基于邻域粗糙集的航空发电机健康诊断方法

提出一种基于邻域粗糙集和支持向量机相结合的航空发电机智能健康诊断方法.采用专业健康试验平台对某型战斗机的真实航空发电机进行试验,得到转速、负载、油压等大量表征发电机健康状态的监测数据.引入数据挖掘思想,采用邻域粗糙集理论对监测数据进行属性约简,将约简后的属性集输入给所设计的支持向量机健康诊断器,对航空发电机的健康状态进行了诊断研究.研究表明,该方法能够很好实现对某真实航空发电机的健康诊断,具有较高的推广应用价值.

Health Diagnosis of Aero-Generator Based on Neighborhood Rough Sets Theory

Health diagnosis of an aero-generator is important to flight safety.One of requirements is availability of extracting useful information from raw data.A health diagnosis method is presented based on neighborhood rough sets theory and support vector machine(SVM).Raw data are obtained from a specific aero-generator test platform.An approach of attribute reduction using neighborhood rough sets theory is outlined and a diagnosis classifier is designed based on SVM for further carrying out health diagnosis of aero-generator.The effectiveness of the proposed method is demonstrated through an experimental research.The result shows a better performance of the classifier that uses attribute reduction subsets as inputs,and also indicates that the method can have wide popularization and application potential.