Search

In this paper, the detection problem of intermittent multiplicative sensor fault is investigated for stochastic uncertain systems. A robust optimal filter is designed according to the criterion of minimum estimation error covariance. Then, based on this, a residual generator is constructed, and the quantitative effect of the fault on it is discussed in detail. After that we design the evaluation function and detection threshold to achieve intermittent fault detection. Our proposed strategy has a recursive form and only includes simple arithmetic operations, thus it is suitable for real‐time online applications. Finally, a simulation example is given to demonstrate the effectiveness of the proposed strategy. [ABSTRACT FROM AUTHOR]

Summary: In this paper, the event‐triggered filtering and intermittent fault detection problems are investigated for a class of time‐varying systems with stochastic parameter uncertainty and sensor saturation. Due to the existence of event‐triggered mechanism, the measured signal could be transmitted only when it satisfies the triggering condition. An event‐triggered filter is developed, which takes the event‐triggered mechanism, parameter uncertainty, and sensor saturation into full consideration but does not depend on any specific uncertainty structure. By utilizing the inductive and stochastic analysis technique, the filter gain is designed to ensure that the upper bound of the estimation error covariance is minimized at each time step. Based on the proposed filter, a residual is generated and the corresponding evaluation function and detection threshold are given to achieve fault detection. At last, two simulation studies are carried out to demonstrate the effectiveness and applicability of the proposed method. [ABSTRACT FROM AUTHOR]

This paper presents a new data-driven fault detection method called covariance eigenpairs neighbour distance (CEND) for monitoring chemical processes. It processes measured data in one-step sliding windows to estimate covariance, and the eigenpairs of each sample covariance matrix are recursively calculated using rank-one modification. The eigenvalues and selected elements of eigenvectors are stacked into reference vectors. For each window data containing the latest measurement vector, the neighbour distance of eigenpairs from the reference matrix can be effectively calculated by virtue of k-d tree. The neighbour distance serves as the detection index, whose control limit can be determined by validation dataset with assigning a significance level. A high neighbour distance exceeding the control limit implies the occurrence of fault. Simulations on the continuous stirred tank reactor (CSTR) and the Tennessee Eastman process (TEP) both indicate the superior fault detectability of the proposed method, compared with conventional multivariate statistical process monitoring (MSPM) methods such as principal component analysis (PCA) and independent component analysis (ICA). [ABSTRACT FROM AUTHOR]

The article presents a study which proposed a total projection to latent structures (T-PLS) algorithm. The properties of T-PLS are studied, including its relationship to the orthogonal partial least squares or projection to latent structures (PLS). The purpose of T-PLS is to acquire a further decomposition on X-space which is more suitable for process monitoring. The T-PLS is proven to be an oblique space decomposition of X- Space. Simulation examples show the effectiveness of T-PLS based fault detection methods.