The operation of air handling unit (AHU) always exhibits hybrid linear, nonlinear and time-varying dynamic characteristics, however the traditional single modelling strategy based methods are not effective in tackling these hybrid characteristics. To resolve this issue, a new hybrid modelling strategy based fault detection and diagnosis (FDD) method has been developed by this study. The method has integrated slow features analyses (SFA) with kernel SFA (KSFA), and we called this the hybrid SFA (HSFA). Specifically, to effectively handle the AHU's linear and time-varying dynamic properties, the SFA was first employed to mine linear slow features (SFs) of input data. Subsequently, to deal with the AHU's nonlinear and time-varying dynamic characteristics, the KSFA was applied in the residual subspace of the input data to capture the nonlinear SFs. To detect the fault, the T2 statistic was constructed using the linear and nonlinear SFs while the SPE statistic was established using the residuals of nonlinear SFs. To further identify the fault variable, a novel reconstruction based contribution plot was developed based on the statistic in the HSFA's principal subspace. The experiments and comparisons with the ASHRAE RP-1312 dataset have demonstrated the superiority of the proposed HSFA based approach in terms of the FDD.
WangZQinYKongYWangLLengQZhangC. Advanced fault detection, diagnosis and prognosis in HVAC systems: lifecycle insight, key challenges, and promising approaches. Renew Sust Energ Rev2025; 219: 115867.
2.
RogersAGuoFRasmussenB. A review of fault detection and diagnosis methods for residential air conditioning systems. Build Environ2019; 161: 106236–106247.
3.
MirnaghiMSHaghighatF. Fault detection and diagnosis of large scale HVAC systems in buildings using data-driven methods: a comprehensive review. Energy Build2020; 229: 110492.
4.
KordestaniMSaifMOrchardMERazavi-FarRKhorasaniK. Failure prognosis and applications a survey of recent literature. IEEE Trans Reliab2019; 70(2): 728–748.
5.
ZhuPMaSHanQChuF. Deep contrastive transfer learning for rotating machinery fault diagnosis. IEEE Trans Instrum Meas2025; 74: 1–10.
6.
YangWZhangHLimJBZhangYMengH. A new chiller fault diagnosis method under the imbalanced data environment via combining an improved generative adversarial network with an enhanced deep extreme learning machine. Eng Appl Artif Intell2024; 137: 109218.
7.
ZhaoYWenJXiaoFYangXWangS. Diagnostic Bayesian networks for diagnosing air handling units faults part i: faults in dampers, fans, filters and sensors. Appl Therm Eng2017; 111: 1272–1286.
8.
YanKZhongCJiZHuangJ. Semi-supervised learning for early detection and diagnosis of various air handling unit faults. Energy Build2018; 181: 75–83.
9.
JallalMAValléeMLamaisonN. Fouling fault detection and diagnosis in district heating substations: validation of a hybrid CNN-based PCA model with uncertainty quantification on virtual replica synthesis and real data. Energy2024; 312: 133590.
10.
YangCMaSHanQ. Robust discriminant latent variable manifold learning for rotating machinery fault diagnosis. Eng Appl Artif Intell2023; 126: 106996.
11.
LiGHuY. An enhanced PCA-based chiller sensor fault detection method using ensemble empirical mode decomposition based denoising. Energy Build2019; 183: 311–324.
12.
XuYLiuJ. High-speed train fault detection with unsupervised causality-based feature extraction methods. Adv Eng Inform2021; 49: 101312.
13.
ShahMZHHuLAhmedZ. Modified LPP based on riemannian metric for feature extraction and fault detection. Measurement ( Mahwah N J)2022; 193: 110923.
14.
ZhangHZhangYMengHLimJBYangW. A novel global modelling strategy integrated dynamic kernel canonical variate analysis for the air handling unit fault detection via considering the two-directional dynamics. J Build Eng2024; 96: 110402.
15.
DengXTianXChenSHarrisCJ. Nonlinear process fault diagnosis based on serial principal component analysis. IEEE Trans Neural Netw Learn Syst2018; 29(3): 560–572.
16.
DengXTianXChenSHarrisCJ. Deep principal component analysis based on layerwise feature extraction and its application to nonlinear process monitoring. IEEE Trans Control Syst Technol2019; 27(6): 2526–2540.
17.
WuPFerrariRMGLiuYvan WingerdenJW. Data-driven incipient fault detection via canonical variate dissimilarity and mixed kernel principal component analysis. IEEE Trans Ind Inform2021; 17(8): 5380–5390.
18.
ZhangSZhaoC. Slow feature analysis based batch process monitoring with comprehensive interpretation of operation condition deviation and dynamic anomaly. IEEE Trans Ind Electron2018; 66(5): 3773–3783.
19.
