一种基于改进SVM算法的爆破飞石预测方法
By constructing a blasting fly rock prediction model using an improved SVM algorithm, the problem of inaccurate blasting fly rock prediction in existing technologies is solved, and more efficient construction safety management is achieved.
CN118094355BActive Publication Date: 2026-07-17CHINA ROAD & BRIDGE +1
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHINA ROAD & BRIDGE
- Filing Date
- 2024-03-22
- Publication Date
- 2026-07-17
AI Technical Summary
Technical Problem
Current technology cannot accurately predict the distance of flying rocks during blasting, resulting in safety hazards and environmental impacts during blasting operations.
Method used
An improved support vector machine (SVM) algorithm was adopted to construct a blasting flyrock prediction model through data dimensionality reduction and model optimization. The model was trained using optimization formulas and kernel functions, and flyrock distance was predicted by combining on-site factors.
Benefits of technology
It improves the accuracy and safety of predicting flying rocks from blasting, enables the reasonable setting of safe distances, reduces construction risks, and protects the surrounding environment and personnel safety.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN118094355B_ABST
Abstract
本发明公开了一种基于改进SVM算法的爆破飞石预测方法，包括以下步骤：采集原始数据X，根据原始数据X计算投影矩阵P，并将原始数据X投影到投影矩阵P中，得到降维后的数据Y'，构建SVM模型，利用优化公式对SVM模型进行优化，将数据Y'输入至SVM模型中进行训练，得到爆破飞石距离f(x)，再通过SVM模型对测试样本进行预测，并采用计算召回率的方式来评价对应样本的适应度r，评估SVM模型的性能；本发明中，可以减少输入变量之间的相关性，减少了相关性评估中重复相似的因素，有效的把变量降低维度，同时又保留了建模工程中的基本信息，可以有效的预测到爆破中飞石距离。
Need to check novelty before this filing date? Find Prior Art