Structural Damage Detection Method Research Articles

Artificial intelligence-based hull structural plate corrosion damage detection and recognition using convolutional neural network

With the support of big data and GPU acceleration training, the artificial intelligence technology with deep learning as its core is developing rapidly and has been widely used in many fields. At the same time, feature extraction operations are required by the current image-based corrosion damage detection method in the field of ships, with little effect but consuming the large amount of manpower and financial resources. Therefore, a new method for hull structural plate corrosion damage detection and recognition based on artificial intelligence using convolutional neural network is proposed. The convolutional neural network (CNN) model is trained through a large number of classified corrosion damage images to obtain a classifier model. Then the classifier model is used with overlap-scanning sliding window algorithm to recognize and position the location of corrosion damage. Finally, the damage detection pattern for hull structural plate corrosion damage as well as other types of superficial structural damage using convolutional neural network is proposed, which can accelerate the application of artificial intelligence technology into the field of naval architecture & ocean engineering.

Principal Component Analysis Method with Space and Time Windows for Damage Detection.

Long-term structural health monitoring (SHM) has become an important tool to ensure the safety of infrastructures. However, determining methods to extract valuable information from large amounts of data from SHM systems for effective identification of damage still remains a major challenge. This paper provides a novel effective method for structural damage detection by introduction of space and time windows in the traditional principal component analysis (PCA) technique. Numerical results with a planar beam model demonstrate that, due to the presence of space and time windows, the proposed double-window PCA method (DWPCA) has a higher sensitivity for damage identification than the previous method moving PCA (MPCA), which combines only time windows with PCA. Further studies indicate that the developed approach, as compared to the MPCA method, has a higher resolution in localizing damage by space windows and also in quantitative evaluation of damage severity. Finally, a finite-element model of a practical bridge is used to prove that the proposed DWPCA method has greater sensitivity for damage detection than traditional methods and potential for applications in practical engineering.

Photogrammetry-based structural damage detection by tracking a visible laser line

Research works on photogrammetry have received tremendous attention in the past few decades. One advantage of photogrammetry is that it can measure displacement and deformation of a structure in a fully non-contact, full-field manner. As a non-destructive evaluation method, photogrammetry can be used to detect structural damage by identifying local anomalies in measured deformation of a structure. Numerous methods have been proposed to measure deformations by tracking exterior features of structures, assuming that the features can be consistently identified and tracked on sequences of digital images captured by cameras. Such feature-tracking methods can fail if the features do not exist on captured images. One feasible solution to the potential failure is to artificially add exterior features to structures. However, painting and mounting such features can introduce unwanted permanent surficial modifications, mass loads, and stiffness changes to structures. In this article, a photogrammetry-based structural damage detection method is developed, where a visible laser line is projected to a surface of a structure, serving as an exterior feature to be tracked; the projected laser line is massless and its existence is temporary. A laser-line-tracking technique is proposed to track the projected laser line on captured digital images. Modal parameters of a target line corresponding to the projected laser line can be estimated by conducting experimental modal analysis. By identifying anomalies in curvature mode shapes of the target line and mapping the anomalies to the projected laser line, structural damage can be detected with identified positions and sizes. An experimental investigation of the damage detection method was conducted on a damaged beam. Modal parameters of a target line corresponding to a projected laser line were estimated, which compared well with those from a finite element model of the damaged beam. Experimental damage detection results were validated by numerical ones from the finite element model.

Damage identification in bridge structures subject to moving vehicle based on extended Kalman filter with l1-norm regularization

ABSTRACTAn innovative damage detection method for bridge structures under moving vehicular load is proposed on the basis of extended Kalman filter (EKF) and l1-norm regularization. An augmented state vector includes structural damage parameters and motion state variables of bridge and vehicle. Through a recursive process of the EKF, the structural damage parameters and state variables of a bridge are updated continually to obtain an optimal estimate using bridge responses due to a moving vehicle. The distribution of element stiffness reduction of a structure with local damages is sparse. Thus, l1-norm regularization is introduced into the updating process of the EKF using pseudo-measurement (PM) technology to improve the ill-posedness of the inverse problem. Numerical studies on a simple-supported and continuous beam bridge deck, with a smooth road surface that is subject to a moving vehicle, are performed to test the proposed approach. Furthermore, using the robustness of the EKF, the proposed algorithm is applied as a simplified method to the case where a bridge deck with road roughness is considered. Results show that the proposed identification algorithm is robust and effective for different vehicle speeds and measurement noises under smooth and good road conditions.

