Search results

1 – 3 of 3
Per page
102050
Citations:
Loading...
Access Restricted. View access options
Article
Publication date: 26 November 2024

Shikha Pandey, Yogesh Iyer Murthy and Sumit Gandhi

This study aims to investigate the use of 20 commonly applied regression methods to predict concrete corrosion. These models are assessed for accuracy and interpretability using…

35

Abstract

Purpose

This study aims to investigate the use of 20 commonly applied regression methods to predict concrete corrosion. These models are assessed for accuracy and interpretability using SHapley Additive Explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) analysis to provide structural health monitoring prognostic tools.

Design/methodology/approach

This study evaluated model performance using standard measures including root mean square error (RMSE), mean square error (MSE), R-squared (R2) and mean absolute error (MAE). Interpretability was evaluated using SHAP and LIME. The X and Y distances, concrete age, relative humidity and temperature were input parameters, whereas half-cell potential (HCP) values were considered output. The experimental data set consisted of observations taken for 270 days.

Findings

Gaussian process regression (GPR) models with rational quadratic, square exponential and matern 5/2 kernels outperformed others, with RMSE values around 16.35, MSE of roughly 267.50 and R2 values near 0.964. Bagged and boosted ensemble models performed well, with RMSE around 17.20 and R2 values over 0.95. Linear approaches, such as efficient linear least squares and linear SVM, resulted in much higher RMSE values (approximately 40.17 and 40.02) and lower R2 values (approximately 0.79), indicating decreased prediction accuracy.

Practical implications

The findings highlight the effectiveness of GPR models in forecasting corrosion in concrete buildings. The use of both SHAP and LIME for model interpretability improves the transparency of predictive maintenance models, making them more reliable for practical applications.

Social implications

Safe infrastructure is crucial to public health. Predicting corrosion and other structural problems improves the safety of buildings, bridges and other community-dependent structures. Public safety, infrastructure durability and transportation and utility interruptions are improved by reducing catastrophic breakdowns.

Originality/value

This study reduces the gap between model accuracy and interpretability in predicting concrete corrosion by proposing a data-driven method for structural health monitoring. The combination of GPR models and ensemble approaches provides a solid foundation for future research and practical applications in predictive maintenance. This comprehensive approach underscores the potential of data-driven methods for predictive maintenance in concrete structures, with implications for broader applications in various industries.

Details

Anti-Corrosion Methods and Materials, vol. 72 no. 1
Type: Research Article
ISSN: 0003-5599

Keywords

Access Restricted. View access options
Article
Publication date: 1 August 2024

Shikha Pandey, Yogesh Iyer Murthy and Sumit Gandhi

This study aims to assess support vector machine (SVM) models' predictive ability to estimate half-cell potential (HCP) values from input parameters by using Bayesian…

16

Abstract

Purpose

This study aims to assess support vector machine (SVM) models' predictive ability to estimate half-cell potential (HCP) values from input parameters by using Bayesian optimization, grid search and random search.

Design/methodology/approach

A data set with 1,134 rows and 6 columns is used for principal component analysis (PCA) to minimize dimensionality and preserve 95% of explained variance. HCP is output from temperature, age, relative humidity, X and Y lengths. Root mean square error (RMSE), R-squared, mean squared error (MSE), mean absolute error, prediction speed and training time are used to measure model effectiveness. SHAPLEY analysis is also executed.

Findings

The study reveals variations in predictive performance across different optimization methods, with RMSE values ranging from 18.365 to 30.205 and R-squared values spanning from 0.88 to 0.96. Additionally, differences in training times, prediction speeds and model complexities are observed, highlighting the trade-offs between model accuracy and computational efficiency.

Originality/value

This study contributes to the understanding of SVM model efficacy in HCP prediction, emphasizing the importance of optimization techniques, model complexity and dimensionality reduction methods such as PCA.

Details

Anti-Corrosion Methods and Materials, vol. 71 no. 6
Type: Research Article
ISSN: 0003-5599

Keywords

Access Restricted. View access options
Article
Publication date: 31 May 2024

Shikha Pandey, Sumit Gandhi and Yogesh Iyer Murthy

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…

51

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.

Details

Anti-Corrosion Methods and Materials, vol. 71 no. 5
Type: Research Article
ISSN: 0003-5599

Keywords

1 – 3 of 3
Per page
102050