基于一种改进稀疏动态慢特征分析的高速公路服务区空调空气处理单元故障检测研究
Fault Detection of Air Conditioning Unit in Expressway Service Area Based on an Improved Sparse Dynamic Slow Feature Analysis
摘要: 高速公路服务区暖通空调空气处理系统表现出很强的双向动态特性，为了通过处理空气处理系统的双向动态特性和对提取的潜在变量施加稀疏性，本文提出一种改进的稀疏动态慢特征分析策略来检测空气处理系统的故障。在提出的稀疏动态慢特征分析中，采用自回归移动平均模型来揭示变量之间的自相关关系。然后应用多路数据分析，通过将扩充的三维数据集转换为展开的矩阵，计算出在多个批处理运行中的分批动态特性。进一步建立动态慢特征分析模型充分处理批运行中的时间动态特性。最后，融入特征稀疏表示技术，通过对负载向量进行稀疏约束，消除了无意义变量之间的耦合。在ASHRAE研究项目RP-1312实验数据集上进行的案例研究验证了所提出的故障检测方案的有效性。
Abstract: HVAC air handling systems in expressway service areas exhibit strong bidirectional dynamics. In order to detect the faults of the air handling system by dealing with the bidirectional dynamics of the air handling system and imposing the sparsity on the extracted latent variables, this paper proposes an improved sparse dynamic slow feature analysis strategy. In the proposed sparse dynamic slow feature analysis, an autoregressive moving average model is employed to reveal the autocorrelation among the variables. Multi-way data analysis is then applied to handle the batch dynamics over multiple batch runs by converting the augmented 3D dataset into an unfolded matrix. A dynamic slow feature analysis model is further established to fully deal with the time dynamic characteristics in batch operation. Finally, feature sparse representation technology is incorporated, and the coupling between meaningless variables is eliminated by sparsely constraining the load vector. A case study conducted on the ASHRAE research project RP-1312 experimental dataset verifies the effectiveness of the proposed fault detection scheme.
文章引用：宋圆圆, 刘雪菲. 基于一种改进稀疏动态慢特征分析的高速公路服务区空调空气处理单元故障检测研究[J]. 计算机科学与应用, 2024, 14(5): 94-107. https://doi.org/10.12677/csa.2024.145118

参考文献

[1] Mirnaghi, M.S. and Haghighat, F. (2020) Fault Detection and Diagnosis of Large-Scale HVAC Systems in Buildings Using Data-Driven Methods: A Comprehensive Review. Energy & Buildings, 229, Article ID: 110492. [Google Scholar] [CrossRef] 
[2] Rogers, A.P., Guo, F. and Rasmussen, B.P. (2019) A Review of Fault Detection and Diagnosis Methods for Residential Air Conditioning Systems. Building and Environment, 161, 106236-106247. [Google Scholar] [CrossRef] 
[3] Lee, K.P., Wu, B.H. and Peng, S.L. (2019) Deep-Learning-Based Fault Detection and Diagnosis of Air-Handling Units. Building and Environment, 157, 24-33. [Google Scholar] [CrossRef] 
[4] Yan, K., Zhong, C., Ji, Z. and Huang, J. (2018) Semi-Supervised Learning for Early Detection and Diagnosis of Various Air Handling Unit Faults. Energy and Buildings, 181, 75-83. [Google Scholar] [CrossRef] 
[5] Li, D., Zhou, Y., Hu, G. and Spanos, C.J. (2016) Optimal Sensor Configuration and Feature Selection for AHU Fault Detection and Diagnosis. IEEE Transactions on Industrial Informatics, 13, 1369-1380. [Google Scholar] [CrossRef] 
[6] Wang, Z.W., Wang, L., Liang, K.F. and Tan, Y.Y. (2018) Enhanced Chiller Fault Detection Using Bayesian Network and Principal Component Analysis. Applied Thermal Engineering, 141, 898-905. [Google Scholar] [CrossRef] 
[7] Wang, H.T. and ChenM Y.M. (2016) A Robust Fault Detection and Diagnosis Strategy for Multiple Faults of VAV Air Handling Units. Energy and Buildings, 127, 442-451. [Google Scholar] [CrossRef] 
[8] Zhang, H.Y., Li, C.D., Li, D., Zhang, Y.C. and Peng, W. (2021) 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 and Buildings, 253, Article ID: 111467. [Google Scholar] [CrossRef] 
