Crack Detection Technique Research Articles

Railway Track Crack Detection Technique

Railway Track Crack Detection Technique

Automated Vision-Based Detection of Cracks on Concrete Surfaces Using a Deep Learning Technique.

At present, a number of computer vision-based crack detection techniques have been developed to efficiently inspect and manage a large number of structures. However, these techniques have not replaced visual inspection, as they have been developed under near-ideal conditions and not in an on-site environment. This article proposes an automated detection technique for crack morphology on concrete surface under an on-site environment based on convolutional neural networks (CNNs). A well-known CNN, AlexNet is trained for crack detection with images scraped from the Internet. The training set is divided into five classes involving cracks, intact surfaces, two types of similar patterns of cracks, and plants. A comparative study evaluates the successfulness of the detailed surface categorization. A probability map is developed using a softmax layer value to add robustness to sliding window detection and a parametric study was carried out to determine its threshold. The applicability of the proposed method is evaluated on images taken from the field and real-time video frames taken using an unmanned aerial vehicle. The evaluation results confirm the high adoptability of the proposed method for crack inspection in an on-site environment.

Self-Sensing Nonlinear Ultrasonic Fatigue Crack Detection under Temperature Variation †.

This paper proposes a self-sensing nonlinear ultrasonic technique for fatigue crack detection under temperature variations. Fatigue cracks are identified from linear (α) and nonlinear (β) ultrasonic parameters recorded by a self-sensing piezoelectric transducer (PZT). The self-sensing PZT scheme minimizes the data acquisition system’s inherent nonlinearity, which often prevents the identification of fatigue cracks. Also, temperature-dependent false alarms are prevented based on the different behaviors of α and β. The proposed technique was numerically pre-validated with finite element method simulations to confirm the trends of α and β with changing temperature, and then was experimentally validated using an aluminum plate with an artificially induced fatigue crack. These validation tests reveal that fatigue cracks can be detected successfully in realistic conditions of unpredictable temperature and that positive false alarms of 0.12% occur.

Damage Detection in a Plate Structure based on FBG sensing Technique under a Single-Mode Lamb Wave

Lamb wave is widely acknowledged as one of the most encouraging tools for damage identification in plate structures, and relevant research has been conducted intensively. However Lamb wave modes have different wave structure, frequency dispersion and attenuation characteristics, which are sensitivity to different types of damages and it is difficult to solve such engineering problems by conventional techniques. Although the single pattern detection method has been researched by piezoelectric wafers, there is little research about FBG sensing detection under single-mode ultrasonic Lamb wave technique currently. So this paper puts forward a single-mode Lamb wave technique for crack detection based on Fiber Bragg Grating sensor, which is used to receive the waves in the plate. First of all, measuring principle of single-mode ultrasonic Lamb technique and demodulation principle of the FBG sensor are introduced. And simulation analysis in the acoustic field is devoted, whose results lay the foundation for the damage detection in the plate. Then, the experimental system is built by a single-mode Lamb wave excitation, and the feasibility of fiber Bragg grating sensors in single-mode excitation method is verified by experiments.

Crack detection in the rotor ball bearing system using switching control strategy and Short Time Fourier Transform

In case of simple Jeffcott rotors, bearings lie on edges of the rotors, hence bearing nonlinearities are not properly absorbed in the dynamic response. Real rotors containing multiple disks, flexible bearing supports, centrally located ball bearings and couplings are far more complex in terms of their dynamic response than simple Jeffcott rotors. Nonlinear dynamic modelling of the flexible rotor with centrally located ball bearing has been developed and used for simulation purposes. It has been observed that crack detection techniques based on the steady-state vibration response work well for simple Jeffcott rotors only. The presence of ball bearings and other system nonlinearities inhibit the direct application of steady-state dynamic response based crack detection techniques for real rotor-bearing systems condition monitoring. However, transient response based crack detection techniques can be successfully applied to work in the presence of system nonlinearities. Crack propagation is enhanced during high amplitude vibrations, hence, instead of working in the resonance region, working in pre-resonance regions is advantageous due to lower vibration amplitudes. Switching control strategy based on a combination of active vibration control and Short Time Fourier Transform is proposed in present work. The proposed technique basically operates on the signal in pre-resonance regions (with low vibration amplitude) hence avoids chances of the crack propagation. This technique can be used to detect the presence of even small cracks and works well in the presence of bearing nonlinearities and flexible bearing supports that are inherently present in real rotor-bearing systems and qualitatively change dynamics of the overall system.

