Automated Damage Detection Research Articles

Cultural Heritage Sites in Danger—Towards Automatic Damage Detection from Space

The intentional damage to local Cultural Heritage sites carried out in recent months by the Islamic State have received wide coverage from the media worldwide. Earth Observation data provide important information to assess this damage in such non-accessible areas, and automated image processing techniques will be needed to speed up the analysis if a fast response is desired. This paper shows the first results of applying fast and robust change detection techniques to sensitive areas, based on the extraction of textural information and robust differences of brightness values related to pre- and post-disaster satellite images. A map highlighting potentially damaged buildings is derived, which could help experts at timely assessing the damages to the Cultural Heritage sites of interest. Encouraging results are obtained for two archaeological sites in Syria and Iraq.

Full-scale experimental investigation of wire breakage detection in deviated multi-strand tendon systems

The use of post-tensioning tendons with flexible filler is expected to increase in U.S. bridges in the coming years as an alternative to grouted tendons. Flexible filler results in purely unbonded behavior when used with either internal or external tendons, which creates opportunities for the application of tendon monitoring techniques that were not possible with grouted tendons. One such technique is the detection of wire breakage based on the strain response of the post-tensioning anchorage. The encouraging results from simplified laboratory experiments and analytical models in support of the proposed method motivated the full-scale experiments reported in this paper. Tests were conducted with flexible filler in both external and internal tendons in I-girder specimens having deviated multi-strand tendon profiles, allowing the investigation of the effects of deviators on stress recovery and anchor strain response. The strands of the post-tensioned girders were detensioned by individual wire cuts and the resulting changes in anchor strain distribution were captured. Finally, a broken strand identification algorithm developed for automated damage detection was applied to the experimental results. In addition to instrumenting the anchors with strain gauges, an acoustic sensing system was employed to independently monitor and confirm the breakage events. The findings reported in this study suggest that the wire breakage detection method based on anchor strain measurement can be a reliable and cost-effective approach for in-field bridge monitoring applications.

Automated Cell-Based Quantitation of 8-OHdG Damage.

Detection of 8-OHdG-base damage has been a big challenge for decades, though different analytical methods are developed. The recent approaches that are used for quantitating either the total amount of base damage or the amount of base damage per cell from different sources of samples are not automated. We have developed a method for automated damage detection from a single cell and applied it to 8-OHdG quantitation.

A FRF-based algorithm for damage detection using experimentally collected data

Automated damage detection through Structural Health Monitoring (SHM) techniques has become an active area of research in the bridge engineering community but widespread implementation on in-service infrastructure still presents some challenges. In the meantime, visual inspection remains as the most common method for condition assessment even though collected information is highly subjective and certain types of damage can be overlooked by the inspector. In this article, a Frequency Response Functions-based model updating algorithm is evaluated using experimentally collected data from the University of Central Florida (UCF)-Benchmark Structure. A protocol for measurement selection and a regularization technique are presented in this work in order to provide the most well-conditioned model updating scenario for the target structure. The proposed technique is composed of two main stages. First, the initial finite element model (FEM) is calibrated through model updating so that it captures the dynamic signature of the UCF Benchmark Structure in its healthy condition. Second, based upon collected data from the damaged condition, the updating process is repeated on the baseline (healthy) FEM. The difference between the updated parameters from subsequent stages revealed both location and extent of damage in a blind scenario, without any previous information about type and location of damage.

Degradation Assessment of Industrial Composites Using Thermography

Thermographic inspection is a relatively new technique for Non-Destructive Testing (NDT) which has been gathering increasing interest due to its relatively low cost hardware and extremely fast data acquisition properties. This technique is especially promising in the area of rapid automated damage detection and quantification. In collaboration with a major industry partner from the aerospace sector advanced thermography-based NDT software for impact damaged composites is introduced. The software is based on correlation analysis of time-temperature profiles in combination with an image enhancement process. The prototype software is aiming to a) better visualise the damages in a relatively easy-to-use way and b) automatically and quantitatively measure the properties of the degradation. Knowing that degradation properties play an important role in the identification of degradation types, tests and results on specimens which were artificially damaged have been performed and analyzed.

