Dissertations / Theses on the topic 'Detecting defects'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Detecting defects.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Palmquist, Jonathan. "Detecting defects on cheese using hyperspectral image analysis." Thesis, Umeå universitet, Institutionen för fysik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-172695.
Full textBaghalian, Amin. "Detecting Structural Defects Using Novel Smart Sensory and Sensor-less Approaches." FIU Digital Commons, 2017. https://digitalcommons.fiu.edu/etd/3560.
Full textStorozhenko, V. A., A. V. Myagkiy, and R. P. Orel. "Filtering of interference of inhomogeneous regular structure in thermal non-destructive control of cellular structures." Thesis, Eskisehir technical university, 2021. https://openarchive.nure.ua/handle/document/18954.
Full textRainer, Alexander. "Detecting critical defects : towards standards for conducting NDE on cast iron trunk mains." Thesis, University of Surrey, 2017. http://epubs.surrey.ac.uk/844891/.
Full textPoudel, Anish. "AN INTELLIGENT SYSTEMS APPROACH FOR DETECTING DEFECTS IN AIRCRAFT COMPOSITES BY USING AIR-COUPLED ULTRASONIC TESTING." OpenSIUC, 2011. https://opensiuc.lib.siu.edu/theses/594.
Full textHassan, Syed Karimuddin and Syed Muhammad. "Defect Detection in SRS using Requirement Defect Taxonomy." Thesis, Blekinge Tekniska Högskola, Sektionen för datavetenskap och kommunikation, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-5253.
Full textskarimuddin@yahoo.com, hassanshah357@gmail.com
Klíma, Jakub. "Automatické vyhodnocování termovizních snímků fotovoltaických panelů." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2016. http://www.nusl.cz/ntk/nusl-242855.
Full textRogers, Stuart Craig. "Defect Detection Microscopy." BYU ScholarsArchive, 2010. https://scholarsarchive.byu.edu/etd/2256.
Full textNgan, Yuk-tung Henry, and 顏旭東. "Patterned Jacquard fabric defect detection." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2004. http://hub.hku.hk/bib/B30070880.
Full textAuger, Marc. "Detection of laser-welding defects using neural networks." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2002. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp05/MQ65599.pdf.
Full textKehoe, A. "Detection and evaluation of defects in industrial images." Thesis, University of Surrey, 1990. http://epubs.surrey.ac.uk/804357/.
Full textJandová, Kristýna. "Diagnostické metody plošného rozložení defektů solárních článků." Doctoral thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2009. http://www.nusl.cz/ntk/nusl-233487.
Full textHunt, Kevin. "Modelling the origin of defects in injection moulded ceramics." Thesis, Brunel University, 1990. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.280892.
Full textPriyosulistyo, Henricus. "Detection of defects in concrete structures using vibration technique." Thesis, University of Strathclyde, 1992. http://oleg.lib.strath.ac.uk:80/R/?func=dbin-jump-full&object_id=21555.
Full textNg, Nga-yi Ada. "Defect detection in semiconductor die images." Click to view the E-thesis via HKUTO, 2005. http://sunzi.lib.hku.hk/hkuto/record/B32040799.
Full textNg, Nga-yi Ada, and 伍雅怡. "Defect detection in semiconductor die images." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 2005. http://hub.hku.hk/bib/B32040799.
Full textXie, Xianghua. "Defect detection in random colour textures." Thesis, University of Bristol, 2006. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.425096.
Full textPathak, Ajay Kumar. "Automated defect detection in textured materials." Thesis, Hong Kong : University of Hong Kong, 2001. http://sunzi.lib.hku.hk/hkuto/record.jsp?B23295168.
Full textGrönlund, Jakob, and Angelina Johansson. "Defect Detection and OCR on Steel." Thesis, Linköpings universitet, Datorseende, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-157508.
Full textSong, Keng Yew. "Surface defect detection on textured background." Thesis, University of Surrey, 1993. http://epubs.surrey.ac.uk/844113/.
Full textFoster, Moira. "Defect Detection in Selective Laser Melting." DigitalCommons@CalPoly, 2018. https://digitalcommons.calpoly.edu/theses/1874.
Full textFox, Matthew William. "Thermography approaches for building defect detection." Thesis, University of Plymouth, 2016. http://hdl.handle.net/10026.1/4304.
