Automatic damage type classification and severity quantification using signal based and nonlinear model based damage sensitive features

This article suggests the process of structural health monitoring (SHM) in the context of a nonstatistical damage detection paradigm. We particularly focus on applying the theory of possibility to the damage detection problem. The basic idea behind the proposed approach is that the application of possibility theory does not require probabilistic knowledge or assumptions on the damage feature and thus encompasses aleatoric and epistemic types of uncertainties. The approach is not damage feature dependent and thus is generic for use in many SHM systems. Additionally, two new damage metrics are introduced. These metrics extract information concerning damage evidence from observations performed at unknown health states of structures. Damage detection with the aid of the proposed approach is demonstrated by means of a case study.

This thesis is devoted to present some novel techniques in Structural Health Monitoring (SHM). SHM is a developing field that tries to monitor structures to make sure that they remain in their desired condition to avoid any catastrophe. SHM includes different levels from damage detection area to prognosis field. This work is dedicated to the first level, which might be considered the main and most important level. New techniques presented in this work are based on different statistical and signal processing methods such as Principal Component Analysis and its robust counterpart, Wavelet Transform, Fuzzy similarity, Andrew plots, etc. These techniques are applied on the propagated waves that are activated and captured in the structure using appropriate transducers. Piezoceramic (PZT) devices are chosen in this work to capture the signals due to their special characteristics such as high performance, low energy consumption and reasonable price. To guarantee the efficiency of the suggested techniques, they are tested on different laboratory and real scale test benchmarks, such as aluminum and composite plates, fuselage, wing skeleton, tube, etc. Because of the variety of tested benchmarks, this thesis is called damage detection in smart structures. This variety may promise the ability and capability of the proposed methods on different fields such as aerospace and gas/oil industry. In addition to the normal laboratory conditions, it is shown in this work that environmental changes can affect the performance of the damage detection and wave propagation significantly. As such, there is a vital need to consider their effect. In this work, temperature change is chosen as it is one of the main environmental fluctuation factors. To scrutinize its effect on damage detection, first, the effect of temperature is considered on wave propagation and then all the proposed methods are tested to check whether they are sensitive to temperature change or not. Finally, a temperature compensation method is applied to ensure that the proposed methods are stable and robust even when structures are subjected to variant environmental conditions. La presente tesis doctoral se dedica a la exploración y presentación de técnicas novedosas para la Monitorización y detección de defectos en estructuras (Structural Health Monitoring -SHM-) SHM es un campo actualmente en desarrollo que pretende asegurarse que las estructuras permanecen en su condición deseada para evitar cualquier catástrofe. En SHM se presentan diferentes niveles de diagnóstico, Este trabajo se concentra en el primer nivel, que se considera el más importante, la detección de los defectos. Las nuevas técnicas presentadas en esta tesis se basan en diferentes métodos estadísticos y de procesamiento de señales tales como el Análisis de Componentes Princpales (PCA) y sus variaciones robustas, Transformada wavelets, lógica difusa, gráficas de Andrew, etc. Estas técnicas de aplican sobre las ondas de vibración que se generan y se miden en la estructura utilizando trasductores apropiados. Dispositivos piezocerámicos (PZT's) se han escogido para este trabajo ya que presentan características especiales tales como: alto rendimiento, bajo consumo de energia y bajo costo. Para garantizar la eficacia de la metodología propuesta,se ha validado en diferentes laboratorios y estructuras a escala real: placas de aluminio y de material compuesto, fuselage de un avión, revestimiento del ala de un avóin, tubería, etc. Debido a la gran variedad de estructuras utilizadas, su aplicación en la industria aeroespacial y/o petrolera es prometedora. Por otra parte, los cambios ambientales pueden afectar al rendimiento de la detección de daños y propagación de la onda significativamente . En este trabajo , se estudia el efecto de las variaciones de temperatura ya que es uno de los principales factores de fluctuación del medio ambiente . Para examinar su efecto en la detección de daños, en primer lugar, todos los métodos propuestos se prueban para comprobar si son sensibles a los cambios de temperatura o no. Finalmente , se aplica un método de compensación de temperatura para garantizar que los métodos propuestos son estables y robustos incluso cuando las estructuras se someten a condiciones ambientales variantes

