论文部分内容阅读
多故障作为标准单故障的组合,很多文献对多故障的诊断都提出行之有效的解决策略,但却忽视单故障模式之间的相互关系,而影响到多故障诊断效率,尤其对于故障繁多的复杂产品.为了克服该缺点,引入KFCM-F算法和核化聚类有效性指标KV_k,提出两阶段聚类框架,数据仿真试验证明该框架能有效发现单故障之间的潜在关系,从而达到压缩故障模式以期提高诊断效率的目的.
Many failures as a combination of standard single fault, a lot of literature on multi-fault diagnosis are put forward effective solutions to the strategy, but neglected the relationship between single-fault mode, and affect the efficiency of multi-fault diagnosis, especially for many faulty In order to overcome this shortcomings, the KFCM-F algorithm and KV_k kernel effectiveness index KV_k are introduced, and a two-stage clustering framework is proposed. The data simulation results show that the framework can effectively find the potential relationship between single failures, Failure mode in order to improve the diagnostic efficiency of the purpose.