摘要: 针对一般模型算法在传感器相关性识别中存在的不足,提出一种基于Fuzzy ART神经网络的传感器相关性量化提取与识别方法,并与免疫网组合构成诊断系统。通过对某热控系统温度传感器故障的仿真诊断,验证了方法的有效性。仿真结果表明,系统能准确识别并诊断单传感故障和多传感故障。当传感器输出偏差大于±5%时,识别与诊断的准确率均达90%以上。
关键词:
免疫网模型,
诊断算法,
Fuzzy ART神经网络,
传感器,
相关性识别,
故障诊断
Abstract: Aiming at the deficiency of sensor correlation identification of model algorithm, a new sensor correlation extraction and recognition algorithm is proposed based on Fuzzy ART neural network, of which the diagnosis system is consisted with immune network. By the simulation of temperature sensor fault in certain thermal control system, the method is valid. Simulation result shows that the system can recognize and diagnose the faults accurately, regardless of s single or multiple sensor faults. The accuracy of recognition and diagnosis is above 90 percent when the sensor output is less than ±5 percent deviation.
Key words:
immune network model,
diagnosis algorithm,
Fuzzy ART neural network,
sensor,
correlation identification,
fault diagnosis
中图分类号:
谷吉海;金向阳;. 基于免疫网与相关性识别的传感器故障诊断[J]. 计算机工程, 2010, 36(1): 203-205.
GU Ji-hai; JIN Xiang-yang;. Sensor Fault Diagnosis Based on Immune Network and Correlation Identification[J]. Computer Engineering, 2010, 36(1): 203-205.