Full textHu, Yazhe. "Degenerate Near-planar Road Surface 3D Reconstruction and Automatic Defects Detection." Diss., Virginia Tech, 2020. http://hdl.handle.net/10919/98671.
Full textDoctor of Philosophy
Road is one of the key infrastructures for ground transportation. A good road surface condition can benefit mainly on three aspects: 1. Avoiding the potential traffic accident caused by road surface defects, such as potholes. 2. Reducing the damage to the vehicle initiated by the bad road surface condition. 3. Improving the driving and riding comfort on a healthy road surface. With all the benefits mentioned above, it is important to examine and check the road surface quality frequently and efficiently to make sure that the road surface is in a healthy condition. In order to detect any road surface defects on public road in time, this dissertation proposes three techniques to tackle the road surface defects detection problem: First, a near-planar road surface three-dimensional (3D) reconstruction technique is proposed. Unlike traditional 3D reconstruction technique, the proposed technique solves the degenerate issue for road surface 3D reconstruction from two images. The degenerate issue appears when the object reconstructed has near-planar surfaces. Second, after getting the accuracy-enhanced 3D road surface reconstruction, this dissertation proposes an automatic defects detection technique using both the 3D reconstructed road surface and the road surface image information. Although physics-based detection using 3D reconstruction and 2D images are reliable and explainable, it needs more time to process these data. To speed up the road surface defects detection task, the third contribution is a technique that proposes a self-supervised learning structure with data-driven Convolutional Neural Networks (CNN). Different from traditional neural network-based detection techniques, the proposed combines the 3D road information with the CNN output to jointly determine the road surface defects region. All the proposed techniques are evaluated using both the simulation and real-world experiments. Results show the efficacy and efficiency of the proposed techniques in this dissertation.
Hegstam, Björn. "Defect detection and segmentation inmultivariate image streams." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-150456.
Full textOptoNova är en världsledande leverantör av inspektionssystem for kvali-tetskontroll av ytor och kanter i hög hastighet. Företaget utvecklar egnasensorsystem och mjukvara, och är intresserade av att undersöka möj-ligheten att bättre utnyttja tillgänglig sensordata genom att användametoder baserade på maskininlärning.Syftet med det här projektet var att utveckla en metod för att upp-täcka ytdefekter i multivariata bilder. Ett tidigare examensarbete gjorthos OptoNova visade på lovande resultat vid inspektion av kanter påköksluckor. Modellen som utvecklades i det projektet använde sig av ettDifference of Gaussians-skalrum. Den modellen användes som utgångs-punkt för det här arbetet med vissa förändringar gjorda för att läggafokus på texturdefekter i plana ytor.Den utvecklade modellen tar in en multivariat bild och genereraren Laplacepyramid. Varje nivå i pyramiden skickas sedan igenom entränad bildmodell som i sin tur producerar en gråskalebild där möjligadefekter är markerade. Samtliga bildmodellers resultat skalas upp tillsamma storlek som ursprungsbilden och en medelvärdesbild beräknas.Detta ger den slutliga defektbilden som visar vilka delar av det inlästaprovet som är defekta. Varje bildmodell består dels av en modul somextraherar särdragsvektorer och dels av en modul som modellerar hurvektorer från oskadade ytor är fördelade i rummet av särdragsvektorer.För det senare användes en Gaussian mixture model (GMM). Modellensmodullära design gör det enkelt att använda olika typer av särdragsvek-torer och modeller för dessa.Tester visade att pyramidmodellen kan prestera bättre än den tidi-gare utvecklade modellen. Utmärkta resultat uppnåddes vid detektionav defekter som karaktäriserades av tydliga avvikelser i textur. Defektersom däremot endast utgjordes av mindre variationer i intensitet hittadesgenerellt sett inte.Det konstaterades att den nya modellen visar på potential till attfungera väl, men att mer arbete fortfarande behöver göras. Framföralltmåste fler tester göras med fler prover, samt prover med varierandeytmönster, såsom träytor.
Renshaw, Jeremy Blake. "The mechanics of defect detection in vibrothermography." [Ames, Iowa : Iowa State University], 2009. http://gateway.proquest.com/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqdiss&rft_dat=xri:pqdiss:3389142.
Full textHEGSTAM, BJÖRN. "Defect detection and segmentation inmultivariate image streams." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-142069.
