欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
为将支持向量机理论应用于浅埋巷道围岩松动圈厚度的预测中，结合巷道矿压显现特点和松动圈支护理论，选取巷道埋深、巷道跨度、围岩强度、围岩节理裂隙发育程度和巷道掘进断面积等5个主要影响因素作为松动圈厚度的判别指标。根据支持向量机回归预测算法，以20组实测数据作为训练样本，基于Libsvm软件建立了松动圈厚度预测的支持向量机模型。为检验该模型的可靠性，利用该模型对10组测试样本的松动圈厚度进行预测并与实测值做了对比分析。结果表明，用该模型预测松动圈厚度的平均相对误差为2．66％，比神经网络方法和灰色理论方法预测的结果更精确。这充分说明用支持向量机模型预测松动圈厚度具有良好的实用性和较高的可靠度，可为松动圈厚度的确定提供一条新的途径。
英文摘要：
To apply support vector machine （SVM） theory to predict the thickness of excavationdamaged zone （EDZ） of shallow roadway, the depth, span, intensity of rock, rock joint develop- ment degree, and roadway basal area are regard EDZ, with a consideration of characteristics of EDZ. The SVM model for predicting the thickness ed as the discriminant factors of the thickness of underground pressure and the support theory of of EDZ is established by using 20 groups of meas- ured data as training samples, based on Libsvm software and the regression prediction algorithm of SVM. To test the model＇s reliability, 10 groups of measured data are used as testing samples and the predictive value by the model is compared with the measured value. The results show that the model＇s average relative error is 2. 66% , which is more accurate than that by the methods of artificial neural network and gray theory, showing that the model is practical and reliable, and could provide a new way for ascertaining the thickness of EDZ.
同期刊论文项目
同项目期刊论文
期刊信息
位置：