基于模糊神经网络的薄板不同指标裂纹诊断

DIFFERENT INDEXES CRACKS DIAGNOSIS TO THIN PLATE BASED ON FUZZY NEURAL NETWORKS

将采用模糊神经网络的故障诊断技术和诊断模型,利用改进的BP算法对模糊神经网络进行训练,并利用训练好的网络,对悬臂薄铝板仿真裂纹进行了诊断。对悬臂薄铝板裂纹的诊断方法是:首先得到完好板结构和各种仿真裂纹板结构的振型和固有频率,在此基础上提取各种裂纹损伤情况下的五种裂纹诊断指标。将五种诊断指标分成三组,构成三个模糊神经网络,对模糊神经网络进行训练之后,利用训练好的网络对悬臂铝板裂纹进行了故障诊断,将裂纹的诊断结果与实际情况进行了比较,得到了不同诊断指标组合下,不同神经网络的诊断结果。并对不同组别裂纹诊断指标的诊断结果与实际裂纹情况进行了比较。

Fuzzy neural networks fault diagnosis technology and diagnosis mode are used to diagnose cracks. The fuzzy neural networks are trained with promoted BP arithmetic. The faults of cracked cantilever plate are diagnosed using the trained fuzzy neural networks. Firstly the mode and frequency of numerical simulation intact plate and different cracked plates are calculated. Then five crack diagnosis indexes are calculated. Divide five indexes into three groups and create three fuzzy neural networks. The fuzzy neural networks are trained using these indexes, and diagnosis is taken to the crack in the end. Compared the diagnosis result with the actual crack and an effective result is gotten.