A Framework for Determining the Optimal Vibratory Frequency of Graded Gravel Fillers Using Hammering Modal Approach and ANN
To address the uncertainty of optimal vibratory frequency <i>f<sub>ov</sub></i> of high-speed railway graded gravel (<i>HRGG</i>) and achieve high-precision prediction of the <i>f<sub>ov</sub></i>, the following research was conducted. Firs...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/2/689 |
| _version_ | 1827369341231824896 |
|---|---|
| author | Xianpu Xiao Taifeng Li Feng Lin Xinzhi Li Zherui Hao Jiashen Li |
| author_facet | Xianpu Xiao Taifeng Li Feng Lin Xinzhi Li Zherui Hao Jiashen Li |
| author_sort | Xianpu Xiao |
| collection | DOAJ |
| description | To address the uncertainty of optimal vibratory frequency <i>f<sub>ov</sub></i> of high-speed railway graded gravel (<i>HRGG</i>) and achieve high-precision prediction of the <i>f<sub>ov</sub></i>, the following research was conducted. Firstly, commencing with vibratory compaction experiments and the hammering modal analysis method, the resonance frequency <i>f</i><sub>0</sub> of <i>HRGG</i> fillers, varying in compactness <i>K</i>, was initially determined. The correlation between <i>f</i><sub>0</sub> and <i>f<sub>ov</sub></i> was revealed through vibratory compaction experiments conducted at different vibratory frequencies. This correlation was established based on the compaction physical–mechanical properties of <i>HRGG</i> fillers, encompassing maximum dry density <i>ρd</i><sub>max</sub>, stiffness <i>K<sub>rd</sub></i>, and bearing capacity coefficient <i>K</i><sub>20</sub>. Secondly, the gray relational analysis algorithm was used to determine the key feature influencing the <i>f<sub>ov</sub></i> based on the quantified relationship between the filler feature and <i>f<sub>ov</sub></i>. Finally, the key features influencing the <i>f<sub>ov</sub></i> were used as input parameters to establish the artificial neural network prediction model (<i>ANN-PM</i>) for <i>f<sub>ov</sub></i>. The predictive performance of <i>ANN-PM</i> was evaluated from the ablation study, prediction accuracy, and prediction error. The results showed that the <i>ρ<sub>d</sub></i><sub>max</sub>, <i>K<sub>rd</sub></i>, and <i>K</i><sub>20</sub> all obtained optimal states when <i>f<sub>ov</sub></i> was set as <i>f</i><sub>0</sub> for different gradation <i>HRGG</i> fillers. Furthermore, it was found that the key features influencing the <i>f<sub>ov</sub></i> were determined to be the maximum particle diameter <i>d</i><sub>max</sub>, gradation parameters <i>b</i> and <i>m</i>, flat and elongated particles in coarse aggregate <i>Q<sub>e</sub></i>, and the Los Angeles abrasion of coarse aggregate <i>LAA</i>. Among them, the influence of <i>d</i><sub>max</sub> on the <i>ANN-PM</i> predictive performance was the most significant. On the training and testing sets, the goodness-of-fit <i>R</i><sup>2</sup> of <i>ANN-PM</i> all exceeded 0.95, and the prediction errors were small, which indicated that the accuracy of <i>ANN-PM</i> predictions was relatively high. In addition, it was clear that the <i>ANN-PM</i> exhibited excellent robust performance. The research results provide a novel method for determining the <i>f<sub>ov</sub></i> of subgrade fillers and provide theoretical guidance for the intelligent construction of high-speed railway subgrades. |
| first_indexed | 2024-03-08T09:46:44Z |
| format | Article |
| id | doaj.art-86d1732162d64ceea3b52b8bfeb0aa4d |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-08T09:46:44Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-86d1732162d64ceea3b52b8bfeb0aa4d2024-01-29T14:18:24ZengMDPI AGSensors1424-82202024-01-0124268910.3390/s24020689A Framework for Determining the Optimal Vibratory Frequency of Graded Gravel Fillers Using Hammering Modal Approach and ANNXianpu Xiao0Taifeng Li1Feng Lin2Xinzhi Li3Zherui Hao4Jiashen Li5China Academy of Railway Sciences Co., Ltd., Beijing 100081, ChinaChina Academy of Railway Sciences Co., Ltd., Beijing 100081, ChinaChina Academy of Railway Sciences Co., Ltd., Beijing 100081, ChinaDepartment of Civil Engineering, Shijiazhuang Tiedao University, Shijiazhuang 050043, ChinaDepartment of Civil Engineering, Central South University, Changsha 410075, ChinaDepartment of Civil Engineering, Central South University, Changsha 410075, ChinaTo address the uncertainty of optimal vibratory frequency <i>f<sub>ov</sub></i> of high-speed railway graded gravel (<i>HRGG</i>) and achieve high-precision prediction of the <i>f<sub>ov</sub></i>, the following research was conducted. Firstly, commencing with vibratory compaction experiments and the hammering modal analysis method, the resonance frequency <i>f</i><sub>0</sub> of <i>HRGG</i> fillers, varying in compactness <i>K</i>, was initially determined. The correlation between <i>f</i><sub>0</sub> and <i>f<sub>ov</sub></i> was revealed through vibratory compaction experiments conducted at different vibratory