Structural damage detection with wavelet support vector machine: introduction and applications

Beam string structure (BSS) is introduced as a new type of hybrid prestressed string structures. The composition and mechanics features of BSS are discussed. The main principles of wavelet packet transform (WPT), principal component analysis (PCA) and support vector machine (SVM) have been reviewed. WPT is applied to the structural response signals, and feature vectors are obtained by feature extraction and PCA. The feature vectors are used for training and classification as the inputs of the support vector machine. The method is used to a single one-way arched beam string structure for damage detection. The cable prestress loss and web members damage experiment for a beam string structure is carried through. Different prestressing forces are applied on the cable to simulate cable prestress loss, the prestressing forces are calculated by the frequencies which are solved by Fourier transform or wavelet transform under impulse excitation. Test results verify this method is accurate and convenient. The damage cases of web members on the beam are tested to validate the efficiency of the method presented in this study. Wavelet packet decomposition is applied to the structural response signals under ambient vibration, feature vectors are obtained by feature extraction method. The feature vectors are used for training and classification as the inputs of the support vector machine. The structural damage position and degree can be identified and classified, and the test result is highly accurate especially combined with principle component analysis.

In the present paper, Structural health monitoring has become an evolving area of research in last few decades with increasing need of online monitoring the health of large structures. The damage detection by visual inspection of the structure can prove impractical, expensive and ineffective in case of large structures like offshore platforms, multistoried buildings and bridges. Structural health monitoring is defined as the process of detecting damage in a structural system. Damage in the system causes a change in dynamic properties of a system. The structural damage is typically a local phenomenon, which tends to be captured by higher frequency signals. Most of vibration-based damage detection methods require the modal properties that are obtained from measured signals through the system identification techniques. However, the modal properties such as natural frequencies and mode shapes are not such a good sensitive indication of structural damage. Structural damage detection and damage localization of jacket platforms, based on wavelet packet transforms is presented in this paper. Dynamic signals measured from the structure by the finite element software package ANSYS are first decomposed into wavelet packet components. Component energies are then calculated and used for damage assessment. The results show that the WPT-based component energies are good candidate indices that are sensitive to structural damage. These component energies can be used for damage assessment including identifying damage occurrence and location.

Efficient wind energy harvesting becomes more and more important as a consequence of the increasing interest in renewable energy in the European Union [1]. This leads to growing sizes of wind turbines (WTs), and with it, larger WT blades (WTBs). The structural designs of these WTBs are created to optimize the potential energy output, where low mass is a key requirement. However, high flexibilities and lower buckling capacities are further results of these developments [2], thus certain damage scenarios become significant. Intelligently designed structural health monitoring (SHM) systems can help to reduce the associated operations and maintenance costs. Even though, several techniques are already developed for structural damage detection (SDD) in WTBs, the majority of these methods is not suitable for inservice measurements. This paper presents a SDD and structural damage localization (SDL) method based on the partial autocorrelation function (PACF) of vibration responses. The approach is applied to a numerical model of a large WTB, where the acceleration responses are obtained from transient dynamic simulations with a simplified aerodynamic loading approach. The novel damage sensitive feature (DSF) is developed as the Mahalanobis distance between a baseline and current vector of PACF coefficients. First, numerical modal analysis of the finite element (FE) WTB model is performed in order to estimate the effect of a disbonding damage scenario on the vibration characteristics. Second, the behaviour of the PACF for time series of the healthy system is discussed. Third, the SDD results on the basis of statistical hypothesis testing are assessed for two selected sensor locations and increasing damage extents. Finally, the performance of the proposed DSF with respect to SDL is illustrated for multiple locations on the WTB’s surface. This study demonstrated the efficiency of a DSF based on the PACF for SDD and SDL, which is promising for future developments of vibration-based SHM techniques in WTBs.

