โก Quick Summary
This study explores the use of machine learning algorithms to predict the displacements of pile tops and the ground surface around piles, addressing issues caused by the soil squeezing effect. The AdaBoost-BP model demonstrated superior prediction accuracy compared to traditional methods, particularly for small sample datasets.
๐ Key Details
- ๐ Dataset: Various sample datasets analyzed
- โ๏ธ Technology: AdaBoost-BP model, Random Forest (RF), Deep Neural Networks (DNN), and Back Propagation (BP) model
- ๐ Performance: AdaBoost-BP model outperformed BP model in small datasets
- ๐ Key Influencing Factors: Horizontal distance, angle, resting time, moisture content, relative density, internal friction angle
๐ Key Takeaways
- ๐ Machine learning offers a novel approach to predict displacements around piles.
- ๐ก AdaBoost-BP model enhances the learning ability of traditional BP neural networks.
- ๐ Prediction accuracy is significantly higher for small datasets using AdaBoost-BP compared to BP.
- ๐ Horizontal distance and angle are the most critical factors influencing displacements.
- ๐ง Moisture content and relative density also play significant roles in displacement predictions.
- ๐ Quantile regression analysis reveals negative correlation with horizontal distance and positive correlation with resting time and moisture content.
- ๐ค Machine learning models like DNN outperform traditional cylindrical hole expansion methods.
๐ Background
The soil squeezing effect around pile groups can lead to significant structural issues, including broken piles and damage to adjacent buildings and utilities. Traditional methods of predicting these displacements often fall short, prompting the need for innovative solutions. The integration of artificial intelligence and machine learning presents a promising avenue for enhancing prediction accuracy and reliability in geotechnical engineering.
๐๏ธ Study
This research focused on developing a predictive model for the displacements of pile tops and ground surfaces around piles, utilizing the AdaBoost-BP model in conjunction with other machine learning techniques. The study aimed to identify key factors influencing these displacements and to compare the performance of various models, including Random Forest and Deep Neural Networks.
๐ Results
The findings indicated that the AdaBoost-BP model significantly improved prediction accuracy, especially for small sample datasets. In contrast, the traditional BP model exhibited lower accuracy compared to other machine learning models when larger datasets were analyzed. The study identified that the horizontal distance and angle between the bearing platform and pile tops were the most influential factors affecting displacements.
๐ Impact and Implications
The implications of this study are profound for the field of geotechnical engineering. By leveraging machine learning algorithms, engineers can achieve more accurate predictions of pile displacements, potentially preventing structural failures and enhancing the safety of construction projects. This research paves the way for further exploration of AI applications in civil engineering, promising improved methodologies for managing soil-structure interactions.
๐ฎ Conclusion
This study highlights the transformative potential of machine learning in predicting pile displacements due to soil squeezing effects. The superior performance of the AdaBoost-BP model underscores the importance of adopting advanced technologies in engineering practices. Continued research in this area could lead to significant advancements in the safety and reliability of construction practices worldwide.
๐ฌ Your comments
What are your thoughts on the application of machine learning in geotechnical engineering? We would love to hear your insights! ๐ฌ Share your comments below or connect with us on social media:
Prediction of the displacements of the pile tops and ground surface around piles based on machine learning algorithms.
Abstract
The soil squeezing effect of pile groups may cause displacements and deformation at the pile tops and ground surface around piles. In severe cases, it can cause problems such as broken piles, cracking of adjacent buildings or cracking of pipes. Artificial intelligence provides a new way to predict horizontal displacements of the pile tops and ground surface around piles caused by soil squeezing effect. The adaptive boosting (AdaBoost) algorithm was applied to the back propagation (BP) neural network model to form the Adaboost-BP model, which improved the learning ability of the BP neural network. For small sample datasets, the prediction accuracy of AdaBoost-BP model, Random Forest (RF) model and Deep Neural Networks (DNN) model is higher than that of BP model. For large sample datasets, the prediction accuracy of various models has improved, but the BP model is lower than that of other models. Analysis shows that the horizontal distance and angle between the center of the bearing platform and the center of the pile tops (or ground surface monitoring points) are the two most important influencing factors. The resting time is also an important influencing factor. Moisture content, relative density, and internal friction angle have a more significant influence on the horizontal displacements of the pile tops and ground surface around piles than other soil property indexes. Quantile regression analysis shows that the horizontal displacements is negatively correlated with the horizontal distance, and positively correlated with the rest time and moisture content. The prediction accuracy of machine learning algorithms (such as DNN) is higher than that of the cylindrical hole expansion method.
Author: [‘Li P’, ‘Guo S’, ‘Liang M’, ‘Lu Q’]
Journal: Sci Rep
Citation: Li P, et al. Prediction of the displacements of the pile tops and ground surface around piles based on machine learning algorithms. Prediction of the displacements of the pile tops and ground surface around piles based on machine learning algorithms. 2026; (unknown volume):(unknown pages). doi: 10.1038/s41598-026-36502-5