Lamb wave based automatic damage detection using matching pursuit and machine learning

In this study, matching pursuit (MP) has been tested with machine learning algorithms such as artificial neural networks (ANNs) and support vector machines (SVMs) to automate the process of damage detection in metallic plates. Here, damage detection is done using the Lamb wave response in a thin aluminium plate simulated using a finite element (FE) method. To reduce the complexity of the Lamb wave response, only the mode is excited and sensed. The procedure adopted for damage detection consists of three major steps, involving signal processing and machine learning (ML). In the first step, MP is used for de-noising and enhancing the sparsity of the database. In the existing literature, MP is used to decompose any signal into a linear combination of waveforms that are selected from a redundant dictionary. In this work, MP is deployed in two stages to make the database sparse as well as to de-noise it. After using MP on the database, it is then passed as input data for ML classifiers. ANN and SVM are used to detect the location of the potential damage from the reduced data. The study demonstrates that the SVM is a robust classifier in the presence of noise and is more efficient than the ANN. Out-of-sample data are used for the validation of the trained and tested classifier. Trained classifiers are found to be successful in the detection of damage with a detection rate of more than 95%.

Automatic Damage Detection and Monitoring of a Stitch Laminate System Using a Fiber Bragg Grating Strain Sensor

There are numerous aspects and questions related to the use of composite materials for primary structures in aircraft where the structural integrity is the most important factor. This is especially true if the main concerns are that the material should have good reliability and durability for the primary structural application. Composite laminates are highly sensitive to out-of-plane failure due to their low inter laminar fracture toughness. An alternate method to increase the damage resistance is through three-dimensional fibrous reinforcement such as through-the-thickness stitching with a single fiber as the thread. Recent studies have shown that the stitching of standard laminates can enhance damage tolerance to levels obtainable with toughened resin systems. However, for next-generation aircraft, material improvement alone is not enough to assure or increase the safety and reliability of the structure. Continuous damage monitoring during operation will become an important issue in aircraft safety. Embed ding fiber Bragg grating (FBG) technology into the composite structure as strain sensors could potentially solve the above problem because the FBG can be used to detect and characterize the damage before it reaches a critical stage. The model used to represent this problem is a 6 × 6 Vectran stitched carbon/ epoxy laminate under tension loading, and the real-time monitoring using the FBG strain sensors is combined with acoustic emissions that were conducted during the test. A numerical laminate theory using a rebar element and first-ply failure criterion is performed to determine the preferred area on the specimen for the placement of the FBG before manufacturing and testing. Experiments are presented to determine the damage growth that was quantified with an ultrasonic (water immersion) c-scan. In this research, the FBG successfully detected and characterized the damage in the carbon/epoxy stitch laminate caused in tension loading cases. The FBG is enhanced with acoustic emission data and can quantitatively predict the damage growth.

Automatic damage detection of engineering ceramics ground surface based on texture analysis

Ground textures seriously interfere with the exact identification of grinding damage. The common nondestructive testing techniques for engineering ceramics are limited by their difficulty and cost. Therefore, this paper proposes a global image reconstruction scheme in ground texture surface using Fourier transform (FT). The lines associated with high-energy frequency components in the spectrum that represent ground texture information can be detected by Hough transform (HT), and the corresponding high-energy frequency components are set to zero. Then the spectrum image is back-transformed into the spatial domain image with inverse Fourier transform (IFT). In the reconstructed image, the main ground texture information has been removed, whereas the surface defects information is preserved. Finally, Canny edge detection is used to extract damage image in the reconstructed image. The experimental results of damage detection for the ground texture surfaces of engineering ceramics have shown that the proposed method is effective.

