Forecasting solar still performance from conventional weather data variation by machine learning method

作     者：高文杰 沈乐山 孙森山 彭桂龙 申震 王云鹏 AbdAllah Wagih Kandeal 骆周扬 A.E.Kabeel 张坚群 鲍华 杨诺 Wenjie Gao;Leshan Shen;Senshan Sun;Guilong Peng;Zhen Shen;Yunpeng Wang;AbdAllah Wagih Kandeal;Zhouyang Luo;A.E.Kabeel;Jianqun Zhang;Hua Bao;Nuo Yang

作者机构：State Key Laboratory of Coal Combustionand School of Energy and Power EngineeringHuazhong University of Science and TechnologyWuhan 430074China Zhejiang Baima Lake Laboratory Co.Ltd.Hangzhou 31121China Zhejiang Energy Group R&D InstituteCo.Ltd.Hangzhou 311121China Zhejiang Zheneng Yueqing Electric Power Generation Co.Ltd.Yueqing 325609China University of Michigan-Shanghai Jiao Tong University Joint InstituteShanghai Jiao Tong UniversityShanghai 200240China Mechanical Engineering DepartmentFaculty of EngineeringKafrelsheikh UniversityKafrelsheikh 33516Egypt Mechanical Power Engineering DepartmentFaculty of EngineeringTanta UniversityTantaEgypt Faculty of EngineeringDelta University for Science and TechnologyGamasaEgypt 

出 版 物：《Chinese Physics B》 (中国物理B（英文版）)

年 卷 期：2023年第32卷第4期

页      面：19-25页

核心收录：

学科分类：12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 080703[工学-动力机械及工程] 07[理学] 081104[工学-模式识别与智能系统] 070601[理学-气象学] 08[工学] 0807[工学-动力工程及工程热物理] 0706[理学-大气科学] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：Project supported by the National Key Research and Development Program of China(Grant No.2018YFE0127800) the Science,Technology&Innovation Funding Authority(STIFA),Egypt grant(Grant No.40517) China Postdoctoral Science Foundation(Grant No.2020M682411) the Fundamental Research Funds for the Central Universities(Grant No.2019kfy RCPY045) 

主　　题：solar still production forecasting forecasting model weather data random forest 

摘      要：Solar stills are considered an effective method to solve the scarcity of drinkable ***,it is still missing a way to forecast its ***,it is proposed that a convenient forecasting model which just needs to input the conventional weather forecasting *** model is established by using machine learning methods of random forest and optimized by Bayesian *** required data to train the model are obtained from daily measurements lasting9 *** validate the accuracy model,the determination coefficients of two types of solar stills are calculated as 0.935and 0.929,respectively,which are much higher than the value of both multiple linear regression(0.767)and the traditional models(0.829 and 0.847).Moreover,by applying the model,we predicted the freshwater production of four cities in *** predicted production is approved to be reliable by a high value of correlation(0.868)between the predicted production and the solar *** the help of the forecasting model,it would greatly promote the global application of solar stills.