The representation of structural dynamics in the absence of physics-based models, is often accomplished through the identification of parametric models, such as the autoregressive with exogenous inputs, e.g. ARX models. When the structure is amenable to environmental variations, parameter-varying extensions of the original ARX model can be implemented, allowing for tracking of the operational variability. Yet, the latter occurs in sufficiently longer time-scales (days, weeks, months), as compared to system dynamics. For inferring a “global”, long time-scale varying ARX model, data from a full operational cycle has to typically become available. In addition, when the sensor network comprises multiple nodes, the identification of long time-scale varying, vector ARX models grow in complexity. We address these issues by proposing a distributed framework for structural identification, damage detection and localization. Its main features are: (i) the individual estimation of local, single-input-single-output ARX models at every operational point; (ii) the long time-scale representation of each individual ARX coefficient via a Gaussian process regression, which captures dependency on varying Environmental and Operational Conditions (EOCs); (iii) the establishment of a distributed residual generation algorithm for damage detection, which produces time-series of well-defined stationary statistics, with detected discrepancies used for damage diagnosis; and, (iv) exploitation of ARX-inferred mode shape curvatures, obtained via ARX-inferred global state-space models, of the healthy and damaged states, for damage localization. The method is assessed via application on two numerical case studies of different complexity, with the results confirming its efficacy for diagnostics under varying EOCs.

Substantial work has shown that the modulation of structural damage on probing guided ultrasonic waves can result in wave components corresponding to different frequencies, causing wave energy transfer from central frequency to other frequency bands. To make use of the damage-induced wave energy transfer in different frequency bands, a data-driven method which combines wavelet packet decomposition (WPD), principal component analysis (PCA) and support vector machine (SVM), is proposed in this study for structural damage identification in both metallic and composite materials. Firstly, WPD is employed to decompose the original signal into different frequency bands, based on which the wave energy at each frequency band can be determined. A wave energy distribution vector is constructed according to the energy proportion of each frequency band. Then, PCA is recalled conducting dimensionality reduction for the energy distribution vectors, in order to improve the computational efficiency for subsequent SVM classification. The compressed energy distribution vectors are used as the input to train an SVM-based classifier for identifying structural damage. To validate the proposed WPD-PCA-SVM method, experiments are performed on both aluminum plate and glass fiber reinforced polymer (GFRP) laminate. According to the experimental results, the embryonic fatigue crack in the (aluminum) plate and the anomaly in the GFRP laminate can be identified by the proposed method, with a detection accuracy of 92.86% for aluminum plate and 95.45% for GFRP laminate, respectively, demonstrating the effectiveness of the proposed method for damage detection in both metallic and composite materials.

Two-stage structural damage detection using fuzzy neural networks and data fusion techniques

In this paper, a new image denoising method based on wavelet analysis and support vector machine regression (SVR) is presented. The feasibility of image denoising via support vector regression is discussed and is demonstrated by an illustrative example which denoise a 1-dimension signal with Gauss KBF SVM. The wavelet theory is discussed and applied to construct the wavelet kernel, then the wavelet support vector machine (WSVM) is proposed. The result of experiment shows that the denoising method based on WSVM can reduce noise well, the comparison between the method proposed in this paper and other ones is also given which proves this method is better than Gaussian KBF SVM and other traditional methods.

Partial discharge is an important cause of the deterioration of the cable insulation condition, and also an important manifestation of the deteriorated insulation condition. Partial discharge detection for cable insulation is an important means to find the cable insulation defects and assess state of the cable insulation. Partial discharge signals from different sources have great harm to the power equipment, so pattern identification is an important purpose in this research. First, the four kinds of discharge waveforms are processed by de-noising preprocessing, then discharge waveforms are decomposed by wavelet packet, and finally the energy percentage in different frequency bands can be obtained. Studies show that when the type of discharge signal is different, the wavelet packet coefficients in the distribution of each band is also different. So energy percentage of the wavelet packet coefficients can be used for discharge signal feature recognition. In this paper, SVM binary classification is first extended to multi-classification by M-ary algorithm, then the feature vectors composed by energy percentage of the wavelet packet coefficients are inputted into SVM for recognition. The recognition results of test samples show that feature vectors composed by the percentage of energy of wavelet packet coefficients can well reflect the characteristics of the original signal, and the method based on SVM has better recognition performance.

The data shows that about 20% of car failures come from the rear axle of the car. Accordingly we use a support vector machine based on optimization algorithm of Drosophila melanogaster as the fault diagnosis method. The vibration signal is denoised by double-tree complex wavelet transform. The feature extraction is performed by wavelet packet decomposition, and the extracted feature vector is taken as the input data. The support vector machine (SVM) optimized by FOA is used as the classifier to obtain the feature vector of the collected vibration signal to get fault recognition rate. Experimental results show that this method has higher diagnostic accuracy than some other SVMs.