Automated inspection of engineering ceramic grinding surface damage based on image recognition

As the engineering ceramic ground workpieces usually contain machining damage such as breaks and cracks, the traditional test methods cannot accurately reflect the real surface. Therefore, this paper describes an automatic damage detection system of the engineering ceramic machined surface using image processing techniques, pattern recognition, and machine vision. First, it has great influence on the exact identification of surface damage if engineering ceramic machined surfaces contain grinding texture, so Fourier transform is skillfully adopted to remove grinding texture. Second, through image noise reduction, contrast enhancement, and image segmentation, an optimal combination of image preprocessing is obtained. Then, by comprehensive extraction of surface feature parameters, decision tree classifier based on the C4.5 algorithm is built according to shape features and texture features. Finally, the paper achieves automatic extraction and classification of engineering ceramic grinding surface damage, and the recognition accuracy of breakage reaches over 93 %. Experimental results show that this method is effective in defect detection of the engineering ceramic surface, and it also can provide some analytical basis for the post-function hierarchy partition of engineering ceramic workpieces.

Co-seismic surface effects from very high resolution panchromatic images: the case of the 2005 Kashmir (Pakistan) earthquake

Abstract. The use of Very High Resolution (VHR) satellite panchromatic image is nowadays an effective tool to detect and investigate surface effects of natural disasters. We specifically examined the capabilities of VHR images to analyse earthquake features and detect changes based on the combination of visual inspection and automatic classification tools. In particular, we have used Quickbird (0.6 m spatial resolution) images for detecting the three main co-seismic surface features: damages, ruptures and landslides. The present approach has been applied to the 8 October 2005, Mw7.6 Kashmir, Pakistan, earthquake. We have focused our study in and around the main urban areas hit by the above earthquake specifically at Muzaffarabad and Balakot towns. The automatic classification techniques provided the best results wherever dealing with the damage to man-made structures and landslides. On the other hand, the visual inspection method demonstrated in addressing the identification of rupture traces and associated features. The synoptic view (concerning landslide, more than 190 millions of pixels have been automatically classified), the spatiotemporal sampling and the fast automatic damage detection using satellite images provided a reliable contribution to the prompt response during natural disaster and for the evaluation of seismic hazard as well.

Small-Format Aerial Photography for Highway-Bridge Monitoring

Small-format aerial photography (SFAP) is a low-cost solution for bridge-surface imaging and is proposed as a remote bridge-inspection technique to supplement current bridge visual inspection. Providing top-down views, photos taken from airplanes flying at 305 m (1,000 ft) allow for the visualization of subinch (i.e., large) cracks and joint openings on bridge decks or highway pavements. An onboard global positioning system can help geo-reference images collected and allow automated damage detection. However, the site lighting, surrounding tree shades, and highway surface reflectivity may affect the quality of the images. Several examples of bridge evaluation using SFAP are presented to demonstrate the capability of remote sensing as an effective tool for bridge-construction monitoring and condition assessment. A deck condition rating technique for large crack detection is proposed to quantify the condition of the existing bridge decks.

Damage Detection and Assessment System of Roads for Decision Support for Disaster

After the occurrence of significant natural disaster, the resulting damaged roads interrupt the rapid emergency response for disaster, and therefore, the disaster relief department is desperate for the destruction condition of roads in the devastated region, which can help make relief decisions and deploy rescue actions. In view of the practical needs of the disaster relief department and the objective fact that at present there is not any special, high automatic damage detection system of roads, we develop Road Damage Detection and Evaluation System (RODDES). Using the basic road data in GIS (Geographical information system) as the prior knowledge, the system extracts the pre-disaster and post-disaster roads from post-disaster remotely sensed imageries, and then detects the damaged regions and evaluates the destruction condition. This paper emphasizes the overall design of the system and the submodule design and their functions. The system is applied in detecting and evaluating the damaged roads in Wenchuan County, China and the experiment results show that nearly all producer’s and user’s accuracies of the road extractions and damage detections are above 75%, and it accurately evaluates the destruction condition of roads.

