日韩欧美国产综合_国产成人精品网址_欧美大波大乳巨大乳_激情综合五月网_99视频免费观看_欧美日韩国产综合久久_久久在线视频_国产小黄视频_丁香激情五月少妇_国产在线98福利播放视频

        戴   汀1 ,2 ,  李向國(guó)1 ,2 ,  王    凱3

( 1 .  道路與鐵道工程安全保障省部共建教育部重點(diǎn)實(shí)驗(yàn)室（石家莊鐵道大學(xué)），石家莊 050043 ;   2.  石家莊鐵道大學(xué) 土木工程學(xué)院 ，石家莊 050043 ;  3 .   中建三局一公司基礎(chǔ)分公司 ，武漢 430064)

摘   要 ：針對(duì)傳統(tǒng)方法難以快速精準(zhǔn)預(yù)測(cè)隴中地區(qū)黃土濕陷性的問(wèn)題 ，開(kāi)展基于支持向量機(jī)回歸的黃土濕 陷性預(yù)測(cè)研究。研究依托隴中地區(qū)某鐵路項(xiàng)目 ，于人工探井中采集樣土進(jìn)行室內(nèi)土工試驗(yàn) ， 以獲取土的相關(guān)物 性指標(biāo)數(shù)據(jù)。通文獻(xiàn)分析法和數(shù)理分析 ，探究黃土濕陷系數(shù)與各物性指標(biāo)的相關(guān)性。在此基礎(chǔ)上 ，基于支持 向量機(jī) ，采用高斯核函數(shù)構(gòu)建黃土濕陷性預(yù)測(cè)模型。以 45 組試驗(yàn)數(shù)據(jù)作為訓(xùn)練集 ，9 組作為測(cè)試集進(jìn)行誤差分 析。結(jié)果表明：預(yù)測(cè)模型訓(xùn)練集平均絕對(duì)誤差為 0. 003 、平均偏差誤差為 0. 001 、均方根誤差為 0. 015 9 ;  測(cè)試集 平均絕對(duì)誤差為 0. 013 2 、平均偏差誤差為 0. 001 8 、均方根誤差為 0. 015 ,  表明該模型預(yù)測(cè)精度良好 ，可有效預(yù) 測(cè)隴中地區(qū)黃土濕陷系數(shù) ，為實(shí)際工程中黃土濕陷性的預(yù)測(cè)提供了可靠的新方法。

關(guān)鍵詞：黃土濕陷性 ；物性指標(biāo) ；相關(guān)性 ；支持向量機(jī) ；預(yù)測(cè)模型

中圖分類(lèi)號(hào)：TU444           文獻(xiàn)標(biāo)志碼：A   

文章編號(hào)： 1005- 8249   (2025)  03- 0073- 05 

DOI:10. 19860/j.cnki.issn1005 - 8249.2025 .03 .014

DAI Ting1 , 2  ,  LI Xiangguo1 , 2  ,  WANG Kai3

(1. Key Laboratory of Road and Railway Engineering Safety and security, Ministry of Education (Shijiazhuang Railway University), Shijiazhuang 050043, China;

2. School of Civil Engineering, Shijiazhuang University of Railways, Shijiazhuang 050043, China

3. Basic Branch of China Construction Third Bureau One Company, Wuhan 430064, Hubei)

Abstract:   To address the challenges in rapid and accurate prediction of loess collapsibility in Central Gansu using conventional methods, a support vector machine regression-based predictive model was developed. Leveraging data from a railway project in this region, soil samples collected from manually excavated test pits underwent comprehensive laboratory geotechnical testing to obtain key physical property indices.Correlations between loess collapse coefficients and physical indices were systematically investigated through literature analysis and mathematical statistics. A Gaussian kernel function-based SVM prediction model was subsequently established. The model was trained with 45 experimental datasets, while 15 datasets were utilized for validation and error analysis. Results demonstrate that the model achieves a mean absolute error (MAE) of 0.003, mean bias error (MBE) of 0.001, and root mean square error (RMSE) of 0.0159 on the training set. For the testing set, performance metrics indicate MAE=0.0132, MBE=0.0018, and RMSE=0.015. These findings confirm the model's high predictive accuracy for estimating loess collapse coefficients in Central Gansu, providing a reliable novel methodology for practical engineering applications.

Key words:   loess collapsibility ; physical property index ; correlation ; support vector machine ; prediction model

基金項(xiàng)目： 國(guó)家自然科學(xué)基金  (52378453) 。

作者簡(jiǎn)介：戴   汀  (1998—) ,  男 ，碩士研究生 ，研究方向： 黃土濕陷性。

通信作者：李向國(guó)  (1973—) ,  男 ，博士 ，教授 ，研究方向：鐵路線路結(jié)構(gòu)設(shè)計(jì) 、施工等方面。

收稿日期：2025 - 01 - 18