Physics-Based Graphics Models in 3D Synthetic Environments as Autonomous Vision-Based Inspection Testbeds

Manual visual inspection of civil infrastructure is high-risk, subjective, and time-consuming. The success of deep learning and the proliferation of low-cost consumer robots has spurred rapid growth in research and application of autonomous inspections. The major components of autonomous inspection include data acquisition, data processing, and decision making, which are usually studied independently. However, for robust real-world applicability, these three aspects of the overall process need to be addressed concurrently with end-to-end testing, incorporating scenarios such as variations in structure type, color, damage level, camera distance, view angle, lighting, etc. Developing real-world datasets that span all these scenarios is nearly impossible. In this paper, we propose a framework to create a virtual visual inspection testbed using 3D synthetic environments that can enable end-to-end testing of autonomous inspection strategies. To populate the 3D synthetic environment with virtual damaged buildings, we propose the use of a non-linear finite element model to inform the realistic and automated visual rendering of different damage types, the damage state, and the material textures of what are termed herein physics-based graphics models (PBGMs). To demonstrate the benefits of the autonomous inspection testbed, three experiments are conducted with models of earthquake damaged reinforced concrete buildings. First, we implement the proposed framework to generate a new large-scale annotated benchmark dataset for post-earthquake inspections of buildings termed QuakeCity. Second, we demonstrate the improved performance of deep learning models trained using the QuakeCity dataset for inference on real data. Finally, a comparison of deep learning-based damage state estimation for different data acquisition strategies is carried out. The results demonstrate the use of PBGMs as an effective testbed for the development and validation of strategies for autonomous vision-based inspections of civil infrastructure.

Methodology and Application of Safety Evaluation of Reinforced Concrete Girder Bridges during Earthquakes

The actual earthquake resistance performance and the seismic damage state of bridges during future earthquakes are important issues that need to be resolved. Using an expressway reinforced concrete (RC) girder bridge in a high seismic intensity area of China as the research object, the damage correlation between different structural components of the bridge is analyzed, and the key components that determine the structural safety state of the bridge are determined. Then, the safety evaluation indexes of the bridge pier and bearing are researched, and a two-stage seismic safety evaluation methodology for RC girder bridges is proposed. The first stage is a rapid and general evaluation using empirical statistical methods, and the second stage is a precise evaluation obtained by calculating the damage index of the components. Subsequently, the seismic damage prediction matrix is presented. Considering the modification of the bridge span number, service life, and skew angle, a seismic safety evaluation from a typical single bridge to a group of bridges of the same type is implemented. Finally, an actual expressway bridge in China is presented as a numerical example to illustrate the application of the method. The research results show that damage to the key components, including bearings, piers, and abutments, is the deciding factor of the bridge damage state. The seismic damage states of piers and bearings can be conveniently assessed according to the pier top displacement angle and bearing shear deformation during earthquakes. According to the suggested standard of RC girder bridge seismic damage, the seismic safety evaluation of the whole bridge structure can be obtained using the seismic safety evaluation of individual key components of the bridge structure. According to the evaluation results of individual bridges and considering the modification of influencing factors, an earthquake performance evaluation of a group of bridges of the same type can be obtained. The two-stage seismic safety evaluation methodology proposed in this study is effective and efficient.

Damage evaluation and precursor of sandstone under the uniaxial compression: Insights from the strain-field heterogeneity

The stress-induced microcrack evolution in rock specimens causes a series of physical changes and heterogeneous deformations. Some of these attributes (such as sound, electricity, heat, etc.) have been effectively used to identify the damage state and precursory information of the rock specimens. However, the strain-field heterogeneity has not been investigated previously. In this study, the relationship of the strain-field heterogeneity and damage evolution of three sandstone specimens under the uniaxial compressive load was analyzed statistically. The acoustic emission (AE) and two-dimensional digital image correlation were employed for real-time evaluation of the AE parameters and strain-field heterogeneity. The results showed that the strain-field heterogeneity was closely related to the rock damage that amplified with the applied stress, and exhibited two features; numerical difference and spatial concentration. Subsequently, these two features were characterized by the two proposed heterogeneous quantitative indicators (i.e., the degree and space heterogeneities). Further, their four transition processes were in agreement with the damage stages confirmed by AE parameters: a relatively constant trend; growth with a relatively constant rate; drastic increase trend; and increase with a high rate to maximum value. Moreover, a time sequence chain for damage precursor was built, where the heterogeneous quantitative indicators and AE parameters differed in sensitivity to microcrack development and can be used as a damage warning at the varying magnitude of the external load.

Numerical Simulation of Dynamic Response and Evaluation of Flexural Damage of RC Columns under Horizontal Impact Load

By using the ABAQUS finite element (FE) model, which has been verified by experiments, the deformation and internal force changes of RC columns during the impact process are investigated, and a parametric analysis is conducted under different impact kinetic energies Ek. According to the development path of the bottom bending moment-column top displacement curve under impact, the member is in a slight damage state when the curve rebounds before reaching the peak and in a moderate or severe damage state when the curve exceeds the peak, in which case the specific damage state of the member needs to be determined by examining whether there is a secondary descending stage in the curve. Accordingly, a qualitative method for evaluating the bending failure of RC column members under impact is obtained. In addition, the damage state of RC columns under impact can also be quantitatively evaluated by the ratio of the equivalent static load Feq and the ultimate static load-bearing capacity Fsu.

Physics-Based Graphics Models in 3D Synthetic Environments Enabling Autonomous Vision-Based Structural Inspections

Manual visual inspections typically conducted after an earthquake are high-risk, subjective, and time-consuming. Delays from inspections often exacerbate the social and economic impact of the disaster on affected communities. Rapid and autonomous inspection using images acquired from unmanned aerial vehicles offer the potential to reduce such delays. Indeed, a vast amount of re-search has been conducted toward developing automated vision-based methods to assess the health of infrastructure at the component and structure level. Most proposed methods typically rely on images of the damaged structure, but seldom consider how the images were acquired. To achieve autonomous inspections, methods must be evaluated in a comprehensive end-to-end manner, incorporating both data acquisition and data processing. In this paper, we leverage recent advances in computer generated imagery (CGI) to construct a 3D synthetic environment for simulation of post-earthquake inspections that allows for comprehensive evaluation and valida-tion of autonomous inspection strategies. A critical issue is how to simulate and subsequently render the damage in the structure after an earthquake. To this end, a high-fidelity nonlinear finite element model is incorporated in the synthetic environment to provide a representation of earthquake-induced damage; this finite element model, combined with photo-realistic rendering of the damage, is termed herein a physics-based graphics models (PBGM). The 3D synthetic en-vironment with PBGMs provide a comprehensive end-to-end approach for development and validation of autonomous post-earthquake strategies using UAVs, including: (i) simulation of path planning of virtual UAVs and image capture under different environmental conditions; (ii) au-tomatic labeling of captured images, potentially providing an infinite amount of data for training deep neural networks; (iii) availability of the ground truth damage state from the results of the finite-element simulation; and (iv) direct comparison of different approaches to autonomous as-sessments. Moreover, the synthetic data generated has the potential to be used to augment field datasets. To demonstrate the efficacy of PBGMs, models of reinforced concrete moment-frame buildings with masonry infill walls are examined. The 3D synthetic environment employing PBGMs is shown to provide an effective testbed for development and validation of autonomous vision-based post-earthquake inspections that can serve as an important building block for ad-vancing autonomous data to decision frameworks.