{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T14:54:10Z","timestamp":1767192850956,"version":"build-2065373602"},"reference-count":43,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2017,4,29]],"date-time":"2017-04-29T00:00:00Z","timestamp":1493424000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Algorithms"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/a10020049","type":"journal-article","created":{"date-parts":[[2017,5,2]],"date-time":"2017-05-02T11:37:20Z","timestamp":1493725040000},"page":"49","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Multivariate Statistical Process Control Using Enhanced Bottleneck Neural Network"],"prefix":"10.3390","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3391-1383","authenticated-orcid":false,"given":"Khaled","family":"Bouzenad","sequence":"first","affiliation":[{"name":"Laboratory of Automatic and Signals-Annaba (LASA), Department of Electronics, Faculty of Engineering, Badji-Mokhtar University, P.O. Box 12, 23000 Annaba, Algeria"}]},{"given":"Messaoud","family":"Ramdani","sequence":"additional","affiliation":[{"name":"Laboratory of Automatic and Signals-Annaba (LASA), Department of Electronics, Faculty of Engineering, Badji-Mokhtar University, P.O. Box 12, 23000 Annaba, Algeria"}]}],"member":"1968","published-online":{"date-parts":[[2017,4,29]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1002\/cjce.5450690105","article-title":"Multivariate statistical monitoring of process operating performance","volume":"69","author":"Kresta","year":"1991","journal-title":"Can. J. Chem. Eng."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1016\/0098-1354(94)88019-0","article-title":"Base Control for the Tennessee Eastman Problem","volume":"18","author":"McAvoy","year":"1994","journal-title":"Comput. Chem. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"409","DOI":"10.1080\/00224065.1996.11979699","article-title":"Recent Developments in Multivariate SPC Methods for Monitoring and Diagnosing Process and Product Performance","volume":"28","author":"Kourti","year":"1996","journal-title":"J. Qual. Technol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"S713","DOI":"10.1016\/0098-1354(96)00128-7","article-title":"Use of principal component analysis for sensor fault identification","volume":"20","author":"Dunia","year":"1996","journal-title":"Comput. Chem. Eng."},{"key":"ref_5","unstructured":"MacGregor, J.F., Kourti, T., and Nomikos, P. (July, January 30). Anlysis, Monitoring and fault diagnosis of industrial process using multivariate statistical projection methods. Proceedings of the 13th Triennial Word Congress (IFAC), San Francisco, CA, USA."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1016\/0959-1524(96)00009-1","article-title":"The process chemometrics approach to process monitoring and fault detection","volume":"6","author":"Wise","year":"1996","journal-title":"J. Process Control"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1596","DOI":"10.1002\/aic.690440712","article-title":"Multiscale PCA with application to multivariate statistical process monitoring","volume":"44","author":"Bakshi","year":"1998","journal-title":"AIChE J."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1016\/0967-0661(95)00014-L","article-title":"Statistical process control of multivariate processes","volume":"3","author":"MacGregor","year":"1995","journal-title":"Control Eng. Pract."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2797","DOI":"10.1002\/aic.690421011","article-title":"Identification of faulty sensors using principal component analysis","volume":"42","author":"Dunia","year":"1996","journal-title":"AIChE J."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/0098-1354(95)00003-K","article-title":"Nonlinear principal component analysis based on principal curves and neural networks","volume":"20","author":"Dong","year":"1996","journal-title":"Comput. Chem. Eng."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"132","DOI":"10.1049\/ip-cta:19960321","article-title":"Process performance monitoring using multivariate statistical process control","volume":"143","author":"Martin","year":"1996","journal-title":"IEE Proc.-Control Theory Appl."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2054","DOI":"10.1021\/ie061083g","article-title":"Process monitoring based on independent component analysis\u2014Principal component analysis (ICA-PCA) and similarity factors","volume":"46","author":"Ge","year":"2007","journal-title":"Ind. Eng. Chem. Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1002\/aic.690370209","article-title":"Nonlinear principal component analysis using autoassociative neural networks","volume":"37","author":"Kramer","year":"1991","journal-title":"AIChE J."