English

应用科学学报 ›› 2025, Vol. 43 ›› Issue (1): 35-50.doi: 10.3969/j.issn.0255-8297.2025.01.003

• 计算机应用专辑 • 上一篇    下一篇

融合机器学习与动态模型优化的雪崩预测及防治策略

金永超1, 王志坚2, 贾慧爽1, 杜云天1, 胡鑫婷3, 陈学斌1,4   

  1. 1. 华北理工大学 理学院, 河北 唐山 063210;
    2. 华北理工大学 经济管理学院, 河北 唐山 063210;
    3. 华北理工大学 冶金与能源学院, 河北 唐山 063210;
    4. 华北理工大学 河北省数据科学与应用重点实验室, 河北 唐山 063210
  • 收稿日期:2024-07-17 出版日期:2025-01-30 发布日期:2025-01-24
  • 通信作者: 陈学斌，教授，博导，研究方向为数据安全、物联网安全、网络安全。E-mail:chxb@qq.com E-mail:chxb@qq.com
  • 基金资助:
    国家自然科学基金（No.U20A20179）资助

Avalanche Prediction and Prevention Strategies Integrating Machine Learning and Dynamic Model Optimization

JIN Yongchao1, WANG Zhijian2, JIA Huishuang1, DU Yuntian1, HU Xinting3, CHEN Xuebin1,4   

  1. 1. College of Sciences, North China University of Science and Technology, Tangshan 063210, Hebei, China;
    2. College of Economics and Management, North China University of Science and Technology, Tangshan 063210, Hebei, China;
    3. College of Metallurgy and Energy, North China University of Science and Technology, Tangshan 063210, Hebei, China;
    4. Hebei Provincial Key Laboratory of Data Science and Application, North China University of Science and Technology, Tangshan 063210, Hebei, China
  • Received:2024-07-17 Online:2025-01-30 Published:2025-01-24

PDF

58

摘要： 爆破是防止雪崩的有效方法，但合适的爆破时间、爆破位置和爆破能量很难确定。本文首先收集、爬取了关于雪崩的指标数据，并对数据进行预处理。然后对数据进行探索性数据分析，重点分析时间与雪崩发生的关系，发现雪崩具有明显的季节性。以数据的80%为训练集，20%为测试集，建立支持向量机、随机森林和感知器神经网络模型，并利用贝叶斯优化算法对模型进行参数寻优，结果显示感知器神经网络的准确率最高。最后根据损失度对3个模型进行集成，对3个集成策略进行对比，结果显示SVM-RF-MLP模型的准确率最高为0.952。此后，建立基础的爆破能量模型，考虑山体高度、雪层密度随时间的变化，再基于历史数据寻找雪层稳定性的分布规律，构建动态雪崩稳定性爆破能量模型。通过对数据进行模拟验证以及对其进行三维山体可视化分析，获得最佳的爆破时机、爆破位置和爆破能量。

关键词: 贝叶斯优化算法, SVM-RF-MLP模型, 动态雪崩稳定性爆破能量模型

Abstract: Blasting is an effective method to prevent avalanches, but it is difficult to determine the appropriate blasting time, blasting location and blasting energy. This study began by collecting and preprocessing indicator data about avalanches. Then we conducted exploratory data analysis on the data, and found a strong seasonal pattern in avalanche occurrences. Using 80% of the data as the training set and 20% as the test set, the support vector machine, random forest and perceptron neural network models were established, with parameters optimized using the Bayesian optimization algorithm. The results showed that the perceptron neural network achieved the highest accuracy. Subsequently, the three models were integrated according to the loss degree, and three integration strategies were compared. The results showed that the highest accuracy of the SVM-RF-MLP model was 0.952. A basic blasting energy model was then developed, taking into account the changes in mountain height and snow layer density over time. Using historical data, a dynamic avalanche stability blasting energy model was built to identify the distribution patterns in snow layer stability. The data is simulated and verified, and a three-dimensional mountain visualization analysis is performed to obtain the optimal blasting timing, blasting location and blasting energy.

Key words: Bayesian optimization algorithm, SVM-RF-MLP model, dynamic avalanche stability blasting energy model

中图分类号: