钢渣粉-矿渣粉复合胶凝材料力学性能的研究及预测

打开文本图片集

DOI：10.19860/j.cnki.issn1005-8249.2025.04.001

WANG Yifei14，WAITI Litipu²， JI Haojie14，LIU Zunqing1，3，4 （1.School of Trafic and Logistics Engineering， Xinjiang Agricultural University， Urumqi 830o52，China; 2. Xinjiang Transportation Investment and Construction Management Co. Ltd.， Urumqi 830OOO，China; 3. College of Hydraulic and Civil Engineering， Xinjiang Agricultural University， Urumqi 83O052，China; 4. Xinjiang Road Engineering Test and Inspection Research Center （Xinjiang Agricultural University Road Engineering Research Center），Urumqi 830O52，China）

Abstract：Tosystematicallyinvestigate theevolutionlawof mechanical propertiesof steeslag powder-slagpowdercomposite cementitious materials，mortar specimens were preparedusing diferent proportionsof slag powder，steel slag powder，and cement，andtheirflexuralandcompresivestrengthswere testedatcuringagesof1，3，7and28days；BPneuralnetworkand random forestmodelswere furtherestablished topredictthelater mechanicalpropertiesof thecompositecementitiousmaterial.

材料科学

The results showed that when 10% steel slag powder and 30% slagpowder were added，the mechanical properties were excellent，with flexural strength reaching 12. 22 MPa and compressive strength reaching 50.10MPa at 28 days；The prediction accuracyoftheBPneural networkwassignificantlysuperior tothatof therandom forest model，withmeanabsoluteerror （ MAE ），root mean square error（RMSE），and coeficient of determination （ R2 ）for compressive strength prediction being 1.823，2.136andO.956，respectively.This studyprovidesareliable methodfor predicting the performanceof industrial solid waste-basedcementitious materialsandofers theoreticalbasisandreference for promoting theapplicationof greenand lowcarbon building materials.

Key words： steel slag powder； slag powder; BP neural network；random forest； strength prediction

0 引言

我国水泥产业在快速发展的同时，也面临着石灰石资源日益紧缺和市场价格持续上涨的双重挑战。（剩余5759字）