Diagnosis Of Damage Research Articles

Machine-Learning-Based Methods for Acoustic Emission Testing: A Review

Acoustic emission is a nondestructive control technique as it does not involve any input of energy into the materials. It is based on the acquisition of ultrasonic signals spontaneously emitted by a material under stress due to irreversible phenomena such as damage, microcracking, degradation, and corrosion. It is a dynamic and passive-receptive technique that analyzes the ultrasonic pulses emitted by a crack when it is generated. This technique allows for an early diagnosis of incipient structural damage by capturing the precursor signals of the fracture. Recently, the scientific community is making extensive use of methodologies based on machine learning: the use of machine learning makes a machine capable of receiving a series of data, modifying the algorithms as they receive information on what they are processing. In this way, the machine can learn without being explicitly programmed, and this implies a huge use of data and an efficient algorithm to adapt. This review described the methodologies for the implementation of the acoustic emission (AE) technique in the evaluation of the conditions and in the monitoring of materials and structures. The latest research products were also analyzed in the development of new methodologies based on machine learning for the detection and localization of damage for the characterization of the fracture and the prediction of the failure mode. The work carried out highlighted the strong use of these methods, which confirms the extreme usefulness of these techniques in identifying structural damage in scenarios heavily contaminated by residual noise.

Damage features extraction of prestressed near-surface mounted CFRP beams based on tunable Q-factor wavelet transform and improved variational modal decomposition

Damage detection of prestressed near-surface mounted (NSM) carbon fiber reinforced polymer (CFRP) beams has attracted much attention over the last few decades due to the dramatic increase in the proportion of prestressed NSM CFRP beams in the civil infrastructure. Although many studies have demonstrated the effectiveness of piezoelectric transducer-based damage detection techniques, one of the most reported problems is the variation in signal vibration characteristics caused by external noise, which limits the effectiveness of detection and quantification using traditional basic damage indicators. This study proposed a novel signal processing method of damage feature extraction in a noisy environment based on the tunable Q-factor wavelet transform with improved variational modal decomposition, which is aimed to expand the applicability of the piezoelectric transducer-based damage detection techniques in the damage diagnosis of the prestressed NSM CFRP beam. The proposed method is validated by a numerical case study of an analog signal and an experimental study of NSM CFRP beams. The results show that the tunable Q-factor wavelet transform and improved variational modal decomposition can be employed to remove the environment noise and extract the damage feature of the NSM CFRP beam, which helps in the damage assessment of the NSM CFRP beam.

Review on the Damage and Fault Diagnosis of Wind Turbine Blades in the Germination Stage

In recent years, wind turbines have shown a maximization trend. However, most of the wind turbine blades operate in areas with a relatively poor natural environment. The stability, safety, and reliability of blade operation are facing many challenges. Therefore, it is of great significance to monitor the structural health of wind turbine blades to avoid the failure of wind turbine outages and reduce maintenance costs. This paper reviews the commonly observed types of damage and damage detection methods of wind turbine blades. First of all, a comprehensive summary of the common embryonic damage, leading edge erosion, micro-cracking, fiber defects, and coating defects damage. Secondly, three fault diagnosis methods of wind turbine blades, including nondestructive testing (NDT), supervisory control and data acquisition (SCADA), and vibration signal-based fault diagnosis, are introduced. The working principles, advantages, disadvantages, and development status of nondestructive testing methods are analyzed and summarized. Finally, the future development trend of wind turbine blade detection and diagnosis technology is discussed. This paper can guide the use of technical means in the actual detection of wind turbine blades. In addition, the research prospect of fault diagnosis technology can be understood.