A Review on SHM Techniques and Current Challenges for Characteristic Investigation of Damage in Composite Material Components of Aviation Industry

Abstract Introduction of composites for aircraft fabrication has given the opportunity to all researchers and original equipment manufacturers to design a lightweight structure that will reduce both fuel consumption and harmful emissions. Reliability and cost of implementing structural health monitoring (SHM) systems are two critical parameters for the utilization of composite materials in the aviation industry. SHM of composite material components in the aviation industry not only lessens the downtime of aircraft but also enhances the possibility of damage detection in order to avoid severe failure. This article presents a case study of SHM systems that has been developed from research and implemented for the inspection and safety of recent aircraft structures. Compulsory components required for proper working of an SHM system and the basis and classification of defects in composite material components of aircraft are thoroughly explained in this article. Furthermore, characterization of SHM techniques (on the basis of functioning, advantages, and limitations) for crack detection and challenges of SHM systems are also part of this case study. An experimental work and its results have been well expressed regarding guided wave inspection using two different types of fiber-optic sensors for quasi-isotropic carbon fiber–reinforced plastic laminate. The ultimate goal of this article is to highlight the current challenges of SHM and promote the concept that SHM has great potential for research in the aviation industry.

Detection and segmentation of mechanical damage in concrete with X-Ray microtomography

X-Ray computed microtomography (micro-CT) is an imaging technique that has seen increasing application in the field of experimental mechanics for its ability to take non-destructive, precise, 3D measurements of material morphology. The microstructure of a heterogeneous material with distinct constituent phases can be segregated using micro-CT as a result of the differences in X-Ray attenuation between the various phases. However, detection and segmentation of different features within the same phase requires more complex methods beyond the segmentation by X-Ray attenuation rate. For example, cracks and porosity are recognized as the same phase by X-Ray attenuation-based segmentation methods. However, these two microstructural features are the result of different processes, as pores are inherent to the microstructure of cementitious materials, while cracks are often considered to be material damage. This study aims to compare a novel quasi-3D crack detection technique with two other techniques reported in previously published studies, with the goal of finding the most effective technique for identifying cracks/damage in concrete specimens subjected to controlled intermittent dynamic mechanical loadings. The results show that while the previously reported techniques work well for detecting cracks in concrete specimens with discrete porosity and/or large interconnected crack networks, they were not as effective in distinguishing small cracks from clusters of voids. The quasi-3D geometric segmentation technique proposed in this study is shown to perform well across all crack length scales even in concrete specimens with interconnected porosity.

Nonlinear Dynamic Modeling of the Cracked Rotor Ball Bearing System With Emphasis on Damage Detection Capabilities

It is confirmed experimentally that in case of a rotor with crack, multiple harmonics are generated when the rotor revolves at a particular frequency. Only few modeling techniques successfully predict this particular behavior of the cracked rotor. It is observed in this research that modeling cracked rotors using conventional finite element methods cannot predict this particular behavior successfully. A nonlinear dynamic model of the flexible rotor with ball bearings is developed using discrete mass spring damper elements combined with an existing model of the crack to truly predict this confirmed experimental behavior. Certain crack detection techniques based on the steady-state response work well on this basic concept of the multiharmonics generation due to nonlinearities caused by cracks in the rotor. The presence of ball bearings, rotor-coupling misalignment, rotor-stator rub, and rotor bow can also cause significant nonlinearities in the overall system. These additional nonlinearities render these crack detection techniques to lose their effectiveness. Our work justifies through simulations that the Jeffcott rotors are the over simplified version of real-life rotor-bearing systems. Hence, these crack detection techniques cannot be efficiently applied for condition monitoring of real-life rotor-bearing systems. The proposed model also helps to understand that the presence of flexible bearing supports affects the dynamics of the system considerably and negatively affects the effectiveness of these crack detection techniques.

Embedded Distributed Optical Fiber Sensors in Reinforced Concrete Structures-A Case Study.

