Deep learning, geometric characterization and hydrodynamic modeling for assessing sewer defect impacts on urban flooding: A case study in Guangzhou, China.

Deep learning techniques have offered innovative and efficient tools for accurate and automated detection of sewer defects by leveraging large-scale sewer data and advanced feature learning algorithms. However, there has been a lack of thorough characterization of the geometric properties of segmented defects, let alone systematically calculate the severity level of sewer defects and quantitatively evaluate their impacts on flood conditions in hydrodynamic models. This study proposed a comprehensive framework and related metrics to accurately and automatically detect, segment, characterize, and evaluate the impacts of sewer defects on flooded nodes and volumes by integrating a DeepLabv3+-based segmentation technique, an automated geometric characterization and severity quantification module, and a GIS and SWMM-based hydrodynamic modeling. The results clearly showed in details where and how much the urban flooding was affected by the different defect types. The segmentation model achieved satisfactory detection performance, with mean pixel accuracy (MPA), mean intersection over union (MIoU), and frequency weighted intersection over union (FWIoU) of 0.99, 0.74 and 0.95, respectively. In terms of severity level quantification, there were 98%, 90%, 90% and 83% of predictions consistent with real conditions for falling off, obstacle, disjoint and leakage. It was shown that the number of surcharging manholes and total flood volume (TFV) were greatly affected by sewer defects, with over 16% increase in TFVs under all investigated rainfall events. The results addressed the impacts of sewer defects on urban flooding and demonstrated the powerful tools provided by the proposed framework for decision-making on sewer defect detection and management.

Reconstruction of Composite Stiffness Matrix with Array-Guided Wave-Based Genetic Algorithm.

Accurate measurement of the material parameters of composite in a nondestructive manner is of great significance for evaluating mechanical performance. This study proposes to use a genetic algorithm (GA) to reconstruct the stiffness matrix of carbon fiber reinforced polymer (CFRP) with array-guided wave (GW)-based GA. By comparing the numerically calculated GW dispersion curves with the experimental wave number-frequency contour calculated with a two-dimensional Fourier transform (2D-FFT), the matching coefficient is directly obtained as the objective function of the GA, avoiding the overhead of sorting out the respective GW modes. Then the measured stiffness matrix with tensile testing and the longitudinal wave in the unidirectional CFRP is compared with the reconstructed parameters from unidirectional, cross-ply, and quasi-isotropic CFRPs with the GA. For the four independent parameters, excluding C12, an average value of 11.62% for the maximum deviation is achieved among the CFRPs with three stacking sequences, and an average deviation of 11.03% in unidirectional CFRPs is achieved for the parameters measured with different methods. A further correction of fiber orientation results in a relative deviation of only 2.72% for the elastic modulus along the tensile direction, and an expansion of the GW frequency range for the GA narrows down the relative deviation of C12 to 3.9%. The proposed GW-based GA opens up a way of in situ and nondestructive measurement for the composite stiffness matrix.

Comparisons of Differential Filtering and Homography Transformation in Modal Parameter Identification from UAV Measurement.

This paper proposes a differential filtering method for the identification of modal parameters of bridges from unmanned aerial vehicle (UAV) measurement. The determination of the modal parameters of bridges is a key issue in bridge damage detection. Accelerometers and fixed cameras have disadvantages of deployment difficulty. Hence, the actual displacement of a bridge may be obtained by using the digital image correlation (DIC) technology from the images collected by a UAV. As drone movement introduces false displacement into the collected images, the homography transformation is commonly used to achieve geometric correction of the images and obtain the true displacement of the bridge. The homography transformation is not always applicable as it is based on at least four static reference points on the plane of target points. The proposed differential filtering method does not request any reference points and will greatly accelerate the identification of the modal parameters. The displacement of the points of interest is tracked by the DIC technology, and the obtained time history curves are processed by differential filtering. The filtered signals are input into the modal analysis system, and the basic modal parameters of the bridge model are obtained by the operational modal analysis (OMA) method. In this paper, the power spectral density (PSD) is used to identify the natural frequencies; the mode shapes are determined by the ratio of the PSD transmissibility (PSDT). The identification results of three types of signals are compared: UAV measurement with differential filtering, UAV measurement with homography transformation, and accelerometer-based measurement. It is found that the natural frequencies recognized by these three methods are almost the same. This paper demonstrates the feasibility of UAV-differential filtering method in obtaining the bridge modal parameters; the problems and challenges in UAV measurement are also discussed.

