The research investigates ensemble machine learning techniques to forecast high-performance concrete(HPC)compressive strength through analysis of Gradient Boosting Machines(GBM)together with Random Forest(RF)and Deep ...The research investigates ensemble machine learning techniques to forecast high-performance concrete(HPC)compressive strength through analysis of Gradient Boosting Machines(GBM)together with Random Forest(RF)and Deep Neural Network(DNN)performances.Previous experiment data served as model inputs for the machine learning systems that comprised cement,fly ash,blast furnace slag,water,superplasticizer,coarse aggregate,and fine aggregate for HPC compressive strength prediction.The research study utilizes input parameters and direct bypassing of dimensionality reduction to evaluate the performance of models that capture intricate nonlinear patterns from concrete compressive strength data.RF produced the most accurate results during training by establishing 0.9650 R^(2) measurements and 0.0798 RMSE indicators,thus demonstrating exceptional accuracy at a minimal error level.In testing,RF maintained its lead with an R^(2) of 0.9399,followed closely by GBM,while DNN showed slightly higher error rates.A comprehensive ranking analysis across multiple statistical metrics highlighted RF as the most dependable concrete compressive strength prediction model.Further,Regression Error Characteristic(REC)curves visually assessed model performance relative to error tolerance,revealing RF and GBM’s reliable accuracy across different thresholds.A Graphical User Interface(GUI)with user-oriented features connected to the prediction models was created for smooth system usage.The results indicate that RF provides accurate predictions for concrete compressive strength because of the effectiveness of ML models,according to this study.Predictions of tensile strength,modulus of elasticity,and fracture energy parameters in concrete materials become possible when categorized based on their compressive strength values.This approach significantly enhances structural analysis by reducing both cost and time requirements.展开更多
文摘The research investigates ensemble machine learning techniques to forecast high-performance concrete(HPC)compressive strength through analysis of Gradient Boosting Machines(GBM)together with Random Forest(RF)and Deep Neural Network(DNN)performances.Previous experiment data served as model inputs for the machine learning systems that comprised cement,fly ash,blast furnace slag,water,superplasticizer,coarse aggregate,and fine aggregate for HPC compressive strength prediction.The research study utilizes input parameters and direct bypassing of dimensionality reduction to evaluate the performance of models that capture intricate nonlinear patterns from concrete compressive strength data.RF produced the most accurate results during training by establishing 0.9650 R^(2) measurements and 0.0798 RMSE indicators,thus demonstrating exceptional accuracy at a minimal error level.In testing,RF maintained its lead with an R^(2) of 0.9399,followed closely by GBM,while DNN showed slightly higher error rates.A comprehensive ranking analysis across multiple statistical metrics highlighted RF as the most dependable concrete compressive strength prediction model.Further,Regression Error Characteristic(REC)curves visually assessed model performance relative to error tolerance,revealing RF and GBM’s reliable accuracy across different thresholds.A Graphical User Interface(GUI)with user-oriented features connected to the prediction models was created for smooth system usage.The results indicate that RF provides accurate predictions for concrete compressive strength because of the effectiveness of ML models,according to this study.Predictions of tensile strength,modulus of elasticity,and fracture energy parameters in concrete materials become possible when categorized based on their compressive strength values.This approach significantly enhances structural analysis by reducing both cost and time requirements.
