摘要
提出了一种基于自组织免疫网络的传感器故障检测模型。该模型将自组织学习的思想引入到传感器免疫网络的建模中,通过学习向量量化确定免疫网络的连接权值,并对其结构和特点进行了分析,给出了相应的诊断算法。仿真结果表明,所提出的方法对故障传感器具有较高的检测灵敏度,并且对噪声具有一定的容忍能力,对于航空发动机传感器的监测具有一定的应用价值,并可方便地推广到其他类似的工业应用领域。
A self-organizing immune network for sensor fault detection in aircraft engine was presented. The self- organizing map was used in the modeling of sensor immune network. The weights of immune network were determined based on learning vector quantization. The structure and the features of the immune network, for sensor fault detection, were presented, and the algorithms of sensor failure detection were given. Simulation results show that this method can effectively detect the sensor failures. Moreover, this method is sensitive to fault and robust to noise interference. This method is contributive for sensors fault detection in aircraft engine and it can be easily extended to other relative industrial application areas.
出处
《计算机应用》
CSCD
北大核心
2009年第5期1426-1429,共4页
journal of Computer Applications
关键词
传感器
故障检测
人工免疫网络
学习向量量化
sensors
fault detection
artificial immune network
learning vector quantization