Damage Detection Algorithm Research Articles

Automatic Detection of Real Damage in Operating Tie-Rods.

Many researchers have proposed vibration-based damage-detection approaches for continuous structural health monitoring. Translation to real applications is not always straightforward because the proposed methods have mostly been developed and validated in controlled environments, and they have not proven to be effective in detecting real damage when considering real scenarios in which environmental and operational variations are not controlled. This work was aimed to develop a fully-automated strategy to detect damage in operating tie-rods that only requires one sensor and that can be carried out without knowledge of physical variables, e.g., the axial load. This strategy was created by defining a damage feature based on tie-rod eigenfrequencies and developing a data-cleansing strategy that could significantly improve performance of outlier detection based on the Mahalanobis squared distance in real applications. Additionally, the majority of damage-detection algorithms presented in the literature related to structural health monitoring were validated in controlled environments considering simulated damage conditions. On the contrary, the approach proposed in this paper was shown to allow for the early detection of real damage associated with a corrosion attack under the effects of an intentionally uncontrolled environment.

A modified teaching–learning optimization algorithm for structural damage detection using a novel damage index based on modal flexibility and strain energy under environmental variations

A modified teaching–learning optimization algorithm for structural damage detection using a novel damage index based on modal flexibility and strain energy under environmental variations

Effect of mechanical properties and geometric dimensions on electromechanical impedance signatures for adhesive joint integrity monitoring

Adhesive joints are prone to damage, which may be difficult to detect using Nondestructive Test. Structural Health Monitoring techniques, such as the Electromechanical Impedance Spectroscopy (EMIS), allow for continuous monitoring and early detection of structural defects. Developing efficient damage detection algorithms requires simulations of adhesive structures, which require elastic and damping properties under high frequency range. Tests were performed for crash-resistant and silicone adhesives. Numerical simulations with said properties were compared with experimental impedance measurements from Single Lap Joints (SLJ). This allowed for the estimation of adhesive properties, but numerical results for SLJs with silicone adhesive diverged from experimental results.

Verifying the suitability of uncoupled numerical methods for solving vehicle-bridge interaction problems

The response of a structure subjected to a moving load can be obtained using coupled or uncoupled methods. The uncoupled method is often preferred since modal superposition is applicable, which implies computational efficiency and ease of implementation. However, the uncoupled method ignores the changes in the dynamic features of the combined structural system due to the time-varying location of the load. This paper analyses the extent to which the accuracy of the uncoupled method is affected by these changes. First, a parametric study is conducted on two discretized beam models traversed by a sprung mass at a constant speed. The error associated with the uncoupled method is calculated using the coupled solution as a reference. The influence of the load to structure mass and frequency ratios and the speed of the vehicle on the error is quantified. Heavier loads travelling at higher speeds are found to increase the inaccuracy of the uncoupled method. Then, the analysis is extended to a half-car travelling on a rough profile. Although errors from the uncoupled simulation remain low for the range of parameters under investigation, they may not be acceptable in some applications, i.e., the training of an algorithm for early damage detection.

Road damage detection using super-resolution and semi-supervised learning with generative adversarial network

Road maintenance technology is required to maintain favorable driving conditions and prevent accidents. In particular, a sensor technology is required for detecting road damage. In this study, we developed a new sensor technology that can detect road damage using a deep learning-based image processing algorithm. The proposed technology includes a super-resolution and semi-supervised learning method based on a generative adversarial network. The former improves the quality of the road image to make the damaged area clearly visible. The latter enhances the detection performance using 5327 road images and 1327 label images. These two methods were applied to four lightweight segmentation neural networks. For 400 road images, the average recognition performance was 81.540% and 79.228% in terms of the mean intersection over union and F1-score, respectively. Consequently, the proposed training method improves the road damage detection algorithm and can be used for efficient road management in the future.

