Prediction of compressive strength of High-Performance Concrete by Random Forest algorithm
Liu Pengcheng, Xianguo Wu, Hongyu Cheng, Zheng Tiemei
Abstract
Abstract The prediction results of the compressive strength of high-performance concrete (HPC) based on intelligent algorithms are seriously affected by the input variables. In this study, the Random Forest algorithm (RF) is introduced to optimize the number of input variables by evaluating the importance of influencing factors, and then predict the 28-day compressive strength through Random Forest Regression. The results show that this method is effective for the optimization of input variables, and when the parameters are set within a reasonable range, better prediction results can be obtained than non-variable optimization.
Topics & Concepts
Random forestCompressive strengthRange (aeronautics)Set (abstract data type)Computer scienceRandom variableAlgorithmVariable (mathematics)Optimization algorithmCompressed sensingVariablesSensitivity (control systems)Mathematical optimizationStatisticsMathematicsMachine learningEngineeringMaterials scienceProgramming languageMathematical analysisComposite materialElectronic engineeringAerospace engineeringInnovative concrete reinforcement materialsInfrastructure Maintenance and MonitoringConcrete and Cement Materials Research