The eddy current pulsed thermography(ECPT)technique is a research focus in the non-destructive testing(NDT)area for defect inspection.Defect feature extraction for defect information analysis in ECPT is limited by ima...The eddy current pulsed thermography(ECPT)technique is a research focus in the non-destructive testing(NDT)area for defect inspection.Defect feature extraction for defect information analysis in ECPT is limited by image contrast,heat diffusion,background interference,etc.In this paper,a defect feature extraction approach in ECPT has been proposed to improve the quality of defect features,which is based on image partition,local sparse component evaluation,and feature fusion.This method can extract complete defect features by enhancing the defect area and removing background interference,such as noises and heating coil.Two typical steel specimens are utilized to testify the validity of the proposed approach.Compared with other three common feature extraction algorithms in ECPT,the proposed method can reserve more complete defect features and suppress more background interference.展开更多
Crack of conductive component is one of the biggest threats to daily production. In order to detect the crack on conductive component,the pulsed eddy current thermography models were built according to different mater...Crack of conductive component is one of the biggest threats to daily production. In order to detect the crack on conductive component,the pulsed eddy current thermography models were built according to different materials with the cracks based on finite element method(FEM) simulation. The influence of the induction heating temperature distribution with the different defect depths were simulated for the carbon fiber reinforced plastic(CFRP) materials and general metal materials. The grey value of image sequence was extracted to analyze its relationship with the depth of crack. Simulative and experimental results show that in the carbon fiber reinforced composite materials,the bigger depth of the crack is,the larger temperature rise of the crack during the heating phase is; and the bigger depth of the crack is,the faster the cooling rate of the crack during the cooling phase is. In general metal materials,the smaller depth of the crack is,the lager temperature rise of the crack during the heating phase is; and the smaller depth of the crack is,the faster the cooling rate of crack during the cooling phase is.展开更多
涡流脉冲热像(Eddy current pulsed thermography,ECPT)技术是一种新型的无损检测方法,广泛应用于金属材料结构的检测,但该技术常依赖人工经验提取特征进行裂纹检测与识别,自动化和智能性化程度不足。结合涡流脉冲热像技术以及循环神经...涡流脉冲热像(Eddy current pulsed thermography,ECPT)技术是一种新型的无损检测方法,广泛应用于金属材料结构的检测,但该技术常依赖人工经验提取特征进行裂纹检测与识别,自动化和智能性化程度不足。结合涡流脉冲热像技术以及循环神经网络(Recurrent Neural Network,RNN)的特性,提出一种基于双向长短期记忆网络(Bidirectional Long Short-Term Memory Network,Bi-LSTM)金属疲劳裂纹涡流脉冲热像分类识别方法。实验通过涡流加热装置对被测金属试件进行感应加热,使用红外热像采集装置对金属平板试件进行实时的数据采集,获得图像序列并制作数据集。运用设计的Bi-LSTM模型增强特征向量中的时序信息,对不同尺寸裂纹的热图像进行训练并测试。实验分析表明,Bi-LSTM网络可有效应用于金属疲劳裂纹检测与识别,针对现有裂纹检测准确率可达到100%,优于传统神经网络和其他深度学习的模型,具有更高的识别精度。展开更多
基金the National Natural Science Foundation of China under Grants No.51607024 and No.61671109.
文摘The eddy current pulsed thermography(ECPT)technique is a research focus in the non-destructive testing(NDT)area for defect inspection.Defect feature extraction for defect information analysis in ECPT is limited by image contrast,heat diffusion,background interference,etc.In this paper,a defect feature extraction approach in ECPT has been proposed to improve the quality of defect features,which is based on image partition,local sparse component evaluation,and feature fusion.This method can extract complete defect features by enhancing the defect area and removing background interference,such as noises and heating coil.Two typical steel specimens are utilized to testify the validity of the proposed approach.Compared with other three common feature extraction algorithms in ECPT,the proposed method can reserve more complete defect features and suppress more background interference.
基金supported by National Natural Science Foundation of China under Grant No. 51107053, 61501483 and 11402264Key Laboratory of Nondestructive Testing (Nanchang Hangkong University) ,Ministry of Education under Grant No ZD201629001+1 种基金National Key Research and Development Program of China (2016YFF0203400)Postgraduate Research & Practice Innovation Program of Jiangsu Provence under Grant No SJCX17_0487
文摘Crack of conductive component is one of the biggest threats to daily production. In order to detect the crack on conductive component,the pulsed eddy current thermography models were built according to different materials with the cracks based on finite element method(FEM) simulation. The influence of the induction heating temperature distribution with the different defect depths were simulated for the carbon fiber reinforced plastic(CFRP) materials and general metal materials. The grey value of image sequence was extracted to analyze its relationship with the depth of crack. Simulative and experimental results show that in the carbon fiber reinforced composite materials,the bigger depth of the crack is,the larger temperature rise of the crack during the heating phase is; and the bigger depth of the crack is,the faster the cooling rate of the crack during the cooling phase is. In general metal materials,the smaller depth of the crack is,the lager temperature rise of the crack during the heating phase is; and the smaller depth of the crack is,the faster the cooling rate of crack during the cooling phase is.
文摘涡流脉冲热像(Eddy current pulsed thermography,ECPT)技术是一种新型的无损检测方法,广泛应用于金属材料结构的检测,但该技术常依赖人工经验提取特征进行裂纹检测与识别,自动化和智能性化程度不足。结合涡流脉冲热像技术以及循环神经网络(Recurrent Neural Network,RNN)的特性,提出一种基于双向长短期记忆网络(Bidirectional Long Short-Term Memory Network,Bi-LSTM)金属疲劳裂纹涡流脉冲热像分类识别方法。实验通过涡流加热装置对被测金属试件进行感应加热,使用红外热像采集装置对金属平板试件进行实时的数据采集,获得图像序列并制作数据集。运用设计的Bi-LSTM模型增强特征向量中的时序信息,对不同尺寸裂纹的热图像进行训练并测试。实验分析表明,Bi-LSTM网络可有效应用于金属疲劳裂纹检测与识别,针对现有裂纹检测准确率可达到100%,优于传统神经网络和其他深度学习的模型,具有更高的识别精度。
