An adaptive policy for on-line Energy-Efficient Control of machine tools under throughput constraint

Controlling the machine power state by switching off/on the machine when idle is one of the most promising energy efficient measure for machining processes. Part arrival process is affected by uncertainty and acquiring knowledge to obtain a proper and updated control model is difficult in industrial practice. Hence, control policies should be connected to the shop floor exploiting data acquired on-line. This work extends an on-line time-based policy recently proposed in the literature by including constraints on machine performance. A novel optimization algorithm is proposed to minimize energy consumption while assuring a target production rate and mitigating the risk of incurring in unexpected high energy consumption. Moreover, the policy is also broadened to autonomously adapt the control when the arrival process is non-stationary in time. The benefits of the proposed algorithms are assessed by means of realistic simulated cases and are around 25% of the energy consumed in idle states. Differently from existing studies dealing with the off-line problem, the proposed algorithm learns on-line while acquiring information from the real system.