A wavelet-based approach is proposed for structural damage detection and health monitoring. Characteristics of representative vibration signals under the wavelet transformation are examined. The methodology is then applied to simulation data generated from a simple structural model subjected to a harmonic excitation. The model consists of multiple breakable springs, some of which may suffer irreversible damage when the response exceeds a threshold value or the number of cycles of motion is accumulated beyond their fatigue life. In cases of either abrupt or accumulative damages, occurrence of damage and the moment when it occurs can be clearly determined in the details of the wavelet decomposition of these data. Similar results are observed for the real acceleration data of the seismic response recorded on the roof of a building during the 1971 San Fernando earthquake. Effects of noise intensity and damage severity are investigated and presented by a detectability map. Results show the great promise of the wavelet approach for damage detection and structural health monitoring.

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.

Structural health monitoring offers new approaches to interrogate the integrity of complex structures. The structural health monitoring process classically relies on four sequential steps: damage detection, localization, classification, and quantification. The most critical step of such process is the damage detection step since it is the first one and because performances of the following steps depend on it. A common method to design such a detector consists of relying on a statistical characterization of the damage indexes available in the healthy behavior of the structure. On the basis of this information, a decision threshold can then be computed in order to achieve a desired probability of false alarm. To determine the decision threshold corresponding to such desired probability of false alarm, the approach considered here is based on a model of the tail of the damage indexes distribution built using the Peaks Over Threshold method extracted from the extreme value theory. This approach of tail distribution estimation is interesting since it is not necessary to know the whole distribution of the damage indexes to develop a detector, but only its tail. This methodology is applied here in the context of a composite aircraft nacelle (where desired probability of false alarm is typically between 10−4 and 10−9) for different configurations of learning sample size and probability of false alarm and is compared to a more classical one which consists of modeling the entire damage indexes distribution by means of Parzen windows. Results show that given a set of data in the healthy state, the effective probability of false alarm obtained using the Peaks Over Threshold method is closer to the desired probability of false alarm than the one obtained using the Parzen-window method, which appears to be more conservative.

Structural health monitoring has been increasingly used due to the advances in sensing technology and data analysis, facilitating the shift from time-based to condition-based maintenance. This work is part of the efforts which have applied structural health monitoring to the Sydney Harbour Bridge – one of Australia’s iconic structures. It combines dimensionality reduction and pattern recognition techniques to accurately and efficiently distinguish faulty components from well-functioning ones. Specifically, random projection is used for dimensionality reduction on the vibration feature data. Then, healthy and damaged patterns of bridge components are learned in the lower dimensional projected space using supervised and unsupervised machine learning methods, namely, support vector machine and one-class support vector machine. The experimental results using data from a laboratory-based building structure and the Sydney Harbour Bridge showed high feasibility of applying machine learning techniques to dimensionality reduction and damage detection in structural health monitoring. Random projection combined with support vector machine significantly reduces the computational time while maintaining the detection accuracy. The proposed method also outperformed popular dimensionality reduction techniques. The computational time of the method using random projection can be more than 200 times faster than that without using dimensionality reduction while still achieving similar detection accuracy.

Visualization of sensor networks, data, and metadata is becoming one of the most pivotal aspects of the structural health monitoring (SHM) process. Without the ability to communicate efficiently and effectively between disparate groups working on a project, an SHM system can be underused, misunderstood, or even abandoned. For this reason, this work seeks to evaluate visualization techniques in the field, identify flaws in current practices, and devise a new method for visualizing and accessing SHM data and metadata in 3D. More precisely, the work presented here reflects a method and digital workflow for integrating SHM sensor networks, data, and metadata into a virtual reality environment by combining spherical imaging and informational modeling. Both intuitive and interactive, this method fosters communication on a project enabling diverse practitioners of SHM to efficiently consult and use the sensor networks, data, and metadata. The method is presented through its implementation on a case study, Streicker Bridge at Princeton University campus. To illustrate the efficiency of the new method, the time and data file size were compared to other potential methods used for visualizing and accessing SHM sensor networks, data, and metadata in 3D. Additionally, feedback from civil engineering students familiar with SHM is used for validation. Recommendations on how different groups working together on an SHM project can create SHM virtual environment and convey data to proper audiences, are also included.

