Steel crack depth estimation based on 2D images using artificial neural networks

Abstract Automatic crack detection is needed to reduce cost and to improve quality of surface inspection that is needed for maintenance of infrastructures. In this research, a novel system was developed to detect steel cracks and to estimate their depth from 2D images. The objective is to develop an affordable and user-friendly inspection system in replacement of expensive 3D measurement devices. A learning strategy was adopted and several learning structures were exploited to decide on the suitable structure. The average intensities of 2D steel crack profiles was fed to neural network together with the maximum depth of steel cracks measured by laser microscope to train a learning structure. Feed forward back propagation Neural Network was found to produce an overall average error of 18.81% in testing which is 10% less than the previous error using another learning strategy (updated 3D Make toolbox) for depth recovery. The system performance is comparable to the state of the art and provides an applicable and affordable inspection device.

[1]  Lu Sun,et al.  Weighted Neighborhood Pixels Segmentation Method for Automated Detection of Cracks on Pavement Surface Images , 2016, J. Comput. Civ. Eng..

[2]  Dariush Mirshekar-Syahkal,et al.  A Method for Sizing Long Surface Cracks in Metals Based on the Measurement of the Surface Magnetic Field , 1990 .

[3]  Yun Liu,et al.  Automatic Crack Detection and Classification Method for Subway Tunnel Safety Monitoring , 2014, Sensors.

[4]  Yasser S. Mohamed,et al.  Crack Width Estimation Using Feed and Cascade Forward Back Propagation Artificial Neural Networks , 2018, Key Engineering Materials.

[5]  Baldev Raj,et al.  AN INTELLIGENT IMAGING SCHEME FOR AUTOMATED EDDY CURRENT TESTING , 2001 .

[6]  Sudeep Sarkar,et al.  Modeling of Crack Depths in Digital Images of Concrete Pavements Using Optical Reflection Properties , 2010 .

[7]  Manjriker Gunaratne,et al.  Neural Network for Rapid Depth Evaluation of Shallow Cracks in Asphalt Pavements , 2004 .

[8]  Tara C. Hutchinson,et al.  Image-Based Framework for Concrete Surface Crack Monitoring and Quantification , 2010 .

[9]  Ning Wang,et al.  An improved algorithm for image crack detection based on percolation model , 2015 .

[10]  Baldev Raj,et al.  Quantitative eddy current testing using radial basis function neural networks , 2004 .

[11]  Jérôme Idier,et al.  Automatic Crack Detection on Two-Dimensional Pavement Images: An Algorithm Based on Minimal Path Selection , 2016, IEEE transactions on intelligent transportation systems (Print).

[12]  B. Raj,et al.  Influence of crack length on crack depth measurement by an alternating current potential drop technique , 2010 .

[13]  S Dixon,et al.  Detection of cracks in metal sheets using pulsed laser generated ultrasound and EMAT detection. , 2011, Ultrasonics.

[14]  Kristin J. Dana,et al.  Automated Crack Detection on Concrete Bridges , 2016, IEEE Transactions on Automation Science and Engineering.

[15]  D. Dădârlat,et al.  Depth estimation of surface cracks on metallic components by means of lock-in thermography. , 2013, The Review of scientific instruments.

[16]  Takeo Kanade,et al.  Geometric reasoning for single image structure recovery , 2009, CVPR.

[17]  Yonghong Zhang,et al.  Estimating crack size and location in a steel plate using ultrasonic signals and CFBP Neural Networks , 2008, 2008 Canadian Conference on Electrical and Computer Engineering.

[18]  Pedro Arias-Sánchez,et al.  Assessment of cracks on concrete bridges using image processing supported by laser scanning survey , 2017 .

[19]  Fan Meng,et al.  Automatic Road Crack Detection Using Random Structured Forests , 2016, IEEE Transactions on Intelligent Transportation Systems.

[20]  Oral Büyüköztürk,et al.  Deep Learning‐Based Crack Damage Detection Using Convolutional Neural Networks , 2017, Comput. Aided Civ. Infrastructure Eng..