Structural Control and Health Monitoring

The detection of ballastless track surface (BTS) defects is a prerequisite for ensuring the safe operation of high-speed railways. Traditional convolutional neural networks fail to fully exploit contextual information and lack global pixel representations. The extensive stacking of convolutions leads deep learning models to play a black-box detection role, lacking interpretability. Due to the current lack of sufficient high-quality surface data for ballastless tracks, it is a severe constraint on the accurate identification of the substructure state in high-speed railways. This paper proposes an intelligent detection method for BTS defects named TrackNet based on self-attention and transfer learning. The method enhances the fusion ability of global features of BTS defects using multihead self-attention. The model’s dependence on extensive defect data is reduced by transferring knowledge from large-scale publicly available datasets. Experimental results demonstrate that compared to advanced Swin Transformer model results, the TrackNet model achieves improvements in average accuracy and F1-score by 5.15% and 5.16%, respectively, on limited test data. The TrackNet model visualizes the decision regions of the model in identifying BTS defects, revealing the black-box recognition mechanism of deep learning models. This research performs engineering applications and provides valuable insights for the multiclass recognition of BTS defects in high-speed railways.

The multiple intersecting stiffeners on the chemical milling stiffened panel (CMSP) limit the application of active health monitoring methods on it. An imaging algorithm based on electromechanical impedance (EMI) and probability-weighting is proposed to achieve quantitative evaluation and localization of the damage on CMSP. The proposed algorithm compensates for the difference in sensor performance with coefficients and there is no need to determine the key parameters of the algorithm through prior experiments. In the paper, the applicability of ultrasonic guided wave (GW) and EMI on CMSP was first studied through the finite element method. Based on EMI and the mean absolute percentage deviation (MAPD), the selected damage indicator (DI), a probability-weighted damage imaging algorithm are proposed and experimentally verified. The results indicate that due to the reflection and attenuation effects of stiffeners on GW, the signal characteristics of damage scattering waves are contaminated, making it difficult to quantitatively characterize the damage from GW signals through DIs. MAPD is positively correlated with the damage degree and has consistency in characterizing the signal of different PZTs under the same working condition. The feasibility and accuracy of the proposed algorithm are verified through experiments which show a strong engineering application capability.

Rapid and accurate structural damage assessment after an earthquake is important for efficient emergency management. The widespread application of surveillance cameras provides a new possibility for improving the efficiency of assessment. However, it is still challenging to directly assess the structural seismic damage based on videos captured by indoor surveillance cameras during earthquakes. In this study, we elaborate on the concept of estimating the structural natural frequency based on the relative pixel displacement of inter-stories. Furthermore, we propose a strategy for post-earthquake structural damage assessment that integrates the computer vision and time-frequency analysis. This approach aims to navigate the difficulties inherent in earthquake damage assessment and improve emergency responses. The relative pixel displacement between the camera and the fixed features on the floor is extracted from videos by using the Harris corner detection and Kanade–Lucas–Tomasi algorithms. The structural natural frequency is estimated using the synchroextracting transform-enhanced empirical wavelet transform. The natural frequency shift-related seismic damage index is defined and calculated for damage assessment. A shake table experiment of a small-scale steel model is conducted to verify the accuracy and feasibility of the approach, and the practicality of the proposed approach is further verified by utilizing the data from a full-scale reinforced concrete benchmark model experiment. The results demonstrate that the approach can accurately and efficiently evaluate the structural damage after an earthquake based on the video captured by surveillance cameras during the earthquake. The error of the acquired damage index is less than 0.1. We will apply more advanced algorithms in the future to alleviate this problem.

In this study, wavelet-based damage-sensitive features are employed to derive the seismic fragility functions/curves for reinforced concrete moment-resisting frames. Two different wavelet transform functions, namely, Bior3.3 and Morlet mother wavelet families, were applied to absolute acceleration time histories of building frames to extract the wavelet-based and refined wavelet-based damage-sensitive features (i.e., DSF and rDSF). The accuracy of seismic assessments and certainty in predicting structural behavior strongly depend on the specific optimal intensity measures selected, reliability of wavelet-based damage-sensitive features, and some such intensity measures as PGA, PGV, PGD, Sa, and Sdi as the conventionally utilized measures to detect the damage state of a structure. These measures were examined against their statistical properties of efficiency, practicality, proficiency, coefficient of determination, and sufficiency to select the appropriate optimal intensity measures, which were then used to drive the fragility curves disclosing the failure or other damage states of interest. For the purposes of this study, three different concrete moment-resisting frames with four-, eight-, and twelve-story building frames were adopted for implementing the proposed approach. The findings demonstrate that the wavelet-based damage-sensitive features (DSFs/rDSF) simultaneously satisfy all the statistical properties cited above. This is evidenced by the low variance and dispersions observed in the frame damage state predictions by the fragility functions derived from the wavelet-based DSF when compared with those derived from the classical fragility analyses such as spectral acceleration at the first mode period of the structure. A final aspect of the study concerns the superior performance and efficiency of the fragility curves derived by the Bior3.3 wavelet-based DSF over those derived from Morlet wavelet-based DSF.

During the process of urban development, there is large-scale laying of underground pipeline networks and coordinated operation of both new and old networks. The underground concrete drainage pipes have become a focus of operation and maintenance due to their strong concealment and serious corrosion. The current manual inspections for subterranean concrete drainage pipelines involve high workloads and risks, which makes meeting the diagnostic needs of intricate urban pipeline networks challenging. Through advanced information technology, it has reached a consensus to intelligently perceive, accurately identify, and precise prediction of the condition of urban subterranean drainage networks. The development process of detection and evaluation methods for underground concrete drainage pipe networks is the focus of this study. The study discusses common algorithms for classifying, locating, and quantifying pipeline defects by combining the principles of deep learning with typical application examples. The intelligent progression of information collection methods, image processing techniques, damage prediction models, and pipeline diagnostic systems is systematically elaborated upon. Lastly, prospects for future research of intelligent pipeline diagnosis are provided.

Parameter identification is of great significance for the postearthquake performance evaluation of structure equipped with tuned mass damper (TMD). However, the soil-structure interaction (SSI) effects have not been considered in the parameter identification of structure with TMD yet, which influence the dynamic characteristics and seismic responses of structures. This paper aims at proposing a framework for identifying the physical parameters of soil-structure-TMD system. Firstly, the accelerated particle swarm optimization (APSO) algorithm is combined with the search space reduction (SSR) method. Then, the frequency response function and transmissibility function are adopted for output-input and input-only cases, respectively, and a simplified mechanical model for soil-structure-TMD system is employed. Next, the measured responses are used to identify the physical parameters of structure with TMD considering SSI effects. Finally, the effectiveness of the proposed identification method is investigated, and the influences of frequency band and noise pollution on the identification performance are discussed. The results show that the proposed strategy can identify the system physical parameters accurately and quickly. It is worth noting that high frequency bands and noise pollution may lead to estimation error, especially for output-only case.