基于主成分分析和支持向量机的苏锡常地区地裂缝危险性预测

地裂缝地质灾害是由多种复杂因素共同导致的岩层、土体开裂现象,常规数学模型难以对地裂缝的危险性做出准确预测。该文首先采用主成分分析(PCA)方法对选取的导水系数、水位、粘性土层厚度、基岩起伏度、基岩埋深5个影响因素提取3个主成分,对导致地裂缝发生的主成分进行了全新的解释,同时引入支持向量机的方法(SVM)建立了基于主成分分析和支持向量机的苏锡常地区地裂缝危险性预测模型。并结合工程实例将预测结果与SVM模型预测结果进行比较分析。结果表明:基于主成分分析和支持向量机的地裂缝危险性预测模型精度较高,具有一定的参考价值,可为预测苏锡常地区地裂缝危险性提供有效依据。

Prediction of Ground Fissures Risk in Suxichang Area Based on Principal Component Analysis and Support Vector Machine

Geological hazard of ground fissures is a phenomenon of rock and soil cracking caused by many complex factors. It is difficult to predict the risk of ground fissures accurately by conventional mathematical models. Firstly, the Principle Component Analysis (PCA) method is used to extract three principal components from five influencing factors, namely, transmissibility, water level, thickness of cohesive soil layer, fluctuation degree of bedrock and buried depth of bedrock. A new interpretation of the principal components leading to the occurrence of ground fissures is given. At the same time, the Support Vector Machine (SVM) method is introduced to establish the risk prediction model of ground fissures in Suzhou-Wuxi-Changzhou area based on Principle Component Analysis (PCA) and Support Vector Machine (SVM). Combined with practical work, the predicted results are compared with the predicted results of SVM model. The results show that the risk prediction model of ground fissures based on Principal Component Analysis and Support Vector Machine has high accuracy and certain reference value. It can provide effective basis for predicting the risk of ground fissures in Suzhou-Wuxi-Changzhou area.