When using distributed optical fiber sensors (DOFS) on reinforced concrete structures, a compromise must be achieved between the protection requirements and robustness of the sensor deployment and the accuracy of the measurements both in the uncracked and cracked stages and under loading, unloading and reloading processes. With this in mind the authors have carried out an experiment where polyimide-coated DOFS were installed on two concrete beams, both embedded in the rebar elements and also bonded to the concrete surface. The specimens were subjected to a three-point load test where after cracking, they are unloaded and reloaded again to assess the capability of the sensor when applied to a real loading scenarios in concrete structures. Rayleigh Optical Frequency Domain Reflectometry (OFDR) was used as the most suitable technique for crack detection in reinforced concrete elements. To verify the reliability and accuracy of the DOFS measurements, additional strain gauges were also installed at three locations along the rebar. The results show the feasibility of using a thin coated polyimide DOFS directly bonded on the reinforcing bar without the need of indention or mechanization. A proposal for a Spectral Shift Quality (SSQ) threshold is also obtained and proposed for future works when using polyimide-coated DOFS bonded to rebars with cyanoacrylate adhesive.

Reliability and sensitivity of magnetic particle nondestructive testing in detecting the surface cracks of welded components

Defects generated during a welding process, specifically surface cracks, have a significant impact on the safety of welded components. Therefore, the detection of these types of defects has a considerable effect on avoiding the failure of the components. Since each nondestructive testing technique has its own limitations in defect detection, evaluating the detection properties of such techniques would be key for the inspectors of welded structures to possess a more proper technique selection. Moreover, the properties can be obtained from a number of maintenance and fracture control procedures such as the damage tolerance design technique. Reliability and sensitivity, as common tools, are extensively utilised to assess detection properties. Magnetic particle nondestructive testing is often used in the surface crack detection of welded components. To use this crack detection technique wisely, the properties have to be considered. However, to date, there has not been a comprehensive study on the reliability and sensitivity of the technique in detecting the surface cracks of welded components. To fill the gap, in this research, based on experiments and an analysis of the obtained data, the reliability and sensitivity of the technique in detecting the surface cracks of welded components are attained and presented.

Detection of Cracks in Rotating Shafts by Using the Combination Resonances Approach and the Approximated Entropy Algorithm

Shaft crack detection is a very serious matter and machines suspected of having a crack must be treated carefully. The importance attributed to this problem is addressed due to the serious consequences when cracks are not early detected in rotating systems. Various crack detection techniques were proposed in the last years, in which the vibration based techniques have demonstrated being efficient. However, these techniques fail for the cases in which incipient cracks are concerned. Recently, a nonlinear approach to detect cracks in rotating shafts was presented. The idea is to excite the shaft by using a harmonic force to induce combination resonances in the system. If the combination resonances appear in the vibration responses of the rotating system, the presence of cracks is confirmed. However, this methodology demonstrated being effective in detecting only deep cracks. In this context, the uniqueness of this paper relies on the possibility of detecting incipient transverse cracks in rotating shafts by associating the combination resonances approach with the so‐called Approximated Entropy algorithm (ApEn algorithm). ApEn is a statistical value used to quantify irregularities in data series. Patterns and correspondences between samples of the same series are searched to detect anomalies. Considering that the combination resonances change the pattern of the shaft vibration responses, the ApEn algorithm can be used to highlight the presence of such resonances and, consequently, the detection of incipient cracks. The proposed approach was numerically evaluated by considering a horizontal rotating machine. A preliminary experimental investigation is also presented. The results demonstrated the efficiency of the conveyed methodology.

Image-Based Crack Detection Using Crack Width Transform (CWT) Algorithm

This paper describes an image-based methodology for the detection of structural cracks in concrete. The conventional approach based on line enhancement filtering has problems associated with an inaccurate extraction of edge pixels. We therefore propose an edge-based crack detection technique consisting of five steps: crack width transform, aspect ratio filtering, crack region search, hole filling, and relative thresholding. In the first step, crack width transform, opposing edges are identified and classified as crack candidate pixels, and a width map is generated. In the second step, aspect ratio filtering, the width map generated is used to remove noise. In the next two steps, the method searches for and restores missing pixels. In the last step, relative thresholding, residual noise is removed through reclassification of crack regions based on image-adaptive thresholding. The performance of this technique was tested using synthetic and real images. The results show that the proposed technique has greater accuracy and consistency in measuring crack width compared with the conventional technique.

