Characterizing Magnetic Flux Leakage Signal of Cracks Based on Improved BP Neural Network
-
摘要: 为量化油气管道的裂纹漏磁信号, 提出使用改进型BP神经网络的方法。介绍了BP神经网络的运作方式、改进的BP算法和如何将遗传算法用于改进BP神经网络的初始权值和阈值。测试样本和实际检测数据的输出结果表明, 采用改进型BP神经网络量化裂纹漏磁信号是可行的。Abstract: An improved BP neural network was proposed to characterize magnetic flux leakage signal of cracks in pipeline. The artificial neural network in simplicity, ways to improve BP(back propagation) algorithm, and usage of genetic algorithm to adjust parameters of BP neural network were introduced. Experimental results were presented and demonstrated the effectiveness of this method.
-
-
[1] 彭永胜.基于漏磁检测机理的钢管小缺陷精确量化识别理论及系统研究[D].天津: 天津大学,2005. [2] 李久春.基于SVR的管道裂纹漏磁场的预测分析模型[J].微计算机信息,2008,24(15): 285-287. [3] Han Wenhua, Que Peiwen. Defect reconstruction from MFL signals using an improved genetic local search algorithm[C]. IEEE International Conference on Industrial Technology.[S.l]:[s.n.],2005: 1438-1443. [4] Han Wenhua, Que Peiwen. 2-D defect reconstruction from MFL signals based on genetic optimization algorithm[C]. IEEE International Conference on Industrial Technology.[S.l]:[s.n.],2005: 508-513. [5] Ameet Joshi, Lalita Udpa, Satish Udpa, et al. Adaptive wavelets for characterizing magnetic flux leakage signals from pipeline inspection[J]. IEEE Tras on Magnetics,2006,42(10): 3168-3170. [6] 吴欣怡, 赵 伟, 黄松岭.基于漏磁检测的缺陷量化方法[J].电测与仪表,2008,45(5): 20-22. [7] 谭显胜, 周铁军.BP算法改进方法的研究进展[J].怀化学院学报,2006,25(2): 126-130. [8] 董长虹.Matlab神经网络与应用[M].北京: 国防工业出版社,2005. [9] 雷英杰, 张善文, 李续武,等.MATLAB遗传算法工具箱及应用[M].西安: 西安电子科技大学出版社,2005. [10] 万盛萍.GA优化BP神经网络[J].软件导刊,2007,3(3): 24-25.
计量
- 文章访问数: 1
- HTML全文浏览量: 0
- PDF下载量: 1