数据驱动的机床等待过程节能方法研究

为了降低机床等待过程中的能耗，提出了一种实时数据驱动的机床等待时间预测与节能控制方法。首先，建立了射频识别驱动的生产进度评估方法，并以生产进度数据作为输入，构建了基于堆栈降噪自编码的机床等待时间预测模型；其次，依据预测的机床等待时间，提出了机床状态切换方法，以降低机床能耗；最后，通过一个电梯零部件制造车间的案例分析，表明该方法的预测误差仅为4.1%，同时将机床等待过程能耗降低了57%，实现了制造车间的节能减排。

Research on Data Driven Energy-conservation Method of Machine Tool Waiting Processes

In order to reduce the energy consumption of machine tool waiting processes, a real-time data driven waiting time prediction and energy-conservation control method of machine tool waiting processes was proposed.Firstly, an radio frequency identification (RFID) driven production progress evaluation method was established, and taking production progress as input data, a machine waiting time prediction model was constructed based on stacked denoising auto-encoder.Secondly, according to the predicted waiting time of machine tools, a machine state switching method was proposed to reduce the energy consumption.Finally, analyzing an elevator parts manufacturing workshop, it shows that the prediction errors of the proposed method are only 4.1%, and the energy consumption of machine waiting processes is reduced by 57%, which may realize energy saving and emission reduction in the manufacturing workshops.