In-Situ Loading Test in Deep Soft Soil and Back Analysis Based on Machine Learning Method

To investigate the effects of overlying surcharge on ground deformation in soft soil areas, in-situ loading tests are conducted to monitor soil behavior. Monitoring data, including surface settlement, lateral displacement, stratified settlement, and pore water pressure, are collected from 5th Januar...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:International journal of civil engineering (Tehran. Online) Ročník 23; číslo 8; s. 1701 - 1716
Hlavní autori: Liu, Zhicheng, Zhang, Wengang, Zhang, Xiaoguang
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Cham Springer International Publishing 01.08.2025
Springer Nature B.V
Predmet:
Civil Engineering
Engineering
Research Paper
Soil deformation
Soft soil
Genetic algorithm-backpropagation neural network
Back analysis
In-site loading test
ISSN:1735-0522, 2383-3874
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:To investigate the effects of overlying surcharge on ground deformation in soft soil areas, in-situ loading tests are conducted to monitor soil behavior. Monitoring data, including surface settlement, lateral displacement, stratified settlement, and pore water pressure, are collected from 5th January to 22nd February. The three-dimensional finite element model is established to analyze the loading test, and a Genetic Algorithm-Backpropagation Neural Network (GA-BPNN) model is employed for the back-analysis of soil parameters. The analysis of the monitoring data reveals that the cumulative settlement initially exhibits an uplift followed by settlement, while lateral displacement progressively decreases, with the influence range of the load extending to approximately 108 m. Sensitivity analysis identifies the internal friction angle φ and E ref oed of the 2-1A mud layer as the most significant parameters influencing horizontal displacement. The back analysis shows good agreement with the monitoring data, indicating that the model’s predictions align well with the observed results. The in-situ loading tests and back analysis results offer valuable insights into the deformation behavior of soils under surcharge loading and provide a robust framework for model calibration, ultimately contributing to the safety and stability of similar infrastructure projects.
Bibliografia:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1735-0522
2383-3874
DOI:10.1007/s40999-025-01135-8