A structural damage detection algorithm based on discrete wavelet transform and ensemble pattern recognition models

Damage detection is of great importance in reducing maintenance cost and preventing collapse of structures. Despite existing damage detection methods, the current literature lacks a comprehensive method, which: (i) is applicable to complex structures with large degrees of freedom, (ii) captures even low-level damages, and (iii) gives reasonable accuracy in the presence of uncertainty conditions such as noise and temperature. Hence, this study proposes a damage detection algorithm based on discrete wavelet transform and an ensemble of pattern recognition models, in which: (1) vibration data is decomposed through discrete wavelet transforms, (2) the decomposed data is compressed using principal component analysis, (3) individual damage models of the structure are trained through pattern recognition models of deep neural network and couple sparse coding, where the compressed decomposed vibration data as well as damage data are inputted, and (4) ultimately, the individual damage models are merged into one by majority voting to predict damage location and severity of the structure. The proposed algorithm is tested on a numerical model of a one-bay three-story steel frame, and experimental data of a large-scale bridge structure. It is found that the algorithm can precisely detect low-level damages at multiple locations, even in beam–column connections and complex structures, in the presence of uncertainty conditions such as noise and temperature.

Методологія проектування автоматичної системи структурного моніторингу технічного стану будівель та споруд

The development of smart systems in various architectural structures leads to the fact that if earlier information about the structural condition was not always important, now when talking about the safety of the population, it is a very high-priority information and direction of research. In general, systems for monitoring the condition of structures allow identification, localization and assessment of damage. Such information about the object allows making appropriate decisions in advance to eliminate possible emergency situations. To solve the task of developing a methodology for the design of an automatic structural monitoring system for various architectural structures, a list of stages that allow designing the necessary system was proposed. So, the research is generally divided into three main stages. At the first stage, topologies of sensor networks are considered. Questions regarding the choice of topology for a wireless sensor network are discussed, and the main advantages and disadvantages of each topology are presented. This will allow to choose the right topology for the system. At the second stage, the levels of damage identification that must be performed, which approaches are based on the used algorithms for damage detection are considered. The most popular algorithms used for damage identification are also listed, their disadvantages and advantages were displayed. The third stage is devoted to the selection of the element base of the sensor node, the comparative characteristics of digital and analog accelerometers are highlighted. Also in this section, popular digital accelerometers are presented and an analysis of the characteristics of how and what is affected by each of them is performed. It was described what characteristics should be taken into account when choosing a microcontroller. When designing, it is necessary to take into account the location of sensor nodes and how this affects the distance of data transmission.

Structural monitoring of RPAS MILANO in the flight test phase

The RPAS (Remote Piloted Air System) MILANO is the largest unmanned aerial system developed by INTA that aims to become a research platform capable of carrying out in-flight tests with many scientific payload, thus complementing the Air Research Platforms (PAIs) of INTA. At the structural level, the RPAS MILANO is made in its entirety in carbon / epoxy composite material that is cured out of the autoclave. Its design has been followed by the airworthiness regulations applicable to the aircraft type (STANAG-4671). In the month of December 2018, the RPAS MILANO flight test phase began and it’s Health and Usage Monitoring System (HUMS) is being used to collect data before, after and during flights, providing very useful information when evaluating and analyzing the state of the structure and the possible appearance of structural overloads not foreseen during the mission. Information about special events, such as forced landing or burst loading, can be provided to maintenance operators after each flight. The simulation model and its predictions have been validated in a real structure of the rear fuselage of the MILANO and in which real damage of larger sizes is introduced by eliminating rivets progressively. In our study, three different damage detection algorithms are used, based on a damage index, PCA and Artificial Neural Networks (ANN).

Damage detection in a fiber reinforced polymers based tower of a floating offshore wind and tidal power platform using structural dynamic parameters

The development of offshore renewable energy structures is growing at a fast pace, and their maintenance will become critical in further years. Because steel corrosion on offshore structures is one of their highest maintenance cost, researchers are working to replace steel by Fibre Reinforced Polymers (FRP), due to their immunity to corrosion. This is done in the EU H2020 funded project FIBREGY, which also seeks improving maintenance costs by incorporating Structural Health Monitoring (SHM) strategies. A critical issue in SHM is the damage detection process, which is addressed in this paper. This study aims to characterize the dynamic behaviour of an offshore windmill FRP tower, and its evolution due the presence of structural damage. This analysis will be carried out using a Finite Element Model (FEM) of the structure, and the Serial-Parallel mixing theory to characterize the material performance. A sensitivity analysis of the changes in the dynamic response of the tower (frequencies and modal shapes) produced by structural damage is carried out. This analysis will provide the optimum design variables and objective functions required by a damage detection algorithm. The algorithm is optimization based, since it converts the damage detection problem into a mathematical one, and finds the best design variables to minimize the objective function. The algorithm is also model based, as it uses the structural model to obtain the objective function for the proposed design variables. Finally, this work presents the analysis of a potential damage scenario, in order to evaluate if the damage is effectively detected.

