基于网格搜索与支持向量回归的粉煤灰混凝土抗压强度预测研究

Prediction of the compressive strength of fly ash concrete based onhybridizing grid search and support vector regression

支持向量回归(support vector regression,SVR)已被应用于混凝土力学性能的预测,但其超参数的选择一直是影响预测精度的关键因素.本研究提出一种结合网格搜索方法(grid search,GS)和支持向量回归模型的混合机器学习,即GS-SVR模型,用于混凝土抗压强度预测和敏感性分析.该混合模型在从文献中检索到的98个数据集上进行了训练和测试,并在相同的数据集下将模型与原始SVR模型进行性能比较.所获得R为0.981,MSE为3.44,RMSE为1.85,MAE为1.17,MAPE为0.05.研究结果表明:所提出的GS-SVR模型可以作为后续相关研究中抗压强度预测的一个候选方法.此外,还开发了一个图形用户界面(GUI),以便在进行大量的实验室或现场工作之前,能够提供一些初步的估计结果.最后,分析了随机环境下各变量对抗压强度的影响.

Support vector regression(SVR)has been applied to the prediction of mechanical properties of concrete,but the selection of its hyper-parameters has been a key factor affecting the prediction accuracy.A hybrid machine learning combines the SVR model and grid search(GS),namely the GS-SVR model,is proposed to predict the compressive strength of concrete and to analyze its sensitivity in this work.The hybrid model is trained and tested on a total of 98 data sets retrieved from literature,and the model performance is compared with that of the original SVR model on the same data sets.The results obtained for R,MSE,RMSE,MAE and MAPE are 0.981,3.44,1.85,1.17 and 0.05,respectively,demonstrating that the GS-SVR model proposed can be a candidate method for compressive strength prediction in subsequent related studies.Additionally,a graphical user interface(GUI)is developed to conveniently provide some initial estimates of the outcomes before performing extensive laboratory or fieldwork.Finally,the effect of each variable on the compressive strength in a random environment is analyzed.