| 张文,陈文昭,胡荣,卢铎方.考虑围岩应力梯度分布的岩爆预测的FCM-ANFIS模型[J].南华大学学报(自然科学版),2025,(1):44~55.[ZHANG Wen,CHEN Wenzhao,HU Rong,LU Duofang.FCM-ANFIS Model for Rock Burst Prediction Considering Stress Gradient Distribution of Surrounding Rock[J].Journal of University of South China(Science and Technology),2025,(1):44~55.] |
| 考虑围岩应力梯度分布的岩爆预测的FCM-ANFIS模型 |
| FCM-ANFIS Model for Rock Burst Prediction Considering Stress Gradient Distribution of Surrounding Rock |
| 投稿时间：2024-07-09 |
| DOI： |
| 中文关键词: 岩爆预测 梯度应力 应力集度 FCM-ANFIS模型 |
| 英文关键词:rock burst prediction gradient stress stress concentration FCM-ANFIS mode |
| 基金项目:湖南省自然科学基金项目(2023JJ30511);湖南省自然资源科研项目(20230144DZ);湖南省教育厅项目(重点)(18A252) |
|
| 摘要点击次数: 0 |
| 全文下载次数: 1 |
| 中文摘要: |
| 在深入分析岩爆影响因素的基础上,为量化表示围岩扰动区二次应力分布,引入“应力集度”的概念,建立岩爆的FCM-ANFIS(fuzzy clustering mean-adaptive network-based fuzzy inference system)模型,结果表明:将应力集度、强度应力比、脆性系数和弹性能量指数作为岩爆预测模型的输入指标,考虑了围岩应力分布的影响,使得所采用的岩爆预测指标更加全面合理。采用模糊聚类算法(fuzzy clustering mean,FCM)算法改进的自适应神经模糊推理系统(adaptive network-based fuzzy inference system,ANFIS)模型避免了当网格分割数较多时,模糊规则数呈指数型增长的缺陷,提高了计算效率和预测准确率。测试样本的预测结果表明,考虑应力集度影响的FCM-ANFIS模型的预测误差更小,预测准确率可提高至90%。 |
| 英文摘要: |
| On the basis of in-depth analysis of the influencing factors of rock burst, in order to quantitatively express the secondary stress distribution in the disturbed zone of surrounding rock, the concept of “stress concentration” is introduced, and the FCM-ANFIS (fuzzy clustering mean-adaptive network-based fuzzy inference system) model of rock burst is established. The results show that the stress concentration, strength stress ratio, brittleness coefficient and elastic energy index are used as the input indexes of the rock burst prediction model, and the influence of the stress distribution of surrounding rock is considered, which makes the rock burst prediction index more comprehensive and reasonable. The ANFIS model improved by FCM algorithm avoids the defect that the number of fuzzy rules increases exponentially when the number of mesh segmentation is large, and improves the calculation efficiency and prediction accuracy. The prediction results of the test samples show that the prediction error of the FCM-ANFIS model considering the influence of stress concentration is smaller and the prediction accuracy can be improved to 90%. |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
|
|
|