Ultrasonic Guided Waves-Based Monitoring of Rail Head: Laboratory and Field Tests

Recent train accidents have reaffirmed the need for developing a rail defect detection system more effective than that currently used. One of the most promising techniques in rail inspection is the use of ultrasonic guided waves and noncontact probes. A rail inspection prototype based on these concepts and devoted to the automatic damage detection of defects in rail head is the focus of this paper. The prototype includes an algorithm based on wavelet transform and outlier analysis. The discrete wavelet transform is utilized to denoise ultrasonic signals and to generate a set of relevant damage sensitive data. These data are combined into a damage index vector fed to an unsupervised learning algorithm based on outlier analysis that determines the anomalous conditions of the rail. The first part of the paper shows the prototype in action on a railroad track mock-up built at the University of California, San Diego. The mock-up contained surface and internal defects. The results from three experiments are presented. The importance of feature selection to maximize the sensitivity of the inspection system is demonstrated here. The second part of the paper shows the results of field testing conducted in south east Pennsylvania under the auspices of the U.S. Federal Railroad Administration.

Near-field Sub-band Beamforming for Damage Detection in Bridges

Traditional structural health monitoring techniques based on the vibration response of bridge structures are limited because of several factors — including a poorly formed aggregate system model, very low SNR, and unrealistic boundary conditions. Many times, these methods rely on global parameters to describe the dynamic behavior of local structural elements. In this paper, we proposed a novel efficient SHM technique that employs the use of compactly supported sub-band space/ frequency and time/frequency analysis using local vibration characteristics. To overcome the problem of the low-error sensitivity of features extracted from vibration signals, a near-field adaptive beamforming approach was used. This technique allows the sensor array to `scan' local portions of the structure, resulting in accurate spatial selectivity on the array and high signal-to-noise ratio for any given scan direction. Moreover, the sensor array was in direct contact with the vibrating structure, and thus the measured source is in the near-field of the array. Therefore, compensation of the sensor output was needed. Sub-band analysis and adaptive beamforming were integrated in a wavelet packet sub-band framework. We utilized the 3D energy map of the optimized sub-band signals for any given scan direction and for each sub-band center frequency as the damage detection feature. We validated our method using classical finite elements approximation to the dynamic behavior of the system. The comparison of a simulated undamaged simply supported beam with a damaged equivalent revealed that damage is localized in frequency and aligned with the direction of the simulated damage. The energy signature comparison after the beamforming stage validates these results, localizing the damage in areas of high probability around the direction of the damage. Automatic analysis of the energy comparison map was possible using a pseudo density estimation of the damage location, allowing for an automatic damage detection procedure. The focus of our research was aimed toward the adaptation of this damage detection method to real highway bridges.

Structural Health Monitoring of an Advanced Grid Structure with Embedded Fiber Bragg Grating Sensors

The authors focus on the construction of a structural health monitoring (SHM) system with an advanced grid structure (AGS) made of carbon-fiber reinforced plastic (CFRP). AGS is often applied to aerospace structures because the ribs carry only axial forces in the carbon fiber direction, making AGS structurally effective and lightweight, and because the repetition of many ribs in the AGS composition results in damage tolerance. The failure of a single rib hardly affects the fracture of the whole structure, making AGS a fail-safe structure. In this research, the authors have embedded multiplexed-fiber Bragg grating (FBG) sensors into an AGS rib in the longitudinal direction to measure mechanical strains of all ribs in order to detect the existence and regions of AGS rib fractures. Monitoring the change in rib-longitudinal strains is the most effective SHM system for AGS. To confirm the proposal, the authors explore the following. First, various damage characteristics under low-velocity impact loading are investigated and it is verified that partial rib cracks are the most typical damage in AGS. An AGS is then fabricated with embedded FBG sensors and verified that the SHM system is able to measure all rib strains. Subsequently, it is analytically determined that the change in longitudinal-rib strains is the most appropriate mechanical feature for damage detection. Moreover, a statistical outlier analysis is introduced into the SHM system for automatic damage detection. Finally, AGS is established with the SHM system and verified experimentally. Results confirm that the existence of damage and its regions in AGS can be detected with the proposed SHM system.