Chapter 1 - Introduction

This research proposed and verified an innovative method to identify and locate structural damage using only the response of operational vibration, that is the displacement acquired by a non-contact optical method. The most efficient and economical way to detect damage within the structure is to monitor its structural health while in operation. However, the uncertainties and the randomness of ambient vibrations due to the operation and environments cause a challenge in conducting the operational analysis. Current technology limits the ability to collect data on the properties of the structure without the interruption of operation. Frequencies and mode shapes have been widely used in structural damage detection, but they are not sensitive enough and cannot provide sufficient information for identifying damage locations and their quantification. Therefore, the goal of this research is to design and verify a method to detect the damage, as well as its location and severity, of structures in operation without any physical contacts for data acquisition (i.e., non-contact based structural health monitoring (SHM)). Three algorithms are integrated into this SHM process. The first algorithm is the determination of structural characteristics (frequencies and mode shapes) of a vibrating structure from output-only data. Stochastic Subspace Identification (SSI) method is applied to measured displacements over time to extract the structural characteristics. The second algorithm is to estimate the scaling factor. The mode shapes obtained from the output-only model analysis are unscaled due to the absence of the information of input excitation forces. Mass Change Modal Scale (McMS) algorithm is used to estimate the modal scaling factors and determine the scaled mode shapes. The third algorithm is to estimate the structural system matrices (i.e., mass and stiffness matrices) and assess the damages. A Finite Element Model Updating (FEMU) is applied and the system matrices are updated from frequencies and scaled mode shapes. The damage within the structure can then be detected by analysing changes in mass and stiffness matrices. All three phases are verified by numerical simulation and laboratory experiments with deflections acquired by non-contact optical methods through video system. At last, to achieve the non-contact based SHM, a modal scaling method based on temperature change is proposed and verified by numerical simulation. Experimental program reveals that the proposed algorithm using McMS method is applicable to detect damage locations and their mass losses. With proposed non-contacted based SHM, the limitations of contact based sensor can be addressed, and the structural damage

This study employed electronic nose (E-nose) to detect tea plants with different types of damage (undamaged, mechanically damaged, damages caused by Ectropis obliqua and Ectropis grisescens). Gas chromatography–mass spectrometry was employed as an auxiliary technique for proving the potential of E-nose detection. A new feature extraction method was applied for obtaining comprehensive features of E-nose dataset. Feature selection method based on principal component analysis (PCA) was applied for further feature selection. Four dimensionality reduction methods [PCA, locality preserving projections (LPP), kernel principal component analysis and locally linear embedding] and three classification algorithms [multilayer perceptron neural network, extreme learning machine and support vector machine (SVM)] were employed, and the best combination of dimensionality reduction method and classification algorithm was determined. The results showed that the combination of LPP and SVM was the best, and its correct discrimination rate was as high as 100%, which proved the advantage of the new signal processing method and the feasibility of E-nose in discriminating among tea plants with different types of damage.

Machine learning techniques have great potential in structural health monitoring (SHM) and damage assessment of precast concrete (PC) structures. However, traditional damage assessment methods, such as finite element analysis, structural reliability analysis, and model testing, have limitations in terms of accuracy, efficiency, and applicability to complex real-world scenarios. This article proposes a hybrid machine learning approach combining random forest (RF) and support vector machine (SVM) for damage detection and classification in PC structures. The proposed RFSVM method utilizes continuous wavelet transform (CWT) to extract damage-sensitive features from vibration response data and employs RF for initial feature selection and damage classification. The RF output is then concatenated with the original features to form an enhanced feature vector, which is fed into the SVM model for precise damage type identification. The RF-SVM model is trained and tested using vibration response data generated from a simplified PC frame structure finite element model built in OpenSEES software. The experimental results demonstrate that the proposed method achieves an overall accuracy of 82.5% in detecting and classifying typical damage types in PC structures, with high precision, recall. However, the model's performance in identifying joint connection damage is relatively lower due to the subtle changes in vibration responses caused by this damage type. Compared to traditional methods that require extensive damage scenario data, the RF-SVM method simplifies the data preparation process and reduces computational complexity by utilizing only baseline data for training. This hybrid approach not only advances the field of SHM for PC structures but also offers a robust tool for infrastructure management, potentially increasing safety and reducing maintenance costs.