Combination of Intermittent Search Strategy and an Improve Particle Swarm Optimization algorithm (IPSO) for damage detection of steel frame

Modality and intermittent search strategy in combination with an Improve Particle Swarm Optimization algorithm (IPSO) to detect damage structure via using vibration analysis basic principle of a decline stiffness matrix a structure is presented in the study as a new technique. Unlike an optimization problem using a simplistic algorithm application, the combination leads to promising results. Interestingly, the PSO algorithm solves the optimal problem around the location determined previously. In contrast, Eagle Strategy (ES) is the charging of locating the position in intermittent space for the PSO algorithm to search locally. ES is easy to deal with its problem via drastic support of Levy flight. As known, the PSO algorithm has a fast search speed, yet the accuracy of the PSO algorithm is not as good as expected in many problems. Meanwhile, the combination is powerful to solve two problems: 1) avoiding local optimization, and 2) obtaining more accurate results. The paper compares the results obtained from the PSO algorithm with the combination of IPSO and ES for some problems and between experiment and FEM to demonstrate its effectiveness. Natural frequencies are used in the objective function to solve this optimization problem. The results show that the combination of IPSO and ES is quite effective.

Image-based operational modal analysis and damage detection validated in an instrumented small-scale steel frame structure

The use of image-based techniques in structural dynamics is constantly growing thanks to the decrease in the cost of high-speed cameras and the improvement in image processing algorithms. Compared to traditional sensors, such as accelerometers or velocimeters, the use of fast cameras for data acquisition allows the number of measurements points to be significantly increased. However, such an abundance of points, not always lead to an increased accuracy of damage detection algorithms. With this in mind, we compare different damage detection techniques by using displacement data and modal quantities. A small scale steel frame structure is used to validate the damage detection by using measurements acquired through a high-speed camera with different image processing techniques. The Hybrid Lagrangian Particle Tracking (HLPT) algorithm and Digital Image Correlation (DIC) are both used to extract displacement measurements from images. The results are compared with those obtained with seismic class accelerometers which are normally used in the lab for such an application. Damage localization and intensity have been determined through image-based measurements without losing the accuracy obtained with accelerometers.

Effects of Damaged Rotor on Wake Dynamics of Vertical Axis Wind Turbines

Vertical Axis Wind Turbines (VAWTs) are omnidirectional turbomachines commonly used in rural areas for small-to-medium-scale power generation. The complex flow observed in the wake region of VAWTs is affected by a number of factors, such as rotor blades design. A damaged rotor significantly alters the flow field in the wake region of the VAWT, degrading its power generation capability. Published literature on damaged wind turbine blades is severely limited to torque signal analysis and basic flow field description in the wake region. In this study, detailed numerical investigations have been carried out to establish and quantify the relationship between damaged rotor and the wake dynamics of a VAWT. Time-based Computational Fluid Dynamics analyses have been performed on two VAWT models, one undamaged and the other with a missing rotor blade. Proper Orthogonal Decomposition has been used to extract the energy content and temporal coefficients of the various flow patterns associated with the wake region. The results indicate that the first pressure-based flow mode contains 99% of the energy and provides a functional basis for accurate reconstruction of the wake. It is envisaged that this study will aid the development of novel machine learning algorithms for rotor damage detection in wind farms.

Procedures of Detecting Damage to a Conveyor Belt with Use of an Inspection Legged Robot for Deep Mine Infrastructure

Conveying systems are responsible for a large part of continuous horizontal transportation in underground mines. The total length of a conveyor network can reach hundreds of kilometers, while a single conveyor usually has a route length of about 0.5–2 km. The belt is a critical and one of the most costly components of the conveyor, and damage to it can result in long unexpected stoppages of production. This is why proper monitoring of conveyor belts is crucial for continuous operation. In this article, algorithms for the detection of potential damage to a conveyor belt are described. The algorithms for analysis used video recordings of a moving belt conveyor, which, in case the of hazardous conditions of deep mines, can be collected, for example, by a legged autonomous inspection robot. The video was then analyzed frame by frame. In this article, algorithms for edge damage detection, belt deviation, and conveyor load estimation are described. The main goal of the research was to find a potential application for image recognition to detect damage to conveyor belts in mines.