Monitoring of Delamination of the CFRP Beam by the Smart Structure System Using the SI-F Method

The structure with the sensor and the actuator is called Smart Structure. Installation of the sensor and the actuator to the structure enables the automatic damage detection. In this paper, a novel damage detection method called “SI-F method” is applied to the Smart Structure to detect the delamination in the CFRP beam. The artificial delamination in the CFRP is introduced by the out-of-plane bending. CFRP beam will be exited by the PZT actuator, and the strain of the surface will be measured by the strain gauge. As the result, the delamination is successfully detected by varying the condition of the excitation.

Building Damage Mapping of the 2003 Bam, Iran, Earthquake Using Envisat/ASAR Intensity Imagery

A strong earthquake occurred beneath the city of Bam, Iran, on 26 December 2003. High-resolution optical satellite images, such as Ikonos and QuickBird, obtained after the earthquake indicate that severely damaged areas were widely distributed in the city. A European radar satellite, Envisat, also captured the hard-hit areas on 07 January 2004. This paper introduces an automated damage detection technique that was developed based on the data set of the 1995 Kobe, Japan, earthquake and applied to Envisat/ASAR images of Bam. A detailed investigation of the characteristics of the areas damaged due to the Bam earthquake in terms of the differences in the backscattering coefficient and the correlation coefficient of the pre- and post-event Envisat/ASAR images was conducted in order to raise the precision of damage detection. Finally, the damage-mapping scheme was revised to present the distribution of damaged areas in Bam.

An Automatic Damage Detection Methodology for Structural Health Monitoring during Fatigue Tests

An Automatic Damage Detection Methodology for Structural Health Monitoring during Fatigue Tests

Fuzzy logic expert system for automated damage detection from changes in strain energy mode shapes

In recent years, researchers have developed several methods for damage detection in structures employing strain energy or curvature mode shapes. Experience shows that mode shape methods are highly sensitive to measurement noise. Such sensitivity is a direct result of the second derivative applied to the displacement mode shapes, which produces curvature mode shapes. Calculation of strain energy mode shapes includes calculation of curvature as well. Consequently, the artifact false peaks (normally an indicator of damage) appear on the strain energy mode shapes, reducing accuracy of damage recognition. Combined with the intrinsic variance in damage peak shapes and amplitudes dependent upon magnitude and location of damage, the false peaks create a major problem for automated detection of damage location. Most often, a highly qualified expert is required to analyze the data and to identify and locate damage. In an attempt to replace the human expert with a computer, this paper describes a fuzzy logic expert system designed to mimic the human decision process. An expert system allows for easy encoding of expert knowledge as a set of rules. "Fuzziness" of the expert system allows better treatment of the uncertainties of the problem and to simplify the expert system itself. The fuzzy expert system has been designed based on a finite element (FE) model of a simple beam and has provided reliable detection of damage for every tested damage scenario (100% recognition). The same system recognized damages with 100% accuracy, and no false positives or negatives on mode shapes acquired by impact testing and/or non-contact laser vibrometer techniques.

Detection of laser damage to the surfaces of materials and coatings with the aid of an induced gas discharge

A method for detection of laser damage to the surfaces of optical materials and coatings was investigated. The damage was detected with the aid of a gas discharge induced by the products of a laser ablation plume. A suitable selection of the parameters of the detection system made it possible to investigate laser surface damage at radiation intensities W>130 MW cm-2 (λ = 1.06 μm, tp=10 ns). A special feature of the electric response was that the result was determined solely by the occurrence of damage and not by its nature or by the laser damage threshold. This feature makes the method suitable for automatic damage detection systems used in statistical investigations.