基于机器学习的智慧实验室能耗预测模型研究

打开文本图片集

中图分类号：TP39 文献标识码：A 文章编号：2096-4706（2026）06-0064-07

Research on Energy Consumption Prediction Model of Smart Laboratory Based on Machine Learning

HUA Kangmin’，LIU Zongzhe²， YIN Xusong³ （1.Laboratory and Equipment Management Offce， Zhengzhou University of Aeronautics， Zhengzhou 450046， China; 2.School of Computer Science， Zhengzhou University of Aeronautics， Zhengzhou 45oo46， China; 3.School ofCyberspace Security， Zhongyuan University of Technology， Zhengzhou 45ooo7，China）

Abstract： In recent years，thedevelopment ofsmart aboratories has been very rapid， with an increasing variety and scale of equipmentinthelaboratoryleading toincreasinglyprominentenergyconsumptionissues.Thisstudytakes thelaboratoryof ZhengzhuAviationInstituteas theresearchobject，exploringaMachineLearningbasedenergyconsumptionpredictionmethod， aimingtooptimizeenergyallocationthrough inteligent means.Thearticleuses Pythonprogramming language tobuildMachine Learming models such as XGBoost （Extreme Gradient Boosting Tree）and Random Forest，andconducts training.The models are evaluated using three performance indicators：MAE，RMSE，and R2 ，and the two models are mixed to improve prediction acuracy.Bycomparing the performance indicators and actual prediction results of various models，the most suitable energy consumptionprediction modelisanalyzed.Theresearchresultscanrespondtothenational“dual carbon”strategyneeds and the schol's policyofopening upresources and reducing costs，while providing technical supportfor thesustainable development of university laboratories.

Keywords： smart laboratory; energy consumption prediction; Machine Learning; XGBoost; Random Forest

0 引言

随着全球科技水平的进步、社会的发展，全世界对能源的消耗需求飞速上升，环境保护与可持续发展问题随之而来。（剩余9789字）