Research on intelligent prediction of optimal compaction parameters for graded gravel based on PSO-ML-AdaBoost model
To achieve the rapid and accurate determination of optimal compaction parameters for graded gravel in high-speed railway subgrades,the research was conducted on optimal compaction parameters and the intelligent prediction of fillers.First,based on the method of determining vibration compaction parameters under resonance,the optimal frequency(fop)and optimal water content(wop)for graded gravel under the optimal compaction state were obtained by combining the compaction physical and mechanics indicators.Second,the relationship between the features of graded gravel and fop/wop was established through filler performance tests.The Grey Relational Analysis(GRA)algorithm was applied to determine the key features influencing fop and wop.Lastly,the dominant features were used as input parameters to establish three typical Machine Learning(ML)models for predicting fop and wop.The PSO-ML-AdaBoost model was established using the AdaBoost algorithm to address limitations in basic ML algorithms.The optimal prediction model was determined based on a three-level assessment system for prediction model,and the reliability of the optimal prediction model was further verified through ablation analysis.The results indicated that setting wop as the critical water content and fop as the inherent frequency of the filler can optimize the compacted state of graded gravel.The dominant features influencing fop and wop included the maximum particle size(dmax),grading parameters(b,m),coarse aggregate aspect ratio(Ei),Los Angeles abrasion(Laa),and water absorption rates(Wac,Waf).Based on the comprehensive evaluation results of the three-level assessment system,the comprehensive evaluation index(Cei)values for predicting fop/wop using the PSO-BPNN-AdaBoost model were 12.264 5/1.838 2,which were lower than those of other ML integration algorithms,suggesting it as the optimal predictive model.Combining the results of the ablation analysis,it was indicated that the input parameters of the PSO-BPNN-AdaBoost model had a consistent impact on the predictions of fop and wop,consistent with the results obtained by GRA,further confirming the reliability of the optimal predictive model.The research results provide novel insights into determining the optimal compaction parameters for subgrade fillers and offer theoretical guidance for the intelligent assessment of compaction quality in high-speed railway subgrades.
high-speed railway graded gravelvibratory compactionkey featuresmachine learningablation study
万方数据
维普