Sparse Bayesian learning with model reduction for probabilistic structural damage detection with limited measurements

A new variant of damage detection algorithm is proposed based on Sparse Bayesian Learning (SBL) and model reduction for probabilistic structural damage detection. By exploring recent developments in SBL, we aim to produce reliable damage identification even for high-dimensional model parameter spaces for higher-resolution damage localization. By introducing the system modal parameters, the matching of model and experimental modes and solving the nonlinear eigenvalue problem of a structural model are not required. However, one inherent difficulty is that, because only a small number of degrees of freedom (DOFs) can be measured in practice due to limited instrumentation and unmeasurable rotational DOFs, the computation of the system mode shapes has a minimum chance of success. The proposed algorithm extends the applicability of SBL-based damage detection to cases with limited measurements by exploiting model reduction techniques to avoid computation of the system mode shapes for the full model. To effectively incorporate the model reduction procedure, a two-stage SBL-based damage detection algorithm is proposed, in which the first stage updates the reduced system modal properties employing the modal data, and the second stage learns the stiffness parameters and their associated hyper-parameters to produce model sparseness of stiffness losses. The performance of the proposed algorithm is investigated through a series of numerical and experimental studies involving two beam structures and a long-span cable-stayed bridge. Both modeling errors and measurement noises are considered in these studies. The results show that, despite limited measured DOFs in conjunction with modeling error and measurement noise, the proposed algorithm based on SBL and model reduction can successfully locate and quantify the damage along with their posterior uncertainties, which give a sense of identification confidence.

Adaptive Probabilistic Optimization Approach for Vibration-Based Structural Health Monitoring

This paper presents a novel adaptive probabilistic algorithm to identify damage characteristics by integrating the use of the frequency response function with an optimization approach. The proposed algorithm evaluates the probability of damage existence and determines salient details such as damage location and damage severity in a probabilistic manner. A multistage sequence is used to determine the probability of damage parameters including crack depth and crack location while minimizing uncertainties. A simply supported beam with an open edge crack was used to demonstrate the application of the algorithm for damage detection. The robustness of the algorithm was tested by incorporating varying levels of noise into the frequency response. All simulation results show successful detection of damage with a relatively high probability even in the presence of noise. Results indicate that the probabilistic algorithm could have significant advantages over conventional deterministic methods since it has the ability to avoid yielding false negatives that are quite common among deterministic damage detection techniques.

Identification and damage detection of beam-like structure using vibration signals based on simulated model, real healthy state and deep convolutional neural network

Condition monitoring of mechanical systems, such as structures and rotating machines is always a major challenge. This paper is presented a new method for damage detection of real mechanical systems in presence of the uncertainties such as modeling errors, measurement errors, varying loading conditions, and environmental noises based on a simulated model and real healthy state. In this method, data of a real healthy system is used to updating the parameters of the simulated model. Some parts of the signals that are not related to the nature of the system are removed using the complete ensemble empirical mode decomposition method. A deep convolutional network is designed to learn damage-sensitive features from raw frequency data of simulated model and real healthy state. Raw frequency data is extracted from vibration signals using the power spectral density method. In order to train the proposed deep network, raw frequency data of the simulated model andreal healthy state are used. Then, raw frequency data of the real model are used to test the proposed deep network. The proposed method is validated using an experimental beam structure. The results show that using the proposed algorithm for identification and damage detection of the beam-like structure has more accuracy with respect to the other comparative methods

Neutralization of temperature effects in damage diagnosis of MDOF systems by combinations of autoencoders and particle filters

In the last years, scientific and industrial communities have put a lot of efforts into the development of a new framework for the assessment of structural integrity, generally known as Structural Health Monitoring (SHM), which should allow real-time, automatic evaluations of the state of the structures based on a network of permanently installed sensors. In the context of mechanical, aerospace and civil structures, several approaches have been proposed to address the SHM problem, yet, it remains often difficult to diagnose damages and estimate the structural health when dealing with varying operating and environmental conditions. Particle Filters have already been proposed as a time-domain-based method in the field of SHM, showing promising results as estimators of hidden, not directly observable states, such as those typically related to damages. At the same time, neural networks-based autoencoders have been proposed for structural damage detection, demonstrating to be capable of capturing damage-related features from vibration measurements. This work aims at exploiting the individual advantages offered by the two approaches by combining them in a novel algorithm for structural damage detection and localization, robust with respect to changing environmental conditions. The algorithm is further equipped with a fault indicator module stemming from the introduction of an automatic threshold and both deterministic and probabilistic fault indicators, thus offering a complete, valuable tool for supporting decision making with limited human intervention. The method is demonstrated with reference to a numerical MDOF system whose parameters are taken from a literature benchmark case study.