[9] Li, D., Li, D.H., Li, C.D., Li, L. and Gao, L. (2019) A Novel Data-Temporal Attention Network Based Strategy for Fault Diagnosis of Chiller Sensors. Energy and Buildings, 198, 377-394. [Google Scholar] [CrossRef] 
[10] Karami, M. and Wang, L. (2018) Fault Detection and Diagnosis for Nonlinear Systems: A New Adaptive Gaussian Mixture Modeling Approach. Energy and Buildings, 166, 477-488. [Google Scholar] [CrossRef] 
[11] Gao, X.R. and Shardt, Y.A.W. (2021) Dynamic System Modelling and Process Monitoring Based on Long-Term Dependency Slow Feature Analysis. Journal of Process Control, 105, 27-47. [Google Scholar] [CrossRef] 
[12] Aggoun, L. and Chetouani, Y. (2021) Fault Detection Strategy Combining NARMAX Model and Bhattacharyya Distance for Process Monitoring. Journal of the Franklin Institute-Engineering and Applied Mathematics, 358, 2212-2228. [Google Scholar] [CrossRef] 
[13] Mei, L., Li, H.G., Zhou, Y.L., Wang, W.L. and Xing, F. (2019) Substructural Damage Detection in Shear Structures via ARMAX Model and Optimal Subpattern Assignment Distance. Engineering Structures, 191, 625-639. [Google Scholar] [CrossRef] 
[14] Jiang, Q.C., Gao, F.R., Yan, X.F. and Yi, H. (2019) Multiobjective Two-Dimensional CCA-Based Monitoring for Successive Batch Processes with Industrial Injection Molding Application. IEEE Transactions on Industrial Electronics, 66, 3825-3834. [Google Scholar] [CrossRef] 
[15] Kong, Y., Qin, Z.Y., Wang, T.Y., Han, Q.K. and Chu, F.L. (2021) An Enhanced Sparse Representation-Based Intelligent Recognition Method for Planet Bearing Fault Diagnosis in Wind Turbines. Renewable Energy, 173, 987-1004. [Google Scholar] [CrossRef] 
[16] Luo, L.J., Bao, S.Y. and Tong, C.D. (2019) Sparse Robust Principal Component Analysis with Applications to Fault Detection and Diagnosis. Industrial & Engineering Chemistry Research, 58, 1300-1309. [Google Scholar] [CrossRef] 
[17] Liu, Y., Zeng, J.S., Xie, L., Luo, S.H. and Su, H.Y. (2019) Structured Joint Sparse Principal Component Analysis for Fault Detection and Isolation. IEEE Transactions on Industrial Informatics, 15, 2721-2731. [Google Scholar] [CrossRef] 
[18] Hu, Y.Y., Wang, Y. and Zhao, C.H. (2019) A Sparse Fault Degradation Oriented Fisher Discriminant Analysis (FDFDA) Algorithm for Faulty Variable Isolation and Its Industrial Application. Control Engineering Practice, 90, 311-320. [Google Scholar] [CrossRef] 
[19] Fan, C., Liu, X.Y., Xue, P. and Wang, J.Y. (2021) Statistical Characterization of Semi-Supervised Neural Networks for Fault Detection and Diagnosis of Air Handling Units. Energy and Buildings, 234, Article ID: 110733. [Google Scholar] [CrossRef] 
[20] Bonvini, M., Sohn, M.D., Granderson, J., Wetter, M. and Piette, M.A. (2014) Robust On-Line Fault Detection Diagnosis for HVAC Components Based on Nonlinear State Estimation Techniques. Applied Energy, 124, 156-166. [Google Scholar] [CrossRef] 
[21] Xing, Y. and Lv, C. (2020) Dynamic State Estimation for the Advanced Brake System of Electric Vehicles by Using Deep Recurrent Neural Networks. IEEE Transactions on Industrial Electronics, 67, 9536-9547. [Google Scholar] [CrossRef] 
[22] Han, Y.M., Ding, N., Geng, Z.Q., Wang, Z. and Chu. C. (2020) An Optimized Long Short-Term Memory Network Based Fault Diagnosis Model for Chemical Processes. Journal of Process Control, 92, 161-168. [Google Scholar] [CrossRef]