Modelling and prediction of aeration efficiency of the venturi aeration system using ANN-PSO and ANN-GA

Author:

Yadav Anamika,Roy Subha M.,Biswas Abhijit,Swain Bhagaban,Majumder Sudipta

Abstract

The significance of this study involves the optimisation of the aeration efficiency (AE) of the venturi aerator using an artificial neural network (ANN) technique integrated with an optimisation algorithm, i.e., particle swarm optimisation (PSO) and genetic algorithm (GA). To optimise the effects of operational factors on aeration efficiency by utilising a venturi aeration system, aeration experiments were conducted in an experimental tank with dimensions of 90cm×55cm×45cm. The operating parameters of the venturi aerator include throat length (TL), effective outlet pipe (EOP), and flow rate (Q) to estimate the efficacy of the venturi aerator in terms of AE. A 3–6-1 ANN model was developed and integrated with the PSO and GA techniques to find out the best possible optimal operating variables of the venturi aerator. The coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) determined from the experimental and estimated data were used to assess and compare the performance of the ANN-PSO and ANN-GA modelling. It is shown that ANN-PSO provides a better result as compared to ANN-GA. The operational parameters, TL, EOP, and Q, were determined to have the most optimum values at 50 mm, 6 m, and 0.6 L/s, respectively. The optimised aeration efficiency of the venturi was found to be 0.105 kg O2/kWh at optimum operational circumstances. In fact, the neural network having an ideal design of (3-6-1) and a correlation coefficient value that is extremely close to unity has validated the results indicated above.

Publisher

Frontiers Media SA

Reference63 articles.

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3