Visual Analytics with Machine Learning for Data-Driven Investigations of Product State Transmission in Production System

Abstract

In recent years, the significance of effectiveness and productivity has grown. Furthermore, the industry has been able to improve production system performance thanks to advances in processing power and advanced analytics. A better understanding of intermediate product stages is therefore required to take the relevant measures. To highlight the importance of this field of study, a study on data-driven probabilistic ML algorithms and their real-time applications to smart energy systems and networks was done. The use of ML in fundamental energy technologies and ML use cases for utilities involved in energy distribution were the two main topics of this study. The purpose of this research is to create a framework for data-driven understanding of the various state propagation inside manufacturing systems in order to increase the transparency of cause-effect linkages linked to product quality. Machine learning algorithms classify items into groups based on their intermediate properties. A research study as within electronic manufacturing sector illustrates how this strategy might be put into practise. Product state propagation along the production process chain may be examined in detail utilising visual analytics tools.