使用机器学习方法预测和评估浅基础的结算.
Thi Thanh Huong Ngo1, Van Quan Tran2
1Faculty of Civil Engineering, University of Transport Technology, Thanh Xuan, Hanoi, Vietnam.
Science progress
|December 13, 2024
概括
预测浅层基础解决方案至关重要. 这项研究发现,标准的梯度增强和随机森林模型,没有优化,在定居点预测方面表现最好,突出标准透测试 (SPT) 和脚宽度作为关键因素.
科学领域:
- 地质技术工程 地质技术工程
- 计算力学 计算力学 计算力学
- 土木工程 土木工程是指土木工程.
背景情况:
- 准确预测浅基础沉积的情况对于结构完整性和安全性至关重要.
- 机器学习为地质技术分析提供了有前途的工具,但模型优化需要仔细评估.
- 了解各种参数对基础结算的影响对于设计至关重要.
研究的目的:
- 评估粒子群集优化 (PSO) 在增强机器学习模型的有效性,以预测浅基础定居点.
- 为了比较梯度增强 (GB),随机森林 (RF),支向量机 (SVM) 和K-近邻 (KNN) 模型的性能,无论是带有PSO调还是没有PSO调.
- 通过敏感性分析,确定影响浅基础结算的关键变量.
主要方法:
- 开发和评估四种混合机器学习模型:GB-PSO,RF-PSO,SVM-PSO和KNN-PSO.
- 使用 189 个样本的实验数据集进行模型培训和验证.
- 使用K折交叉验证,R2,RMSE,MAE和MAPE指标进行严格的绩效评估.
- 灵敏度分析采用沙普利添加式解释 (SHAP) 来确定变量的重要性.
主要成果:
- 粒子集群优化 (PSO) 并没有持续提高机器学习模型的预测准确性.
- 原始梯度增强 (GB) 和随机森林 (RF) 模型与其PSO优化的对应模型相比,表现优越.
- 平均标准透测试 (SPT) 吹数和脚宽度 (B) 被确定为影响结算预测的最重要的变量.
- 脚部嵌入率 (Df/B) 和净施加压力 (q) 也对结算预测产生了相当大的影响.
结论:
- 标准的机器学习模型,特别是GB和RF,对于预测没有PSO增强的浅基础解决非常有效.
- 标准透试验 (SPT) 吹数和脚宽度 (B) 是工程师在结算分析中必须考虑的关键参数.
- 基于GB模型的用户友好的Excel工具可用于土木工程中的实际应用,有助于可靠的定居点预测.
更多相关视频
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
8.2K
07:05Visualization Method for Proprioceptive Drift on a 2D Plane Using Support Vector Machine
Published on: October 27, 2016
9.2K
相关概念视频
Design Example: Maintaining Level of an Embankment
52
Constructing a roadway embankment over uneven terrain requires precise leveling to ensure stability and proper drainage. Surveyors use a leveling instrument and staff to calculate ground elevations and determine the required fill material at each point along the embankment alignment.The process begins by positioning a leveling instrument near a benchmark with a known elevation. A backsight reading establishes the instrument height, which serves as a reference for subsequent measurements. A...
52
Shrinkage in Concrete
79
Shrinkage in concrete is primarily due to water loss from evaporation, hydration of cement, or carbonation, leading to a reduction in volume. The volumetric contraction results in volumetric strain in concrete. However, in practice, shrinkage is measured as linear strain, which is one-third of the volumetric strain.
When concrete is still in its plastic state, it can undergo a decrease in volume by about 1% of its absolute volume. This decrease is known as plastic shrinkage. It arises either...
When concrete is still in its plastic state, it can undergo a decrease in volume by about 1% of its absolute volume. This decrease is known as plastic shrinkage. It arises either...
79
Survival Tree
60
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
Building a Survival Tree
Constructing a...
Building a Survival Tree
Constructing a...
60
Types of Building Separation Joints
192
Building separation joints divide large or complex building structures into smaller, discrete units that can move independently. These joints are categorized into three types: volume-change joints, settlement joints, and seismic separation joints.
Volume-change joints address the effects of expansion and contraction due to temperature and moisture variations. They are strategically placed at discontinuities in a building's mass where cracking is most likely and are spaced about 150 to 200...
Volume-change joints address the effects of expansion and contraction due to temperature and moisture variations. They are strategically placed at discontinuities in a building's mass where cracking is most likely and are spaced about 150 to 200...
192
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
40
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
40
