The k-nearest neighbour (kNN) rule, which naturally handles the possible non-linearity of data, is introduced to solve the fault detection problem of gas sensor arrays. In traditional fault detection methods based on the kNN rule, the detection process of each new test sample involves all samples in the entire training sample set. Therefore, these methods can be computation intensive in monitoring processes with a large volume of variables and training samples and may be impossible for real-time monitoring. To address this problem, a novel clustering-kNN rule is presented. The landmark-based spectral clustering (LSC) algorithm, which has low computational complexity, is employed to divide the entire training sample set into several clusters. Further, the kNN rule is only conducted in the cluster that is nearest to the test sample; thus, the efficiency of the fault detection methods can be enhanced by reducing the number of training samples involved in the detection process of each test sample. The performance of the proposed clustering-kNN rule is fully verified in numerical simulations with both linear and non-linear models and a real gas sensor array experimental system with different kinds of faults. The results of simulations and experiments demonstrate that the clustering-kNN rule can greatly enhance both the accuracy and efficiency of fault detection methods and provide an excellent solution to reliable and real-time monitoring of gas sensor arrays.
The traditional gas sensor array has been viewed as a simple apparatus for information acquisition in chemosensory systems. Gas sensor arrays frequently undergo impairments in the form of sensor failures that cause significant deterioration of the performance of previously trained pattern recognition models. Reliability monitoring of gas sensor arrays is a challenging and critical issue in the chemosensory system. Because of its importance, we design and implement a status self-validating gas sensor array prototype to enhance the reliability of its measurements. A novel fault detection, isolation, and diagnosis (FDID) strategy is presented in this paper. The principal component analysis-based multivariate statistical process monitoring model can effectively perform fault detection by using the squared prediction error statistic and can locate the faulty sensor in the gas sensor array by using the variables contribution plot. The signal features of gas sensor arrays for different fault modes are extracted by using ensemble empirical mode decomposition (EEMD) coupled with sample entropy (SampEn). The EEMD is applied to adaptively decompose the original gas sensor signals into a finite number of intrinsic mode functions (IMFs) and a residual. The SampEn values of each IMF and the residual are calculated to reveal the multi-scale intrinsic characteristics of the faulty sensor signals. Sparse representation-based classification is introduced to identify the sensor fault type for the purpose of diagnosing deterioration in the gas sensor array. The performance of the proposed strategy is compared with other different diagnostic approaches, and it is fully evaluated in a real status self-validating gas sensor array experimental system. The experimental results demonstrate that the proposed strategy provides an excellent solution to the FDID of status self-validating gas sensor arrays.
A novel fault detection, isolation, and diagnosis (FDID) strategy for self-validating multifunctional sensors is presented in this paper. The sparse non-negative matrix factorization-based method can effectively detect faults by using the squared prediction error (SPE) statistic, and the variables contribution plots based on SPE statistic can help to locate and isolate the faulty sensitive units. The complete ensemble empirical mode decomposition is employed to decompose the fault signals to a series of intrinsic mode functions (IMFs) and a residual. The sample entropy (SampEn)-weighted energy values of each IMFs and the residual are estimated to represent the characteristics of the fault signals. Multi-class support vector machine is introduced to identify the fault mode with the purpose of diagnosing status of the faulty sensitive units. The performance of the proposed strategy is compared with other fault detection strategies such as principal component analysis, independent component analysis, and fault diagnosis strategies such as empirical mode decomposition coupled with support vector machine. The proposed strategy is fully evaluated in a real self-validating multifunctional sensors experimental system, and the experimental results demonstrate that the proposed strategy provides an excellent solution to the FDID research topic of self-validating multifunctional sensors.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.