{"title":"Unveiling optimal half-cell potentials in RCC slabs through cutting-edge ANFIS, ANN and genetic algorithm integration","authors":"Shikha Pandey, Sumit Gandhi, Yogesh Iyer Murthy","doi":"10.1108/acmm-01-2024-2950","DOIUrl":null,"url":null,"abstract":"<h3>Purpose</h3>\n<p>The purpose of this study is to compare the prediction models for half-cell potential (HCP) of RCC slabs cathodically protected using pure magnesium anodes and subjected to chloride ingress.The models for HCP using 1,134 data set values based on experimentation are developed and compared using ANFIS, artificial neural network (ANN) and integrated ANN-GA algorithms.</p><!--/ Abstract__block -->\n<h3>Design/methodology/approach</h3>\n<p>In this study, RCC slabs, 1000 mm × 1000 mm × 100 mm were cast. Five slabs were cast with 3.5% NaCl by weight of cement, and five more were cast without NaCl. The distance of the point under consideration from the anode in the <em>x</em>- and <em>y</em>-axes, temperature, relative humidity and age of the slab in days were the input parameters, while the HCP values with reference to the Standard Calomel Electrode were the output. Experimental values consisting of 80 HCP values per slab per day were collected for 270 days and were averaged for both cases to generate the prediction model.</p><!--/ Abstract__block -->\n<h3>Findings</h3>\n<p>In this study, the premise and consequent parameters are trained, validated and tested using ANFIS, ANN and by using ANN as fitness function of GA. The MAPE, RMSE and MAE of the ANFIS model were 24.57, 1702.601 and 871.762, respectively. Amongst the ANN algorithms, Levenberg−Marquardt (LM) algorithm outperforms the other methods, with an overall <em>R</em>-value of 0.983. GA with ANN as the objective function proves to be the best means for the development of prediction model.</p><!--/ Abstract__block -->\n<h3>Originality/value</h3>\n<p>Based on the original experimental values, the performance of ANFIS, ANN and GA with ANN as objective function provides excellent results.</p><!--/ Abstract__block -->","PeriodicalId":8217,"journal":{"name":"Anti-corrosion Methods and Materials","volume":null,"pages":null},"PeriodicalIF":2.3000,"publicationDate":"2024-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Anti-corrosion Methods and Materials","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1108/acmm-01-2024-2950","RegionNum":4,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"METALLURGY & METALLURGICAL ENGINEERING","Score":null,"Total":0}
引用次数: 0
Abstract
Purpose
The purpose of this study is to compare the prediction models for half-cell potential (HCP) of RCC slabs cathodically protected using pure magnesium anodes and subjected to chloride ingress.The models for HCP using 1,134 data set values based on experimentation are developed and compared using ANFIS, artificial neural network (ANN) and integrated ANN-GA algorithms.
Design/methodology/approach
In this study, RCC slabs, 1000 mm × 1000 mm × 100 mm were cast. Five slabs were cast with 3.5% NaCl by weight of cement, and five more were cast without NaCl. The distance of the point under consideration from the anode in the x- and y-axes, temperature, relative humidity and age of the slab in days were the input parameters, while the HCP values with reference to the Standard Calomel Electrode were the output. Experimental values consisting of 80 HCP values per slab per day were collected for 270 days and were averaged for both cases to generate the prediction model.
Findings
In this study, the premise and consequent parameters are trained, validated and tested using ANFIS, ANN and by using ANN as fitness function of GA. The MAPE, RMSE and MAE of the ANFIS model were 24.57, 1702.601 and 871.762, respectively. Amongst the ANN algorithms, Levenberg−Marquardt (LM) algorithm outperforms the other methods, with an overall R-value of 0.983. GA with ANN as the objective function proves to be the best means for the development of prediction model.
Originality/value
Based on the original experimental values, the performance of ANFIS, ANN and GA with ANN as objective function provides excellent results.
本研究的目的是比较使用纯镁阳极进行阴极保护并受到氯化物侵蚀的 RCC 板的半电池电位 (HCP) 预测模型。本研究使用 ANFIS、人工神经网络 (ANN) 和集成 ANN-GA 算法开发并比较了基于实验的 1,134 个数据集值的 HCP 模型。其中五块板浇注时加入了水泥重量 3.5% 的氯化钠,另外五块浇注时未加入氯化钠。所考虑的点与阳极在 x 轴和 y 轴上的距离、温度、相对湿度和板龄(以天为单位)是输入参数,而参照标准甘汞电极得出的 HCP 值是输出参数。本研究使用 ANFIS、ANN 以及作为 GA 健身函数的 ANN 对前提条件和相应参数进行了训练、验证和测试。ANFIS 模型的 MAPE、RMSE 和 MAE 分别为 24.57、1702.601 和 871.762。在 ANN 算法中,Levenberg-Marquardt(LM)算法的总体 R 值为 0.983,优于其他方法。以 ANN 为目标函数的 GA 被证明是开发预测模型的最佳手段。原创性/价值基于原始实验值,ANFIS、ANN 和以 ANN 为目标函数的 GA 的性能提供了出色的结果。
期刊介绍:
Anti-Corrosion Methods and Materials publishes a broad coverage of the materials and techniques employed in corrosion prevention. Coverage is essentially of a practical nature and designed to be of material benefit to those working in the field. Proven applications are covered together with company news and new product information. Anti-Corrosion Methods and Materials now also includes research articles that reflect the most interesting and strategically important research and development activities from around the world.
Every year, industry pays a massive and rising cost for its corrosion problems. Research and development into new materials, processes and initiatives to combat this loss is increasing, and new findings are constantly coming to light which can help to beat corrosion problems throughout industry. This journal uniquely focuses on these exciting developments to make essential reading for anyone aiming to regain profits lost through corrosion difficulties.
• New methods, materials and software
• New developments in research and industry
• Stainless steels
• Protection of structural steelwork
• Industry update, conference news, dates and events
• Environmental issues
• Health & safety, including EC regulations
• Corrosion monitoring and plant health assessment
• The latest equipment and processes
• Corrosion cost and corrosion risk management.