Granular Model of Long-Term Prediction for Energy System in Steel Industry
提出一种基于粒度计算的长期预测方法，利用动态时间规整处理不等长时间粒度，并用模糊C均值聚类构建模型，在钢铁厂实际数据上验证了优于其他数据驱动方法。
Sound energy scheduling and allocation is of paramount significance for the current steel industry, and the quantitative prediction of energy media is being regarded as the prerequisite for such challenging tasks. In this paper, a long-term prediction for the energy flows is proposed by using a granular computing-based method that considers industrial-driven semantics and granulates the initial data based on the specificity of manufacturing processes. When forming information granules on a basis of experimental data, we propose to deal with the unequal-length temporal granules by exploiting dynamic time warping, which becomes instrumental to the realization of the prediction model. The model engages the fuzzy C -means clustering method. To quantify the performance of the proposed method, real-world industrial energy data coming from a steel plant in China are employed. The experimental results demonstrate that the proposed method is superior to some other data-driven methods and becomes capable of satisfying the requirements of the practically viable prediction.