Data Analytics for Industrial Process Improvement A Vision Paper (Workshop Paper)

Nowadays, manufacturers are increasingly able tocollect and analyze data from sensors on manufacturing equip-ment, and also from other types of machinery, such as smartmeters, pipelines, delivery trucks, etc. Nevertheless, many manu-facturers are not yet ready to use analytics beyond a tool to trackhistorical performance. However, just knowing what happenedand why it happened does not use the full potential of thedata and is not sufficient anymore. Manufacturers need to knowwhat happens next and what actions to take in order to getoptimal results. It is a challenge to develop advanced analyticstechniques including machine learning and predictive algorithmsto transform data into relevant information for gaining usefulinsights to take appropriate action. In the proposed research wetarget new analytic methods and tools that make insights not onlymore understandable but also actionable by decision makers.The latter requires that the results of data analytics have animmediate effect on the processes of the manufacturer. Thereby,data analytics has the potential to improve industrial processesby reducing maintenance costs, avoiding equipment failures andimproving business operations. Accordingly, the overall objectiveof this project is to develop a set of tools — including algorithms,analytic machinery, planning approaches and visualizations —for industrial process improvements based on data analytics.