[1]王 可,卢焕达,郑军红,等.基于划分工作方式的中央空调达标时间预测[J].南京师范大学学报(工程技术版),2023,23(01):056-65.[doi:10.3969/j.issn.1672-1292.2023.01.008]
　Wang Ke,Lu Huanda,Zheng Junhong,et al.Forecasting Model of the Time Required for Central Air Conditioning to Achieve Control Effect Based on Divided Working Mode[J].Journal of Nanjing Normal University(Engineering and Technology),2023,23(01):056-65.[doi:10.3969/j.issn.1672-1292.2023.01.008]
点击复制

基于划分工作方式的中央空调达标时间预测
分享到：

南京师范大学学报（工程技术版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
23卷
期数:
2023年01期
页码:
056-65
栏目:
计算机科学与技术
出版日期:
2023-03-15

文章信息/Info

Title:
Forecasting Model of the Time Required for Central Air Conditioning to Achieve Control Effect Based on Divided Working Mode
文章编号:
1672-1292(2023)01-0056-10
作者:
王 可1; 卢焕达2; 郑军红1; 何利力1
(1.浙江理工大学信息学院,浙江 杭州 310018) (2.浙大宁波理工学院计算机与数据工程学院,浙江 宁波 315100)
Author(s):
Wang Ke1; Lu Huanda2; Zheng Junhong1; He Lili1
(1.School of Information Science and Technology,Zhejiang Sci-Tech University,Hangzhou 310018,China) (2.School of Computer and Data Engineering,NingboTech University,Ningbo 315100,China)
关键词:
中央空调达标时间; 组合预测模型; 随机森林; 深度特征提取; 过拟合; 样本不平衡
Keywords:
time required for central air conditioning to achieve control effect; combined prediction mode; random forest; depth feature extraction; over-fitting problem; sample unbalanced
分类号:
TP181
DOI:
10.3969/j.issn.1672-1292.2023.01.008
文献标志码:
A
摘要:
为了同时满足中央空调温湿度控制工艺要求和企业节能降耗要求,解决中央空调达标时间预测问题,提出了一种在划分空调工作方式基础上的组合预测模型. 在加温加湿工作方式下,采用随机森林算法构建分类预测模型,用深度特征提取后的高级特征作为模型输入,解决了小样本分类预测的过拟合问题. 为进一步降低算法时间复杂度,利用改进粒子群方法对模型参数寻优. 在降温除湿工作方式下,使用K近邻算法动态划分类别区间,并利用密度峰值改进SMOTE算法解决类别不平衡问题,采用极限梯度提升算法构建分类模型. 考虑到空调延迟开启或提前开启对企业效益造成的损失不同,采用多角度综合评价方法对模型进行评估. 通过与支持向量机(现用模型)等多种预测模型的对比实验,验证了组合模型的有效性和实用性. 实验表明组合模型平均绝对误差为3.2 min,与现用模型相比,组合模型折标能耗降低了14.71%.
Abstract:
In order to solve the prediction problem of the time for central air conditioning to achieve the control effect, while meeting central air conditioning temperature-humidity control process requirements and enterprise energy saving reduction requirements, a combined prediction model is proposed in accordance with different working methods of air conditioning units.In the mode of Heating-Humidifying, the classification prediction model is constructed by Random Forest algorithm, and the advanced features extracted from depth features are used as the input of the model, which solves the over-fitting problem of small sample classification prediction.IPSO optimization parameters are used to reduce the time complexity of the algorithm. In the working mode of Cooling-Dehumidifying, the algorithm uses KNN to dynamically divide the category interval and uses density peak to improve SMOTE algorithm, so as to solve the problem of unbalanced sample. Then, the XGBoost algorithm is used to build the classification model. Considering that the air conditioning delay is turned on to generate a large loss to the workshop operation, a multi-angle comprehensive evaluation method is adopted to evaluate the model. Finally, the effectiveness and practicality of the combined model is verified by comparative experiments with a variety of predictive models. Experimental results show that the mean absolute error of the combined model is 3.2 minutes, and that the energy consumption of the combined model is 14.71% lower than that of the current model.

