Improving the planning quality in production planning and control with machine learning

There are always deviations between production planning and subsequent execution. These deviations are caused by uncertainties, e.g. inaccurate or insufficient planning data (e.g. data quality and availability), inappropriate planning and control systems or unforeseeable events. Production planners therefore use buffers in the form of inventories or extended transitional periods to create possibilities for implementing corrective measures in production control. Buffers, however, lead to increased coordination and control effort and to negative effects, e.g. on inventory, throughput time and capacity utilization. Furthermore, it was found that the reliability of the production plans and thus the planning quality (PQ) can drop down to 25% in the first three days after plan creation [1]. Potentials for more accurate planning remains largely unexploited. The objective of this paper is to investigate the possibilities to increase planning quality. Two approaches are presented, focusing on reducing gaps between master data and predicted data used during the production planning process.