• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.141-151
• /
• 2022

In recent years, the industry and research communities have focused on developing autonomous crack inspection approaches, which mainly include image acquisition and crack detection. In these approaches, mobile devices such as cameras, drones or smartphones are utilized as sensing platforms to acquire structural images, and the deep learning (DL)-based methods are being developed as important crack detection approaches. However, the process of image acquisition and collection is time-consuming, which delays the inspection. Also, the present mobile devices such as smartphones can be not only a sensing platform but also a computing platform that can be embedded with deep neural networks (DNNs) to conduct on-site crack detection. Due to the limited computing resources of mobile devices, the size of the DNNs should be reduced to improve the computational efficiency. In this study, an architecture called pruned crack recognition network (PCR-Net) was developed for the detection of structural cracks. A dataset containing 11000 images was established based on the raw images from bridge inspections. A pruning method was introduced to reduce the size of the base architecture for the optimization of the model size. Comparative studies were conducted with image processing techniques (IPTs) and other DNNs for the evaluation of the performance of the proposed PCR-Net. Furthermore, a modularly designed framework that integrated the PCR-Net was developed to realize a DL-based crack detection application for smartphones. Finally, on-site crack detection experiments were carried out to validate the performance of the developed system of smartphone-based detection of structural cracks.

• Structural Engineering and Mechanics
• /
• v.81 no.3
• /
• pp.293-303
• /
• 2022

As infrastructure ages and traffic load increases, serious public concerns have arisen for the well-being of bridges. The current health monitoring practice focuses on large-scale bridges rather than short span bridges. However, it is critical that more attention should be given to these behind-the-scene bridges. The relevant information about the construction methods and as-built properties are most likely missing. Additionally, since the condition of a bridge has unavoidably changed during service, due to weathering and deterioration, the material properties and boundary conditions would also have changed since its construction. Therefore, it is not appropriate to continue using the design values of the bridge parameters when undertaking any analysis to evaluate bridge performance. It is imperative to update the model, using finite element (FE) analysis to reflect the current structural condition. In this study, a FE model is established to simulate a concrete culvert bridge in New South Wales, Australia. That model, however, contains a number of parameter uncertainties that would compromise the accuracy of analytical results. The model is therefore updated with a neural network (NN) optimisation algorithm incorporating Monte Carlo (MC) simulation to minimise the uncertainties in parameters. The modal frequency and strain responses produced by the updated FE model are compared with the frequency and strain values on-site measured by sensors. The outcome indicates that the NN model updating incorporating MC simulation is a feasible and robust optimisation method for updating numerical models so as to minimise the difference between numerical models and their real-world counterparts.

• Wind and Structures
• /
• v.11 no.1
• /
• pp.35-50
• /
• 2008

Wind and temperature have been shown to be the critical sources causing changes in the modal properties of large-scale bridges. While the individual effects of wind and temperature on modal variability have been widely studied, the investigation about the effects of multiple environmental factors on structural modal properties was scarcely reported. This paper addresses the modeling of the simultaneous effects of wind and temperature on the modal frequencies of an instrumented cable-stayed bridge. Making use of the long-term monitoring data from anemometers, temperature sensors and accelerometers, a neural network model is formulated to correlate the modal frequency of each vibration mode with wind speed and temperature simultaneously. Research efforts have been made on enhancing the prediction capability of the neural network model through optimal selection of the number of hidden nodes and an analysis of relative strength of effect (RSE) for input reconstruction. The generalization performance of the formulated model is verified with a set of new testing data that have not been used in formulating the model. It is shown that using the significant components of wind speeds and temperatures rather than the whole measurement components as input to neural network can enhance the prediction capability. For the fundamental mode of the bridge investigated, wind and temperature together apply an overall negative action on the modal frequency, and the change in wind condition contributes less to the modal variability than the change in temperature.

• Structural Engineering and Mechanics
• /
• v.64 no.4
• /
• pp.449-459
• /
• 2017

High-rise buildings are generally sensitive to strong winds. The evaluation of wind loads for the structural design, structural health monitoring (SHM), and vibration control of high-rise buildings is of primary importance. Nevertheless, it is difficult or even infeasible to measure the wind loads on an existing building directly. In this regard, a new inverse method for evaluating wind loads on high-rise buildings is developed in this study based on a discrete-time Kalman filter. The unknown structural responses are identified in conjunction with the wind loads on the basis of limited structural response measurements. The algorithm is applicable for estimating wind loads using different types of wind-induced response. The performance of the method is comprehensively investigated based on wind tunnel testing results of two high-rise buildings with typical external shapes. The stability of the proposed algorithm is evaluated. Furthermore, the effects of crucial factors such as cross-section shapes of building, the wind-induced response type, errors of structural modal parameters, covariance matrix of noise, noise levels in the response measurements and number of vibration modes on the identification accuracy are examined through a detailed parametric study. The research outputs of the proposed study will provide valuable information to enhance our understanding of the effects of wind on high-rise buildings and improve codes of practice.