Nowadays, structural health monitoring has attracted much attention, due to the construction of important and complex structures and their safety. One branch of structural health monitoring is damage detection, estimating the location and extent of eventual damages in the structural systems. In this study, an efficient method is introduced to determine the location and extent of damage in the frame, beam and truss structures using time domain response and an optimization algorithm. First of all, the structural damage detection problem is formulated as a standard optimization problem. So that, the optimization objective function is defined by using the acceleration of damaged structures and analytical model acceleration. The acceleration is obtained using Newmark method. Damage is simulated by reducing the elasticity modulus of structural members. Then, damage problem converted to an optimization problem are solved by teaching–learning-based optimization (TLBO) algorithm therefore, the exact location and extent of damage in structure can be determined. In order to show the capabilities of the proposed approach for identifying structural damage, four illustrative test examples are considered with considering measurement noise effect. The results clearly show that the proposed method is as a powerful method to detect multiple damage in structures.

Short-Term Load Forecasting Based on Gaussian Wavelet SVM

In structural health monitoring (SHM), data-driven is a model free method that mines the internal characteristics of the raw measured responses, does not need considering the structural model. This paper proposes a new data-driven damage detection method based on wavelet packet transform (WPT) combining with principal component analysis (PCA). In this method, the responses are firstly decomposed by WPT, and each layer of wavelet packet energy of each measurement is obtained. Since the wavelet packet components of small energy magnitudes are easily contaminated by noises and should be discarded. PCA is utilised to reduce and eliminate redundant information of wavelet packet energy, and a damage index named the rate of the wavelet packet energy score change (WPESCR) is proposed to locate the damage. A simple beam is employed to demonstrate the effectiveness of this method. The numerical and experimental results show that the method combined with WPT and PCA can successfully locate the damage. As a data-driven method, the new WPESCR indicator is a better candidate for continuous online SHM.

We proposed a new method of aero-engine early fault intelligent diagnosis which combined with stochastic resonance, wavelet packet analysis and support vector machine. This method can effectively extract the early fault feature of aero-engine and it can fast identify the early faults. At first, we use the principle of stochastic resonance to zooms the early weak fault feature signals and amplify fault features. Then, we make use of multi-resolution analysis characteristic of wavelet packet to extract the early fault feature vectors. At last, the feather vector is inputted to a classifier which is constructed by support vector machines and carries on identification of the early faults. The results shown that its effect of classification identification is well and it is effective to identify early fault in strong noise.

The detection of structural damage from the high-frequency local impedance spectra is addressed with a spectral classification approach consisting of features extraction followed by probabilistic neural network pattern recognition. The paper starts with a review of the neural network principles, followed by a presentation of the state of the art in the use of pattern recognition methods for damage detection. The construction and experimentation of a controlled experiment for determining benchmark spectral data with know amounts of damage and inherent statistical variation is presented. Spectra were collected in the 10-40 kHz, 10-150 kHz, and 300-450 kHz for 5 damage situations, each situation containing 5 members, identical, but slightly different. A features extraction algorithm was used to determine the resonance frequencies and amplitudes contained in these high-frequency spectra. The feature vectors were used as input to a probabilistic neural network. The training was attained using one randomly selected member from each of the 5 damage classes, while the validation was performed on all the remaining members. When features vector had a small size, some misclassifications were observed. Upon increasing the size of the features vector, excellent classification was attained in all cases. Directions for further studies include the study of other frequency bands and different neural network algorithms.

An original dual-class voting mechanism was put forward as the final decision method for brain computer interface, which is based on wavelet packet decomposition (WPD) to extract the brainwave features from EEG signals, and support vector machines (SVMs) to classify five mental tasks. Moreover, several preprocessing methods were applied efficiently. Segmentation along the time axis for increasing the correct classification rate, and nonlinear as well as linear normalization for emphasizing the important information in small magnitude and optimizing data distribution. Further, an especial grouping method was proposed to realize optimizing parameters automatically. Approximately, 95% of correct classification rate is obtained based on the proposed method, which is higher than the conventional.