Modeling of an activated sludge process for effluent prediction—a comparative study using ANFIS and GLM regression
| Autor: | Dauda Olurotimi Araromi, Taofeeq Olalekan Salawudeen, Jamiu Adetayo Adeniran, Olukayode Titus Majekodunmi |
|---|---|
| Přispěvatelé: | Majekodunmi, Olukayode Titus, Izmir Institute of Technology. Chemical Engineering |
| Rok vydání: | 2018 |
| Předmět: |
Generalized linear model
Correlation coefficient Mean squared error 0208 environmental biotechnology 02 engineering and technology Wastewater 010501 environmental sciences Management Monitoring Policy and Law 01 natural sciences Fuzzy logic Predictive models Fuzzy Logic Lasso (statistics) GLM regression Statistics Water Pollution Chemical Organic Chemicals Wastewater treatment process ANFIS LASSO regularization 0105 earth and related environmental sciences General Environmental Science Mathematics Adaptive neuro fuzzy inference system Sewage Nonlinear system identification General Medicine Pollution Regression 020801 environmental engineering Models Chemical Linear Models Neural Networks Computer Fuzzy exhaustive search Environmental Monitoring |
| Zdroj: | Environmental Monitoring and Assessment. 190 |
| ISSN: | 1573-2959 0167-6369 |
| DOI: | 10.1007/s10661-018-6878-x |
| Popis: | In this paper, nonlinear system identification of the activated sludge process in an industrial wastewater treatment plant was completed using adaptive neuro-fuzzy inference system (ANFIS) and generalized linear model (GLM) regression. Predictive models of the effluent chemical and 5-day biochemical oxygen demands were developed from measured past inputs and outputs. From a set of candidates, least absolute shrinkage and selection operator (LASSO), and a fuzzy brute-force search were utilized in selecting the best combination of regressors for the GLMs and ANFIS models respectively. Root mean square error (RMSE) and Pearson's correlation coefficient (R-value) served as metrics in assessing the predicting performance of the models. Contrasted with the GLM predictions, the obtained modeling results show that the ANFIS models provide better predictions of the studied effluent variables. The results of the empirical search for the dominant regressors indicate the models have an enormous potential in the estimation of the time lag before a desired effluent quality can be realized, and preempting process disturbances. Hence, the models can be used in developing a software tool that will facilitate the effective management of the treatment operation. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink