Performance Prediction of Eco-Friendly Concrete with Artificial Neural Networks (ANNs) DOI Creative Commons

Bheemshetty Kushal,

K. Anand Goud, Kranti Kumar

и другие.

E3S Web of Conferences, Год журнала: 2024, Номер 596, С. 01021 - 01021

Опубликована: Янв. 1, 2024

Concrete is renowned for its durability and versatility in construction, making it essential global infrastructure development. Its extensive use contributes significantly to carbon emissions environmental harm. In response, eco-friendly concrete has developed as a viable option, including elements such Alccofine Graphene oxide improve performance while lowering effect. this study Alccofine, which accounts 10% of the mix, replaces portion Ordinary Portland cement with supplemental substance obtained from industrial slag, minimizing concrete's footprint. oxide, at 0.045%, improves mechanical strength potentially increasing lifespan maintenance requirements when compared typical mixes. Artificial Neural Networks (ANNs) serve reliable way properly estimating compressive environmentally friendly concrete. By training ANNs on 80% datasets containing composition variables, curing conditions, other important parameters, models capture complicated, complex relationships was tested remaining 20% forecast minimal error. The Decision Tree Regressor scored precision 0.4679 testing 0.2955, Random Forest 0.4592 0.3010. Based these findings, Regressor's higher accuracy prediction establishes more effective model purpose. According results, ANN can effectively learn recognise patterns forecasting This demonstrates potential machine learning techniques optimize mixtures propel advancements technology.

Язык: Английский

Prediction of the Compressive Strength of Vibrocentrifuged Concrete Using Machine Learning Methods DOI Creative Commons
Alexey N. Beskopylny, Sergey A. Stel’makh, Evgenii M. Shcherban’

и другие.

Buildings, Год журнала: 2024, Номер 14(2), С. 377 - 377

Опубликована: Фев. 1, 2024

The determination of mechanical properties for different building materials is a highly relevant and practical field application machine learning (ML) techniques within the construction sector. When working with vibrocentrifuged concrete products structures, it crucial to consider factors related impact aggressive environments. Artificial intelligence methods can enhance prediction through use specialized algorithms materials’ strength determination. aim this article establish evaluate algorithms, specifically Linear Regression (LR), Support Vector (SVR), Random Forest (RF), CatBoost (CB), compressive in under diverse operational conditions. This achieved by utilizing comprehensive database experimental values obtained laboratory settings. following metrics were used analyze accuracy constructed regression models: Mean Absolute Error (MAE), Squared (MSE), Root-Mean-Square (RMSE), Percentage (MAPE) coefficient (R2). average MAPE range from 2% (RF, CB) 7% (LR, SVR) allowed us draw conclusions about possibility using “smart” development compositions quality control concrete, which ultimately entails improvement acceleration manufacture. best model, CatBoost, showed MAE = 0.89, MSE 4.37, RMSE 2.09, R2 0.94.

Язык: Английский

Процитировано

9
Prediction of the Properties of Vibro-Centrifuged Variatropic Concrete in Aggressive Environments Using Machine Learning Methods DOI Creative Commons
Alexey N. Beskopylny, Sergey A. Stel’makh, Evgenii M. Shcherban’

и другие.

Buildings, Год журнала: 2024, Номер 14(5), С. 1198 - 1198

Опубликована: Апрель 23, 2024

In recent years, one of the most promising areas in modern concrete science and technology reinforced structures is vibro-centrifugation concrete, which makes it possible to obtain elements with a variatropic structure. However, this area poorly studied there serious deficiency both scientific practical terms, expressed absence systematic knowledge life cycle management processes vibro-centrifuged concrete. Artificial intelligence methods are seen as for improving process managing such structures. The purpose study develop compare machine learning algorithms based on ridge regression, decision tree extreme gradient boosting (XGBoost) predicting compressive strength using database experimental values obtained under laboratory conditions. As result tests, dataset 664 samples was generated, describing influence aggressive environmental factors (freezing–thawing, chloride content, sulfate content number wetting–drying cycles) final characteristics use analytical techniques extract additional from data contributed resulting predictive properties models. result, average absolute percentage error (MAPE) best XGBoost algorithm 2.72%, mean (MAE) = 1.134627, squared (MSE) 4.801390, root-mean-square (RMSE) 2.191208 R2 0.93, allows conclude that “smart” improve by reducing time required assessment new

Язык: Английский

Процитировано

6
Advancing mix design prediction in 3D printed concrete: Predicting anisotropic compressive strength and slump flow DOI Creative Commons
Umair Jalil Malik, Raja Dilawar Riaz, Saif Ur Rehman

и другие.

