which integrates big data analytics and IoT to help overcome the above-mentioned barriers.

Manufacturing enterprises have been able to reduce energy consumption and to avoid uncertainties in their manufacturing processes, and dramatically improve their quality of products and services by adopting advanced production management paradigms. However, in some manufacturing environments in which process complexity and process uncertainty are present, e.g. e.g. mineral and metal processing (MMP) of large equipment and complex product, the internal and hidden interdependencies among the different stages or parameters are difficult to discover, sometimes even after advanced production management paradigms have been applied. Given the complexity of MMP for complex product that influences the efficiency of successfully implementing and maintaining a smart manufacturing strategy, manufacturers need a new systematic and integrated method to diagnose, correct and optimize the MMP flaws. Big data analytics based on the MMP data developed by us provides such an approach. During MMP of complex products, enterprise managers can use big data analytics to make a deep analysis on the historical and real-time MMP data, identify hidden relationships among different stages and parameters, and then optimize the factors that are proven to have the greatest effect on the PLM. In addition, big data analytics can be a critical tool to realize the optimization of lifecycle decision-making. The processes include gathering historical isolated data sets actively, aggregating them, and analyzing them to reveal invaluable new insights. Therefore, manufacturing enterprises taking advantage of our big data analytics system can reduce manufacturing defect and energy consumption, save time and money.