Abstract: An intelligent method for efficiently classifying concrete cracks from large amounts of image data is proposed, named inverted residual (IR) 7-Efficient Channel Attention and Convolutional Block Attention Module (EC) network. The IR7-EC network consists of a convolutional layer, seven inverted residual-ECA structures, a CBAM attention mechanism, a pooling layer, and multiple fully connected layers that are sequentially connected. The inverted residual-ECA structure consists of two components: a depthwise separable convolution-based inverted residual structure and an ECA attention mechanism. The new inverted residual structure facilitates the feature extraction of concrete cracks. Compared to conventional network structures like VGG and Resnet, the proposed IR7-EC network excels in both accuracy and efficiency. Once the IR7-EC network is fully trained, it can accurately classify various types of concrete cracks in captured images.

Abstract: An evaluation method for corrosion damage evolution of underwater concrete structures includes performing the time reversal test on the concrete beam specimen placed in the water, performing the uniaxial compression test on the concrete cube specimens; immersing the concrete beam specimen and the concrete cube specimens in a hydrochloric acid solution, and performing the time reversal test on the concrete beam specimen on the 10th, 20th and 30th days respectively. At the same time, a concrete cube specimen is taken out to perform the uniaxial compression test on the 10th, 20th and 30th days respectively; and using the above calculation results to evaluate the corrosion evolution process thereof without damaging the underwater concrete structure.