Multivariate Statistical Process Control Using Enhanced Bottleneck Neural Network

Abstract

Abstract:Monitoring process upsets and malfunctions as early as possible and then finding and removing the factors causing the respective events is of great importance for safe operation and improved productivity. Conventional process monitoring using principal component analysis (PCA) often supposes that process data follow a Gaussian distribution. However, this kind of constraint cannot be satisfied in practice because many industrial processes frequently span multiple operating states. To overcome this difficulty, PCA can be combined with nonparametric control charts for which there is no assumption need on the distribution. However, this approach still uses a constant confidence limit where a relatively high rate of false alarms are generated. Although nonlinear PCA (NLPCA) using autoassociative bottle-neck neural networks plays an important role in the monitoring of industrial processes, it is difficult to design correct monitoring statistics and confidence limits that check new performance. In this work, a new monitoring strategy using an enhanced bottleneck neural network (EBNN) with an adaptive confidence limit for non Gaussian data is proposed. The basic idea behind it is to extract internally homogeneous segments from the historical normal data sets by filling a Gaussian mixture model (GMM). Based on the assumption that process data follow a Gaussian distribution within an operating mode, a local confidence limit can be established. The EBNN is used to reconstruct input data and estimate probabilities of belonging to the various local operating regimes, as modelled by GMM. An abnormal event for an input measurement vector is detected if the squared prediction error (SPE) is too large, or above a certain threshold which is made adaptive. Moreover, the sensor validity index (SVI) is employed successfully to identify the detected faulty variable. The results demonstrate that, compared with NLPCA, the proposed approach can effectively reduce the number of false alarms, and is hence expected to better monitor many practical processes.Keywords: multivariate statistical process control (MSPC); bottleneck neural network (BNN); Gaussian mixture model (GMM); adaptive confidence limit (ACL); wastewater treatment plant (WWTP); benchmark simulation model No. 1 (BSM1)

Application of the Mathematical Simulation Methods for the Assessment of the Wastewater Treatment Plant Operation Work Reliability

“…This is because of the similarity of PWRMSE parameter for total suspended solids GEV and GMM distributions. The possibility of using Gaussian Mixture Model (GMM) for the assessment of the operation work of the wastewater treatment plant was also presented by Yu [52] and Bouzenad and Ramdani [53]. The results of the analysis performed using PWRMSE parameter turned out to be compatible with the results of Anderson-Darling (A-D) test.…”

Investigation of the Wastewater Treatment Plant Processes Efficiency Using Statistical Tools

“…The authors of the cited paper [19] also showed that GMM distribution is the best for pollutant indicator value descriptions. The possibility of using GMM distribution for the control of WWTP operation work has been presented by Bouzenad and Ramdani [43] and Yu [44] too. Table 3 shows that for BOD 5 , the best-fitted theoretical distribution in raw sewage was GEV distribution, while for the sewage after mechanical treatment and biological treatment, it was GMM distribution.…”

“…The authors of the cited paper [19] also showed that GMM distribution is the best for pollutant indicator value descriptions. The possibility of using GMM distribution for the control of WWTP operation work has been presented by Bouzenad and Ramdani [43] and Yu [44] too.…”

Unsteady State Lightweight Iris Certification Based on Multi-Algorithm Parallel Integration

“…To reduce the dimensions, G1, G2 and G3 are first equally divided into 12 sub-blocks with 64 × 8 dimensions. The principal component analysis method [33] is used to reduce the dimension of 12 sub-blocks to 64 × 1 dimensions, which is 64 feature points. The average value of 64 feature points is calculated as the feature value of each sub-block.…”