Artificial intelligence based ensemble modeling of wastewater treatment plant using jittered data
| Autor: | Parisa Asghari, Elnaz Sharghi, Vahid Nourani |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Adaptive neuro fuzzy inference system
Artificial neural network Ensemble forecasting Renewable Energy Sustainability and the Environment business.industry 020209 energy Strategy and Management 05 social sciences Linear model 02 engineering and technology Ensemble learning Industrial and Manufacturing Engineering Black box 050501 criminology 0202 electrical engineering electronic engineering information engineering Feedforward neural network Artificial intelligence Autoregressive integrated moving average business 0505 law General Environmental Science Mathematics |
| Zdroj: | Journal of Cleaner Production. 291:125772 |
| ISSN: | 0959-6526 |
| Popis: | In this study, black box artificial intelligence models (AI) including feed forward neural network (FFNN), support vector regression (SVR) and adaptive neuro-fuzzy inference system (ANFIS) were used to predict effluent biological oxygen demand (BODeff) and chemical oxygen demand (CODeff) of Tabriz wastewater treatment plant (WWTP) using the daily data collected from 2016 to 2018. In addition, the autoregressive integrated moving average (ARIMA) linear model was used to predict BODeff and CODeff parameters in order to compare the linear and non-linear models abilities in complex processes prediction. To improve the prediction of BODeff and CODeff parameters, the data post-processing ensemble method and the jittering data pre-processing method were also used. The input data set included daily influent BOD, COD, total suspended solids (TSS), pH at the current time (t) and BODeff and CODeff at the previous time (t-1), also, the output data included BODeff and CODeff at t. The results of the single models indicated that SVR model provides better results than the other single models. To create jittered series, different levels of noise series were added to the original time series to produce more time series with similar patterns to the original time series to extend the scale of the training data set. In the ensemble modeling, simple and weighted linear averaging, and neural network ensemble methods were applied to enhance the performance of the single AI models. The results indicated that using jittering and ensemble models could increase the prediction accuracy up to 20% at the verification phase. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect