Ground penetrating radar (GPR) is one of the most recommended tools for routine inspection of tunnel linings. However, the rebars in the reinforced concrete produce a strong shielding effect on the electromagnetic waves, which may hinder the interpretation of GPR data. In this work, we proposed a method to improve the identification of tunnel lining voids by designing a generative adversarial network-based rebar clutter elimination network (RCE-GAN). The designed network has two sets of generators and discriminators, and by introducing the cycle-consistency loss, the network is capable of learning high-level features between unpaired GPR images. In addition, an attention module and a dilation center part were designed in the network to improve the network performance. Validation of the proposed method was conducted on both synthetic and real-world GPR images, collected from the implementation of finite-difference time-domain (FDTD) simulations and a controlled physical model experiment, respectively. The results demonstrate that the proposed method is promising for its lower demand on the training dataset and the improvement in the identification of tunnel lining voids.

The crosshole ground-penetrating radar (GPR) technique is widely used to characterize subsurface structures, yet the interpretation of crosshole GPR data involves solving non-linear and ill-posed inverse problems. In this work, we developed a generative adversarial network (GAN)-based inversion framework to translate crosshole GPR images to their corresponding 2D defect reconstruction images automatically. This approach uses fully connected layers to extract global features from crosshole GPR images and employs a series of cascaded U-Net structures to produce high-resolution defect reconstruction results. The feasibility of the proposed framework was demonstrated on a synthetic crosshole GPR dataset created with the finite-difference time-domain (FDTD) method and real-world data from a field experiment. Our inversion network obtained recognition accuracy of 91.36%, structural similarity index measure (SSIM) of 0.93, and RAscore of 91.77 on the test dataset. Furthermore, comparisons with ray-based tomography and full-waveform inversion (FWI) suggest that the proposed method provides a good balance between inversion accuracy and efficiency and has the best generalization when inverting actual measured crosshole GPR data.

The crosshole ground penetrating radar (GPR) is a widely used tool to map subsurface properties, and inversion methods are used to derive electrical parameters from crosshole GPR data. In this paper, a probabilistic inversion algorithm that uses Markov chain Monte Carlo (MCMC) simulations within the Bayesian framework is implemented to infer the posterior distribution of the relative permittivity of the subsurface medium. Close attention is paid to the critical elements of this method, including the forward model, data type and prior information, and their influence on the inversion results are investigated. First, a uniform prior distribution is used to reflect the lack of prior knowledge of model parameters, and inversions are performed using the straight-ray model with first-arrival traveltime data, the finite-difference time-domain (FDTD) model with first-arrival traveltime data, and the FDTD model with waveform data, respectively. The cases using first-arrival traveltime data require an unreasonable number of model evaluations to converge, yet are not able to recover the real relative permittivity field. In contrast, the inversion using the FDTD model with waveform data successfully infers the correct model parameters. Then, the smooth constraint of model parameters is employed as the prior distribution. The inversion results demonstrate that the prior information barely affects the inversion results using the FDTD model with waveform data, but significantly improves the inversion results using first-arrival traveltime data by decreasing the computing time and reducing uncertainties of the posterior distribution of model parameters.

Low-coherent fiber-optic sensors combined with neural network algorithms were designed to carry out a load-sensitizing spherical bearing. Four sensing fibers were wound around the outside of the pot support of the spherical bearing uniformly deployed from upper to bottom. The upper three were configured in a distributed way to respond to the applied load as a function of the three strain sensors. The bottom one was employed as a temperature compensation sensor. A loading experiment was implemented to test the performance of the designed system. The results showed that there was a hysteresis in all the three sensors between loading and unloading process. The neural network algorithm is proposed to set up a function of the three sensors, treated as a set of input vectors to establish the input-output relationship between the applied loads and the constructed input vectors, in order to overcome the hysteresis existing in each sensor. An accuracy of 6% for load sensing was approached after temperature compensation.

In view of the first domestic offshore suspension bridge with caisson foundation, this paper mainly studies the bonding properties between underwater pre-filled aggregate grouting bed and anchorage caisson foundation. Through the test, the cohesive force of adding ordinary concrete between the anchorage caisson foundation and the grouting bed, the cohesive force of adding paper base asphalt felt between the anchorage caisson foundation and the grouting bed, and the cohesive force of adding geotextile between the anchorage caisson foundation and the grouting bed are measured, respectively. When the contact surface is concrete and geotextile, the fracture form of the specimen was analyzed by numerical simulation, and the AE variation trend of the two specimens have been studied. The results of this article can provide references for other projects.

Concrete three-point bending beams with preexisting cracks are widely used to study the growth process of I-II mixed mode cracks. Studying the failure characteristics of preexisting cracks at different locations on concrete three-point bending beams not only has important scientific significance but also has a wide range of engineering application backgrounds in the safety assessment of engineering structures. In this paper, through several numerical experiments, the influence of preexisting cracks at different positions on the failure characteristics of concrete three-point bending beams is studied, and three typical failure modes are obtained. The failure process of the specimens with three typical failure modes is discussed in detail, and it is pointed out that the crack failure mode is tensile failure. The change trends of bearing capacity, acoustic emission quantity, and acoustic emission energy of three typical failure modes are analyzed. The maximum bearing capacity, the maximum acoustic emission quantity, and energy of three failure modes of concrete three-point bending beams generally show an increasing trend.