Search

The damage degree of a reinforced concrete structure is closely related to the generation and expansion of cracks. However, the traditional damage assessment methods of reinforced concrete structures have defects, including low efficiency of crack detection, low accuracy of crack extraction, and dependence on the experience of inspectors to evaluate the damage of structures. Because of the above problems, this paper proposes a damage assessment method for concrete members combining the U-Net convolutional neural network and crack fractal features. Firstly, the collected test crack images are input into U-Net for segmenting and extracting the output cracks. The damage to the concrete structure is then classified into four empirical levels according to the damage index (DI). Subsequently, a linear regression equation is constructed between the fractal dimension (D) of the cracks and the damage index (DI) of the reinforced concrete members. The damage assessment is then performed by predicting the damage index using linear regression. The method was subsequently employed to predict the damage level of a reinforced concrete shear wall–beam combination specimen, which was then compared with the actual damage level. The results demonstrate that the damage assessment method for concrete members proposed in this study is capable of effectively identifying the damage degree of the concrete members, indicating that the method is both robust and generalizable. [ABSTRACT FROM AUTHOR]

The rapid and accurate reconstruction of the supersonic combustor flow field is of great significance for sensing and predicting the combustion state. Existing deep learning methods pay less attention to the convergence speed of flow field reconstruction, which results in longer training and prediction times for the models. This study proposes a method for reconstructing the flow field in supersonic combustor by combining a reduced-order model based on proper orthogonal decomposition (POD) with a multi-branch convolutional neural network. This method first analyzes the effectiveness of POD reconstruction. Then, based on the wall pressure data of the supersonic engine combustor, it performs flow field image reconstruction. Finally, through error calculation and gradient updating with low-resolution principal component flow field shadow images obtained from the POD algorithm, the high-precision and efficient prediction of flow field images is achieved. Different equivalence ratio hydrogen fuel combustion experiments were conducted in a pulsed combustion wind tunnel with an incoming flow Mach number of 2.5. The learning model was trained and tested using the dataset obtained from these experiments. Numerous experiments demonstrated that the model can effectively reconstruct the wave structures of complex flow fields. Multiple evaluation indicators indicated that the reconstructed flow field of the combustor shows good agreement with that obtained from ground wind tunnel testing. Furthermore, after introducing the POD dimensionality reduction model, the training time was reduced by 32.03%, effectively improving the training time complexity of the model. [ABSTRACT FROM AUTHOR]

At present, the surveillance of river floating in China is labor-intensive, time-consuming, and may miss something, so a fast and accurate automatic detection method is necessary. The two-stage convolutional neural network models appear to have high detection accuracy, but it is hard to reach real-time detection, while on the other hand, the one-stage models are less time-consuming but have lower accuracy. In response to the above problems, we propose a one-stage object detection model EYOLOv3 to achieve real-time and high accuracy detection of floating objects in video streams. Firstly, we design a multi-scale feature extraction and fusion module to improve the feature extraction capability of the network. Secondly, a better clustering algorithm is used to analyze the size characteristics of floating objects to design the anchor box, enabling the network to detect objects more effectively. Then a focus loss function is proposed to make the network effectively overcome the sample imbalance problem, and finally, an improved NMS algorithm is proposed to solve the object suppressed problem. Experiments show that the proposed model is efficient in detection of river floating objects, and has better performance than the classical object detection method and the latest method, realizing real-time floating detection in video streams. [ABSTRACT FROM AUTHOR]

Ultrasound image segmentation is a challenging task due to the complexity of lesion types, fuzzy boundaries, and low-contrast images along with the presence of noises and artifacts. To address these issues, we propose an end-to-end multi-scale feature extraction and fusion network (MEF-UNet) for the automatic segmentation of ultrasound images. Specifically, we first design a selective feature extraction encoder, including detail extraction stage and structure extraction stage, to precisely capture the edge details and overall shape features of the lesions. In order to enhance the representation capacity of contextual information, we develop a context information storage module in the skip-connection section, responsible for integrating information from adjacent two-layer feature maps. In addition, we design a multi-scale feature fusion module in the decoder section to merge feature maps with different scales. Experimental results indicate that our MEF-UNet can significantly improve the segmentation results in both quantitative analysis and visual effects. • Proposing a multi-scale feature extraction and fusion network (MEF-UNet) for ultrasound image segmentation. • MEF-UNet includes selective feature extraction module, context information storage module and multi-scale feature fusion module. • MEF-UNet demonstrates superior performance in both quantitative analysis and visual effects. [ABSTRACT FROM AUTHOR]