Fatigue damage detection from imbalanced inspection data of Lamb wave

The core of structural health monitoring is to provide a real-time monitoring, inspection, and damage detection of structures. As one of the most promising technology to structural health monitoring, the Lamb wave method has attracted interest because it is sensitive to small-scale damage with a long detection range. However, in many real-world structural health monitoring applications, the nature of the problem implies structures work under normal condition in most of its operating phases; therefore, classes of data collected are not equally represented. The predictive capability of damage detection algorithms may significantly be impaired by class imbalance. This article presents a damage detection method using imbalanced inspection data which is collected through Lamb wave detection. Aiming at maximizing detection accuracy, an improved synthetic minority over-sampling technique using three-point triangle (triangle synthetic minority over-sampling technique) is proposed to conduct the over-sampling procedure and increase the number of minority samples. The iterative-partitioning filter is employed to remove the noisy examples which may be introduced by triangle synthetic minority over-sampling technique. Three conventional classification methods, namely, support vector machine, decision tree, and k-nearest neighbor, are used to perform the damage detection. A fatigue crack detection test using Lamb wave is performed to demonstrate the overall procedure of the proposed method. Three damage sensitive features, namely, normalized amplitude, correlation coefficient, and normalized energy, are extracted from signals as datasets. A cross-validation is performed to verify the performance of the proposed method for crack size identification.

Structural anomaly detection based on probabilistic distance measures of transmissibility function and statistical threshold selection scheme

As a mathematical representation of the output-to-output relationship, transmissibility function (TF) has been extensively applied in structural damage detection due to its robustness to influences of the input variations. As in most engineering fields, dealing with the problem of uncertainty in TF-based feature detection is an issue of fundamental importance. In this study, a new statistical, data-driven damage detection algorithm is proposed by rigorously modelling the variability of TF without postprocessing with circularly-symmetric complex Gaussian ratio distribution. The probabilistic distance of Symmetric Kullback-Leibler (SKL) divergence between TFs under baseline condition and potential damage scenarios which can measure the dissimilarity of probability distributions for the TFs under different states are computed as a damage index (DI) to detect structural anomaly. Compared against Mahalanobis distance which has the implicit assumption that the normal condition set is governed by Gaussian statistics, the probabilistic distance measure proposed in this study can deal with the deviations in TFs not following Gaussian distribution. A statistically rigorous threshold selection scheme integrating Bayesian inference strategy and Monte Carlo discordancy test is proposed to detect the the presence of damage by accommodating the uncertainties of measurements and the probabilistic model of TF. Numerical, experimental, and field test studies are conducted to validate the potential of probabilistic distance measure of TFs in anomaly detection under ambient vibration instead of forced vibration testing. Results demonstrate satisfactory performance of the proposed approach for detecting the existence and quantify the relative damage severity from a global perspective.

A decentralized unsupervised structural condition diagnosis approach using deep auto‐encoders

AbstractIn this paper, the ideas of deep auto‐encoder (DAE) and manifold learning are adopted to solve the problem of structural condition diagnosis. A scalable decentralized end‐to‐end unsupervised structural condition diagnostic framework is proposed. Three damage diagnosis mechanisms are clarified. The structural damage diagnosis approaches are presented from the latent coding domain and the time domain, respectively. In the latent coding domain, an undercomplete DAE is established to extract the distribution of the low‐dimensional manifold of the signal. On the contrary, in the time domain, an overcomplete DAE is adopted to extract the reconstruction error of the signal. Subsequently, normalized damage quantitative indicators are developed in the two domains. The damage localization method is also clarified. The proposed method can extract features directly from original vibration data without the need for additional signal preprocessing techniques. More importantly, the algorithm relies only on the output signals and does not require a numerical or scale model. This framework can be used to identify, locate, and quantify structural damages. The validity of the diagnostic framework is verified using a well‐designed laboratory benchmark structure. A large‐scale grandstand structure is further used to prove the ability of the proposed method for identifying slight structural damage caused by the loosening of joint bolts. The results clearly demonstrate an elegant performance of the proposed damage detection algorithm in structural condition assessment and damage localization.