Diagnosis and Prognosis of Fatigue Damage in Adhesively Bonded Joints Using Ultrasound Non-Destructive Evaluation

Abstract Increased effort for lightweighting of automotive structures results in the replacement of traditional metals with composites. Adhesive bonding is the best joining solution for composite components owing to its superior stress distribution and lightweighting. However, adhesive and adhesive-adhered interfaces are the weakest links in the structure. During fatigue crack propagation, joints do not show any significant visual changes. Thus, fatigue damage in adhesive bond lines is one of the challenging and complex failure mechanisms that requires real-time diagnostic and prognostic techniques to avoid any catastrophic failure. This paper proposes an acoustic technique for real-time fatigue damage diagnosis and prognosis. Based on experimental guided wave modal analysis, symmetric mode at 85 kHz is found to be the most sensitive mode–frequency combination for fatigue monitoring of selected lap-joint specimens. Further, a hybrid data-driven damage propagation model is used to estimate the remaining useful life in the bond line. The developed techniques were successfully implemented and validated on a single lap joint under fatigue loading. Estimated damage levels and remaining useful life are in good agreement with reference measurements. Successful validation is an indicator of the potential application of this technology in automotive industries.

Extrapulmonary manifestations of SARS-CoV-2: a new coronavirus infectionas an aggravating factor in peptic ulcer disease

The global pandemic of the new coronavirus infection (COVID-19) has become an extreme challenge for the health care of the whole world since 2020.The main target of the SARS-CoV-2 virus is the lungs, but at the same time, more and more evidence is accumulating that the new coronavirus can also aff ect other organs and systems, such as the heart, blood vessels, kidneys, intestines, and brain.Thus, adequate management of a coronavirus patient means not only the therapy of viral pneumonia, but also the timely diagnosis and treatment of damage to other organs.The analysis of predictor factors of severe course and fatal outcome in COVID-19 indicates the aggravating role of comorbid pathology, such as cardiovascular diseases, diabetes mellitus, chronic obstructive pulmonary disease, chronic gastrointestinal diseases. Therefore, in addition to measures to prevent infection with SARS-CoV-2, measures should also be taken to control the comorbid conditions present in the patient.ACE2 receptors, which the virus uses to penetrate human cells, can also be expressed in the esophagus, stomach, small and large intestines, liver and pancreas. This makes the frequency of gastroenterological symptoms in COVID-19 high, which is caused both by the defeat of the digestive organs by the coronavirus itself and by the exacerbation of chronic gastrointestinal diseases against the background of infection and its aggressive therapy. At the same time, the presence and severity of digestive diseases signifi cantly affect the clinical course of COVID-19.This article is devoted to the pathogenesis, clinical picture, approaches to the diagnosis and therapy of erosive ulcerative lesions of the stomach and duodenum against the background of a new coronavirus infection.

Novel Fault Diagnosis of Bearings and Gearboxes Based on Simultaneous Processing of Spectral Kurtoses

Diagnosis of bearings and gears, traditionally uses the envelope (i.e., demodulation) approach. The spectral kurtosis (SK) is a technique used to identify frequency bands for demodulation. These frequency bands are related to the structural resonances, excited by a series of fault-induced impulses. The novel approach for bearing/gear local fault diagnosis is proposed, based on division of bearing/gear vibration signals into specially defined short duration segments and simultaneous processing of SKs of all these segments for damage diagnosis. The SK-filtered vibrations are used for diagnostic feature extraction further subjected to the decision-making process, based on k-means and k-nearest neighbors. The important feature of the proposed approach is robustness to random slippage in bearings. The experimental validation of a bearing inner race local defects (1.2% relative damage size), and simulated gear vibration (15% relative pitting size), shows a very good diagnostic performance on bearing vibrations and gear vibrations to diagnose local faults. Novel diagnostic effectiveness comparison between the proposed technology and wavelet-based technology is performed for diagnosis of local bearing damage.