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1109\/TSM.2007.907607","article-title":"Fault Detection Using the k-Nearest Neighbor Rule for Semiconductor Manufacturing Processes","volume":"20","author":"He","year":"2007","journal-title":"IEEE Trans. Semicond. Manuf."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yu, H. (2015, January 9\u201312). A Just-in-time Learning Approach for Sewage Treatment Process Monitoring with Deterministic Disturbances. Proceedings of the 2015-41st Annual Conference of the IEEE Industrial Electronics Society IECON, Yokohama, Japan.","DOI":"10.1109\/IECON.2015.7392965"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.ces.2012.02.022","article-title":"On-line detection of homogeneous operation ranges by dynamic principal component analysis based time-series segmentation","volume":"75","author":"Dobos","year":"2012","journal-title":"Chem. Eng. Sci."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"582","DOI":"10.1016\/S1007-0214(05)70122-X","article-title":"Multivariate statistical process monitoring using robust nonlinear principal component analysis","volume":"10","author":"Zhao","year":"2005","journal-title":"Tsinghua Sci. Technol."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Verdier, G., and Ferreira, A. (2009, January 6\u20139). Fault detection with an adaptive distance for the k-nearest neighbors rule. Preoceedings of the IEEE International Conference on Computers and Industrial Engineering CIE, Troyes, France.","DOI":"10.1109\/ICCIE.2009.5223844"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"778","DOI":"10.1016\/j.jprocont.2012.02.012","article-title":"A particle filter driven dynamic Gaussian mixture model approach for complex process monitoring and fault diagnosis","volume":"22","author":"Yu","year":"2012","journal-title":"J. Process Control"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"506","DOI":"10.1016\/j.ces.2011.10.011","article-title":"A nonlinear kernel Gaussian mixture model based inferential monitoring approach for fault detection and diagnosis of chemical processes","volume":"68","author":"Yu","year":"2012","journal-title":"Chem. Eng. Sci."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"381","DOI":"10.1109\/34.990138","article-title":"Unsupervised learning of finite mixture models","volume":"24","author":"Figueiredo","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1007\/s10845-012-0636-7","article-title":"On line tool wear monitoring based on auto associative neural network","volume":"24","author":"Wang","year":"2013","journal-title":"J. Intell. Manuf."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"973","DOI":"10.3390\/algor2030973","article-title":"Advances in artificial neural networks methodological development and application","volume":"2","author":"Huang","year":"2009","journal-title":"Algorithms"},{"key":"ref_24","unstructured":"Dev, A., Kr\u00f4se, B.J.A., and and Groen, F.C.A. (1995). Recovering patch parameters from the optic flow with associative neural networks. Proceedings of the 1995 International Conference on Intelligent Autonomous Systems. Karlsruche, Germany, March 27\u201330."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Jung, C., Ban, S.W., Jeong, S., and Lee, M. (2010). Input and output mapping sensitive auto-associative multilayer perceptron for computer interface system based on image processing of laser pointer spot. Neural Inf. Process. Models Appl.","DOI":"10.1007\/978-3-642-17534-3_23"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"290","DOI":"10.1214\/aoms\/1177728786","article-title":"Some Theorems on Quadratic Forms Applied in the Study of Analysis of Variance Problems","volume":"25","author":"Box","year":"1954","journal-title":"Ann. Math. Stat."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"699","DOI":"10.1111\/j.1467-9876.2006.00560.x","article-title":"Probability density estimation via an infinite Gaussian mixture model: Application to statistical process monitoring","volume":"55","author":"Chen","year":"2006","journal-title":"J.R. Stat. Soc. Ser. C (Appl. Stat.)"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"524","DOI":"10.1016\/S1004-9541(07)60119-0","article-title":"Multivariate Statistical Process Monitoring of an Industrial Polypropylene Catalyzer Reactor with Component Analysis and Kernel Density Estimation","volume":"15","author":"Xiong","year":"2007","journal-title":"Chin. J. Chem. Eng."