Identification framework for cracks on a steel structure surface by a restricted Boltzmann machines algorithm based on consumer-grade camera images

Abstract

Summary This paper proposes an identification framework based on a restricted Boltzmann machine (RBM) for crack identification and extraction from images containing cracks and complicated background inside steel box girders of bridges. The original images that include fatigue crack and other background information are obtained by a consumer‐grade camera inside the steel box girder. The original images are cut into a number of elements with small size as the input dataset, and a state representation vector is artificially labeled to every image element used for the crack identification. A deep learning model or network consisting of multiple processing RBM layers to learn the abstract features is constructed to match the input image elements with corresponding state representation vectors. Next, a three‐layer RBM with 500; 500; and 2,000 hidden units is trained as the hidden layers in the deep learning network. A contrastive divergence learning algorithm is employed for training the deep network to update and obtain the optimal parameters (i.e., the biases and weights). The new input image elements labeled as crack are sorted out and assembled to form an output image. A deep network is modeled through the consumer‐grade camera images containing cracks and complicated background information using the proposed approach. The accuracy and ability to identify cracks from new images with different resolutions using the trained deep network are validated. Furthermore, effects of element size on reconstruction error and identification accuracy are investigated. The results show that there exists optimal element size; that is, too small and too large element sizes both increase the reconstruction error and decrease the identification accuracy.

Vision‐Based Fatigue Crack Detection of Steel Structures Using Video Feature Tracking

“…Similar deep learning‐based approaches have been reported by Xu et al. () and Zhang et al. () to detect cracks on a steel box girder and asphalt surfaces, respectively.…”

“…Cha et al (2017) proposed a robust classifier by learning the invariant features from a large volume of images using deep learning technologies to achieve more robust crack detection on concrete components against different lighting conditions. Similar deep learning-based approaches have been reported by Xu et al (2017) and Zhang et al (2017) to detect cracks on a steel box girder and asphalt surfaces, respectively. Chen et al (2017) combined binary patterns, support vector machine, and Bayesian decision theory for accurately and robustly detecting cracks on metallic surfaces.…”

Automatic seismic damage identification of reinforced concrete columns from images by a region-based deep convolutional neural network

“…27 Cracks are one of the most attractive subjects for damage identification. Restricted Boltzmann machine and CNNs are broadly used for crack identification in the surfaces of steel structures, [28][29][30] concrete structures, 31 pavement, 32,33 tunnel, 34,35 and railway. 36,37 Besides investigations on cracks, studies on other types of structural damages are also carried out.…”

Concrete crack detection with handwriting script interferences using faster region‐based convolutional neural network

“…The use of machine learning algorithms (MLAs), on the other hand, is now a promising way to detect objects accurately in real‐world scenarios (Adeli & Hung, ; LeCun, Bengio, & Hinton, ; Rafiei & Adeli, ; Torres, Galicia, Troncoso, & Martínez‐Álvarez, ). Some machine‐learning‐based crack identification models integrated with IPTs for bridge inspection have been presented to identify and extract cracks from images (F. C. Chen, Jahanshahi, Wu, & Joffe, ; J. H. Chen, Su, Cao, Hsu, & Lu, ; Reagan, Sabato, & Niezrecki, ; Y. Xu, Li et al., ). Although many MLAs have been presented for the identification of cracks from images, difficulties remain for these techniques to maintain consistent results depending on image resolution.…”

“…Therefore, some studies were conducted to deal with complex background issues. For example, some algorithms were proposed for the identification of cracks with complicated background information (e.g., hand‐marked information) on a steel structure, which, however, could not predict the location of the cracks (Y. Xu, Bao et al., ; Y. Xu, Li et al., ). The extraction of cracks still required certain complex post processing techniques.…”