Production Planning in the Context of Industry 4.0 with Focus on Efficient Job Allocation & Workers’ Real-Time Status

Abstract

Industry 4.0 (I4.0) has emerged a distinct impact on industrial workforce and created demand for diverse set of workforce skills and domain knowledge. Accordingly, I4.0 production systems are in need for developing and utilizing an appropriate workforce planning that considers workers with different type of skills to cope with the production requirements and keep up an efficient production. The I4.0 philosophy advocates the usage of advanced wearable technologies. Such wearable devices are able to monitor workers’ status and record vital signs and physiological data. It is well known in literature that workers’ performance in production systems is linked to their job satisfaction level as well as psychological well-being. There is much active research in the area of advanced physiology measurement technologies and incorporating the workers’ health data into industrial applications in real time. In essence, it is expected that smart wearable health devices provide the ability to boost job satisfaction, reduce human errors, and affect performance by helping managers for more efficient task matching and scheduling. This research is focused on developing job assignment models in the context of I4.0 and has considered both workers’ physiological status and the skills required to achieve the production goals. The ultimate goal of the proposed models is to maximize productivity by matching operations tasks to workers with different required skills and various skill levels. This study also considers workers' performance indicator which is predicted by machine learning models using workers’ physiology measurement. The assignment model could provide promising results in moving toward real-time application of workers’ physiological status in order to better assign production tasks and maximize production value.