The task of fault detection is crucial in modern chemical industries for improved product quality and process safety. In this regard, data-driven fault detection (FD) strategy based on independent component analysis (ICA) has gained attention since it improves monitoring by capturing non-gaussian features in the process data. However, presence of measurement noise in the process data degrades performance of the FD strategy since the noise masks important information. To enhance the monitoring under noisy environment, wavelet-based multi-scale filtering is integrated with the ICA model to yield a novel multi-scale Independent component analysis (MSICA) FD strategy. One of the challenges in multi-scale ICA modeling is to choose the optimum decomposition depth. A novel scheme based on ICA model parameter estimation at each depth is proposed in this paper to achieve this. The effectiveness of the proposed MSICA-based FD strategy is illustrated through three case studies, namely: dynamic multi-variate process, quadruple tank process and distillation column process. In each case study, the performance of the MSICA FD strategy is assessed for different noise levels by comparing it with the conventional FD strategies. The results indicate that the proposed MSICA FD strategy can enhance performance for higher levels of noise in the data since multi-scale wavelet-based filtering is able to de-noise and capture efficient information from noisy process data.

Fault detection is necessary for safe operation in modern process plants. The kernel principal component analysis (KPCA) technique has been widely utilized for monitoring non-linear processes because it enhances dimension reduction and fault detection in non-linear space. In this paper, an improved nonlinear fault detection strategy based on Kantorovich distance (KD) and kernel principal component analysis is proposed. The KD statistic is based on the optimal mass transport theory where the distance between two distributions is computed with respect to a cost function. The addressed fault detection problem models the data using the KPCA framework and utilizes the ability of the KD statistical indicator to detect faults. The detection stage involves comparing the residuals of training fault-free data and testing faulty data using the KD statistic. Additionally, the reference threshold for the KD statistic is computed using the kernel density estimation (KDE) approach as compared to the previously utilized three-sigma rule approach. The detection performance is illustrated with the help of three benchmark case studies: a continuous stirred tank reactor (CSTR) process, Tennessee Eastman (TE) process and an experimental distillation column process. The performance analysis suggests the superiority of the KPCA-KD fault detection scheme in monitoring various sensor faults. Moreover, comparison with traditional statistical indicators of PCA and KPCA schemes shows that the proposed scheme enhances fault detection and achieves an improved detection rate in monitoring different categories of faults.INDEX TERMS Kantorovich distance, kernal principal component analysis, continuous stirred tank reactor process, Tennessee Eastman process, experimental distillation column process, fault detection.

Vowing to the increasing complexity in industrial processes, the need for safety is of highest priority and this has led to development of efficient fault detection (FD) methods. Also, with rapid development of data acquisition systems, process history based methods have gained importance as their dependency is on large volume of sensor data extracted from the process. The industrial data exhibits some degree of non-gaussianity for which Independent Component Analysis (ICA) technique has usually been applied in practice. Recently, a new fault indicator based on Kantorovich Distance (KD) has been proposed which computes distance between two distributions and uses the distance as an indicator of fault. The KD metric has found to provide good monitoring results for data in presence of noise and offers enhanced detection of small magnitude faults. Considering the benefits offered by KD metric, the objective of this work is to amalgamate KD metric with ICA modeling framework to have a fault detection strategy that can improve process monitoring in noisy environment. The proposed ICA-KD FD strategy is illustrated on four processes that includes Modified Continuous Stirred Tank Heater (CSTH), Tennessee Eastman (TE) process and Experimental Distillation Column Process. The simulation results indicate that the proposed FD strategy exhibits improved performance over conventional strategies while monitoring different sensor faults in noisy environment.INDEX TERMS Process monitoring, fault detection, independent component analysis, Kantorovich distance, small magnitude faults, Tennessee Eastman process, experimental distillation column process, modified continuous stirred tank heater process.

No abstract

No abstract