蚁群神经网络算法在超声检测混凝土缺陷中的应用

基金项目:

河南省科技厅重点科技资助项目(11210231056)

南阳师范学院校级专项基金资助项目(ZX2009002)

详细信息

Ant Colony Algorithm and Application in Inspection of Concrete Structure Defects

摘要: 为了克服BP算法的缺陷与超声检测混凝土材料缺陷时收敛慢、精度低等问题，采用了蚁群优化算法与BP神经网络融合的方法，建立了蚁群神经网络的数学模型，实现了蚁群神经网络的训练，并通过实例验证了该方法的有效性。由试验得知蚁群神经网络识别混凝土缺陷时，对位置的识别比对尺寸更有效。
- 蚁群神经网络 /
- 混凝土结构 /
- 超声检测
Abstract: In order to overcome the deficiency of slower convergence speed and low accuracy of BP algorithm and BP neural network, a combination of Ant Colony optimization algorithm and BP neural network training was used and the validity of the method was verified. It was concluded that the identification of the defect location was shown more effective as compared with the defect size when the ant Colony neural network was used to identify concrete defects.
- Ant colony neural network /
- Concrete structure /
- Defect detection

[1]	王五平，宋人心，傅翔.超声探测混凝土缺陷的概率判断法辨析［J］.混凝土,2011(2):7-9.
[2]	张立新，李慧剑，高柏峰，等.基于小波分析与神经网络的混凝土缺陷超声定量检测［J］.无损检测,2009,31(1):20-22.
[3]	卢结成，王立敏.基于神经网络的砼内缺定量识别［J］.计算机应用研究,2000(1):18-21.
[4]	孙晓霞.蚁群算法理论研究及其在图像识别中的应用［D］.哈尔滨：哈尔滨工程大学,2006.
[5]	LI Lianyuan, LIU Zemin, ZHOU Zheng. A new dynamic distributed routing algorithm otelecommunication networks［C］// International Conference on Communication Technolog Proceedings. Beijing China: ［s.l］2000:849-852.
[6]	GUNES M, SORGES U. ARA the ant colony based routing algorithm for MANETs Proceeding International Conference on Parallel Professing Workshops［C］. Uncover BC Canada［s.l.］:2002:79-85.
[7]	孟照辉.基桩超声波检测中混凝土缺陷异常信号的识别实例［J］.工程地球物理学报,2009(5):580-584.
[8]	朱鸿茂，郑伟花，黄忠文，等.运动界面上反射超声散斑空间运动的研究［J］.物理学报,2004,53(8):2614-2620.
[9]	郑伟花，朱鸿茂，贾虎.超声散斑相关法测量转角的相关性研究［J］.应用声学,2010,29(2):141-147.
[10]	ZHU H-M, WU Y-Y, ZHENG W-H. In-plane and out-of-plane displacement measurement by ultrasonic speckle correlation method［J］.Arch Appl Nlech,2006,75:521-526.