[en] Applications in the water treatment domain
generally rely on complex sensors located at remote sites.
The processing of the corresponding measurements for
generating higher-level information such as optimization of
coagulation dosing must therefore account for possible
sensor failures and imperfect input data. In this paper, selforganizing
map (SOM)-based methods are applied to
multiparameter data validation and missing data reconstruction
in a drinking water treatment. The SOM is a
special kind of artificial neural networks that can be used
for analysis and visualization of large high-dimensional
data sets. It performs both in a nonlinear mapping from a
high-dimensional data space to a low-dimensional space
aiming to preserve the most important topological and
metric relationships of the original data elements and, thus,
inherently clusters the data. Combining the SOM results
with those obtained by a fuzzy technique that uses marginal
adequacy concept to identify the functional states (normal
or abnormal), the SOM performances of validation and
reconstruction process are tested successfully on the
experimental data stemming from a coagulation process
involved in drinking water treatment.
Disciplines :
Computer science
Author, co-author :
Lamrini, B, Lakhal, E K
Wehenkel, Louis ; Université de Liège - ULiège > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation
Language :
English
Title :
Data validation and missing data reconstruction using self-organizing map for water treatment
Aguilar-Martin J, Balssa M, Lopez De Mantras R (1981) Recursive estimation of partitions: examples of learning and self teaching in RN and IN. Questiio: Quaderns d'Etadisticia, Siestems, Informatica i Investigacio Operativa, ISSN 0210-8054 5(3): 150-172.
Badran F, Thiria S, Main B (1992) Smoothing with topological map. In Proceedings of NeuroNimes92 (neural network & their applications), Nîmes, France, pp 107-115.
Barnett V, Lewis T (1994) Outliers in statistical data (Wiley series in probability & statistics), 3rd edn. Wiley, New York.
Biernacki C, Celeux G, Si Abdallah J-F, Govaert G, Langrognet F (2009) MIXMOD user's guide (MIXture MODelling software: high performance model-based cluster and discriminant analysis). Univ. of Franche-Comté, France. http://www-math. univ-fcomte. fr/mixmod/index. php.
Denning D (1987) An intrusion-detection model. IEEE Trans Softw Eng 13(2): 222-232.
Fuente MJ, Vega P (1999) Neural networks applied to fault detection of a biotechnological process. Eng Appl Artif Intell 12: 569-584.
Gagnon C, Grandjean BPA, Thibault J (1997) Modelling of coagulant dosage in a water treatment plant. Artif Intell Eng 11: 401-404.
Gonzalez F, Dasgupta D (2002) Neuro-immune and self-organizing map approaches to anomaly detection: a comparison. In: Proceedings of the 1st international conference on artificial immune systems, Canterbury, UK, pp 203-211.
Hernandez H, Le Lann M-V (2006) Development of a neural sensor for on-line prediction of coagulant dosage in a potable water treatment plant in the way of its diagnosis. In: Sichman JS et al (eds) IBERAMIA-SBIA 2006, LNAI 4140, pp 249-257.
Kasslin M, Kangas J, Simula O (1992). Process state monitoring using self organizing maps. In: Aleksander I, Taylor J (eds) Artificial neural networks II, vol 2, Amsterdam, Netherlands, North-Holland, pp 1531-1534.
Kempowsky T (2004). Surveillance des procédés à base de méthodes de classification: conception d'un outil d'aide pour la détection et le diagnostic des défaillances. PhD Thesis, LAAS-CNRS, Institut National des Sciences Appliquées (INSA), Toulouse, France.
Kohonen T (1995) Self-organizing maps. Volume 30 of Springer series in information sciences. Springer, Berlin.
Kohonen T, Oja E, Simula O, Visa A, Kangas J (1996) Engineering applications of the self-organizing map. Proc IEEE 84(10): 1358-1384.
Kramer MA (1991) Nonlinear principal component analysis using autoassociative neural networks. AIChE J 37(2): 233-243.
Lamrini B, Benhammou A, Le Lann M-V, Karama A (2005) A neural software sensor for on-line prediction of coagulant dosage: application to a drinking water treatment plant. Trans Inst Meas Control 27(3): 95-213.
Lamrini B, Benhammou A, Le Lann M-V, Lakhal El-K (2005) Detection of functional states by "LAMDA" classification technique: application to a coagulation process in drinking water treatment. Comptes Rendus Physique 6: 1161-1168.
Masschelein WJ (1997) Processus unitaires du traitement de l'eau potable. Tec & Doc Lavoisier (Ed), Paris.
Orantes A, Kempowsky T, Le Lann MV (2006) Classification as an aid tool for the selection of sensors used for fault detection and isolation. Trans Inst Meas Control 28(5): 457-480.
Piera-Carreté N, Desroches P, Aguilar-Martin J (1989). LAMDA: an incremental conceptual clustering system. Technical report No. 89420, LAAS-CNRS, Toulouse, France.
Planchon V (2005) Traitement des valeurs aberrantes: concepts actuels et tendances générales. Biotechnol Agron Soc Environ 9(1): 19-34.
Simula O, Alhoniemi E, Hollmen J, Vesanto J (1996). Monitoring and modelling of complex processes using hierarchical self-organizing maps. In: Proceeding of the IEEE international symposium on circuits and systems (ISCAS'96), vol supplement, pp 73-76.
Stanimirova I, Daszykowski M, Walczak B (2007) Dealing with missing values and outliers in principal component analysis. Talanta 72: 172-178.
Trautmann T (1995) Développement d'un modèle de cartes topologiques auto-organisatrices à architecture dynamique: Application au diagnostic. PhD thesis, Univ. of Compiègne, France.
Trautmann T, Denoeux T (1995) Comparison of dynamic feature map models for environmental monitorin. In: Proceedings of international conference on neural networks (ICNN'95), vol 1, Perth, Australia, pp 73-78.
Valentin N, Denoeux T, Fotoohi F (1999) An hybrid neural network based system for optimization of coagulant dosing in a water treatment plant. In: Proceedings of international joint conference on neural networks (IJCNN'99), Washington.
Vercauteren L, Sieben G, Praet M, Otte G, Vingerhoeds L, Boullart L, Lalliauw L, Roeds H (1990) The classification of brains tumours by a topological map. In: Proceedings of international conference on neural networks (ICNN'90), vol 1, Paris, pp 387-391.
Vesanto J, Alhoniemi E, Himberg J, Kiviluoto K, Parviainen J (1999). Self-organizing map for data mining in MATLAB: the SOM toolbox. Simul News Eur 25-54.
Waissmann-Vilanova J (2000) Building a behavioural model for process supervision: application to a wastewater treatment plant. PhD thesis, LAAS-CNRS, Institut National Polytechnique (INP), Toulouse, France.
Zadeh LA (1978) Fuzzy sets as a basis for a theory of possibility. Fuzzy Sets Syst 1: 3-28.