基于模糊神经网络的无损检测参数识别  

Parameter identification of nondestructive testing based on fuzzy neural networks

作　　者：许亮斌[1] 陈国明[1] 徐长航[1] 

机构地区：[1]石油大学(华东)机械工程系,山东东营257061

出　　处：《石油矿场机械》2001年第4期4-6,共3页Oil Field Equipment

基　　金：国家自然科学基金资助项目 (5 97790 0 1)

摘　　要：通过考虑无损检测的模糊不确定性 ,建立起无损检测的模糊神经网络模型 ,来确定缺陷真实尺寸与检测尺寸之间的映射关系 ,从而在一定程度上解决了对平台构件缺陷进行有效定量分析这一难题 ,为海洋平台检测维修和再评估提供了依据。算例表明 ,与传统的 BP网络相比 ,模糊神经网络系统收敛快、精度高。The model of fuzzy neural networks (FNN) of nondestructive testing (NDT) is established considering the fuzzy uncertainty in NDT. The mapping relations between the measured flaw sizes by NDT and the actual flaw sizes are presented. Thus a quantitative method for determining the actual flaw size is successfully developed to make full use of the measured flaw sizes from different NDT sources. The method given in this paper can be used in the inspection, maintenance and repair and the reassessment of offshore structures. The numerical example shows that the performance of FNN is superior to traditional BP neural networks.

关 键 词：无损检测 神经网络模糊 参数识别 导管式平台 海洋平台 海上油气田 

分 类 号：TE951[石油与天然气工程—石油机械设备]