Investigating the Results of Predicting the Quality of Treated Effluent Using Neural Network and Metaheuristic Algorithm (Case Study: Pegah Factory in Azerbaijan)

Document Type : Applied Article

Authors

• mahdi yousefi nejad attari
• Sh. Habbibi
• A derakhshan

Department of Industrial Engineering, Bonab Branch, Islamic Azad university, Bonab, Iran

10.22067/jwsd.v7i3.86040

Abstract

Reducing water resources and increasing demand for safe drinking water requires attention to water resources that can be returned to nature or can be used in industry or agriculture. In this regard, the use of optimal and effective methods for wastewater treatment and development is very important. In order to increase the efficiency of the wastewater treatment system and in order to reduce the pollution load of the effluent, it is very important to predict the quality of the treated effluent. In this research work, using genetic algorithm and neural network method, the effluent treatment system of Azerbaijan Pegah factory has been modeled in order to optimize the results using genetic algorithm and neural network method. The effluent treatment process should be carried out in order to anticipate the removal and disinfection of the remaining carbon materials and microbial contaminants according to the BOD5 and COD data that determine the quality of the effluent. The results show that the combination of the above two algorithms has been successful in predicting the output data compared to the actual data and there is an 87% matching of the data.

Keywords

• Effluent
• Genetic Algorithm
• Neural Network
• BOD5
• COD

Main Subjects

• Water Quality, Recycling and Wastewater

---

References

مرادمند، م. و بیگی هرچگانی، ح. ۱۳۸۸. اثر آبیاری با پساب تصفیه‌شده بر توزیع سرب و نیکل در اندام فلفل سبز و خاک. مجله پژوهش آب ایران، ۵: ۶۳ – ۷۰۳.
رنگ‌زن، ن.، پاینده، خ. و لندی، ا. ۱۳۸۵. بررسی کیفیت پساب بر انباشت عناصر سنگین در دو گیاه سورگوم و شبدر .مجموعه مقالات نهمین کنگره علوم خاک ایران، تهران.
ترابیان، ع. و مطلبی، م. ۱۳۸۲. طرح مدیریتی استفاده مجدد از پساب تصفیه‌شده (مطالعه موردی: شهرک اکباتان). محیط‌شناسی، ۲۹(۳۲):57-62.

Chachuat B., Roche N. and Latfi M.A. 2005. OpTImal aera on control of industrial alterntiang activated sludge pants. Biochemical Engineering Journal, 23(3): 277-289.
Garcia M.D., Grau P., Huete H., Gomez J., Garcia-Heras L. and Ayesa E. 2009. New generic mathematical model for WWTP sludge digesters operating under aerobic and anaerobic conditions: Model building and experimental verification. Water Research, 43(18): 4626-4642.
Li Z, and Lerapetritou M. 2008. Process scheduling under uncertainly: Review and challenges. Computers and Chemical Engineering, 32(405): 715-727.
Lu H., and Ma X. 2020. Hybrid decision tree-based machine learning models for short-term water quality prediction. Chemosphere, 126169.
Metcalf, E. (1819). Inc.(2003), Wastewater engineering treatment and reuse.
Zhang L., Ma X., Shi P., Bi S. and Wang C. 2019. RegCNN: A Deep Multi-output Regression Method for Wastewater Treatment. In 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI) (pp. 816-823). IEEE.