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1109\/TII.2009.2032654","article-title":"Nonlinear dynamic process monitoring using canonical variate analysis and kernel density estimations","volume":"6","author":"Odiowei","year":"2010","journal-title":"IEEE Trans. Ind. Inform."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"531","DOI":"10.1016\/S0967-0661(99)00191-4","article-title":"The application of principal component analysis and kernel density estimation to enhance process monitoring","volume":"8","author":"Chen","year":"2000","journal-title":"Control Eng. Pract."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1002\/apj.5500130117","article-title":"Multivariate statistical process monitoring using kernel density estimation","volume":"13","author":"Liang","year":"2005","journal-title":"Dev. Chem. Eng. Min. Process."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"625","DOI":"10.1016\/j.jprocont.2005.09.007","article-title":"An improved PCA scheme for sensor FDI: Application to an air quality monitoring network","volume":"16","author":"Harkat","year":"2006","journal-title":"J. Process Control"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Bouzenad, K., Ramdani, M., Zermi, N., and Mendaci, K. (2013, January 22\u201324). Use of NLPCA for sensors fault detection and localization applied at WTP. Proceedings of the 2013 World Congress on Computer and Information Technology (WCCIT), Sousse, Tunisia.","DOI":"10.1109\/WCCIT.2013.6618761"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Bouzenad, K., Ramdani, M., and Chaouch, A. (2013, January 9\u201311). Sensor fault detection, localization and reconstruction applied at WWTP. Proceedings of the 2013 Conference on Control and Fault-Tolerant Systems (SysTol), Nice, France.","DOI":"10.1109\/SysTol.2013.6693917"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"131","DOI":"10.12720\/ijoee.2.2.131-137","article-title":"Enhanced Multivariate Process Monitoring for Biological Wastewater Treatment Plants","volume":"2","author":"Chaouch","year":"2014","journal-title":"Int. J. Electr. Energy"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"259","DOI":"10.3390\/a2010259","article-title":"Design of Sensor Networks for Chemical Plants Based on Meta-Heuristics","volume":"2","author":"Carnero","year":"2009","journal-title":"Algorithms"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"130","DOI":"10.3390\/a1020130","article-title":"Machine learning: A crucial tool for sensor design","volume":"1","author":"Zhao","year":"2008","journal-title":"Algorithms"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"1080","DOI":"10.1016\/j.engappai.2007.08.004","article-title":"Multivariate statistical monitoring of continuous wastewater treatment plants","volume":"21","author":"Aguado","year":"2008","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"197","DOI":"10.2166\/wst.1998.0542","article-title":"Disturbance detection in wastewater treatment plants","volume":"37","author":"Rosen","year":"1998","journal-title":"Water Sci. Technol."},{"key":"ref_40","first-page":"1371","article-title":"Multivariate statistical modeling and monitoring of SBR wastewater treatment using double moving window PCA","volume":"3","author":"Zhao","year":"2004","journal-title":"Mach. Learn. Cybern."},{"key":"ref_41","unstructured":"Alex, J., Benedetti, L., Copp, J., Gernaey, K.V., Jeppsson, U., Nopens, I., Pons, M.N., Rieger, L., Rosen, C., and Steyer, J. (2017, April 28). Benchmark Simulation Model no. 1 (BSM1.). Available online: http:\/\/www.iea.lth.se\/publications\/Reports\/LTH-IEA-7229.pdf."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"513","DOI":"10.2166\/wst.2006.155","article-title":"Sensor validation and reconciliation for a partial nitrification process","volume":"53","author":"Yoo","year":"2006","journal-title":"Water Sci. Technol."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1002\/env.900","article-title":"Enhanced process monitoring for wastewater treatment systems","volume":"19","author":"Yoo","year":"2008","journal-title":"Environmetrics"}],"container-title":["Algorithms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-4893\/10\/2\/49\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T18:34:10Z","timestamp":1760207650000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-4893\/10\/2\/49"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,29]]},"references-count":43,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2017,6]]}},"alternative-id":["a10020049"],"URL":"https:\/\/doi.org\/10.3390\/a10020049","relation":{},"ISSN":["1999-4893"],"issn-type":[{"type":"electronic","value":"1999-4893"}],"subject":[],"published":{"date-parts":[[2017,4,29]]}}}