论文部分内容阅读
由于地下工程的复杂性,岩爆的发生受到多种因素的影响,目前尚没有一种可靠的预测方法来对其进行预报,进而有针对性地进行工程灾害的风险控制。笔者提出将应力强度比(σ_θ/σ_c)、脆性系数(σ_c/σ_t)和弹性能量指数(Wet)作为影响岩爆的主要指标,并根据粒子群优化算法的参数选取和收敛速度快的优势及支持向量机的小样本、高维度、非线性的特性,提出了用粒子群优化算法对影响支持向量机分类性能的两个主要参数进行优化,进而获得优化的支持向量机分类器。利用PSO-SVM对在建二广九标茅田界隧道深埋变质砂岩岩爆发生情况进行预测,定量地判断该标段不存在岩爆现象,预测结果与茅田界隧道的实际情况基本相符。
Due to the complexity of underground engineering, the occurrence of rock burst is affected by many factors. At present, there is no reliable prediction method to forecast it, and then the risk control of engineering disaster can be targeted. The author puts forward that the stress intensity ratio (σ_θ / σ_c), the brittleness coefficient (σ_c / σ_t) and the elastic energy index (Wet) are the main indexes affecting the rockburst. According to the advantages of parameter selection and fast convergence of the particle swarm optimization algorithm, SVM is proposed in this paper. Particle swarm optimization (PSO) algorithm is used to optimize the two main parameters that affect the classification performance of SVM, and then the optimal SVM classifier is obtained. The PSO-SVM was used to predict the occurrence of rockburst in the deep metamorphic sandstone of the Miaotiejie tunnel under construction of the Erligou nine standard. The rock burst was quantitatively determined. The prediction results are in good agreement with the actual conditions of the Maotianjie tunnel.