Full textOptoNova är en världsledande leverantör av inspektionssystem for kvalitetskontroll av ytor och kanter i hög hastighet. Företaget utvecklar egna sensorsystem och mjukvara, och är intresserade av att undersöka möjligheten att bättre utnyttja tillgänglig sensordata genom att använda metoder baserade på maskininlärning. Syftet med det här projektet var att utveckla en metod för att upptäcka ytdefekter i multivariata bilder. Ett tidigare examensarbete gjort hos OptoNova visade på lovande resultat vid inspektion av kanter på köksluckor. Modellen som utvecklades i det projektet använde sig av ett Difference of Gaussians-skalrum. Den modellen användes som utgångspunkt för det här arbetet med vissa förändringar gjorda för att lägga fokus på texturdefekter i plana ytor. Den utvecklade modellen tar in en multivariat bild och genererar en Laplacepyramid. Varje nivå i pyramiden skickas sedan igenom en tränad bildmodell som i sin tur producerar en gråskalebild där möjliga defekter är markerade. Samtliga bildmodellers resultat skalas upp till samma storlek som ursprungsbilden och en medelvärdesbild beräknas. Detta ger den slutliga defektbilden som visar vilka delar av det inlästa provet som är defekta. Varje bildmodell består dels av en modul som extraherar särdragsvektorer och dels av en modul som modellerar hur vektorer från oskadade ytor är fördelade i rummet av särdragsvektorer. För det senare användes en Gaussian mixture model (GMM). Modellens modullära design gör det enkelt att använda olika typer av särdragsvektorer och modeller för dessa. Tester visade att pyramidmodellen kan prestera bättre än den tidigare utvecklade modellen. Utmärkta resultat uppnåddes vid detektion av defekter som karaktäriserades av tydliga avvikelser i textur. Defekter som däremot endast utgjordes av mindre variationer i intensitet hittades generellt sett inte. Det konstaterades att den nya modellen visar på potential till att fungera väl, men att mer arbete fortfarande behöver göras. Framförallt måste fler tester göras med fler prover, samt prover med varierande ytmönster, såsom träytor.
Moshiri, Farzad, Bahareh Mobasher, and Issa Osama Talib. "Detection of defects in timber using dynamic excitation and vibration analysis." Thesis, Växjö University, School of Technology and Design, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:vxu:diva-5444.
Full textThis thesis evaluates the possibility to detect natural defects, such as knots, in timber boards using dynamic excitation test and ABAQUS software. In the study the edgewise bending direction were compared with axial direction. Dynamic excitation and modal analysis were used to extract the natural frequencies of several sound and artificially defected boards with the help of Signalcalc. Mobylizer software. By using the first edgewise natural frequency, modulus of elasticity (MOE) was calculated. An ABAQUS 2D Finite Element model was utilized to model the board and to extract the frequencies for the six first mode shapes in both axial and edgewise directions. The extracted frequencies from the model were compared with the frequencies from the tests. The analytical and experimental results, from the homogeneous boards, in edgewise direction has similar frequency variations. The defects in the timber boards decreased the natural frequencies. The bending modes with more curvature at the location of the artificial defect displayed more frequency deviation in that mode. The variation in response frequencies for uniform and defected boards was more noticeable in edgewise bending modes than in longitudinal modes.
Chaiworawitkul, Sakda 1977. "Detection of surface defects in infrastructure using wavelets and neural networks." Thesis, Massachusetts Institute of Technology, 2002. http://hdl.handle.net/1721.1/84310.
Full textIncludes bibliographical references (p. [225]-[228]).
by Sakda Chaiworawitkul.
M.Eng.
Wang, Xiaoting. "Transient thermography for detection of micro-defects in multilayer thin films." Thesis, Loughborough University, 2017. https://dspace.lboro.ac.uk/2134/25174.
Full textOaker, Bradley. "The detection of defects in tubes and plates using guided waves." Master's thesis, University of Cape Town, 2011. http://hdl.handle.net/11427/11182.
Full textCampbell, Craig Maurice. "Signature analysis techniques for needle bearing defect detection." Thesis, Georgia Institute of Technology, 1992. http://hdl.handle.net/1853/19539.
Full textNgan, Yuk-tung Henry. "Motif-based method for patterned texture defect detection." Click to view the E-thesis via HKUTO, 2008. http://sunzi.lib.hku.hk/hkuto/record/b40203608.
Full text"Detecting Dissimilar Classes of Source Code Defects." Thesis, 2013. http://hdl.handle.net/10388/ETD-2013-08-1188.
