基于改进GA算法优化RBF网络的航空发动机叶片损伤图像识别  

Aero-engine Blades Damage Image Recognition Based on RBF Network Optimized by Improved Genetic Algorithms

作　　者：石宏[1] 张维亮[1,2] 田中笑[2] 朱宁[1] 

机构地区：[1]沈阳航空航天大学航空航天工程学部,沈阳110136 [2]沈阳航空航天大学航空航天工程学部沈阳110136 [3]93057部队,吉林132000

出　　处：《科学技术与工程》2013年第28期8534-8538,共5页Science Technology and Engineering

基　　金：航空科学基金(2008ZG54024)资助

摘　　要：通过对航空发动机叶片损伤图像进行识别,可以快速准确地发现叶片损伤状况,有利于对故障进行及时有效的预测。本文对损伤图像进行分割,提取损伤图像特征参数,采用改进GA算法优化RBF网络参数的方法建立航空发动机叶片损伤图像识别模型,对损伤图像特征参数样本进行仿真实验,识别正确率为93.33%,同时与单一RBF网络模型识别结果进行对比分析,结果表明该方法更加优越有效。Through the pattern recognition of aero-engine blades damage image, the blades damage condition can be fast and accurate detection and it is effective to predict malfunction problems. The damage image is segmen- ted and characteristic parameter is extracted. The adaptive genetic algorithm is used to optimize the basis neural network parameters, and dynamic adaptive GA-RBF recognition model is established. The method is applied in simulation. The classification accuracy rate is 93.33%. The method is compared with the radial basis neural net- work, the result show this method is more effective than the basis neural network.

关 键 词：图像分割 特征图像提取 GA算法 RBF网络 

分 类 号：V232.4[航空宇航科学与技术—航空宇航推进理论与工程]