Throughput control and revenue optimization of a poultry product batcher

This article studies the optimal control of batching equipment in poultry processing industry. The problem is to determine a policy that maximizes long-term average revenue while achieving target throughput. formulated as Markov Decision Process (MDP). developed MDP model captures unique characteristics operations, such as, trade-off between giveaway and Structural properties are derived for small-sized problems where utilizes single bin. Since numerically intractable industry-sized problems, we propose heuristic index with Dynamic Rejection Threshold (DRT). DRT constructed based on salient setting easy implement practice. Numerical experiments demonstrate performs well. We present an industry case study benchmarked against current practice, which shows expected can be potentially increased by over 2% (yielding additional 750,000 2,270,000 Euros per year) through use DRT.