参考文献/References:

[1]杨裔. 中央空调节能技术综述[J]. 现代信息技术,2019,3(13):193-194.
[2]SHENG X,SHANG J F,ZHANG J H,et al. An energy-saving based predictive control strategy on central air-conditioning system[C]//Proceedings of 2009 Transmission & Distribution Conference & Exposition:Asia & Pacific. Seoul,Korea:IEEE,2009.
[3]FENG Z X,REN Q C,YU J Q. The optimum start-up of central air-conditioning based on neural network[C]//Procedings of 2013 3rd International Conference on Computer Science and Information Technology. Chengdu,China:IEEE,2010.
[4]计建惠,王可崇.基于Elman网络的空调预冷时间的预测[J]. 微计算机信息,2008,24(13):261-263.
[5]杨建军,何利力.基于长短期记忆网络的工业空调启动时间预测[J]. 软件导刊,2020,19(6):48-52.
[6]李慧,段培永,罗光林.基于数据的空调系统最优启停时间预测[J]. 山东建筑大学学报,2012,27(2):155-159.
[7]朱军,侯振杰,陈树越,等. 深度特征重构与权重分配的交通标志识别算法[J]. 小型微型计算机系统,2019,40(9):1932-1939.
[8]李鸿培,于旸,忽朝俭,等. 2013工业控制系统及其安全性研究报告[R]. 北京:绿盟科技,2013.
[9]SU C,JU S G,LIU Y G,et al. Improving random forest and rotation forest for highly imbalanced datasets[J]. Intelligent Data Analysis,2015,19(6):1409-1432.
[10]CAO X H,LI R J,GE Y M,et al. Densely connected deep random forest for hyperspectral imagery classification[J]. International Journal of Remote Sensing,2019,40(9):3606-3622.
[11]SHAKIBA R,NAJAFIPOUR M R,SELEHI M E. An improved PSO-based path planning algorithm for humanoid soccer playing robots[C]//Proceedings of the 2013 3rd Joint Conference of AI & Robotics and 5th RoboCup Iran Open International Symposium. Tehran,Iran:IEEE,2013.
[12]QIAN W Y,LI M. Convergence analysis of standard particle swarm optimization algorithm and its improvement[J]. Soft Computing,2018,22(12):4047-4070.
[13]HOU G Y,XU Z D,LIU X,et al. Improved particle swarm optimization for selection of shield tunneling parameter values[J]. Computer Modeling in Engineering and Sciences,2019,118(2):317-337.
[14]CHANG W D. An improved PSO algorithm for solving nonlinear programing problems with constrained conditions[J]. International Journal of Modeling,Simulation,and Scientific Computing,2021,12(1):2150001.
[15]王志华,刘绍廷,罗齐.基于改进K-modes聚类的KNN分类算法[J]. 计算机工程与设计,2019,40(8):2228-2234.
[16]SUN J,LANG J,FUJITA H,et al. Imbalanced enterprise credit evaluation with DTE-SBD:Decision tree ensemble based on SMOTE and bagging with differentiated sampling rates[J]. Information Sciences,2018,425:76-91.
[17]ZHANG D H,QIAN L Y,MAO B J,et al. A data-driven design for fault detection of wind turbines using random forests and XGBoost[J]. IEEE Access,2018,6:21020-21031.
[18]TAHMASSEBI A,WENGERT G J,HELBICH T H,et al. Impact of machine learning with multiparametric magnetic resonance imaging of the breast for early prediction of response to neoadjuvant chemotherapy and survival outcomes in breast cancer patients[J]. Investigative Radiology,2019,54(2):110-117.
[19]ZHU M,WU K,ZHOU Y Z,et al. Prediction of cooling moisture content after cut tobacco drying process based on a particle swarm optimization-extreme learning ma-chine algorithm[J]. Mathematical Biosciences and Engineering,2021,18(3):2496-2507.
[20]国家市场监督管理总局,国家标准化管理委员会. 综合能耗计算通则:GB/T 2589-2020[S]. 北京:中国标准出版社,2020.
[21]简毅文,江亿. 住宅供暖空调能耗计算模式的研究[J]. 暖通空调,2005,35(2):11-14.
[22]XU L,HOU L,ZHU Z Y,et al. Midterm prediction of electrical energy consumption for crude oil pipelines using a hybrid algorithm of support vector machine and genetic algorithm[J]. Energy,2021,222(1):119955.
[23]BESROUR A,KSANTINI R. Incremental subclass support vector machine[J]. International Journal on Artificial Intelligence Tools,2019,28(7):1950020.
[24]ALKUBAISI G. The role of ensemble learning in stock market classification model accuracy enhancement based on Naive Bayes Classifiers[J]. International Journal of Statistics and Probability,2020,9(1):1-36.

备注/Memo

备注/Memo:
收稿日期:2021-08-27.
基金项目:浙江省重点研发计划项目(2021C01110).
通讯作者:郑军红,博士,讲师,研究方向:数据挖掘、人工智能. E-mail:zdzhengjh@sohu.com
更新日期/Last Update: 2023-03-15