Sensor fault diagnosis of nonlinear processes based on structured kernel principal component analysis

A new sensor fault diagnosis method based on structured kernel principal component analysis （KPCA） is proposed for nonlinear processes. By performing KPCA on subsets of variables, a set of structured residuals, i.e., scaled powers of KPCA, can be obtained in the same way as partial PCA. The structured residuals are utilized in composing an isolation scheme for sensor fault diagnosis, according to a properly designed incidence matrix. Sensor fault sensitivity and critical sensitivity are defined, based on which an incidence matrix optimization algorithm is proposed to improve the performance of the structured KPCA. The effectiveness of the proposed method is demonstrated on the simulated continuous stirred tank reactor （CSTR） process.

Sensor Fault Diagnosis Observer Design for Linear Sampled-Data Descriptor System with Time-Vary Delay

In this paper, a robust sensor fault diagnosis observer with non-singular structure is proposed for a class of linear sampled-data descriptor system with state time-vary delay. Firstly, a sampled-data descriptor model with time-vary delay is proposed and transformed into a discrete-time non-singular one. Then, a robust sensor fault diagnosis observer is proposed based on the state estimation error and the measurement residual, this observer can guarantee the robustness of the residual against the augmented disturbance and the sensor fault, which means the H∞ performance index is satisfied. As the confining matrix of the designed observer parameters does not meet the Linear Matrix Inequality (LMI), a cone complementary linearization (CCL) algorithm is proposed to solve this problem. The decision logic of the residual is obtained by the residual evaluation function. Simulation results show the effectiveness of the method.

Hybrid Fault Diagnosis and Isolation for Component and Sensor of APU in a Distributed Control System

This paper addresses the gas path component and sensor fault diagnosis and isolation(FDI) for the auxiliary power unit(APU). A nonlinear dynamic model and a distributed state estimator are combined for the distributed control system. The distributed extended Kalman filter(DEKF)is served as a state estimator,which is utilized to estimate the gas path components’ flow capacity. The DEKF includes one main filter and five sub-filter groups related to five sensors of APU and each sub-filter yields local state flow capacity. The main filter collects and fuses the local state information,and then the state estimations are feedback to the sub-filters. The packet loss model is introduced in the DEKF algorithm in the APU distributed control architecture. FDI strategy with a performance index named weight sum of squared residuals(WSSR) is designed and used to identify the APU sensor fault by removing one sub-filter each time. The very sensor fault occurs as its performance index WSSR is different from the remaining sub-filter combinations. And the estimated value of the soft redundancy replaces the fault sensor measurement to isolate the fault measurement. It is worth noting that the proposed approach serves for not only the sensor failure but also the hybrid fault issue of APU gas path components and sensors. The simulation and comparison are systematically carried out by using the APU test data,and the superiority of the proposed methodology is verified.

Fault diagnosis method of hydraulic system based on fusion of neural network and D-S evidence theory

According to fault type diversity and fault information uncertainty problem of the hydraulic driven rocket launcher servo system（HDRLSS） , the fault diagnosis method based on the evidence theory and neural network ensemble is proposed. In order to overcome the shortcomings of the single neural network, two improved neural network models are set up at the com-mon nodes to simplify the network structure. The initial fault diagnosis is based on the iron spectrum data and the pressure, flow and temperature（PFT） characteristic parameters as the input vectors of the two improved neural network models, and the diagnosis result is taken as the basic probability distribution of the evidence theory. Then the objectivity of assignment is real-ized. The initial diagnosis results of two improved neural networks are fused by D-S evidence theory. The experimental results show that this method can avoid the misdiagnosis of neural network recognition and improve the accuracy of the fault diagnosis of HDRLSS.