Structural damage detection based on modal data using moth-flame optimization algorithm

This paper presents a new and efficient damage detection method for civil structures. To identify damage localisation and quantification, the proposed method defines the damage detection problem as...

Automatic pixel‐level multiple damage detection of concrete structure using fully convolutional network

AbstractDeep learning‐based structural damage detection methods overcome the limitation of inferior adaptability caused by extensively varying real‐world situations (e.g., lighting and shadow changes). However, most deep learning‐based methods detect structural damage at the image level and grid‐cell level. To provide pixel‐level detection of multiple damages, a Fully Convolutional Network (FCN)‐based multiple damages detection method for concrete structure is proposed. To realize this method, a database of 2,750 images (with 504 × 376 pixels) including crack, spalling, efflorescence, and hole images in concrete structure is built, and the four damages included in those images are labeled manually. Then, the architecture of the FCN is modified, trained, validated, and tested using this database. A strategy of model‐based transfer learning is used to initialize the parameters of the FCN during the training process. The results show 98.61% pixel accuracy (PA), 91.59% mean pixel accuracy (MPA), 84.53% mean intersection over union (MIoU), and 97.34% frequency weighted intersection over union (FWIoU). Subsequently, the robustness and adaptability of the trained FCN model is tested and the damage is extracted, where damage areas are provided according to a calibrated relation between the ratio (the pixel area and true area of the detected object) and the distance from the smartphone to the concrete surface using a laser range finder. A comparative study is conducted to examine the performance of the proposed FCN‐based approach using a SegNet‐based method. The results show that the proposed method substantiates quite better performance and can indeed detect multiple concrete damages at the pixel level in realistic situations.

Comparative studies on structural damage detection using <i>L</i><SUB align="right"><i>p</i> norm regularisation

In order to get sparse solution to the structural damage detection (SDD) problem, a new SDD method is proposed based on the finite element model updating technique through combining sensitivity analysis with the Lp (0 < p < 1) norm regularisation. Compared with the classical Tikhonov regularisation, the Lp norm regularisation method can avoid over-smoothness, which is a main difficulty for the Tikhonov regularisation, and its solutions are also more accurate than that by the L1 norm regularisation, another widely used sparse regularisation method. Moreover, the effects of different p-values on SDD results are also studied and discussed. Numerical simulations on a cantilever beam and a simple supported beam, and all the laboratory experiments on a cantilever beam under different assumed damage cases verify the effectiveness of the proposed method. The SDD results show that a good sparse solution is assured via the Lp norm regularisation especially when the value of p ranges from 0.1 to 0.5. In contrast, its accuracy shows a slightly decline when the value of p changes from 0.5 to 1.0. Finally, the results also show that p = 1/2 is the best choice for SDD when using Lp norm regularisation.

Comparative studies on structural damage detection using &lt;i&gt;L&lt;/i&gt;&lt;SUB align="right"&gt;&lt;i&gt;p&lt;/i&gt; norm regularisation

In order to get sparse solution to the structural damage detection (SDD) problem, a new SDD method is proposed based on the finite element model updating technique through combining sensitivity analysis with the Lp (0 < p < 1) norm regularisation. Compared with the classical Tikhonov regularisation, the Lp norm regularisation method can avoid over-smoothness, which is a main difficulty for the Tikhonov regularisation, and its solutions are also more accurate than that by the L1 norm regularisation, another widely used sparse regularisation method. Moreover, the effects of different p-values on SDD results are also studied and discussed. Numerical simulations on a cantilever beam and a simple supported beam, and all the laboratory experiments on a cantilever beam under different assumed damage cases verify the effectiveness of the proposed method. The SDD results show that a good sparse solution is assured via the Lp norm regularisation especially when the value of p ranges from 0.1 to 0.5. In contrast, its accuracy shows a slightly decline when the value of p changes from 0.5 to 1.0. Finally, the results also show that p = 1/2 is the best choice for SDD when using Lp norm regularisation.

