Maintenance strategies for cutting tools degradation in milling machine system based on Markov decision process

Milling machines are critical equipment for high-precision milling operations, widely used in manufacturing. The milling machine's operational stability directly governs surface roughness and dimensional accuracy, with progressive tool wear degrading production throughput. As vital components of the milling machine system, cutting tools require regular inspection and maintenance to ensure optimal performance. In this paper, we propose a new condition-based maintenance policy optimization method for degrading cutting tools in milling machine system. It is assumed that the degradation paths are characterized by a gamma process. The maintenance actions, including compensation, replacement, and do nothing, are determined based on the degradation level revealed by an inspection. The compensation action extends the system life at the cost of increased degradation and reduced productivity. The condition-based maintenance model is formulated as a Markov decision process. We derive the structural properties of the optimal policy and employ backward dynamic programming and value iteration algorithms to optimize the maintenance strategies. Numerical examples and sensitivity analyses are provided to illustrate the proposed model. Numerical results show that under certain circumferences compensation action reduces the maintenance cost. It is significant to consider the trade-off between system productivity and cutting tool maintenance costs in decision-making.