A neural software sensor for online prediction of coagulant dosage in a drinking water treatment plant
| Autor: | Ahmed Benhammou, A. Karama, Bouchra Lamrini, M.V. Le Lann |
|---|---|
| Rok vydání: | 2005 |
| Předmět: |
0209 industrial biotechnology
Engineering Artificial neural network business.industry 020208 electrical & electronic engineering 02 engineering and technology Ideal solution Overfitting computer.software_genre Regularization (mathematics) 020901 industrial engineering & automation Software Principal component analysis Linear regression Pattern recognition (psychology) 0202 electrical engineering electronic engineering information engineering Data mining business Instrumentation computer |
| Zdroj: | Transactions of the Institute of Measurement and Control. 27:195-213 |
| ISSN: | 1477-0369 0142-3312 |
| DOI: | 10.1191/0142331205tm141oa |
| Popis: | Artificial Neural Networks have been applied to an increasing number of real-world problems of considerable complexity. Considered as good pattern recognition engines, they offer ideal solutions to a variety of problems such as prediction and modelling where the industrial processes are highly complex. The present paper reports on the elaboration and the validation of a “Software Sensor” using Artificial Neural Networks for on-line prediction of optimal coagulant dosage from raw water quality measurements, in a drinking water treatment plant. In a first part, the main parameters affecting the coagulant dosage are determined using a Principal Component Analysis. A brief description of this statistical study is given and experimental results are included. The second part of this work is dedicated to the development of Neural Software Sensor and the generation of an uncertainty indicator attached to the prediction. The Bootstrap sampling has been therefore used to generate confidence interval for the model outputs. The ANN model was developed using LevenbergMarquardt method in combination with the “Weight Decay” regularization to avoid over fitting. A linear regression model has been also developed for comparison with ANN model. Experimental and performance results obtained from real data are presented and discussed. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|