Estimation of effluent parameters of slaughterhouse wastewater treatment with artificial neural network and B-spline qua
- PDF / 3,979,690 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 74 Downloads / 254 Views
RESEARCH PAPER
Estimation of effluent parameters of slaughterhouse wastewater treatment with artificial neural network and B‑spline quasi interpolation Moein Besharati Fard1 · Seyed Ahmad Mirbagheri1 · Alireza Pendashteh2 · Javad Alavi3 Received: 14 February 2020 / Revised: 23 June 2020 / Accepted: 17 July 2020 © University of Tehran 2020
Abstract Effluent of slaughterhouse wastewater treatment by combined up-flow anaerobic sludge blanket (UASB) reactor and extended aeration reactor was estimated through artificial neural networks (ANN), ANN-genetic algorithm (GA) and B-spline quasi interpolation. The overall system operated at two runs with average total chemical oxygen demand (TCOD) of 1514.65 and 3160.2 mg/L for the first and second run, respectively; with two overall hydraulic retention times of 73 and 104 h for each run. The overall system could remove TCOD, ammonia, phosphate and turbidity to a high extent. The multilayer perceptron artificial neural network (MLPANN) trained by Levenberge–Marquardt algorithm was employed to predict the TCOD, ammonia, phosphate and turbidity of the effluent which resulted in R of 0.8257, 0.6274, 0.7961 and 0.6884, respectively. The optimization of MLPANN by GA performed better than MLPANN with R of 0.8390, 0.7650, 0.8107 and 0.7365 for TCOD, ammonia, phosphate and turbidity, respectively. The B-spline quasi interpolation indicates a more accurate prediction due to its R of 0.9619, 0.8806, 0.8307 and 0.7856 for TCOD, ammonia, phosphate and turbidity, respectively. The B-spline quasi interpolation operation time is notably lower than ANN and ANN-GA. In addition, it has a simple algorithm and is implemented easier than the artificial neural network model. Article Highlights • • • •
Slaughterhouse wastewater treatment by combined biological process. Multi-layer perceptron, genetic algorithm and B-spline quasi interpolation were used for prediction. Prediction of total COD, ammonia, phosphate and turbidity. Effect of HRT investigated on removal efficiency.
Keywords Slaughterhouse wastewater · Up-flow anaerobic sludge blanket · Extended aeration · Artificial neural network · Genetic algorithm · B-spline quasi interpolation * Seyed Ahmad Mirbagheri [email protected]
Introduction
* Alireza Pendashteh [email protected]
Industries produce wastewaters containing a high concentration of organic matter, nutrients concentration and noxious compounds causing serious damages through the environment. Slaughterhouses are one of the high-risk industries having wastewater with a high concentration of organic matters, suspended solids, oil and grease, nitrogen and phosphorus. The major sources of organic matter and nutrients are blood, faeces and fat (Barana et al. 2013). The chemical oxygen demand (COD), total nitrogen (TN) and total phosphorous (TP) concentrations in slaughterhouse wastewater vary in the range of 500–15,900 mg/L, 50–841 mg/L and
Moein Besharati Fard [email protected] Javad Alavi [email protected] 1
Department of Civil Engineering, K. N
Data Loading...
