مقایسه شبکه‌های عصبی نوع GMDHچند هدفی و شبکه خودباوری بیزین در پیش‌بینی کدورت آب تصفیه شده مطالعه موردی: تصفیه خانه بزرگ آب گیلان

Journal Title: آب و فاضلاب - Year 2016, Vol 27, Issue 2

Abstract

Comparison of Multi Objective GMDH-type Neural Network and Bayesian Belief Network in the Prediction of Treated Water Turbidity Case Study: Great Water Treatment Plant in Guilan Province Abstract In this paper, the factors affecting water turbidity removal are identified using the Response Surface Methodology (RSM). The GMDH-type Neural Networks and Bayesian Belief Network (BBN) are subsequently employed for modeling and predicting treated water turbidity using an input-output data set. To validate the proposed model, a case study is carried out based on 700 sets of data obtained from Guilan ¬WTP. For modeling, the experimental data obtained from the operation unit are divided into train and test sections (70% for training and 30% for testing). The predicted values are then compared with experimental ones. The determination coefficients of the predicted values for the two BBN algorithms, consisting of EM and GD, and the GMDH model are found to be 0.9388, 0.9196, and 0.97095, respectively. Evidently, the GMDH model outperforms the BBN model in predicting treated water turbidity.

Authors and Affiliations

Allahyar Daghbandan, Fereshteh Alitaleshi, Mehran Yaghoobi

Keywords

Related Articles

بررسي ايزوترم و سينتيک جذب سرب از پساب سنتتيک با استفاده از خاک اره درخت اوکاليپتوس Kinetic and Isotherm Study of Lead Adsorption from Synthetic Effluent by Eucalyptus Sawdust

Kinetic and Isotherm Study of Lead Adsorption from Synthetic Effluent by Eucalyptus Sawdust Abstract Lead is a heavy metal which has many applications in different industries. Due to toxicity of lead, discharging indu...

ارزیابی آسیب‌پذیری آبخوان خویس با به‌کارگیری مدل دراستیک و سینتکس به‌منظور مدیریت کاربری اراضی

Land Use Management by Assessing Aquifer Vulnerability in Khovayes Plain Using the DRASTIC and SINTACS Models Abstract Land use change is a gradual process that entails dire consequences for groundwater quality and qua...

ارائه مدل تصميم‌گيري به‌منظور مشارکت در سرمايه‌گذاري پروژه‌هاي BOT و BOO بخش آب و فاضلاب کشور

A Decision-Making Model to Attract Private Sector Investors into BOT and BOO Water and Sanitation Projects Economic development in any country depends on a multitude of factors, among which infrastructure construction pr...

پيش‌بيني تغييرات زماني افت فشار در صافي شني Prediction of Temporal Changes of Head Loss in Sand Filter

Abstract Granular media including rapid gravity sand filters are used in water and wastewater treatments. When sand filters are clogged due to deposits of particles and particul-bound pollutants, it will lead to head lo...

گیاه‌پالایی خاک‌های آلوده به هیدروکربن‌های نفتی در اطراف پالایشگاه اصفهان

Phytoremediation of Oil-contaminated Soils Around Isfahan Oil Refinery Abstract Petroleum compounds are pollutants that most commonly occur in soils around oil refineries and that often find their ways into groundwater...

Download PDF file
  • EP ID EP179988
  • DOI -
  • Views 95
  • Downloads 0

How To Cite

Allahyar Daghbandan, Fereshteh Alitaleshi, Mehran Yaghoobi (2016). مقایسه شبکه‌های عصبی نوع GMDHچند هدفی و شبکه خودباوری بیزین در پیش‌بینی کدورت آب تصفیه شده مطالعه موردی: تصفیه خانه بزرگ آب گیلان. آب و فاضلاب, 27(2), 71-83. https://europub.co.uk/articles/-A-179988