Application of Evolutionary Neural Networks and Multiple Objective Evolutionary Algorithms in Infrared Thermography
-
摘要: 针对红外相位法无损检测缺陷定量化要求和试验参数的确定,提出采用进化神经网络及多目标进化算法进行分析,通过对含多缺陷信息的预埋试件进行试验,以试件表面像素点的时间-温度信息作为特征参数进行网络训练,结果表明,经过训练的网络误差在5%以内,试验证实多目标进化算法得到的参数与实际试验最优效果参数相符,可为工程应用提供参数参考。Abstract: To satisfy quantifying evaluation and determine parameters, an evolutionary neural network(ENN) and a multiple objective evolutionary algorithm(MOEA) were presented for infrared thermography nondestructive testing. By means of the measurement of the temperature of specimen with artificial defects, the time against temperature signal was recorded as the network characteristic parameters. The errors of the defects depth were less than 5%. The experimental results showed that the parameters determined by MOEA could satisfy the optimum parameters in the experiments, and it could provide parameters for project application.
-
-
[1] Meola C, Carlomagno G M. Recent advances in the use of infrared thermography[J]. Measurement Science and Technology,2004(15):27-58. [2] Giordano Teza, Antonio Galgaro, Francesca Moro. Contactless recognition of concrete surface damage from laser scanning and curvature computation[J]. NDT&E International,2009,42(4):240-249. [3] Prabhu D R, Winfree W P. Neural network based processing of thermal NDE data for corrosion detection[J]. QNDE,1993(12):48. [4] Bison G, Bressan C, Disarno R, et al. Thermal NDE of delamination in plastic materials by neural network processing[C]. QIRT 94-Eurotherm Series 42-EETI ed. Paris:1995. [5] MaIdague X, Largout Y, Couturier J P. A study of defect depth using neural networks in pulsed phase thermography: modeling, noise, experiments[J]. Rev Gén Therrn,1998,37(8):704-717. [6] Largout Y, Darabi A, Maldague X. Depth evaluation in pulsed phase thermography with neural network, review of progress in quantitative[J]. NDE,1998(18A):611-617. [7] 刘俊岩,戴景民,王扬.红外图像序列处理的锁相热成像理论与试验[J].红外与激光工程,2009,38(02):346-351. [8] 冯立春,陶宁,徐川.锁相热像技术及其在无损检测中的应用[J]. 红外与激光工程,2010,39(6):1120-1123. [9] 雷德明,严新平.多目标智能优化算法[M].北京:科学出版社,2009:36-38.
计量
- 文章访问数: 0
- HTML全文浏览量: 0
- PDF下载量: 0