YuWZhaoC. Recursive exponential slow feature analysis for fine-scale adaptive processes monitoring with comprehensive operation status identification. IEEE Trans Ind Informat2019; 15(6): 3311–3323.
20.
ChangPXuYMengFXiongW. Fault detection in wastewater treatment process using broad slow feature neural network with incremental learning ability. IEEE Trans Ind Inform2024; 20(3): 4540–4549.
21.
ZhangHTianXDengXCaoY. Multiphase batch process with transitions monitoring based on global preserving statistics slow feature analysis. Neurocomputing2018; 293: 64–86.
22.
ZhangKYangJShaJLiuH. Dynamic slow feature analysis and random forest for subway indoor air quality modeling. Building Environ2022; 213: 108876.
23.
ZhangHLiCWeiQZhangY. Fault detection and diagnosis of the air handling unit via combining the feature sparse representation based dynamic SFA and the LSTM network. Energy Build2022; 269: 112241.
24.
WuCZhangLDuB. Kernel slow feature analysis for scene change detection. IEEE Trans Geosci Rem Sens2017; 55(4): 2367–2384.
25.
XuYJiaMMaoZLiH. A novel kernel dynamic inner slow feature analysis method for dynamic nonlinear process concurrent monitoring of operating point deviations and process dynamics anomalies. Process Control2022; 110: 59–75.
26.
CorriganJZhangJ. Developing accurate data-driven soft-sensors through integrating dynamic kernel slow feature analysis with neural networks. Process Control2021; 106: 208–220.
27.
ZhangHDengXZhangYHouCLiC. Dynamic nonlinear batch process fault detection and identification based on two-directional dynamic kernel slow feature analysis. Can J Chem Eng2021; 99(1): 306–333.
28.
ZhangHLiCLiDZhangYPengW. Fault detection and diagnosis of the air handling unit via an enhanced kernel slow feature analysis approach considering the time-wise and batch-wise dynamics. Energy Build2021; 253: 111467.
29.
YuYZhangHPengWWangRLiC. Images based fault diagnosis of air handling unit via combining kernel slow feature analysis and deep learning method. J Build Eng2022; 56: 104718.
30.
XuYJiaMMaoZLiH. A novel kernel dynamic inner slow feature analysis method for dynamic nonlinear process concurrent monitoring of operating point deviations and process dynamics anomalies. J Process Control2022; 110: 59–75.
31.
TanRCaoY. Deviation contribution plots of multivariate statistics. IEEE Trans Ind Informat2019; 15(2): 833–841.
32.
LiGWangLShenLChenLChengHXuCLiF. Interpretation of convolutional neural network-based building HVAC fault diagnosis model using improved layer-wise relevance propagation. Energy Build2023; 286: 112949.
33.
XuPLiuJZhangWWangHHuangY. Multiscale kernel entropy component analysis with application to Complex industrial process monitoring. IEEE Trans Autom Sci Eng2024; 21(3): 3757–3772.
34.
MaMLiXGaoWSunJWangQMiC. Multi-fault diagnosis for series-connected lithium-ion battery pack with reconstruction-based contribution based on parallel PCA-KPCA. Appl Energy2022; 324: 119678.
35.
LiGYaoZChenLLiTXuC. An interpretable graph convolutional neural network based fault diagnosis method for building energy systems. Build Simul2024; 17: 1113–1136.
36.
EllisMJChindeV. An encoder-decoder LSTM-based EMPC framework applied to a building HVAC system. Chem Eng Res Des2020; 160: 508–520.
37.
ShahnazariH. Fault diagnosis of nonlinear systems using recurrent neural networks. Chem Eng Res Des2020; 153: 233–245.
38.
WangJZhaoC. Variants of slow feature analysis framework for automatic detection and isolation of multiple oscillations in coupled control loops. Comput Chem Eng2020; 141: 107029.
39.
SongPZhaoC. Slow down to go better: a survey on slow feature analysis. IEEE Trans Neural Netw Learn Syst2024; 35(3): 3416–3436.
40.
DongYLiuYQinSJ. Efficient dynamic latent variable analysis for high-dimensional time series data. IEEE Trans Ind Inf2019; 16(6): 4068–4076.
41.
DengXZhangXLiuXCaoY. Incipient fault detection of nonlinear chemical processes based on probability-related randomized slow feature analysis. Process Saf Environ Prot2023; 169: 797–807.
42.
ZhangHZhaoHFuYMaJXiangY. The class labels and spatial information based fault diagnosis of air handling unit via combining kernel Fischer discriminant analysis with an improved graph convolutional neural network. Measurement (Mahwah N J)2026; 257: 118622.
43.
WangKLeeRChenJSongZGopaluniRB. Data-driven dynamic modelling and online monitoring for multiphase and multimode batch processes with uneven batch durations. Ind Eng Chem Res2019; 58(30): 13628–13641.
