School of Electrical Engineering, Yanshan University, 438 Hebei Avenue, Qinhuangdao 066004, China.
Sensors (Basel). 2021 Jun 23;21(13):4284. doi: 10.3390/s21134284.
The precision and reliability of the synchronous prediction of multi energy consumption indicators such as electricity and coal consumption are important for the production optimization of industrial processes (e.g., in the cement industry) due to the deficiency of the coupling relationship of the two indicators while forecasting separately. However, the time lags, coupling, and uncertainties of production variables lead to the difficulty of multi-indicator synchronous prediction. In this paper, a data driven forecast approach combining moving window and multi-channel convolutional neural networks (MWMC-CNN) was proposed to predict electricity and coal consumption synchronously, in which the moving window was designed to extract the time-varying delay feature of the time series data to overcome its impact on energy consumption prediction, and the multi-channel structure was designed to reduce the impact of the redundant parameters between weakly correlated variables of energy prediction. The experimental results implemented by the actual raw data of the cement plant demonstrate that the proposed MWMC-CNN structure has a better performance than without the combination structure of the moving window multi-channel with convolutional neural network.
由于分别预测时两个指标的耦合关系不足，多能耗指标（如电耗和煤耗）的同步预测的精度和可靠性对于工业过程的生产优化（例如在水泥行业）非常重要。然而，生产变量的时滞、耦合和不确定性导致了多指标同步预测的困难。在本文中，提出了一种结合移动窗口和多通道卷积神经网络（MWMC-CNN）的数据驱动预测方法，用于同步预测电耗和煤耗，其中移动窗口用于提取时间序列数据的时变延迟特征，以克服其对能耗预测的影响，多通道结构用于减少能耗预测中弱相关变量之间冗余参数的影响。通过水泥厂的实际原始数据进行的实验结果表明，所提出的 MWMC-CNN 结构的性能优于没有移动窗口和卷积神经网络组合结构的性能。
