A structural health monitoring (SHM) system provides an efficient way to diagnose the condition of critical and largescale structures such as long-span bridges. With the development of SHM techniques, numerous condition assessment and damage diagnosis methods have been developed to monitor the evolution of deterioration and long-term structural performance of such structures, as well as to conduct rapid damage and post-disaster assessments. However, the condition assessment and the damage detection methods described in the literature are usually validated by numerical simulation and/or laboratory testing of small-scale structures with assumed deterioration models and artificial damage, which makes the comparison of different methods invalid and unconvincing to a certain extent. This paper presents a full-scale bridge benchmark problem organized by the Center of Structural Monitoring and Control at the Harbin Institute of Technology. The benchmark bridge structure, the SHM system, the finite element model of the bridge, and the monitored data are presented in detail. Focusing on two critical and vulnerable components of cable-stayed bridges, two benchmark problems are proposed on the basis of the field monitoring data from the full-scale bridge, that is, condition assessment of stay cables (Benchmark Problem 1) and damage detection of bridge girders (Benchmark Problem 2). For Benchmark Problem 1, the monitored cable stresses and the fatigue properties of the deteriorated steel wires and cables are presented. The fatigue life prediction model and the residual fatigue life assessment of the cables are the foci of this problem. For Benchmark Problem 2, several damage patterns were observed for the cable-stayed bridge. The acceleration time histories, together with the environmental conditions during the damage development process of the bridge, are provided. Researchers are encouraged to detect and to localize the damage and the damage development process. All the datasets and detailed descriptions, including the cable stresses, the acceleration datasets, and the finite element model, are available on the Structural Monitoring and Control website (http://smc.hit.edu.cn).

Numerous investigations have indicated that structural modal parameters are significantly impacted by varying environmental and operational conditions. This phenomenon will cause confusion when conducting modal-based damage detection and model updating. This paper investigates the dependency of modal frequencies, modal shapes and the associated damping ratios on temperature and wind velocity. The nonlinear principal component analysis (NLPCA) is first employed as a signal pre-processing tool to distinguish temperature and wind effects on structural modal parameters from other environmental factors. The pre-processed dataset by NLPCA implies the relationship between modal parameters and temperature as well as wind velocity. Consequently, the artificial neural network (ANN) technique is employed to model the relationship between the pre-processed modal parameters and environmental factors. Numerical results indicate that pre-processed modal parameters by NLPCA can retain the most features of original signals. Furthermore, the pre-processed modal frequency and damping ratios are dramatically affected by temperature and wind velocity. The ANN regression models have good capacities for mapping relationship of environmental factors and modal frequency, damping ratios. However, environmental effects on the entire modal shapes are insignificant. damping ratio are the accurate reflection of the structural properties such as stiffness and damage. However, the application vibration-based damage detection method for civil engineering structures is complicated, because modal parameters of a real structure are strongly affected by factors other than structural damages. These factors include (i) variations in material properties; (ii) environmental variability (such as temperature, wind velocity and humidity, etc.) and variability in operational conditions (such as traffic flow) during measurement; and (iii) errors associated with measured datasets and processing techniques. If the effect of these uncertainties on modal parameters is larger than or comparable to effect of structural damage on its modal parameters, the structural damage cannot be reliably identified. As a matter of fact, it has been observed from some field tests that the variation of modal parameters due to changes of environmental factors is very significant, and can be even larger than those due to rather severe structural damage. For example, Alampalli [3] presented that the relative modal frequency differences (df ) of a bridge due to freezing of the supports (df 5 40-50%) were an order of magnitude larger than changes due to damage (df 5 3-8%), which was in that case an artificial saw cut across the bottom flanges of both girders. Therefore, studying the environmental effects on modal parameters is important for reliable performance of damage detection algorithm. Considerable research efforts have been devoted to investigating the influence of environmental factors on dynamical characteristics via field measurements and dynamic tests, including Roberts and...

Summary This paper proposes an identification framework based on a restricted Boltzmann machine (RBM) for crack identification and extraction from images containing cracks and complicated background inside steel box girders of bridges. The original images that include fatigue crack and other background information are obtained by a consumer‐grade camera inside the steel box girder. The original images are cut into a number of elements with small size as the input dataset, and a state representation vector is artificially labeled to every image element used for the crack identification. A deep learning model or network consisting of multiple processing RBM layers to learn the abstract features is constructed to match the input image elements with corresponding state representation vectors. Next, a three‐layer RBM with 500; 500; and 2,000 hidden units is trained as the hidden layers in the deep learning network. A contrastive divergence learning algorithm is employed for training the deep network to update and obtain the optimal parameters (i.e., the biases and weights). The new input image elements labeled as crack are sorted out and assembled to form an output image. A deep network is modeled through the consumer‐grade camera images containing cracks and complicated background information using the proposed approach. The accuracy and ability to identify cracks from new images with different resolutions using the trained deep network are validated. Furthermore, effects of element size on reconstruction error and identification accuracy are investigated. The results show that there exists optimal element size; that is, too small and too large element sizes both increase the reconstruction error and decrease the identification accuracy.