舰船变风量空调系统运行性能数据的挖掘分析，可为空调系统的运行性能衰减或设备老化判别提供依据。采用滑动窗口表征舰船变风量空调系统随内外负荷变化的动态响应时变性，主元相似因子选取无故障历史运行参照数据，采用主元分析计算累计贡献率确定最优主成分数构造荷载矩阵，通过比较平方预测误差和控制限的大小，判断空调系统是否发生故障。无故障测试日的平均故障检测率为2.71%，故障测试日的平均故障检测率75.97%。数据的测量精度对故障检测结果的影响很大，如果测量误差较大或者外界的扰动使空调系统处于非稳定状态，故障检测方法就很难识别出系统运行性能特征变化，导致故障检测率较低。
Mining and analyzing the operating performance data of marine VAV air conditioning system can provide a basis for distinguishing the operating performance attenuation and equipment aging of air conditioning system. Moving windows are used to characterize the time-varying dynamic response of marine VAV air conditioning system responding to external and internal loads. The principal component similarity factor is used to screen the reference data of fault-free historical operation. Principal component analysis is used to calculate the cumulative contribution ratio to determine the optimal principal component fraction and thus to construct the load matrix. By comparing the square prediction error and the control limit, some fault can be flagged in air conditioning system. The average fault detection rate of fault-free testing days is 2.71%, and the average fault detection rate of fault testing days is 75.97%. If the measurement error is large or the external disturbance makes system in unstable states, so that the data mining fault detection method could not identify the generated fault, it might lead to low fault detection rate.
2022,44(14): 181-185 收稿日期：2022-03-11
DOI：10.3404/j.issn.1672-7649.2022.14.038
分类号：U667.2
作者简介：罗雯军(1983-)，男，高级工程师，研究方向为暖通空调
参考文献：
[1] HASSANPOUR H, MHASKAR P, HOUSE J M, et al. A hybrid modeling approach integrating first-principles knowledge with statistical methods for fault detection in HVAC systems[J]. Computers & Chemical Engineering, 2020, 142: 107022
[2] WANG S, XIAO F. AHU sensor fault diagnosis using principal component analysis method[J]. Energy and Buildings, 2004, 36(2): 147–160
[3] JIN X, DU Z. Fault tolerant control of outdoor air and AHU supply air temperature in VAV air conditioning systems using PCA method[J]. Applied Thermal Engineering, 2006, 26(11): 1226–1237
[4] BAKDI A, KOUADRI A. A new adaptive PCA based thresholding scheme for fault detection in complex systems[J]. Chemometrics and Intelligent Laboratory Systems, 2017, 162: 83–93
[5] LI S, WEN J. Application of pattern matching method for detecting faults in air handling unit system[J]. Automation in Construction, 2014, 43: 49–58
[6] ZHANG H, CHEN H, GUO Y, et al. Sensor fault detection and diagnosis for a water source heat pump air-conditioning system based on PCA and preprocessed by combined clustering[J]. Applied Thermal Engineering, 2019, 160: 114098
[7] CHINTALA R, WINKLER J, JIN X. Automated fault detection of residential air-conditioning systems using thermostat drive cycles[J]. Energy and Buildings, 2020, 36: 110691
[8] EBRAHIMIFAKHAR A, KABIRIKOPAEI A, YUILL D. Data-driven fault detection and diagnosis for packaged rooftop units using statistical machine learning classification methods[J]. Energy and Buildings, 2020, 225: 110318
[9] WANG H, FENG D, LIU K. Fault detection and diagnosis for multiple faults of VAV terminals using self-adaptive model and layered random forest[J]. Building and Environment, 2021, 193: 107667
[10] KAZEMI P, BENGOA C, STEYER J P, et al. Data-driven techniques for fault detection in anaerobic digestion process[J]. Process Safety and Environmental Protection, 2021, 146: 905–915
[11] LI W, PENG M, WANG Q. Improved PCA method for sensor fault detection and isolation in a nuclear power plant[J]. Nuclear Engineering and Technology, 2019, 51(1): 146–154