Diagnosing Disk-Space Variation in Transformer Windings Using High-Frequency Inductance Measurement

Leakage and magnetizing inductances of transformer windings are routinely measured by power utilities during scheduled maintenance. They are often used to confirm the diagnosis of mechanical damages in windings after Swept Frequency Response Analysis shows a mismatch. Inductance measurements performed at power frequency can possibly reveal the presence of damages that have substantially progressed but cannot detect them at their nascent stages since inductances at power frequency remain almost unaltered. This paper investigates the possibility of using high-frequency inductance to this end considering a frequently encountered mechanical damage, viz., disk-space variation in a disk winding. Effect of disk-space variation is investigated in this article using FEM at first and inductances at different frequencies are considered: magnetizing and leakage inductances at 50 Hz, and inductance at a higher frequency region corresponding to winding resonances, say, 500 kHz. The inductance at high frequencies not only exhibited increased sensitivity compared to that at power frequency, but also captured the extent of damage. Simulations performed using Ansys Maxwell and experimental results on an actual 1- <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\phi$</tex-math></inline-formula> transformer are reported. Results show that the high-frequency inductance not only offers a considerably increased sensitivity to disk-space variation in windings compared to the power frequency inductances, but also provides insight regarding the extent of movement which is not apparent from the frequency response.

Feasibility of transbronchial lung cryobiopsy in patients with veno-venous extracorporeal membrane oxygenation support.

Veno-venous extracorporeal membrane oxygenation (VV-ECMO) is essential life support in patients with severe acute hypoxaemic respiratory failure. However, biopsies should be considered for some patients with unknown aetiology. This study aims to evaluate the feasibility of transbronchial lung cryobiopsy (TBLC) in such patients. All patients with acute hypoxaemic respiratory failure of unknown aetiology who underwent TBLC with VV-ECMO support were retrospectively reviewed. Patients' characteristics, ventilation settings, procedure parameters, complications, pathological diagnosis and survival were summarised and analysed. Eight female and five male patients with VV-ECMO support underwent TBLC. The median age was 58 (interquartile range (IQR) 38-67) years old. Concurrent diseases were present in 10 of the 13 patients, seven of which were immunosuppressed. The median time between biopsy and VV-ECMO establishment was 2.0 (IQR 0.5-6.5) days. No patient died from the procedure. Neither pneumothorax nor severe bleeding occurred in any of the patients. Five of the 13 patients experienced moderate bleeding, and all bleeding events were successfully controlled with prophylactic balloon blockers. Pathological diagnosis by TBLC was obtained in all patients, and the diagnosis of diffuse alveolar damage was made in nine of them. In patients with VV-ECMO support, the TBLC procedure is generally safe when standardised bleeding prophylaxis is in place. TBLC contributes to identifying underlying aetiologies in patients with acute hypoxaemic respiratory failure of unknown aetiology.

THE EFFECTIVENESS OF SHEAR WAVE ELASTOGRAPHY IN THE ASSESSMENT OF LIVER DAMAGE IN PATIENTS WITH POST-COVID SYNDROME

The article presents a review of literature data on the aspects of post-covid liver damage, as well as on the diagnostic capabilities of shear wave ultrasound elastography in its assessment. Development of consequences to the new coronavirus infection COVID-19 resulted in an increased interest in their study. In May 2020, the set of symptoms after COVID-19 was combined by the term "post-covid syndrome" and was introduced into the ICD-10 system – (U09.9). The post-covid syndrome is a set of multisystem manifestations of COVID-19, lasting more than 12 weeks, on a permanent basis or with a wave-like course. According to the literature, 35% of patients have liver damage. As part of the study of pathogenetic mechanisms, several theories have now been proposed: direct damaging effect of the virus, immune-mediated inflammation, hypoxia, drug hepatotoxicity and hepatic comorbidity. Laboratorially liver dysfunction in COVID-19 is characterized by an increase in the level of transaminases, intrahepatic cholestasis, signs of hepatic cell insufficiency. Increased ALAT, thrombocytopenia and hypoalbuminemia are proved to be factors of severe course and increased mortality in patients with COVID-19. Therefore, the issues of early instrumental diagnosis of hepatopathies are actualized in this issue. The "gold standard" for instrumental assessment of liver structure is biopsy, but it is limited in use due to the invasiveness of the procedure. According to the WHO experts, priority in the study of post-covid syndrome should be given to the development of new non-invasive and accessible diagnostic methods. Taking into account the success in the use of ultrasound elastography in the diagnosis of diffuse liver diseases in recent years, it seems that the most informative method in the diagnosis of post-covid liver damage is shear wave ultrasound elastography. The advantages of the method are established to be absence of radiation load on the patient and the doctor, the possibility of conducting the study under optimal visual navigation, non-invasiveness, the choice of any zone of interest, assessment of the structure and functional state of the liver. Shear wave ultrasound elastography is a promising innovative way to assess the structure of the liver in patients with post-COVID syndrome and requires further study.

