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

• It is the first time to regard the AHU system as a batch control process. • A TBKSFA based monitoring method is developed to handle two-directional dynamics. • To identify fault pattern, a KDSFA based similarity factor is further proposed. Air handling unit (AHU) is a typical special batch control process, exhibiting strong nonlinear property and two-directional dynamic characteristics which are the time-wise and batch-wise dynamic characteristics. Specifically, the time-wise dynamic characteristic corresponds to the evolution of different operating modes caused by the underlying driving forces which vary slowly in each running day (a batch run), while the batch-wise dynamic characteristic relates to the dynamic variations and deviations among different running days (batch runs). In order to further improve the AHU FDD performance through capturing the underlying driving forces of the AHU system and tackling the batch-wise dynamic property between different batch runs, in this paper, an enhanced kernel slow feature analysis (SFA) based FDD scheme is developed to detect and identify the faults of the nonlinear AHU system. Firstly, a three-way data based kernel SFA (TBKSFA) approach is proposed to detect the faults. In the proposed TBKSFA approach, the kernel trick is adopted in the SFA to sufficiently deal with the nonlinearity and the time-wise dynamic characteristic, and the multiway data analysis is employed to cope with the batch-wise dynamics among different batch runs by converting the three-way training dataset into a variable-wise unfolding two-way matrix. In addition, to handle the tough problem of nonlinearly identifying the fault pattern, a novel kernel discriminant SFA (KDSFA) model is further built by combining the kernel SFA with the discriminant analysis method. In the fault pattern diagnosis process, the proposed KDSFA is pairwisely implemented on the normal and fault datasets to calculate the fault direction, and the fault is then identified by computing the similar degrees of its own fault direction and the historical fault directions. At last, experiments and comparisons on the FDD performance of the developed approach are made using the experimental data provided by ASHRAE Research Project RP-1312. To be specific, the proposed TBKSFA based fault detection method is compared with the popular kernel principal component analysis (KPCA) method, the closely related kernel SFA method and the emerging manifold learning based kernel locality preserving projections (KLPP) method. While the developed KDSFA based fault pattern diagnosis scheme is compared with the conventional jointed angle analysis technique, the strongly linked DSFA based method and the rising artificial neural networks based long short-term memory(LSTM) classifier. Experimental results demonstrate that significant improvements can be achieved by the proposed approach compared with some other popular methods.