A fast and robust method for damage detection of truss structures

• This paper proposes a two-stage damage detection method for truss structures. • First stage focused on the damage localization and in the second stage, the damage severities are evaluated. • To localize the suspected damaged elements, using the concept of residual force vector, a new index is proposed. • To evaluate the damage severities, the damage detection problem formulated as an optimization problem and solved by GA. Use of optimization search algorithms is recognized as an efficient method for solving structural damage identification problems. Although these algorithms demonstrated their robustness to identify the location and extent of multiple damages in structural systems, they impose so much computational efforts to the damage assessing process that it reduces their attraction. In this paper by utilizing the concept of residual force vector, an efficient approach based on a Truss Element Damage Index (TEDI) is defined to assist in a fast and reliable prediction of damaged elements. Based on the proposed technique, the first step focuses on location detection of most probable damaged members. The healthy members will then be eliminated from the total list of variables. This can reduce the computational effort significantly. In the second step to identify damaged locations and severities, the Genetic Algorithm is employed to search for the optimum solution in the new search space resulted from the first step. Three test examples are considered to investigate the efficiency of proposed method for damage identification.

Optimization-based method for structural damage detection with consideration of uncertainties- a comparative study

In this paper, for efficiently reducing the computational cost of the model updating during the optimization process of damage detection, the structural response is evaluated using properly trained surrogate model. Furthermore, in practice uncertainties in the FE model parameters and modelling errors are inevitable. Hence, an efficient approach based on Monte Carlo simulation is proposed to take into account the effect of uncertainties in developing a surrogate model. The probability of damage existence (PDE) is calculated based on the probability density function of the existence of undamaged and damaged states. The current work builds a framework for Probability Based Damage Detection (PBDD) of structures based on the best combination of metaheuristic optimization algorithm and surrogate models. To reach this goal, three popular metamodeling techniques including Cascade Feed Forward Neural Network (CFNN), Least Square Support Vector Machines (LS-SVMs) and Kriging are constructed, trained and tested in order to inspect features and faults of each algorithm. Furthermore, three well-known optimization algorithms including Ideal Gas Molecular Movement (IGMM), Particle Swarm Optimization (PSO) and Bat Algorithm (BA) are utilized and the comparative results are presented accordingly. Furthermore, efficient schemes are implemented on these algorithms to improve their performance in handling problems with a large number of variables. By considering various indices for measuring the accuracy and computational time of PBDD process, the results indicate that combination of LS-SVM surrogate model by IGMM optimization algorithm have better performance in predicting the of damage compared with other methods.

Design of damage identification algorithm for mechanical structures based on convolutional neural network

SummaryDamage identification, location, and estimation of engineering structures are very popular research topics in recent years. Structural damage detection technology has been widely used in aerospace, civil engineering, machinery, and nuclear industry. It is a multi‐disciplinary and comprehensive technology based on damage mechanism, sensor technology, signal analysis technology, computer technology, and convolutional intelligence technology. Compared with the traditional structural damage detection methods, this paper mainly studies the theory and application of structural damage detection technology based on convolutional neural network. In this paper, the damage location and damage degree of a frame structure are numerically simulated by the combined parameter method, which is suitable for structural damage identification. At the same time, the input parameters of the improved convolutional neural network are constructed by a suitable method, and the structure damage detection and identification are carried out by using the trained convolutional neural network.

Two-phase damage detection of beam structures under moving load using multi-scale wavelet signal processing and wavelet finite element model

• This paper proposes a novel two-phase damage detection method for structures under a moving load. • The proposed method utilizes both wavelet signal processing and wavelet finite element model for damage detection. • The proposed method consists of two sequential phases, namely localization and quantification. • The proposed method is successfully validates it via a laboratory experiment of a scaled beam structure. This paper proposes a damage detection method with two phases, namely, localization and quantification, for beam structures subjected to moving load and successfully validates it via a laboratory experiment. Firstly, the discrete wavelet transform (DWT) is applied to decompose the displacement response change induced by a moving vehicle and locate potential structural damages. Then adaptive-scale wavelet finite element model (WFEM) updating is employed to estimate the damage severity in the identified damage regions in a progressive fashion. The elemental scales of WFEM are adaptively changed according to not only the moving vehicle position but also the progressively identified damage regions. Such a method can effectively minimize the number of modeling degree-of-freedoms (DOFs) and updating parameters during optimization. The feasibility and effectiveness of the proposed method is examined through a laboratory experiment with different damage scenarios. The results indicate the proposed method can achieve good consistency between structural modeling, damage scenarios, and load conditions, as well as an optimal tradeoff between damage detection accuracy and efficiency.