NEW MARKERS FOR DIAGNOSIS AND PROGNOSIS OF COGNITIVE IMPAIRMENT IN PATIENTS WITH MULTIPLE SCLEROSIS (review)

The article presents modern approaches about the diagnosis of brain damage and the development of cognitive impairment in patients with multiple sclerosis. Neurodegenerative changes are considered, which take place in the early stages of the disease and play an important role in the formation of irreversible neurological deficits. Cognitive impairment in patients with multiple sclerosis is quite common, but they are not always noticed, but they significantly reduce patients' quality of life. The article describes the possibilities of neuroimaging methods to identify structural changes in the parts of the brain responsible for cognitive functions. The importance of brain neurotrophic factor (BDNF) as a promising biomarker of multiple sclerosis is presented. Further study of BDNF remains interesting, which will allow to develop algorithms for early diagnosis and prediction of disease progression, that will provide an opportunity to deepen the understanding of the place of BDNF in the pathomorphological chain of nervous system damage in multiple sclerosis.

Editorial: Wind turbine fault and damage diagnosis and prognosis

Editorial: Wind turbine fault and damage diagnosis and prognosis

Improving accuracy of damage quantification based on two-level consistency control of PZT layers

Structural health monitoring-based quantitative damage diagnosis technique plays a key role in real-time condition monitoring. Among the current research, piezoelectric (PZT) sensor and Guided Wave (GW) based damage quantification methods are promising, which normally establish a calibration model between GW feature and damage degree by experiments on batch specimens, and then conduct the calibration model on the monitored specimen. However, the accuracy of PZT and GW based damage quantification is affected by dispersion introduced by sensor network performance, structural material, and damage propagation among the adopted batch specimens. For improving the accuracy of damage quantification, this paper adopts PZT layer as sensor network and creatively implements theoretical and experimental research on batch PZT layers consistency control. On one hand, a two-level consistency control method based on multidimensional features-Euclidean distance is proposed to ensure the performance consistency of PZT layers placed on different specimens. On the other hand, experimental research on typical aircraft lug structures is also carried out to evaluate the requirement on performance consistency of PZT layers when performing quantitative damage diagnosis, and further verify the proposed two-level consistency control method. Experimental results show that the accuracy of damage quantification raises by 38% when the dispersion of different PZT layers is controlled within 5%.

Multi-objective variational autoencoder: an application for smart infrastructure maintenance

Multi-way data analysis has become an essential tool for capturing underlying structures in higher-order data sets where standard two-way analysis techniques often fail to discover the hidden correlations between variables in multi-way data. We propose a multi-objective variational autoencoder (MO-VAE) method for smart infrastructure damage detection and diagnosis in multi-way sensing data based on the reconstruction probability of autoencoder deep neural network (ADNN). Our method fuses data from multiple sensors in one ADNN at which informative features are being extracted and utilized for damage identification. It generates probabilistic anomaly scores to detect damage, asses its severity and further localize it via a new localization layer introduced in the ADNN. We evaluated our method on multi-way laboratory-based and real-life structural datasets in the area of structural health monitoring for damage diagnosis purposes. The data was collected from our deployed data acquisition system on a cable-stayed bridge in Western Sydney, a reinforced concrete cantilever beam which replicates one of the major structural components on the Sydney Harbour Bridge and a laboratory based building structure obtained from Los Alamos National Laboratory (LANL). Experimental results show that the proposed method can accurately detect structural damage. It was also able to estimate the different levels of damage severity, and capture damage locations in an unsupervised aspect. Compared to the state-of-the-art approaches, our proposed method shows better performance in terms of damage detection and localization.

