Predictive exploratory data analysis of shopfloor CNC machine operation through a machine learning model

Industry 4.0 technologies have provided industries and firms with enormous capacities for data exchange, especially shopfloor sectors. This digitized data exchange process is accumulated exponentially and is necessitating mechanisms for adding value to the business firms. This paper has focused on advanced analytic techniques and machine learning algorithms to predict and classify the problems of the manufacturing environment in connection with the supply chain. The research explores the capabilities of exploratory data analysis in the manufacturing shop floor at the machine level. The findings of this research try to provide:•Exhibiting the ML algorithms in the manufacturing shop floor for predictive analysis. •Effective creation of value across the supply chain process by applying predictive analysis. The paper has conducted a literature review around industry 4.0 trends and the trend for predictive models for shop floor level machine operation with a focus on historical data repositories. A framework has been developed to create value across the supply chain process using data analytics and integrated business decision-making. A shop floor dataset related to the CNC milling machine has been considered for illustrating the framework capabilities which include machining experiments in the CNC milling operation besides the supply chain related data repositories.