Tracking hydrogen embrittlement using short fatigue crack behavior of metals

Understanding hydrogen embrittlement phenomenon that leads to deterioration of mechanical properties of metallic components is vital for applications involving hydrogen environment. Among these, understanding the influence of hydrogen on the fatigue behaviour of metals is of great interest. Total fatigue life of a material can be divided into fatigue crack initiation and fatigue crack growth phase. While fatigue crack initiation can be linked with the propagation of short fatigue cracks, the size of which is of the order of grain size (few tens of microns), that are generally not detectable by conventional crack detection techniques applicable for the long fatigue crack growth behaviour using conventional CT specimens. Extensive literature is available on hydrogen effect on long fatigue crack growth behaviour of metals that leads to the change in crack growth rate and the threshold stress intensity factor range (ΔKth). However, it is the short fatigue crack growth behaviour that provides the fundamental understanding and correlation of the metallic microstructure with hydrogen embrittlement phenomenon. Short fatigue crack growth behaviour is characteristically different from long crack growth behaviour showing high propagation rate at much lower values than threshold stress intensity factor range as well as a strong dependency on the microstructural features such as grain boundaries, phase boundaries, and inclusions. To this end, a novel experimental framework is developed to investigate the short fatigue crack behaviour of hydrogen charged materials involving in-situ observation of propagating short cracks coupled with image processing to obtain their da/dN vs a curves. Various metallic materials ranging from austenitic stainless steel (AISI 316L) to reactor pressure vessel steel (SA508 Grade 3 Class I low alloy steel) and line pipe steels (API 5L X65 & X80) are studied in this work.

Reliability improvement of nonlinear ultrasonic modulation based fatigue crack detection using feature-level data fusion

In this study, the reliability of nonlinear ultrasonic modulation based fatigue crack detection is improved using a feature-level data fusion approach. When two ultrasonic inputs at two distinct frequencies are applied to a specimen with a fatigue crack, modulation components at the summation and difference of these two input frequencies appear. First, the spectral amplitudes of the modulation components and their spectral correlations are defined as individual features. Then, a 2D feature space is constructed by combining these two features, and the presence of a fatigue crack is identified in the feature space. The effectiveness of the proposed fatigue crack detection technique is experimentally validated through cyclic loading tests of aluminum plates, full-scale steel girders and a rotating shaft component. Subsequently, the improved reliability of the proposed technique is quantitatively investigated using receiver operating characteristic analysis. The uniqueness of this study lies in (1) improvement of nonlinear ultrasonic modulation based fatigue crack detection reliability using feature-level data fusion, (2) reference-free fatigue crack diagnosis without using the baseline data obtained from the intact condition of the structure, (3) application to full-scale steel girders and shaft component, and (4) quantitative investigation of the improved reliability using receiver operating characteristic analysis.

영상처리 기반 프레스 패널 통합형 크랙 탐지 기법 개발

프레스 패널은 제조사업 전반의 다양한 분야에 사용되고 있으며, 기술 발전을 통해 프레스 성형의 생산성이 향상되었다. 그러나 프레스 성형과정에서 발생하는 크랙(crack) 탐지는 생산 공정의 특성상 일반적인 접촉식 비파괴검사 기술의 적용이 어렵기 때문에 숙련된 검사자에 의한 육안검사를 통해 품질검사를 실시하고 있는 현황이다. 따라서 본 연구에서는 프레스 패널의 품질관리를 위해 자동화된 영상처리 기반 크랙 검사 시스템을 개발하고자 한다. 크랙 검사 시스템은 패널의 기저 이미지를 필요로 하지 않는 무기저 영상처리 기법과 기저 영상처리 기법을 통합하여 크랙 탐지 결과에 대한 향상된 신뢰성을 갖는 통합형 크랙 탐지알고리즘과 해당 알고리즘을 연동하는 카메라 시스템으로 구성되어 있다. 개발된 크랙 검사 시스템을 실제 프레스 패널 생산 라인에서 검증을 실시하여 현장 적용 가능성을 확인하였다.

Fatigue crack monitoring in train track steel structures using plastic optical fiber sensor

