在RCFST列的容量预测中应用机器学习模型
Khaled Megahed1, Nabil Said Mahmoud1, Saad Elden Mostafa Abd-Rabou2
1Department of Structural Engineering, Mansoura University, PO BOX 35516, Mansoura, Egypt.
机器学习模型,高斯过程回归 (GPR) 和极端梯度提升 (XGBoost),准确预测矩形混凝土填充钢管柱 (RCFST) 的压力强度. GPR表现出卓越的性能,提高了结构工程师的设计可靠性.
科学领域:
- 结构工程 结构工程
- 材料科学 材料科学 材料科学
- 计算力学 计算力学 计算力学
背景情况:
- 长方形混凝土填充钢管柱 (RCFST) 具有高承载能力和柔性,但由于不一致的现有方程式而面临设计不确定性.
- 传统的回归方法很难准确地建模RCFST柱体特性和压力强度之间的复杂关系.
研究的目的:
- 开发和评估先进的机器学习 (ML) 模型,以准确预测RCFST柱的压力强度.
- 解决当前设计方程的局限性,提高工程设计师的信心.
主要方法:
- 实施高斯过程回归 (GPR) 和极端梯度增强 (XGBoost) 模型.
- 使用958个轴向和405个异常加载的RCFST列的数据集.
- 引入"强度指数"以通过沙普利增量解释 (SHAP) 增强模型性能和特征分析.
主要成果:
- GPR模型实现了高精度,近99%的标本显示不到20%的误差.
- 机器学习模型在预测准确性方面明显优于现有的标准代码和以前的机器学习研究.
- SHAP分析确定柱长和负载异心率是影响压力强度负面影响的关键因素.
结论:
- 与传统方法相比,GPR和XGBoost模型提供了更可靠和更准确的方法来预测RCFST列强度.
- 开发的ML模型为结构工程师提供了有价值的工具,减少了设计不确定性.
- 了解长度和异常度等几何参数的影响对于优化RCFST柱设计至关重要.
更多相关视频
10:25Construction of Models for Nondestructive Prediction of Ingredient Contents in Blueberries by Near-infrared Spectroscopy Based on HPLC Measurements
Published on: June 28, 2016
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
相关概念视频
Multimachine Stability
In analyzing the system, the nodal equations represent the relationship between bus voltages, machine voltages, and machine currents. The nodal equation is given by:
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
Response Surface Methodology
The process of RSM involves several key steps:
Wind Turbine Machine Models
Induction machines interact through the rotating magnetic field generated by the stator and the rotor. The key parameter is slip, which is the difference between synchronous speed and rotor speed relative to synchronous speed. Slip is...
Parallel RLC Circuits
A simplified parallel RLC circuit model with a DC input source generating a step response is employed in this context. When the switch is turned on, Kirchhoff's current law is applied, leading to a second-order differential equation.
Comparison between RL and RC circuits