Metode Forward Chaining Untuk Mendiagnosa Kerusakan Mesin Mobil Toyota Innova Berbasis Web

The growing development of the automotive industry in Indonesia has an impact on increased car sales. More and more people are buying cars because they have become daily transportation. Damage experienced in the car is handled by experts or expert technicians. Diagnosis of damage is carried out by a technician based on signs of initial damage to the car. This encourages experts to develop new computer systems to support human work. The development of computers today has undergone many very rapid changes, along with the increasing and complex human needs. then we need a method or system that can diagnose damage to the car. One of them is by utilizing artificial intelligence technology. One sub-field of artificial intelligence is an expert system. By utilizing expert system technology can be produced a system to diagnose car engine damage. This expert system discusses the diagnosis of web-based Toyota Innova damage using the forward chaining method. With the aim of helping the community to diagnose the damage to the Toyota Innova car engine.

Application of a remotely bonded fiber-optic Bragg grating sensor to acoustic emission testing for a carbon-carbon composite at a temperature of 1000 °C

This research established an acoustic emission (AE) testing method applicable at high temperatures using a fiber Bragg grating (FBG) sensor. The method was employed to inspect the process of flexural failure of a heat-resistant carbon–carbon (CC) composite material during a three-point bending test conducted at a temperature as high as 1000 °C. This paper reported the AE testing results. Also, the AE signals with different waveform features were classified by a clustering analysis based on machine learning. Those different AE signal clusters were further associated with different damages, such as matrix crack, inter-ply delamination, and breakage of the fiber bundles. The relation between the damage mechanism and the material failure was then investigated based on the classified AE testing results. The investigation clarified that the progressive behavior of those damages depended on the extent of the material oxidation at elevated temperatures. The analysis agreed with the microscopic cross-section observation. Hence, this article demonstrated that the FBG-based AE testing method was capable of reliable in-situ damage diagnosis under high-temperature environments.

Adhesive curing effect of bonded piezoelectric transducer on electromechanical impedance-based concrete structural damage detection

Complete understanding of the adhesive curing effect of a bonded piezoelectric lead zirconate titanate (PZT) sensor on the electromechanical admittance (EMA, inverse of impedance) facilitates the accurate diagnosis of structural damages when employing the impedance technique for structural health monitoring. This article analytically and experimentally investigated the curing effect of adhesive layer on the EMA-based concrete structural damage detection. Curing effect was theoretically incorporated into shearing mechanism of adhesive layer to formulate a new one-dimensional PZT-structural impedance model. Analytical analysis of the curing effect on the EMA signature as well as the EMA-based damage diagnosis was calculably interpreted through the model. Proof-of-concept experiment was performed on testing a four-point bending reinforced concrete (RC) beam bonded with multiple PZT patches under adhesive curing. Experimental results demonstrated that singular shift in the EMA spectra under adhesive curing could be turned into three typical shifts when structural damage occurred, which cogently validated the analytical results. Quantifiable signal index further provided useful information for the identification of crack occurrence, progression, and reinforcement yielding of the RC beam. Results of this study potentially promoted the real-life engineering applications of impedance technique inclusive of deficient adhesive condition.

Endoscopic Diagnosis and Treatment of Iatrogenic Ruptures of the Trachea

Abstract Respiratory tract trauma is not only the result of injuries to the chest and neck, but may be iatrogenic as well. Diagnosis of iatrogenic damage to the trachea is based on data from clinical and instrumental studies. Among the instrumental diagnostic measures, preference is given to early fibrobronchoscopy.The aim of the study is to assess the possibilities of fiberoptic bronchoscopy in the diagnosis of iatrogenic tracheal injuries. Materials and methods. This study analyzed the use of fiberoptic bronchoscopy in 51 patients with suspected iatrogenic damage to the trachea. For iatrogenic ruptures of the trachea, the location on the posterior (membranous) wall and the longitudinal direction (100%), as well as location in the lower and middle thoracic sections of the trachea (71.4%), are typical.Conclusion Bronchoscopy is a direct method for diagnosing this type of damage, which allows the location, size of the defect and tactics to be accurately determined.

