中文摘要：

为解决爆破振动破坏影响因素、民房破坏关联预测问题,应用相关分析法和鱼骨图理论分析影响因素与民房破坏的关联度,计算影响因素的权重,并结合支持向量机（SVM）原理,构建爆破振动对民房破坏的鱼骨图-SVM预测模型。用爆破振动观测数据,对影响因素加权的SVM模型进行训练和测试,测试结果良好。研究表明：用鱼骨图模型可获得影响因素与民房破坏的关系,量化输入变量的重要性。民房自身特点中,施工质量、圈梁构造柱及屋盖形式的重要性明显高于其他影响因素。做好房屋基础建设,能显著改善民房抗破坏能力。该预测模型能更好地考虑影响因素对民房破坏的综合影响,改善民房破坏程度预测准确性。

英文摘要：

factors and For the sake of dealing problems in blasting damage vibration predicting associated relationships among to residential house, considering the characteristics of correlation analysis, fishbone diagram and SVM, the correlations and factors＇weights were obtained, and a fishbone diagram-SVM based model was built for predicting the damage. The model was trained and tested by a series tions of blasting vibration and damage degree of houses. The test results were good. fishbone diagram can obtain the relationships among factors and residential house＇s weights, that as factors affecting the damage of data from observa- The results show that damage, and factors , the quality of construction, the structural column of circle beam and roof forms are more important than others obviously, that making a good job of building foundation construction can increase the strength of residential fold factors can improve the prediction accuracy of houses, and that proposed method damage degree caused by blasting considering the mani- vibration.