中文摘要：

引人基于支持向量机（SVM）的数据挖掘技术，提出了基于SVM的转静碰摩部位诊断知识获取.首先，基于带机匣的航空发动机转子实验器，模拟了通个碰摩部位的碰摩实验，利用机匣通个部位的应变测试，获取了4个碰摩部位和4个测点的大量实验数据;然后提出了一种基于支持向量聚类（SVC）的诊断知识规则提取方法.在该方法中，利用SVC算法得到特征选取后样本的聚类分配矩阵，最后根据聚类分配矩阵构建超矩形规则为使规则更加简洁，易于解释，采用规则合并、维数约简、区间延伸等方法对超矩形规则进行进一步简化.利用基于SVM的数据挖掘方法，从大量的碰摩部位实验数据中提取出了转静碰摩部位诊断的知识规则，并进行了相应解释和验证，规则识别率达到了99%以上，表明了该方法的正确有效性.

英文摘要：

The data mining technology based on support vector machine （SVM） was in troduced, and aeroengine rotorstator rubbing positions diagnosis rule acquisition was pro posed based on SVM. Firstly, the rubbing experiment of 4 rubbing parts was simulated based on aeroengine rotor tester with the casing, and a large number of experimental data were obtained by using the strain test of 4 parts of the casing. A new approach was proposed to extract knowledge rules from support vector clustering （SVC）. Then SVC algorithm was adopted to get the clustering distribution matrix of the sample data with chosen features. Secondly, hyperrectangle rules were constructed on the basis of the clustering distribution matrix. In order to make the rules more concise and explainable, hyperrectangle rules should further simplified by using such means as rules merger, dimension reduction and in terval extension. Finally, using the data mining method based on SVM, aeroengine rotor stator rubbing positions diagnosis rules were extracted from a large number of rubbing posi tion experiment data, then explanation and validated accordingly. The recognition rateswere more than 99%, showing that the method is corrective and effective, and embodies great practical values.