Multisensory collaborative damage diagnosis of a 10 MW floating offshore wind turbine tendons using multi-scale convolutional neural network with attention mechanism

An effective damage diagnosis and prognostic management method can considerably reduce operation and maintenance costs of floating wind turbines. In this research, an intelligent damage diagnosis framework, named “MS-ACNN”, has been developed using a multi-scale deep convolution neural network model fused with an attention mechanism. The framework is used to detect, localize, and quantify existing and potential damages on multibody floating wind turbine tendons. The MS-ACNN framework is fitted with two multi-scale extractors, designed to capture multi-scale information from raw wind turbine response signals measured using multi-sensor. The attention mechanism uses weight ratios of extracted damage feature to enhance the MS-ACNN's capability in offering a better generalization in damage diagnosis. The framework's performance is examined under normal and noisy environments and with a diagnosis accuracy of 80%, which is higher than those obtained using most generic industrial grade diagnostic tools (MS–CNN–I, MSCNN-II, CNN, CNN-LSTM and CNN-BiLSTM) by at least 10%. The framework is also fitted with a Majority Weighted Voting rule to reduce false alarms and ensure optimum performance of the multi-sensor during collaborative diagnosis. Further examination shows that the inclusion of a voting rule increases the diagnostic performance's F1 index from 90% for single sensor and 84% for multi-sensor results to 94%.

Adversarial Fuzzy-Weighted Deep Transfer Learning for Intelligent Damage Diagnosis of Bridge With Multiple New Damages

Recently, domain-adaptation based transfer learning has been extensively studied and successfully achieved promising results in addressing the domain drift in closed-set scenarios. However, in the bridge damage diagnosis field, the target data-sets collected from bridges frequently present samples of new damages that were not observed in the source domain, which is known as the open-set domain adaptation problem. To address this problem, this paper proposes a new open-set deep transfer learning algorithm based on joint weighted sub-domain adaptation. First, a joint weighting mechanism is proposed based on adversarial learning and fuzzy theory to represent the similarity of target-domain samples with source-domain classes, and explore the method of separating the known and unknown classes in the target domain to solve the negative transfer problem. Then, to capture the fine-grained transferable information, a sub-domain adaptation algorithm based on minimizing the multi-channel multi-kernel weighted local maximum mean discrepancy (MCMK-WLMMD) is proposed to align the corresponding sub-domains in the two domains. Finally, membership is introduced to build an unsupervised fuzzy clustering model with evaluation indicator to recognize multiple unknown damages. Extensive experiments on open-set transfer tasks between three bridges verify the effectiveness of the algorithm.

Residual-atrous attention network for lumbosacral plexus segmentation with MR image

Accurate segmentation of the lumbosacral plexus is a crucial step for diagnosis and analysis of nerve damage in clinical. Due to the extremely low contrast and complicated structure around the lumbosacral plexus, it has been remaining a challenging task to effectively segment the lumbosacral plexus from spinal MR images. Even though several deep learning methods for spine segmentation have been developed, most of them only pay attention to the segmentation of vertebral bodies and intervertebral discs rather than nerves. To solve these problems, in this paper, we propose a residual-atrous attention network (RA2-Net) for lumbosacral plexus segmentation with MR images. Specifically, the RA2-Net consists of three main parts, (1) the atrous encoder module is employed to learn multi-scale contextual features from MR images in the encoder, (2) the residual skip connection operation is used to integrate the features with high-resolution spatial details in the encoder and the high-level contextual features in the decoder, and (3) the scale attention block is proposed for fusing the multi-scale high-level features in the decoder. We perform our proposed RA2-Net for the lumbosacral plexus segmentation on the collected spinal MRI dataset with 10 patients (a total of 236 MRI scans). Extensive experiments demonstrate that our RA2-Net achieves better performance in lumbosacral plexus segmentation with MR images when compared with several state-of-the-art methods.