Recognition and Classification of Concrete Cracks under Strong Interference Based on Convolutional Neural Network

Abstract

This paper proposes the UmNet model based on convolutional neutral network (CNN), aiming to improve the ability to recognize and classify concrete cracks in a background complicated by construction seams and seepage traces. The model was derived from the famous CNN AlexNet. Without changing the receptive field, large convolutional kernels were replaced with small ones to reduce the parameters, deepen the network, and increase nonlinear transforms. Next, convolutional block attention module (CBAM) was introduced to highlight the key information in images and focus on high-weight channels. Finally, Bayesian network (BN) layer and L2 regularization were added, and the number of nodes in fully connected layer were reduced. A series of comparative experiments were carried out on three datasets D, P, and W. The results show that the proposed UmNet surpassed AlexNet in the recognition accuracy on D, P, and W by 3.74%, 3.17%, and 5.74%, respectively, and reduced the number of parameters by 75.04%. Therefore, our model is an effective means to recognize and classify of concrete cracks under strong interference.

Flexural Performance and Thermomechanical Coupling Analysis of Full-Iron Tailings Reinforced Concrete Beams

“…The first stage is the elastic stage (section 0A), no crack develops during this stage, when the bending moment increases to the crack bending moment, cracks appear at the bottom of the beam [26], reducing the bending stiffness of the beam. The second stage is the crack development stage (section AB), during this stage, as the bending moment increases, the crack width gradually increases and the cracks develop upward, at a certain distance, new cracks would appear [27].…”

Effect of Thermal Aging on Dynamic Mechanical Performance of a Novel Structural Adhesive

“…With excellent mechanical properties and superior environmental stability, building structural adhesives have gained popularity in the engineering field, and realized wide application in the bonding and reinforcement of structural components of buildings and in the reconstruction of existing buildings [1][2][3]. When applied to load-bearing structural components of buildings, structural adhesives are exposed to a complex environment for a long period, and disturbed by various external factors, such as temperature, humidity, and ultraviolet light.…”