Scholarlink

<p>Numerous relationships between Cone Penetration Test (CPT) and Standard Penetration Test (SPT) have been developed which consist of empirical formulas, statistical models, and machine learning models. However, these models often suffer from low prediction accuracy and limited generalizability when converting CPT data to SPT <i>N</i> or SPT <i>N</i><sub><i>60</i></sub>. In this study, a GA-GBM based model was developed to construct the CPT-SPT relationship in order to address the aforementioned issues. The raw database was segmented by intervals of soil behavior type index (<i>I</i><sub><i>c</i></sub>) using the GA, and the BP method was then employed to identify and eliminate outliers within each <i>I</i><sub><i>c</i></sub> interval. The preprocessed dataset was analyzed using the GBM technique with the results returned to the GA to iteratively adjust boundaries of each <i>I</i><sub><i>c</i></sub> interval (i.e. Method A) or obtain an optimal number of <i>I</i><sub><i>c</i></sub> interval (i.e. Method B) that optimizes the predictive performance of the proposed model. As compared to other widely used models reported in literature, the accuracy of predicted SPT <i>N</i><sub><i>60</i></sub> from CPT data was significantly improved with an R² of 0.80 and an RMSE of only 5.80. For the new dataset, R<sup>2</sup> of 0.73 was obtained by the proposed model which is much higher than other models. It is demonstrated the proposed GA-GBM model exhibits strong generalization capability and can predict SPT <i>N</i><sub><i>60</i></sub> more accurately. Overall, the proposed model offers new insights into the relationship between CPT and SPT.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A novel GA-GBM based model to construct CPT-SPT relationship

  • 期刊论文

  • 发表日期：

    2026年6月25日

查看全文
  • Shuai Fang,
  • Haoqing Xu,
  • Nan Zhang,
  • Xinpeng Lv,
  • Shi He

摘要

Numerous relationships between Cone Penetration Test (CPT) and Standard Penetration Test (SPT) have been developed which consist of empirical formulas, statistical models, and machine learning models. However, these models often suffer from low prediction accuracy and limited generalizability when converting CPT data to SPT N or SPT N60. In this study, a GA-GBM based model was developed to construct the CPT-SPT relationship in order to address the aforementioned issues. The raw database was segmented by intervals of soil behavior type index (Ic) using the GA, and the BP method was then employed to identify and eliminate outliers within each Ic interval. The preprocessed dataset was analyzed using the GBM technique with the results returned to the GA to iteratively adjust boundaries of each Ic interval (i.e. Method A) or obtain an optimal number of Ic interval (i.e. Method B) that optimizes the predictive performance of the proposed model. As compared to other widely used models reported in literature, the accuracy of predicted SPT N60 from CPT data was significantly improved with an R² of 0.80 and an RMSE of only 5.80. For the new dataset, R2 of 0.73 was obtained by the proposed model which is much higher than other models. It is demonstrated the proposed GA-GBM model exhibits strong generalization capability and can predict SPT N60 more accurately. Overall, the proposed model offers new insights into the relationship between CPT and SPT.