基于特征工况挖掘和先验概率引导的暖通空调系统参数辨识方法

贺佳宁; 鲁洁; 赵阳

doi:10.12465/j.issn.0253-4339.2025.05.115

您当前的位置：

首页 >

文章列表页 >

基于特征工况挖掘和先验概率引导的暖通空调系统参数辨识方法

更新时间：2025-09-29

- 基于特征工况挖掘和先验概率引导的暖通空调系统参数辨识方法
- Feature Condition Mining and Prior Probability Guidance Based Model Calibration Methodology for HVAC System
- 制冷学报 2025年46卷第5期页码：115-123
- 作者机构：
  
  浙江大学制冷与低温研究所　杭州　310027
- 作者简介：
  
  赵阳，男，长聘副教授，浙江大学能源工程学院，18814803300，E-mail：youngzhao@zju.edu.cn。研究方向：建筑能源系统大数据分析与认知计算，制冷设备故障检测与诊断。
- 基金信息：
  
  国家自然科学基金(52161135202)
- DOI：10.12465/j.issn.0253-4339.2025.05.115
  中图分类号： TU831.4;TP183
- 收稿日期：2024-04-23，
  
  修回日期：2024-07-13，
  
  录用日期：2024-08-30，
  
  纸质出版日期：2025-10-16
- 稿件说明：
移动端阅览
贺佳宁, 鲁洁, 赵阳. 基于特征工况挖掘和先验概率引导的暖通空调系统参数辨识方法[J]. 制冷学报, 2025,46(5):115-123.

He Jianing, Lu Jie, Zhao Yang. Feature Condition Mining and Prior Probability Guidance Based Model Calibration Methodology for HVAC System[J]. Journal of refrigeration, 2025, 46(5): 115-123.
贺佳宁, 鲁洁, 赵阳. 基于特征工况挖掘和先验概率引导的暖通空调系统参数辨识方法[J]. 制冷学报, 2025,46(5):115-123. DOI： 10.12465/j.issn.0253-4339.2025.05.115.

He Jianing, Lu Jie, Zhao Yang. Feature Condition Mining and Prior Probability Guidance Based Model Calibration Methodology for HVAC System[J]. Journal of refrigeration, 2025, 46(5): 115-123. DOI： 10.12465/j.issn.0253-4339.2025.05.115.

摘要

暖通空调系统实测数据的高度冗余显著降低了其模型参数辨识的计算效率。为了解决上述问题，提出一种基于特征工况挖掘和先验概率引导的参数辨识方法。特征工况挖掘方法对运行数据进行相关性分析，选择暖通空调系统运行工况的关键变量，并根据关键变量维度进行网格采样，得到更具代表性的特征工况，从而提升模型单次计算效率。模型参数辨识过程中，建立待辨识参数的先验概率模型，基于先验概率进行待辨识参数的先验区间估计和改进目标函数，引导模型更快收敛。该方法在武汉某工厂暖通空调系统

供冷季一个月的运行数据集上进行了验证，结果表明：该方法中的MAPE（平均绝对百分比误差）和CV-RMSE（均方根误差变异系数）相比基于K-means聚类的方法分别降低了16.0%和12.0%，比基于原始数据的方法分别降低了20.9%和15.2%，NMBE（归一化平均偏差误差）更接近0，

（决定系数）相比2种方法分别提升了4.7%和8.5%，计算效率提高约39.3%。该方法为实现高效准确的暖通空调系统建模提供了技术指导和数据支撑。

Abstract

The high redundancy of the measured data from heating

ventilation

and air conditioning (HVAC) systems significantly reduces the computational efficiency of model calibration. To address this challenge

a model calibration method based on mining feature operating conditions and a priori probability guidance was introduced in this study. Correlation analysis was conducted on the operational data for mining feature operating conditions. Feature variables related to HVAC system operation were selected

and a grid sampling technique based on these characteristic variables was employed to obtain representative operating conditions

enhancing the efficiency of the model calculations. Additionally

a prior probability model was established for the parameters to be calibrated during the model calibration process. A priori interval estimation was then performed

and the objective function was improved based on the prior probability to guide the model towards faster convergence. The proposed method was validated using a one-month operational dataset from a cooling plant in an industrial building located in Wuhan

China. The results indicated that the proposed method achieved significant improvements in performance metrics. Specifically

mean absolute percentage error (MAPE) and cross-validated root mean square error (CV-RMSE) were reduced by 16.0% and 12.0%

respectively

compared to the K-means clustering-based method

and by 20.9% and 15.2%

respectively

compared to the baseline data-based method. Furthermore

the normalized mean bias error (NMBE) was closer to zero

and the coefficient of determination (

) increased by 4.7% and 8.5%

respectively

compared to the two aforemen

tioned methods. Additionally

our method enhanced the computational efficiency by approximately 39.3%. This method provides technical guidance and data support for achieving an efficient and accurate modeling of HVAC systems.