Case Studies in Construction Materials, Год журнала: 2024, Номер 21, С. e03510 - e03510

Опубликована: Июль 11, 2024

Introducing 3D-concrete printing has started a revolution in the construction industry, presenting unique opportunities alongside undeniable challenges. Among these, major challenge is iterative process associated with mix design formulation, which results significant material and time consumption. This research uses machine learning (ML) techniques such as Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), Decision Tree Regression (DTR), Gaussian Process (GPR), Artificial Neural Network (ANN) to overcome these A dataset containing 21 constituent features 4 output properties (cast printed compressive strength, slump flow) was extracted from literature investigate relationship between performance. The models were assessed using range of evaluation metrics, including Mean Absolute Error (MAE), Root Squared (RMSE), (MSE), R-squared value. (GPR) yielded more favorable results. In case cast GPR achieved an R2 value 0.9069, along RMSE, MSE, MAE values 13.04, 170.12, 9.40, respectively. similar trend observed for strengths directions 1, 2, 3. exceeding 0.91 all directions, accompanied by significantly lower RMSE (below 4.1). also validated four designs. These mixes 3D tested strength flow. GPR's average error 10.55 %, while SVM slightly 9.38 %. Overall, this work presents novel approach optimizing 3D-printed concrete enabling prediction flow directly design. can facilitate fabrication structures that fulfill necessary printability requirements.

Язык: Английский

Процитировано

5
A Novel Identification Approach Using RFECV–Optuna–XGBoost for Assessing Surrounding Rock Grade of Tunnel Boring Machine Based on Tunneling Parameters DOI Creative Commons
Kebin Shi, R Shi, Tao Fu

и другие.

Applied Sciences, Год журнала: 2024, Номер 14(6), С. 2347 - 2347

Опубликована: Март 11, 2024

In order to solve the problem of poor adaptability TBM digging process changes in geological conditions, a new model is proposed. An ensemble learning prediction based on XGBoost, combined with Optuna for hyperparameter optimization, enables real-time identification surrounding rock grades. Firstly, an original dataset was established tunneling parameters under different grades KS tunnel. Subsequently, RF–RFECV employed feature selection and six features were selected as optimal subset according importance measure random forest used construct XGBoost model. Furthermore, framework utilized optimize hyperparameters validated by applying Tunnel. verify applicability efficiency proposed grade identification, results five commonly machine models, Optuna–XGBoost, Random Forest (RF), Gradient Boosting Decision Tree (GBDT), (DT), PSO–XGBoost, compared analyzed. The main conclusions are follows: method improved accuracy 8.26%. Among subset, T most essential model’s input, while PR least important. Optuna–XGBoost this paper had higher (0.9833), precision (0.9803), recall (0.9813), F1 score (0.9807) than other models could be effective means lithological grade.

Язык: Английский

Процитировано

4
Optimizing high-strength concrete compressive strength with explainable machine learning DOI Creative Commons
Sanjog Chhetri Sapkota,

Christina Panagiotakopoulou,

Dipak Dahal

и другие.

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2025, Номер 8(3)

Опубликована: Фев. 3, 2025

Язык: Английский

Процитировано

0
Optimizing compressive strength prediction in eco-friendly recycled concrete via artificial intelligence models DOI
Lihua Chen, Younes Nouri,

Nazanin Allahyarsharahi

и другие.

Multiscale and Multidisciplinary Modeling Experiments and Design, Год журнала: 2024, Номер 8(1)

Опубликована: Ноя. 7, 2024

Язык: Английский

Процитировано

2
Experimental and Machine Learning-Based Investigation of Cyclic Thermal Resilience of Geopolymer Concrete with Slag and Glass Powders DOI
Ashwin Raut, T. Vamsi Nagaraju, Mohammed Rihan Maaze

и другие.

Iranian Journal of Science and Technology Transactions of Civil Engineering, Год журнала: 2024, Номер unknown

Опубликована: Дек. 27, 2024

Язык: Английский

Процитировано

2
Performance Prediction of Eco-Friendly Concrete with Artificial Neural Networks (ANNs) DOI Creative Commons

Bheemshetty Kushal,

K. Anand Goud, Kranti Kumar

и другие.

E3S Web of Conferences, Год журнала: 2024, Номер 596, С. 01021 - 01021

Опубликована: Янв. 1, 2024

Concrete is renowned for its durability and versatility in construction, making it essential global infrastructure development. Its extensive use contributes significantly to carbon emissions environmental harm. In response, eco-friendly concrete has developed as a viable option, including elements such Alccofine Graphene oxide improve performance while lowering effect. this study Alccofine, which accounts 10% of the mix, replaces portion Ordinary Portland cement with supplemental substance obtained from industrial slag, minimizing concrete's footprint. oxide, at 0.045%, improves mechanical strength potentially increasing lifespan maintenance requirements when compared typical mixes. Artificial Neural Networks (ANNs) serve reliable way properly estimating compressive environmentally friendly concrete. By training ANNs on 80% datasets containing composition variables, curing conditions, other important parameters, models capture complicated, complex relationships was tested remaining 20% forecast minimal error. The Decision Tree Regressor scored precision 0.4679 testing 0.2955, Random Forest 0.4592 0.3010. Based these findings, Regressor's higher accuracy prediction establishes more effective model purpose. According results, ANN can effectively learn recognise patterns forecasting This demonstrates potential machine learning techniques optimize mixtures propel advancements technology.

Язык: Английский

Процитировано

0