• Smart Structures and Systems
• /
• v.32 no.5
• /
• pp.339-347
• /
• 2023

Both the first author and the company of the second author were involved, directly or indirectly, in the design stage of a permanent link between the bottom of the Italian peninsula and the nearby Sicily island. This ambitious project was left in stand-by from 2013 to 2023. The current political revival originates some thoughts on the updated desired performance of suspension bridges, without any immediate reference to that specific crossing. It is simply regarded as a starting point. After an update on recent worldwide realizations, the authors focus their attention on four basic aspects: the span length, the girder scheme, the foundation technology and the bridge runability. Eventually, structural control and monitoring aspects are discussed as potentially innovative options in designing suspension bridges with railway crossing.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.25 no.11
• /
• pp.787-797
• /
• 2015

In this paper, a cochlea-inspired artificial filter bank(CAFB) was developed in order to efficiently acquire dynamic response of structure, and it was also evaluated via dynamic response experiments. To sort out signals containing significant modal information from all the dynamic responses of structure, it was made to adopt a band-pass filter optimizing algorithm(BOA) and a peak-picking algorithm (PPA). Optimally designed on the basis of El-centro and Kobe earthquake signals, it was then embedded into the wireless multi-measurement system(WiMMS). In order to evaluate the performance of the developed CAFB, a vibration test was conducted using the El-centro and Kobe earthquake signals, and structural responses of a two-span bridge were obtained and analyzed simultaneously by both a wired measurement system and a CAFB-based WiMMS. The test results showed that the compressed dynamic responses acquired by the CAFB-based WiMMS matched with those of the wired system, and they included significant modal information of the two-span bridge. Therefore this study showed that the developed CAFB could be used as a new, economic, and efficient measurement device for wireless sensor networks(WSNs) based real time structural health monitoring because it could reconstruct the whole dynamic response using the compressed dynamic response with significant modal information.

• Advances in Computational Design
• /
• v.4 no.1
• /
• pp.1-13
• /
• 2019

Recent generations of smartphones offer accelerometer sensors as a standard feature. While this has led to the development of a number of related applications (apps), there has been no study on their comparative or individual performance against a benchmark. This paper investigates the comparative performance of a number of smartphone accelerometer apps amongst themselves and to a calibrated benchmark accelerometer. A total of 12 apps were selected for testing out of 90 following an initial review. The selected apps were subjected to sinusoidal vibration testing of varying frequency and the response of each compared against the calibrated baseline accelerometer. The performance of apps was quantified using analysis of variance (ANOVA) and test of significance was carried out. The apps were then compared for a realistic dynamic scenario of measuring the acceleration response of a bridge due to the passage of a French Train $\grave{a}$ Grande Vitesse (TGV) in a laboratory environment.

• Smart Structures and Systems
• /
• v.24 no.6
• /
• pp.733-744
• /
• 2019

Wind speed forecasting is critical for a variety of engineering tasks, such as wind energy harvesting, scheduling of a wind power system, and dynamic control of structures (e.g., wind turbine, bridge, and building). Wind speed, which has characteristics of random, nonlinear and uncertainty, is difficult to forecast. Nowadays, machine learning approaches (generalized regression neural network (GRNN), back propagation neural network (BPNN), and extreme learning machine (ELM)) are widely used for wind speed forecasting. In this study, two schemes are proposed to improve the forecasting performance of machine learning approaches. One is that optimization algorithms, i.e., cross validation (CV), genetic algorithm (GA), and particle swarm optimization (PSO), are used to automatically find the optimal model parameters. The other is that the combination of different machine learning methods is proposed by finite mixture (FM) method. Specifically, CV-GRNN, GA-BPNN, PSO-ELM belong to optimization algorithm-assisted machine learning approaches, and FM is a hybrid machine learning approach consisting of GRNN, BPNN, and ELM. The effectiveness of these machine learning methods in wind speed forecasting are fully investigated by one-year field monitoring data, and their performance is comprehensively compared.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• Smart Structures and Systems
• /
• v.20 no.2
• /
• pp.127-137
• /
• 2017

Identification of damping characteristics is of significant importance for dynamic response analysis and condition assessment of structural systems. Damping is associated with the behavior of the energy dissipation mechanism. Identification of damping ratios based on the sensitivity of dynamic responses and the model updating technique is investigated with numerical and experimental investigations. The effectiveness and performance of using the sensitivity-based model updating method and vibration monitoring data for damping ratios identification are investigated. Numerical studies on a three-dimensional truss bridge model are conducted to verify the effectiveness of the proposed approach. Measurement noise effect and the initial finite element modelling errors are considered. The results demonstrate that the damping ratio identification with the proposed approach is not sensitive to the noise effect but could be affected significantly by the modelling errors. Experimental studies on a steel planar frame structure are conducted. The robustness and performance of the proposed damping identification approach are investigated with real measured vibration data. The results demonstrate that the proposed approach has a decent and reliable performance to identify the damping ratios.