在广东省H矿区使用PCA和BPNN进行坡度稳定的安全预测因子
Yangfan Jing1,2, Yuefeng Li3, Jian Chang1,2
1State key Laboratory of Metal Mine Mining Safety and Disaster Prevention and Control, Sinosteel Maanshan General Institute of Mining Research Co., Ltd, Xitang Road 666, Maanshan, 243000, China.
Scientific reports
|April 14, 2025
概括
本研究引入了一种新的主要组件分析 (PCA) 与反向传播神经网络 (BPNN) 方法,用于预测地质工程中的安全因子 (FOS). PCA-BPNN方法显著提高了坡度稳定性评估,比现有的机器学习技术提供了更高的准确性.
科学领域:
- 地质技术工程 地质技术工程
- 计算地质科学计算地质科学
背景情况:
- 斜坡故障评估在地质工程中至关重要.
- 准确预测安全系数 (FOS) 对于坡道稳定性至关重要.
- 机器学习为FOS确定提供了先进的设计方法.
研究的目的:
- 引入和评估一种用于预测FOS的新型机器学习方法.
- 将主要组件分析 (PCA) 与反向传播神经网络 (BPNN) 集成,以提高FOS预测.
- 评估拟议方法在现实世界地质技术场景中的实际适用性.
主要方法:
- 主要组件分析 (PCA) 用于缩小维度.
- 逆向传播神经网络 (BPNN) 用于预测建模.
- 整合PCA和BPNN以创建用于FOS预测的PCA-BPNN模型.
主要成果:
- 该PCA-BPNN方法实现了高精度:R2为0.917,RMSE为0.061,MAE为0.047 (训练组).
- 测试组结果显示R2为0.879,RMSE为0.071和MAE为0.057.
- 应用于H矿区,设计的FOS为1.409,符合工程要求.
结论:
- 与现有方法相比,PCA-BPNN方法在预测FOS方面表现出更高的准确性和有效性.
- 这种集成的机器学习技术显著提高了地质技术应用中的斜率稳定性评估.
- 这项研究证实了PCA-BPNN模型对现实工程项目的实际实用性.
相关概念视频
Survival Tree
42
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...
42
Principal Stresses: Problem Solving
149
When analyzing two planes intersecting at right angles under the influence of shearing, tensile, and compressive stresses, it is essential to identify principal planes, maximum shearing stress, and principal stresses. To find the principal planes, apply a formula that equates them to twice the shearing stress divided by the difference between tensile and compressive stresses.
149
Design Consideration
165
Designing a structure involves a series of considerations, primarily the material's ultimate strength, calculated through tests that measure changes under increased force until the material reaches its breaking point or limit. The ultimate load, where the material breaks, is divided by its original cross-sectional area, resulting in the ultimate normal stress or strength. The ultimate shearing stress is another significant factor taken into account.
The factor of safety is another key...
The factor of safety is another key...
165
End Point Prediction: Gran Plot
179
A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...
For potentiometric titration, the Gran plot is created by plotting...
179


