PDF全文下载:
201901018.pdf
文章编号: 16726987(2019)01011108; DOI: 10.16351/j.16726987.2019.01.018
瞿叶奇, 高德欣*, 孙亚光
(青岛科技大学 自动化与电子工程学院,山东 青岛 266061)
摘要:针对中央空调时变、大滞后、非线性、模型复杂度高的问题,提出了一种基于机器学习的优化控制策略。首先,建立中央空调系统的物理模型,根据系统采集的数据信息,进行分类和预处理;其次,利用机器学习的相关算法,建立采集数据之间的机器学习模型,并验证模型的精度;然后,根据构造的机器模型,设计了一种优化控制策略,解决中央空调实际运行中存在的问题,并给出控制算法;最后,用Python进行了仿真,验证了方法的有效性。
关键词:机器学习; 中央空调; 大数据; 随机森林算法
中图分类号:TP 273 文献标志码: A
引用格式:瞿叶奇,高德欣,孙亚光. 基于机器学习的中央空调的优化控制策略[J]. 青岛科技大学学报(自然科学版), 2019, 40(1): 111118.
QU Yeqi, GAO Dexin, SUN Yaguang. An optimal control based on machine learning of central air conditioning[J]. Journal of Qingdao University of Science and Technology(Natural Science Edition), 2019, 40(1): 111118.
An Optimal Control Based on Machine Learning of Central Air Conditioning
QU Yeqi, GAO Dexin, SUN Yaguang
(College of Automation and Electronic Engineering, Qingdao University of Science and Technology, Qingdao 266061,China)
Abstract: Aiming at the problem of time variation, large hysteresis, nonlinearity and high complexity of central air conditioning, a optimization control strategy based on machine learning is proposed. Firstly, the physical model of the central air conditioning system is established and the classification and preprocessing are carried out according to the data collected by the system. Secondly, the machine learning model between the collected data is established by using the algorithm of machine learning and the accuracy of the model is verified. According to the constructed machine model, a optimization control strategy is designed to solve the problems existing in the actual operation of the central air conditioner and the control algorithm is given. Finally, the simulation is carried out in Python to verify the effectiveness of the method.
Key words: machine learning; central air conditioning; big data; random forest algorithm
收稿日期: 20171230
基金项目: 国家自然科学基金项目(61673357);山东省自然科学基金项目(ZR2017LF009,ZR2018LF008);山东省高等学校科学技术计划项目(J18KA323).
作者简介: 瞿叶奇(1990—),男,硕士研究生.*通信联系人.