Despite the rapid development of sensors, structural health monitoring (SHM) still faces challenges in monitoring due to the degradation of devices and harsh environmental loads. These challenges can lead to measurement errors, missing data, or outliers, which can affect the accuracy and reliability of SHM systems. To address this problem, this study proposes a classification method that detects anomaly patterns in sensor data. The proposed classification method involves several steps. First, data scaling is conducted to adjust the scale of the raw data, which may have different magnitudes and ranges. This step ensures that the data is on the same scale, facilitating the comparison of data across different sensors. Next, informative features in the time and frequency domains are extracted and used as input for a deep neural network model. The model can effectively detect the most probable anomaly pattern, allowing for the timely identification of potential issues. To demonstrate the effectiveness of the proposed method, it was applied to actual data obtained from a long-span cable-stayed bridge in China. The results of the study have successfully verified the proposed method's applicability to practical SHM systems for civil infrastructures. The method has the potential to significantly enhance the safety and reliability of civil infrastructures by detecting potential issues and anomalies at an early stage.

In order to realize tiny bridge crack discovery by UAV-based machine vision, a novel method combining deep learning and tensor voting is proposed. Firstly, the grid images of crack are detected and descripted based on SE-ResNet50 to generate feature points. Then, the probability significance map of crack image is calculated by tensor voting with feature points, which can define the direction and region of crack. Further, the crack detection anchor box is formed by non-maximum suppression from the probability significance map, which can improve the robustness of tiny crack detection. Finally, a case study is carried out to demonstrate the effectiveness of the proposed method in the Xiangjiang-River bridge inspection. Compared with the original tensor voting algorithm, the proposed method has higher accuracy in the situation of only 1-2 pixels width crack and the existence of edge blur, crack discontinuity, which is suitable for UAV-based bridge crack discovery.

Drift angle is a significant index for diagnosing post-event structures. A common way to estimate this drift response is by using modal parameters identified under natural excitations. Although the modal parameters of shear structures cannot be identified accurately in the real environment, the identification error has little impact on the estimation when measurements from several floors are used. However, the estimation accuracy falls dramatically when there is only one accelerometer. This paper describes the susceptibility of single sensor identification to modelling error and simulations that preliminarily verified this characteristic. To make a robust evaluation from measurements of one floor of shear structures based on imprecisely identified parameters, a novel scheme is devised to approximately correct the mode shapes with respect to fictitious frequencies generated with a genetic algorithm; in particular, the scheme uses constrained minimization to take both the mathematical aspect and the realistic aspect of the mode shapes into account. The algorithm was validated by using a full-scale shear building. The differences between single-sensor and multiple-sensor estimations were analyzed. It was found that, as the number of accelerometers decreases, the error rises due to insufficient data and becomes very high when there is only one sensor. Moreover, when measurements for only one floor are available, the proposed method yields more precise and appropriate mode shapes, leading to a better estimation on the drift angle of the lower floors compared with a method designed for multiple sensors. As well, it is shown that the reduction in space complexity is offset by increasing the computation complexity.

Piezoelectric (PZT) actuators have been widely used in precision positioning fields for their excellent displacement resolution. However, due to the inherent characteristics of piezoelectric actuators, hysteresis has been proven to greatly reduce positioning performance. In this paper, five mathematical hysteretic models based on activation function are proposed to characterize the nonlinear hysteresis characteristics of piezoelectric actuators. Then the performance of the proposed models is verified by particle swarm optimization (PSO) algorithm and the experiment data. Thirdly, the fitting performance of the proposed models is compared with the classical Bouc-Wen model. Finally, the performance of the five proposed models in modelling hysteresis nonlinearity of piezoelectric drivers is compared, in terms of RMSE, MAPE, SAPE and operation efficiency, and relevant suggestions are given.

The evaluation of dynamic characteristics of bridges under operational traffic loads is a crucial aspect of bridge structural health monitoring. In the vehicle-bridge interaction (VBI) system, the vibration responses of bridge exhibit time-varying characteristics. To address this issue, an accurate time-frequency analysis method that combines the autoregressive power spectrum based empirical wavelet transform (AR-EWT) and local maximum synchrosqueezing transform (LMSST) is proposed to identify the time-varying instantaneous frequencies (IFs) of the bridge in the VBI system. The AR-EWT method decomposes the vibration response of the bridge into mono-component signals. Then, LMSST is employed to identify the IFs of each mono-component signal. The AR-EWT combined with the LMSST method (AR-EWT+LMSST) can resolve the problem that LMSST cannot effectively identify the multi-component signals with weak amplitude components. The proposed AR-EWT+LMSST method is compared with some advanced time-frequency analysis techniques such as synchrosqueezing transform (SST), synchroextracting transform (SET), and LMSST. The results demonstrate that the proposed AR-EWT+LMSST method can improve the accuracy of identified IFs. The effectiveness and applicability of the proposed method are validated through a multi-component signal, a VBI numerical model with a four-degree-of-freedom half-car, and a VBI model experiment. The effect of vehicle characteristics, vehicle speed, and road surface roughness on the identified IFs of bridge are investigated.

Rotating beams play a crucial role in representing complex mechanical components that are prevalent in vital sectors like energy and transportation industries. These components are susceptible to the initiation and propagation of cracks, posing a substantial risk to their structural integrity. This study presents a two-stage methodology for detecting the location and estimating the size of an open-edge transverse crack in a rotating Euler-Bernoulli beam with a uniform cross-section. Understanding the dynamic behavior of beams is vital for the effective design and evaluation of their operational performance. In this regard, modal parameters such as natural frequencies and eigenmodes are frequently employed to detect and identify damages in mechanical components. In this instance, the Frobenius method has been employed to determine the first two natural frequencies and corresponding eigenmodes associated with flapwise bending vibration. These calculations have been performed by solving the governing differential equation that describes the motion of the beam. Various parameters have been considered, such as rotational speed, beam slenderness, hub radius, and crack size and location. The effect of the crack has been replaced by a rotational spring whose stiffness represents the increase in local flexibility as a result of the damage presence. In the initial phase of the proposed methodology, a damage index utilizing the slope of the beam's eigenmode has been employed to estimate the location of the crack. After detecting the presence of damage, the size of the crack is determined using a Genetic Algorithm optimization technique. The ultimate goal of the proposed methodology is to enable the development of more suitable and reliable maintenance plans.