Plastic optical fiber (POF) sensors have shown excellent potential for damage detection and structural health monitoring in a variety of engineering structures. This paper discusses the feasibility of using POF sensors in conjunction with a signal-processing algorithm capable of detecting and monitoring fatigue-induced cracks in train track steel structures in real time. The POF sensor, which was modified from an existing design to increase the signal sensitivity, allows for accurate detection of a fatigue crack developed in a specimen, and was found to compare well to the reference acoustic emission (AE) sensors and crack opening displacement (COD) gauge attached to the specimen. The crack-detection technique, which relies on capturing the intensity variation of the POF sensor, was not susceptible to any signal fluctuations commonly associated with intensity-based optical fiber sensors. The results show that the technique has potential for use in detecting the initiation and propagation of specific segments of a structure vulnerable to cracking due to external cyclic loading, e.g. at welded joints in train tracks under train loads or offshore structures subject to wave loads. The POF sensor system is composed of inexpensive parts (LED light source, photodetectors, and data acquisition units) and can easily be installed to the host structure. To validate the proposed damage-detection technique, the instrumented specimens are subjected to cyclic loading in order to induce stable crack propagation in the specimen. A COD gauge and AE were used for the purpose of calibration and comparison. The results show remarkable resemblance in terms of crack initiation and propagation identification exhibited by all three types of sensors, highlighting the potential of the proposed sensor for crack initiation detection and subsequent monitoring of crack propagation.

Crack detection in pipelines using multiple electromechanical impedance sensors

An extensive network of pipeline systems is used to transport and distribute national energy resources that heavily influence a nation’s economy. Therefore, the structural integrity of these pipeline systems must be monitored and maintained. However, structural damage detection remains a challenge in pipeline engineering. To this end, this study developed a modified electromechanical impedance (EMI) technique for crack detection that involves fusing information from multiple sensors. We derived a new damage-sensitive feature factor based on a pipeline EMI model that considers the influence of the bonding layer between the EMI sensors and pipeline. We experimentally validated the effectiveness of the proposed method. Finally, we used a damage index—root mean square deviation—to examine the degree and position of crack damage in a pipeline.

Crack Detection on Pressed Panel Products using Image Processing Techniques with Camera System

The detection of cracks on panel products is a vital step for ensuring the quality of panel products. General crack detection technique has been performed by human inspectors who are good at detecting crack, which is spend many times and much money. Therefore, it is necessary to detect efficiently crack on panel products by machine vision system during the press forming process. In this study, we performed an automated crack detection using two image processing techniques with camera system. The first technique is evaluating the panel edge lines which are extracted from a percolated object panel image. This technique does not require a reference image for crackdetection. Another technique is based on the comparison between a reference and a test image using the local amplitude mapping on the edge line image. The reference image of panel product is automatically acquired by camera system using image difference and time interval technique. As a result, cracks are efficiently detected using two crack detection techniques based on image processing. For demonstrating the proposed techniques, experiments were performed in the laboratory and the actual manufacturing lines. Experimental results show that the proposed techniques could effectively improve the crack detection rate with improved speed.

An autonomous surface discontinuity detection and quantification method by digital image correlation and phase congruency

Digital image correlation has been routinely used to measure full-field displacements in many areas of solid mechanics, including fracture mechanics. Accurate segmentation of the crack path is needed to study its interaction with the microstructure and stress fields, and studies of crack behaviour, such as the effect of closure or residual stress in fatigue, require data on its opening displacement. Such information can be obtained from any digital image correlation analysis of cracked components, but it collection by manual methods is quite onerous, particularly for massive amounts of data. We introduce the novel application of Phase Congruency to detect and quantify cracks and their opening. Unlike other crack detection techniques, Phase Congruency does not rely on adjustable threshold values that require user interaction, and so allows large datasets to be treated autonomously. The accuracy of the Phase Congruency based algorithm in detecting cracks is evaluated and compared with conventional methods such as Heaviside function fitting. As Phase Congruency is a displacement-based method, it does not suffer from the noise intensification to which gradient-based methods (e.g. strain thresholding) are susceptible. Its application is demonstrated to experimental data for cracks in quasi-brittle (Granitic rock) and ductile (Aluminium alloy) materials.

Fast and Non-invasive Surface Crack Detection of Press Panels Using Image Processing

The crack detection during the manufacturing process is an important step for quality management of panel products. Traditional crack detection methods are subjective and expensive because they are performed by experienced human inspectors. Therefore, crack detection techniques for automated and accurate inspection are required. In this paper, a crack detection technique based on image processing is proposed, which utilizes the images of panel products captured by a regular CCTV camera system. First, the binary panel object image is extracted from various backgrounds after considering RGB color factors. Edge lines are then generated from a binary image using a percolation process. Finally, crack detection and localization are performed with a unique edge line evaluation. In order to demonstrate the capability of the proposed technique, lab-scale experiments were carried out with a thin aluminum plate and a real sample panel. In addition, the test was performed with the images acquired at an actual press line. Experimental results show that the proposed technique could effectively detect panel cracks with an improved rate and speed.