1. 海军航空大学 岸防兵学院， 山东 烟台 264001； 2. 中央军委联合参谋部 第55研究所， 北京 100094
通讯作者:徐廷学，男，教授，博士生导师，电话(Tel.)：0535-6635483;E-mail：kvcelu@163.com.作者简介:逯程(1990-)，男，山东省泰安市人，博士生，主要从事装备综合保障理论与技术研究.基金资助:国家自然科学基金(51605487)，山东省自然科学基金（ZR2016FQ03）资助项目Fault Diagnosis of Terminal Guidance Radar Based on AttributeGranulation Clustering and Echo State Network
LU Cheng,XU Tingxue,WANG Hong1. Coast Guard Academy, Naval Aeronautical and Astronautical University, Yantai 264001, Shandong, China; 2. The 55th Institute, Joint Staff Department, Beijing 100094, China
摘要/Abstract
摘要： 为了提高末制导雷达故障诊断的效率和精度，提出一种基于属性粒化聚类与回声状态网络(ESN)的故障诊断方法.定义一种基于属性值影响度的属性区分能力测量指标，并以此作为相似性度量依据，利用近邻传播(AP)聚类算法得到区分能力相当的若干属性粒，通过选取聚类中心属性来完成故障征兆属性的约简；在储备池构建中，采用Bienenstock-Cooper-Munro (BCM)规则进行连接权矩阵的预训练，在目标函数中添加L1/2范数惩罚项，以提高ESN储备池对样本的动态适应性；同时，采用半阈值迭代法对模型进行求解，通过末制导雷达信号处理模块的故障诊断实例，验证了所提方法的有效性和优越性.结果表明：与BP神经网络和传统ESN模型相比，所提方法的稳定性及诊断准确率更高；将其与基于属性重要度和AP聚类的属性粒化约简算法相结合，能够进一步提高故障诊断的效率和精度，其仿真实验的训练时间仅为 8.98s，诊断正确率可达 95.2%.
关键词: 末制导雷达, 属性粒化聚类, 回声状态网络, BCM规则, 故障诊断
Abstract: In order to improve the efficiency and precision of terminal guidance radar fault diagnosis, a fault diagnosis method based on attribute granulation clustering and echo state network (ESN) was proposed. Firstly, an attribute distinguishing ability index was defined by attribute value influence degree. As the basis of similarity measure, a number of attribute granules of similar distinguish are obtained through affinity propagation clustering algorithm, and then fault attribute reduction was completed by selecting clustering center attributes. In order to improve the dynamic adaptability of ESN reservoir to samples, Bienenstock-Cooper-Munro (BCM) rule was introduced into the reservoir construction to train the connection weight matrix. Meanwhile, the L1/2-norm penalty term was added to the objective function in order to improve the sparsification efficiency, solving a numerical oscillation problem by using a smoothing L1/2 regularizer, the model was solved by using the half threshold iteration method at last. The effectiveness and superiority of the proposed method are verified by a fault diagnosis example of terminal guidance radar signal processing module. The training time of the simulation experiment is only 8.98s, and the diagnostic accuracy can reach 95.2%.
Key words: guidance radar, attribute granulation clustering, echo state network (ESN), Bienenstock-Cooper-Munro (BCM) rule, fault diagnosis
PDF全文下载地址:
点我下载PDF