Full textYang, Ren-Kewi, and 楊仁魁. "An Inspection System for Detecting Defects on Chip." Thesis, 1995. http://ndltd.ncl.edu.tw/handle/79258641590958327275.
Full text國立交通大學
資訊科學學系
83
An image inspection system for detecting defects on chip is developed. The system can automatically inspect defects of chips on wafer after operator's alignment.The system consists of three parts: 1. image acquisition, 2. image preprocessing, 3. defect detection. A chip to be inspected has three parts which are bonding pad, active region, and edge region. In bonding pad, the defect is coating.In active region, the defects are abnormal spots and scratches. In edge region, the defects are scratch and crack. These three parts are inspected sequentially for their defects. Good chip must pass all inspections of these three parts. Otherwise, chip is classified into bad chip without the inspection of next part when one part is rejected. Experimental result shows that the recognition rate of good chip can reach 99.21% and the recognition rate of bad chip can reach 90.48%.For inspection time, the average time of inspecting one chip by the system is about 6327.5 ms.
Chu, Chien-Cheng, and 朱建政. "The Research on the BGA Surface Defects Detecting System." Thesis, 2003. http://ndltd.ncl.edu.tw/handle/27776357187759659286.
Full text元智大學
工業工程與管理學系
91
In the current manufacturing environment, a company still needs to have a faster and a more accurate ways to inspect a Ball Grid Array (BGA) surface defects. Traditionally, the BGA inspection was using gray-level images. However, the background, conduct paths and pads have very similar gray-levels that cannot easy be distinguished. The objectives of the research are: (1) Use some shape and uniformity features without making pattern matching for detecting BGA surface defects. (2) Use color image information instead of gray scales for the inspection. (3) Improve the speed and effectiveness of the inspection system. The traditional process of the image enhancement is to select a suitable color mode and then to proceed on the enhancement. The research proposed a method that to use the gamma correction method to replace the tradition process for image enhancement with the expectations of having better results and faster speeds. Because gamma correction corrects the three color bands (i.e., RGB), it could better separate the image between the high and low contrasts. And it could get the better results in dividing the image into background and foreground by using the Gamma correction and the R color band. As a result, the proposed method can improve the contrast value about 52.09%. Finally, the research uses the eigenvalues of the shape and uniformity to detect the defects. It could find almost all the defects. In using the traditionally enhancement method with a 640* 480 pixels image to do a completely defects detecting needs 1 sec. However, to use the proposed gamma correction method to do the same, needs only 0.3 sec. This research demonstrates the effectiveness of using gamma correction method for separating an image background from its foreground. And the developed method could detect the BGA surface defects without using pattern matching technique that required extensive alignment in both hardware and software.
Chin, Kuo-ming, and 秦國銘. "An Auto-detecting System for Surface Defects on Connectors." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/15136333166234472158.
Full text朝陽科技大學
資訊工程系碩士班
96
Exploiting computer vision techniques, an auto-detecting system is developed for surface defects on connectors. The system hardware consists of a CCD (charge-coupled device) camera, a loop-shaped light-source, and an image capture board. Since the surface of connectors is made of stainless steel with high reflectance, it is difficult to locate the defects specifically. This problem is usually solved by applying extra light on the dark area. However, the reflection of the extra light might induce some detection errors. We classify the surface regions as some regions of interest (ROI) and ones that are not of interest (non-ROI) so as to accomplish real-time on-line diagnosis by image positioning and template recognition. Applied image processing techniques include edge detection, image segmentation, binary images, and template recognition. According to the examination results, the system effectively detects the surface defects. The Examination time is 32ms per sample.
White, Joshua. "Ultrasonic Tomography for Detecting and Locating Defects in Concrete Structures." Thesis, 2012. http://hdl.handle.net/1969.1/ETD-TAMU-2012-05-11097.
Full textLai, Winky Wan Kei. "Meniscus thermal analysis for detecting defects in continuous cast slabs." Thesis, 2000. http://hdl.handle.net/2429/10447.
Full textChen, Yu-Ting, and 陳郁婷. "Detecting genomic aberrations in patients with developmental delays and congenital defects." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/47667337926971113623.