关键词

Keywords

references

中国城市科学研究会 . 《中国建筑节能年度发展研究报告2023（城市能源系统专题）》 [M ] . 北京 : 中国建筑工业出版社 , 2023 .

( Chinese Society for Urban Studies . China building energy efficiency annual development research report 2023 urban energy systems theme [M ] . Beijing : China Architecture Building Press , 2023 .)

JUNG W , JAZIZADEH F . Human-in-the-loop HVAC operations: a quantitative review on occupancy, comfort, and energy-efficiency dimensions [J ] . Applied Energy , 2019 , 239 : 1471 - 1508 .

CHEN K , ZHU X , ANDUV B , et al . Digital twins model and its updating method for heating, ventilation and air conditioning system using broad learning system algorithm [J ] . Energy , 2022 , 251 : 124040 .

DENG Zhang , CHEN Yixing , YANG Jingjing , et al . Archetype identification and urban building energy modeling for city-scale buildings based on GIS datasets [J ] . Building Simulation , 2022 , 15 ( 9 ): 1547 - 1559 .

HONG T , LANGEVIN J , SUN K . Building simulation: ten challenges [J ] . Building Simulation , 2018 , 11 ( 5 ): 871 - 898 .

SUN K , HONG T , KIM J , et al . Application and evaluation of a pattern-based building energy model calibration method using public building datasets [J ] . Building Simulation , 2022 , 15 ( 8 ): 1385 - 1400 .

FABRIZIO E , MONETTI V . Methodologies and advancements in the calibration of building energy models [J ] . Energies , 2015 , 8 ( 4 ): 2548 - 2574 .

RAMOS R G , FERNÁNDEZ B C , GÓMEZ-ACEBO T T , et al . Genetic algorithm for building envelope calibration [J ] . Applied Energy , 2016 , 168 : 691 - 705 .

LAROCHELLE M G , MONFET D , NOUANEGUE H F , et al . Energy calibration of HVAC sub-system model using sensitivity analysis and meta-heuristic optimization [J ] . Energy and Buildings , 2019 , 202 : 109382 .

ZHAO Yang , LI Tingting , ZHANG Xuejun , et al . Artificial intelligence-based fault detection and diagnosis methods for building energy systems: advantages, challenges and the future [J ] . Renewable and Sustainable Energy Reviews , 2019 , 109 : 85 - 101 .

LU Jie , TIAN Xiangning , FENG Chenxin , et al . Clustering compression-based computation-efficient calibration method for digital twin modeling of HVAC system [J ] . Building Simulation , 2023 , 16 ( 6 ): 997 - 1012 .

ZHANG Chaobo , LI Junyang , ZHAO Yang , et al . Problem of data imbalance in building energy load prediction: concept, influence, and solution [J ] . Applied Energy , 2021 , 297 : 117139 .

REN Xinyuyang , ZHANG Chaobo , ZHAO Yang , et al . A data mining-based method for revealing occupant behavior patterns in using mechanical ventilation systems of Dutch dwellings [J ] . Energy and Buildings , 2019 , 193 : 99 - 110 .

LIU Xuying , WU Jianxin , ZHOU Zhihua . Exploratory undersampling for class-imbalance learning [J ] . IEEE Transactions on Systems, Man, and Cybernetics Part B, Cybernetics , 2009 , 39 ( 2 ): 539 - 550 .

LEE K , LIM H . Correlation analysis of building parameters according to ASHRAE Standard 90.1 [J ] . Journal of Building Engineering , 2024 , 82 : 108130 .

LEE R J , ALAN N W . Thirteen ways to look at the correlation coefficient [J ] . The American Statistician , 1988 , 42 ( 1 ): 59 - 66 .

YU Liping , PAN Yuntao , WU Yishan . Research on data normalization methods in multi-attribute evaluation [C ] // 2009 International Conference on Computational Intelli-gence and Software Engineering . Wuhan : IEEE , 2009 .

张丽珠 , 章超波 , 陈琦 , 等 . 基于遗传算法和人工神经网络的冷水机组模型参数辨识及误差补偿方法 [J ] . 制冷学报 , 2021 , 42 ( 3 ): 93 - 99 .

( ZHANG Lizhu , ZHANG Chaobo , CHEN Qi , et al . Genetic-algorithm-based parameter identification and artificial-neural-network-based error compensation for chiller model [J ] . Journal of Refrigeration , 2021 , 42 ( 3 ): 93 - 99 .)

HYDEMAN M , JR GILLESPIE K L . Tools and techniques to calibrate electric chiller component models [J ] . ASHRAE Transactions , 2002 , 108 ( 1 ): 733 - 741 .

KLEIN S A , BECKMAN W A . TRNSYS 16: a transient system simulation program: mathematical reference [J ] . TRNSYS , 2007 , 5 : 389 - 396 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于遗传算法和人工神经网络的冷水机组模型参数辨识及误差补偿方法