Hot rolling production power consumption level prediction method, device and system

• Main Authors: WANG JING, WANG GANG, NIE XIANFENG, LIU SONGJIE, HUANG RUIKUN, GUO DEFU, XIA YUESI, ZHANG HAIBO, CHEN ZHENMIN
• Format: Patent
• Language: Chinese; English
• Published: 29.01.2021
• Subjects: CALCULATING; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; ELECTRIC DIGITAL DATA PROCESSING; HANDLING RECORD CARRIERS; PHYSICS; PRESENTATION OF DATA; RECOGNITION OF DATA; RECORD CARRIERS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The embodiment of the invention provides a hot rolling production power consumption level prediction method, device and system, and the method comprises the steps: extracting a plurality of pieces ofhistorical power consumption data and historical production information data associated with each piece of historical power consumption data from a preset database, wherein the historical production information data comprises historical data corresponding to each piece of production information in a plurality of pieces of production information; generating a training sample for the production information data, and performing power consumption level calibration on the training sample according to historical power consumption data associated with the production information data; and training theinitial random forest classifier by using the training sample subjected to power consumption level calibration to obtain a production power consumption level prediction model, the production power consumption prediction model