Non-baseline method for damage detection in truss structures using displacement and strain measurements

Realistic problems restrict the application of many existing structural damage detection methods. Due to the requirement of a comparison between two system states, lack of appropriate baseline data may become one of the limitations to undertake structural health monitoring strategy. This article suggests a non-baseline damage detection approach based on the mixed measurements and the transmissibility concept and demonstrates it in truss structures. The algorithm uses the measurement data from the strains of the truss elements and the displacements of the truss joints, in which the displacements are utilized to estimate the baseline strains based on the transmissibility matrix from an initial finite element model. Wavelet-based damage-sensitive features are extracted from both estimated and measured strains to detect damages of the target elements. Numerical and experimental studies are performed to investigate the feasibility and effectiveness of the proposed approach. It is concluded from the instances that the robustness of the algorithm is realized when handling the measurement noise, modeling errors and the operational condition variability. These permit the potential development of the damage detection method for real structures in site.

Structural damage detection via combining weighted strategy with trace Lasso

With the rapid development of computation technologies, swarm intelligence–based algorithms become an innovative technique used for addressing structural damage detection issues, but traditional swarm intelligence–based structural damage detection methods often face with insufficient detection accuracy and lower robustness to noise. As an exploring attempt, a novel structural damage detection method is proposed to tackle the above deficiency via combining weighted strategy with trace least absolute shrinkage and selection operator (Lasso). First, an objective function is defined for the structural damage detection optimization problem by using structural modal parameters; a weighted strategy and the trace Lasso are also involved into the objection function. A novel antlion optimizer algorithm is then employed as a solution solver to the structural damage detection optimization problem. To assess the capability of the proposed structural damage detection method, two numerical simulations and a series of laboratory experiments are performed, and a comparative study on effects of different parameters, such as weighted coefficients, regularization parameters and damage patterns, on the proposed structural damage detection methods are also carried out. Illustrated results show that the proposed structural damage detection method via combining weighted strategy with trace Lasso is able to accurately locate structural damages and quantify damage severities of structures.

Anisotropic reduction factor-based damage identification method for fiber-reinforced composite laminates

Nowadays, the existing damage detection methods for composite structures roughly identify the defects by equivalent means without considering their anisotropy. Owing to this reason, this article is aimed at proposing an anisotropic reduction factor (ARF)-based damage identification method in view of the description of damage in composite continuum damage mechanics (CDM). On the basis of the proposed method, the adequate damage information including the damage locations, types, and extent will be achieved. The ARF is established referring to the damage model in structures made of isotropic materials utilizing the damage parameter in CDM. To eliminate the dispersion of composite structures, the model updating for the pristine structure is performed. Then a two-step damage identification for detecting the ARF is put forward. First, the modal strain energy-based method is utilized to locate the damage, by which the candidate damaged elements can be selected. Here, taking advantage of the improved reduction system method, the damage localization method can be completed with incomplete modal information. Second, the optimization method based on direct search algorithm is adopted to identify the damage type and extent of the candidate elements by minimizing the error of the modal information between the reference model and the damage model. The measurement noises are taken into consideration. Two numerical examples and an experimental example are studied to demonstrate the effectiveness of the proposed method.

A three-stage damage detection method for large-scale space structures using forward substructuring approach and enhanced bat optimization algorithm

In this study, an efficient three-stage method is proposed for damage detection of large-scale space structures by employing forward substructuring approach, modal strain energy and enhanced bat algorithm (EBA) optimization. EBA is a modified version of BA that is proposed in this paper and used a passive congregation operator to improve the performance of standard BA. In the first stage, the global structure is divided into manageable substructures. The stiffness matrices of independent substructures are obtained based on Kron’s substructuring method. Then a modal strain energy-based index is employed to precisely locate the eventual damages of the structure. In the third stage, damage severities are estimated via EBA using the second-stage results. To demonstrate the ability of the proposed method for detection of multiple structural damages, large-scale space structures with different types of damage scenarios are considered. The results show that the proposed method can detect the exact locations and severity of damages highly accurate in space structures.

