Coal type identification method based on random forest

• Main Authors: GUO ENTAO, ZHU JIFENG, ZHU QINGGUO, YAN FEI, ZHENG SHUIMING, YANG ZHAN
• Format: Patent
• Language: Chinese; English
• Published: 20.10.2020
• Subjects: CALCULATING; COMPUTING; COUNTING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS

The invention discloses a coal type identification method based on a random forest, the coal type is identified through a random forest model method, the random forest model is an ensemble learning model, the multi-classification problem can be solved, and the method is easy to implement and high in generalization ability. According to the method based on the random forest, additional coal type detection equipment does not need to be added, a complex physical model does not need to be established for the coal pulverizing system, the coal type recognition model can be established only through historical data of coal mill operation parameters and unit operation parameters related to coal type information and a historical coal piling list, and popularization is convenient. 本发明公开了一种基于随机森林的煤种识别方法是通过随机森林模型的方法来识别煤种，随机森林模型是一种集成学习模型，可以解决多分类问题，且容易实现，泛化能力强。基于随机森林的方法不需要增加额外的煤种检测设备，也不需要针对制粉系统建立复杂的物理模型，只需要磨煤机运行参数和与煤种信息相关的机组运行参数的历史数据以及历史堆煤单就能完成煤种识别模型的建立，方便推广。