基于稀疏表示的间歇故障检测方法及仿真

Intermittent fault detection method based on sparse representation

基于间歇故障在某些域的稀疏性,提出一种基于稀疏表示的间歇故障检测方法。利用系统输出数据构造系统的过完备字典,设计间歇故障检测阈值,并对过完备字典和故障检测阈值进行在线更新。此方法适合动态系统的间歇故障检测,并通过仿真结果进行验证,并比较在不同更新策略下的仿真结果。

Based on the sparsity of intermittent faults in some domains, an intermittent fault detection method based on sparse representation was proposed. The system output data were used to build the overcomplete dictionary and design the fault detection threshold of intermittent fault, which was able to update the over-complete dictionary and fault detection threshold with online measurements. With the simulation verification, the proposed method was suitable for intermittent fault detection in dynamic system and results under different online updating strategies were compared.