Vibration-based Structural Damage Detection Using Twin Gaussian Process (TGP)

A new pattern recognition based structural damage detection method using structural mode-shapes along with natural frequencies is presented in this article. A three span RC bridge is selected to verify the proposed method. To conquer the complexities of finite element simulation of the real structure, SAP2000 is employed for FE modeling and analyzing the structure and thus generating the input parameters for damage assessment process.Having the modal data for the intact and damaged structure, extraction of damage properties becomes a “pattern recognition” or “feature discrimination” problem, while Twin Gaussian Process (TGP) as an advantageous pattern recognition technique is employed to compare the measured mode-shapes and frequencies with their healthy state values and identify the damaged elements.The results of this study shows that the suggested method performs precisely in damage identification of structures having an updated as-built model. Furthermore, it can be concluded that TGP, which is used for damage detection process in this study, is an efficient tool to detect both location and severity of structural damages in single and multiple damage scenarios. The proposed method can be widely used for model updating and damage detection of real structures without any restrictions in modeling.

Structural Health Monitoring for Multi-story Shear Frames Based on Signal Processing Approach

Non-destructive vibration-based global structural health monitoring and damage detection methods are divided into modal-based and signal-based methods. There is much research in these areas, but each one has some advantages and disadvantages. The combination of these two areas can greatly overcome these disadvantages and thus can enhance the robustness of the damage detection methods. This article presents a signal-modal-based structural health monitoring technique for multi-story shear buildings subjected to an earthquake event. The proposed method utilizes the combination of wavelet transform and FFT as signal processing tools and also Hilbert transform with the aim of final modal parameters extraction, in order to determine the existence, location, and extent of damage in the multi-story shear frames. In fact, extraction of final modal parameters from the acceleration response signals is desired. To demonstrate the capabilities of the proposed algorithm, numerical simulations are performed on a four-story two-bay and ten-story two-bay shear frame with different damage scenarios using OpenSees. The results show that this method can detect the occurrence, location, and severity of the damage with good accuracy even in different levels of multi-damage scenarios and also in the presence of measurement noise.

Numerical and experimental investigation of modal-energy-based damage localization for offshore wind turbine structures

Offshore wind turbine structures are prone to deterioration and damage during their service life in harsh marine environment. To explore highly efficient and robust damage detection methods for offshore wind turbine structures, three well-known modal strain energy indices are reviewed first and then a new index named total modal energy method is proposed. The innovation of the new index is the simultaneous use of modal strain energy and modal kinetic energy. To investigate the feasibility and robustness of the four modal-energy-based methods, numerical and experimental studies are conducted on a tripod-type offshore wind turbine structure with simulated and measured data. It is indicated that all the four modal-energy-based methods work well with limited incomplete modal data, especially for the single-damage cases. While for the cases of multiple damage locations, the new total modal energy index significantly outperforms the traditional modal strain energy indices. Moreover, high robustness is shown for the indices, when the measured mode shapes of undamaged and damaged structures are polluted with the same noise level. However, when their noise levels have some difference, two of the modal strain energy indices turn invalid, but the new total modal energy index still shows stronger robustness. As frequencies are also used in the total modal energy index, its robustness to the noise in modal frequencies is also studied. It is shown that the results are slightly affected by the measurement noise in modal frequencies. Besides, the influence of finite element modeling errors is also investigated with both simulated and experimental data. Results show that all the four modal-energy-based methods are all very stable and insensitive to certain modeling errors. So, finite element model updating is not necessary in the test structure herein.

Assessment of structural damage detection methods for steel structures using full-scale experimental data and nonlinear analysis

Rapid structural damage assessment methodologies are essential to properly allocate emergency response and minimize business interruption due to downtime in the aftermath of earthquakes. Within this context, data-driven algorithms supported by sensing capabilities can be potentially employed. In this paper, we evaluate an extensive number of damage indicators computed based on nonmodel-based system identification techniques and wavelet analysis. The efficiency of these indicators to infer the damage state of conventional steel moment-resisting frames (MRFs) and concentrically braced frames (CBFs) is evaluated through the utilization of landmark full-scale shake table experiments that examined the inelastic behavior of such frames at various seismic intensities. The same data is complemented with numerical simulations of multi-story steel MRFs and CBFs with the overarching goal to identify potential limitations and propose refinements in commonly used damage indicators for rapid seismic risk assessment. It is shown that wavelet-based damage sensitive features are well correlated with commonly used story-based engineering demand parameters that control structural and non-structural damage in conventional steel frame buildings.