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: A damage identification method for a cantilever beam based on a multifractal spectrum of a multi-scale reconstructed attractor includes: acquiring an original acceleration signal of the cantilever beam by a dynamic measurement system, performing stationary wavelet decomposition on a pretreated acceleration signal to obtain multi-scale sub-signals, selecting the multi-scale sub-signal that can represent main vibration characteristics of the cantilever beam for phase space reconstruction and normalization to obtain a normalized multi-scale reconstructed attractor, constructing the multifractal spectrum of the multi-scale reconstructed attractor, establishing a damage index based on a singularity index of the multifractal spectrum, and identifying and locating damage of the cantilever beam according to a relative numerical value of the damage index.

Abstract: A boundary adaptive structural fatigue damage detection method driven by time-domain information entropy comprises a sensor sequence composed of several sensors arranged on the structure, which is used to apply excitation to the structure, collect the displacement time-history response curves at different positions on the structure, and establish a database of time-history data. According to the data set in the database, the information entropy of the time-history response at different positions on the acquisition structure is obtained based on the information entropy to measure the disorder degree of the time-domain response signal. According to the location of several sensors, the information entropy values of the time-history response are connected in turn to obtain the time-history information entropy curve of the whole structure. Analyze of time-history information entropy curve, and the information entropy curve will show jump phenomena to determine the location of the crack.

Abstract: The present disclosure provides an automatic test system for actual stress of a bridge based on DIC technology, where the system includes a camera, a phosphor spraying device, a computer, and a sliding rail; the sliding rail is arranged on both sides of an upper wing of a box-shaped concrete beam; the phosphor spraying device is used to spray phosphor on a web of the box-shaped concrete beam to form speckles of varying light and shade; the camera is slidably connected to the sliding rail through a bracket, and is used to photograph the speckles and transmit a speckle image to the computer; and the computer is used to analyze and process the speckle image taken by the camera and generate a time history diagram of stress.

Abstract: A structural dynamic parameter identification method aided by a rPCK surrogate model comprises the following steps. Establish a finite element model that roughly reflects the structural system to be analyzed. Establish the dynamic parameter space sample set. The structural system response space sample set driven by the dynamic parameter space sample set is established by using the probabilistic finite element analysis. The robust polynomial Chaos Kriging surrogate model is obtained by mapping the dynamic parameter space sample set to the structural system response space sample set. The measured structural system response is used to drive the rPCK surrogate model, and then Bayesian inference is used to identify the structural dynamic parameters. The mean value of Bayesian posterior estimation is used as the estimated value of structural dynamic parameters. The proposed method creates conditions for establishing a high-fidelity finite element model of the actual engineering structural system.