frequencies. This correlation was established based on the compaction physical–mechanical properties of <i>HRGG</i> fillers, encompassing maximum dry density <i>ρd</i><sub>max</sub>, stiffness <i>K<sub>rd</sub></i>, and bearing capacity coefficient <i>K</i><sub>20</sub>. Secondly, the gray relational analysis algorithm was used to determine the key feature influencing the <i>f<sub>ov</sub></i> based on the quantified relationship between the filler feature and <i>f<sub>ov</sub></i>. Finally, the key features influencing the <i>f<sub>ov</sub></i> were used as input parameters to establish the artificial neural network prediction model (<i>ANN-PM</i>) for <i>f<sub>ov</sub></i>. The predictive performance of <i>ANN-PM</i> was evaluated from the ablation study, prediction accuracy, and prediction error. The results showed that the <i>ρ<sub>d</sub></i><sub>max</sub>, <i>K<sub>rd</sub></i>, and <i>K</i><sub>20</sub> all obtained optimal states when <i>f<sub>ov</sub></i> was set as <i>f</i><sub>0</sub> for different gradation <i>HRGG</i> fillers. Furthermore, it was found that the key features influencing the <i>f<sub>ov</sub></i> were determined to be the maximum particle diameter <i>d</i><sub>max</sub>, gradation parameters <i>b</i> and <i>m</i>, flat and elongated particles in coarse aggregate <i>Q<sub>e</sub></i>, and the Los Angeles abrasion of coarse aggregate <i>LAA</i>. Among them, the influence of <i>d</i><sub>max</sub> on the <i>ANN-PM</i> predictive performance was the most significant. On the training and testing sets, the goodness-of-fit <i>R</i><sup>2</sup> of <i>ANN-PM</i> all exceeded 0.95, and the prediction errors were small, which indicated that the accuracy of <i>ANN-PM</i> predictions was relatively high. In addition, it was clear that the <i>ANN-PM</i> exhibited excellent robust performance. The research results provide a novel method for determining the <i>f<sub>ov</sub></i> of subgrade fillers and provide theoretical guidance for the intelligent construction of high-speed railway subgrades.https://www.mdpi.com/1424-8220/24/2/689high-speed railway subgradevibration compactionoptimal vibration frequencykey features<i>ANN</i> |
| spellingShingle | Xianpu Xiao Taifeng Li Feng Lin Xinzhi Li Zherui Hao Jiashen Li A Framework for Determining the Optimal Vibratory Frequency of Graded Gravel Fillers Using Hammering Modal Approach and ANN Sensors high-speed railway subgrade vibration compaction optimal vibration frequency key features <i>ANN</i> |
| title | A Framework for Determining the Optimal Vibratory Frequency of Graded Gravel Fillers Using Hammering Modal Approach and ANN |
| title_full | A Framework for Determining the Optimal Vibratory Frequency of Graded Gravel Fillers Using Hammering Modal Approach and ANN |
| title_fullStr | A Framework for Determining the Optimal Vibratory Frequency of Graded Gravel Fillers Using Hammering Modal Approach and ANN |
| title_full_unstemmed | A Framework for Determining the Optimal Vibratory Frequency of Graded Gravel Fillers Using Hammering Modal Approach and ANN |
| title_short | A Framework for Determining the Optimal Vibratory Frequency of Graded Gravel Fillers Using Hammering Modal Approach and ANN |
| title_sort | framework for determining the optimal vibratory frequency of graded gravel fillers using hammering modal approach and ann |
| topic | high-speed railway subgrade vibration compaction optimal vibration frequency key features <i>ANN</i> |
| url | https://www.mdpi.com/1424-8220/24/2/689 |
| work_keys_str_mv | AT xianpuxiao aframeworkfordeterminingtheoptimalvibratoryfrequencyofgradedgravelfillersusinghammeringmodalapproachandann AT taifengli aframeworkfordeterminingtheoptimalvibratoryfrequencyofgradedgravelfillersusinghammeringmodalapproachandann AT fenglin aframeworkfordeterminingtheoptimalvibratoryfrequencyofgradedgravelfillersusinghammeringmodalapproachandann AT xinzhili aframeworkfordeterminingtheoptimalvibratoryfrequencyofgradedgravelfillersusinghammeringmodalapproachandann AT zheruihao aframeworkfordeterminingtheoptimalvibratoryfrequencyofgradedgravelfillersusinghammeringmodalapproachandann AT jiashenli aframeworkfordeterminingtheoptimalvibratoryfrequencyofgradedgravelfillersusinghammeringmodalapproachandann AT xianpuxiao frameworkfordeterminingtheoptimalvibratoryfrequencyofgradedgravelfillersusinghammeringmodalapproachandann AT taifengli frameworkfordeterminingtheoptimalvibratoryfrequencyofgradedgravelfillersusinghammeringmodalapproachandann AT fenglin frameworkfordeterminingtheoptimalvibratoryfrequencyofgradedgravelfillersusinghammeringmodalapproachandann AT xinzhili frameworkfordeterminingtheoptimalvibratoryfrequencyofgradedgravelfillersusinghammeringmodalapproachandann AT zheruihao frameworkfordeterminingtheoptimalvibratoryfrequencyofgradedgravelfillersusinghammeringmodalapproachandann AT jiashenli frameworkfordeterminingtheoptimalvibratoryfrequencyofgradedgravelfillersusinghammeringmodalapproachandann |