This work discusses the advantage of using cross-correlation analysis in a data-driven approach based on principal component analysis (PCA) and piezodiagnostics to obtain successful diagnosis of events in structural health monitoring (SHM). In this sense, the identification of noisy data and outliers, as well as the management of data cleansing stages can be facilitated through the implementation of a preprocessing stage based on cross-correlation functions. Additionally, this work evidences an improvement in damage detection when the cross-correlation is included as part of the whole damage assessment approach. The proposed methodology is validated by processing data measurements from piezoelectric devices (PZT), which are used in a piezodiagnostics approach based on PCA and baseline modeling. Thus, the influence of cross-correlation analysis used in the preprocessing stage is evaluated for damage detection by means of statistical plots and self-organizing maps. Three laboratory specimens were used as test structures in order to demonstrate the validity of the methodology: (i) a carbon steel pipe section with leak and mass damage types, (ii) an aircraft wing specimen, and (iii) a blade of a commercial aircraft turbine, where damages are specified as mass-added. As the main concluding remark, the suitability of cross-correlation features combined with a PCA-based piezodiagnostic approach in order to achieve a more robust damage assessment algorithm is verified for SHM tasks.

Detecting structural damage in operational conditions still encounters some difficulties, especially in early-stage, as environmental varieties impose challenges in real engineering applications and may require large computational efforts in the structural health monitoring and potential maintenance. Unlike conventional strategies employing frequency response function or response data, a damage detection methodology is addressed in this study by employing transmissibility functions that retains a strong interrelation with structural damage or deterioration, in order to avoid the measurement of excitation, together with principal component analysis that leads to reduction in computational costs. In this procedure, transmissibility is extracted from the structural responses and main features are selected by principal component analysis for less computational costs. Then, via distance measures damage indicators are constructed for both intact and damaged states, and finally a numerical simulation with a clamped-clamped beam and a four-story benchmark are adopted to verify the applicability of the proposed procedure. The results demonstrate a good performance in structural damage detection.

Structural Health Monitoring (SHM) programs play an essential role in the field of civil engineering, especially for assessing safety conditions involving large structures such as viaducts, bridges, tall buildings, towers, and old historical buildings. Typically, an SHM process needs to be based on a trustful strategy for detecting structural novelties or abnormal behaviors. Usually, such an approach is complemented with human inspection and structural instrumentation routines, where the latter requires proper hardware equipment and software tools. However, most strategies already published in this topic mainly focus on modal identification procedures and tracking their outputs i.e., structural modal parameters. Such approaches usually lead to high computational costs and can still be insensitive to minor changes in structural behavior, thus missing crucial damage scenarios in their initial manifestations. To circumvent these drawbacks, recent studies showed that the use of symbolic representations derived directly from raw time-domain data (e.g., acceleration measurements) obtained from vibration tests could provide more damage-sensitive responses with lower computational effort. The proposed methodology employs a clustering technique over such symbolic representations within a moving time-window framework and uses a single-valued index to indicate if a novelty (i.e., structural damage and/or interventions, such as maintenance/repair) is present in the acquired data. Two practical studies—a highway and a railway bridge located in France—show that the proposed tool provide an unsupervised and adaptive scheme for automated real-time SHM applications based on vibration tests.

The results of numerical simulations to test a method to locate and estimate the severity of damage in a structure in the blind mode, by using the simulated data from a four-story steel frame structure analyzed at the Univ. of British Columbia, are reported here. The blind simulated data include the response in the time domain of the undamaged structure and the responses of the structure with two sets of simulated damage conditions. Elements of the theory utilized here for damage detection and localization (the so-called damage index method) are first summarized. Modal analyses are performed to extract the modal characteristics (i.e., resonant frequencies and mode shapes) for the undamaged structure (designated, Case 1) and the damaged structures (here designated, Damage Cases 2 and 3). The results of the modal analyses are reported in detail. Using the proposed nondestructive damage evaluation technique, the predicted damage locations, and estimation of the damage severity are provided for the two damage cases. The actual locations of damage in the test structure for each of the damage cases were revealed subsequent to the damage predictions proposed by the writers during the 16th International Modal Analysis Conference. The predicted damage locations and severity estimates are compared with the damage inflicted in the original test cases. The current method correctly predicts the inflicted damage locations and provides realistic estimates of the associated damage severities.