Multi-Sensor and Decision-Level Fusion-Based Structural Damage Detection Using a One-Dimensional Convolutional Neural Network.

This paper presents a novel approach to substantially improve the detection accuracy of structural damage via a one-dimensional convolutional neural network (1-D CNN) and a decision-level fusion strategy. As structural damage usually induces changes in the dynamic responses of a structure, a CNN can effectively extract structural damage information from the vibration signals and classify them into the corresponding damage categories. However, it is difficult to build a large-scale sensor system in practical engineering; the collected vibration signals are usually non-synchronous and contain incomplete structure information, resulting in some evident errors in the decision stage of the CNN. In this study, the acceleration signals of multiple acquisition points were obtained, and the signals of each acquisition point were used to train a 1-D CNN, and their performances were evaluated by using the corresponding testing samples. Subsequently, the prediction results of all CNNs were fused (decision-level fusion) to obtain the integrated detection results. This method was validated using both numerical and experimental models and compared with a control experiment (data-level fusion) in which all the acceleration signals were used to train a CNN. The results confirmed that: by fusing the prediction results of multiple CNN models, the detection accuracy was significantly improved; for the numerical and experimental models, the detection accuracy was 10% and 16-30%, respectively, higher than that of the control experiment. It was demonstrated that: training a CNN using the acceleration signals of each acquisition point and making its own decision (the CNN output) and then fusing these decisions could effectively improve the accuracy of damage detection of the CNN.

Thoracic aorta stent grafts design in terms of biomechanical investigations into flexibility.

The present study aimed to design and optimize thoracic aorta stent grafts (SGs) based on the influence of geometric parameters on flexibility and durability. Five geometric parameters were selected, including strut height, strut number, strut radius, wire diameter, and graft thickness. Subsequently, 16 finite element (FE) models were established with an orthogonal design consisting of five factors and four levels. The influences of a single factor and all the geometric parameters' influence magnitude on the device flexibility were then determined. The results showed that all the other parameters had an opposite effect on global and local flexibility except for the wire diameter. The graft thickness exhibited the most remarkable impact on the global flexibility of SGs, while the strut radius influenced flexibility slightly. However, for the local flexibility analysis, the graft thickness became the least significant factor, and the wire diameter exerted the most significant influence. The SG with better global flexibility can be guided easily in the tortuous vessels, and better local flexibility improves the sealing effect between the graft and aortic arch. In conclusion, this study's results indicated that these geometric parameters exerted different influences on flexibility and durability, providing a strategy for designing thoracic aorta SGs, especially for the thoracic aortic arch diseases.

Hemodynamic analysis of a novel stent graft design with slit perforations in thoracic aortic aneurysm.

Thoracic endovascular aortic repair (TEVAR) has been introduced as a less invasive approach to the treatment of thoracic aortic aneurysm (TAA). However, the effectiveness of TEVAR in the treatment of TAA is often limited due to the complex anatomy of aortic arch. Flow preservation at the three supra-aortic branches further increases the overall technical difficulty. This study proposes a novel stent graft design with slit perforations that can positively alter the hemodynamics at the aortic arch while maintaining blood flow to supra-aortic branches. We carried out a computational fluid dynamic (CFD) analysis to evaluate flow characteristics near stented aortic arch in simplified TAA models, followed by in-vitro experiments using particle image velocimetry (PIV) in a mock circulatory loop. The hemodynamics result was studied in terms of time-averaged wall shear stress (TAWSS), oscillating shear index (OSI), and endothelial cell action potential (ECAP). The results showed that the stent graft with slit perforations can reduce the disturbed flow region considerably. Furthermore, the effect of the slits on flow preservation to the supra-aortic branches was simulated and compared with experimental results. The effectiveness of the stent graft with slit perforations in preserving flow to the branches was demonstrated by both simulated and experimental results. Low TAWSS and elevated ECAP were observed in the aortic arch aneurysm after the placement of the stent graft with slits, implying the potential of thrombus formation in the aneurysm. On the other hand, the effects of the stent grafts with full-slit design and half-slit design on the shear stress did not differ significantly. The present analysis indicated that not only could the stent graft with slit perforations shield the aneurysm from rupture, but also it resulted in a favorable environment for thrombus that can contribute to the shrinkage of the aneurysm.