Full text國立陽明大學
生命科學暨基因體科學研究所
95
Mental retardation/developmental delays and congenital defects are common pediatric problems. However, the etiology and pathogenesis of mental retardation and developmental delays are poorly understood, and in about half of cases the causes remain unknown. Submicroscopic chromosomal rearrangements (smaller than 2-3 Mb) are assumed as one of the most important causes of mental retardation and developmental delays, owing to that can results in segmental aneusomy, alter the gene dosage and destroy the gene functions. Therefore, detecting these chromosomal aberrations and interpreting them is an important work which facilitates identification of the etiology and the genotype-phenotype correlation. In addition, effective pre-selection is also essential because of the technical diversities and cost of screening genomic aberrations. Based on the reasons mentioned above, we propose to find out the causes of these patients’ phenotypes and investigate the genotype-phenotype correlations. Moreover, in most of affecting individuals extensive examines are usually called for to find out the cause of their conditions, therefore we also aim to establish a pre-selection system which could help to sort out proper patients for different examinations and so that improve the detecting efficiency. In this study, we used CGH to screening the genomic aberrations in 98 patients with unexplained mental retardation/developmental delays or congenital defects collected from Taipei Veteran General Hospital, and quantitative real-time PCR was performed to detect subtelomeric rearrangements. Combined with CGH and Q-PCR results, we identified the causative chromosomal anomalies in four patients, including one patient as 1p36 deletion syndrome, two patients as 1qter deletion syndrome, and one patient with unbalanced 16pter and 20q13.2-13.3 translocation. All of these chromosomal rearrangements were further mapping for the breakpoints to define the aberrant size. In case 1 of the 1p36 deletion syndrome, the breakpoint was located in chromosome band 1p36.31, with a deletion of ~5.4 Mb in size. For both case 2 and case 3 of the 1qter deletion syndromes, the breakpoints were located in chromosome band 1p43, with a deletion of ~8.4 Mb and ~9.6 Mb in size, respectively. The case 4 was identified as unbalanced translocation with chromosome 16pter deletion of at least 430 Kb in size and chromosome 20q13.2q13.3 duplication of at least 6.6 Mb in size. Our study supported that chromosomal rearrangements are the major causes of patients with mental retardation/developmental delays or multiple congenital anomalies, and also demonstrated the utilities of CGH in clinical cytogenetics. However, due to the limitation of CGH in detecting submicroscopic chromosomal rearrangements, there are still many patients whose causes of conditions are not yet identified. This accentuates again the importance and necessity to develop a high-resolution but low-cost technique which is suitable for applying in clinical screening.
Kou, Chan-Phon, and 郭建峰. "Detecting and Classifying Defects for aluminum foil by Image Processing Techniques." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/92923944745897138222.
Full text國立臺灣科技大學
管理研究所工業管理學程
87
As the competition in the market getting intense,the guality and the price of the product play a critical role in the competitiveness of the product. Companies are therefore focusing their improvement on raising the quality of product and reducing the cost of production. A typical way to achieve both goals is to employ automation technology. One of the indispensible elements in the automatic production line is the automatic inspection capability. This research establishes an image-based inspection system that can be incorporated into automatic production line for detecting and classifying defects of 2D objects. With the low cost of the system and the tremendous saving on the labor,the system provides a feasible solution to improve the quality of the product. Such a system has to be able to capture the appearance of the 2D objects and convert the information into an image file for analysis. With the file,the image is preprocessed,and the features are then extracted and classified. These functions need to be designed with respect to specific domains in which the applications reside. This research considers the inspection of aluminum foil to demonstrate the feasibility and to fine-tune the implemented automatic inspection system.
Chia-HaoHsu and 許家豪. "The Study of Detecting the Internal Defects of Wall Tile and Wooden Member of Buildings." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/80926486397068616377.
Full text國立成功大學
土木工程學系碩博士班
98
Taiwan is located at subtropical area, with high temperature and humidity. Under the construction quality, using of materials and irresistible disasters and so on, lots of factors will cause some defects such as the internal damage, the deterioration of buildings and cracks in the surface even make the exterior brick falling, and then making the influences of durability and the appearance of the buildings even endangered the public safety. However, if we want to knockout and rebuilding, it is not only high costs but also cause the safety of buildings. One of the most important is how to acquire the destruction degree and the distribution of the defects for the building to beneficial the follow-up rehabilitation. This study is aimed to the phenomena of the exterior wall tile hollowed and the internal hole of wooden member of buildings via the non-destructive testing. Discussing the applicability and feasibility of differ defects tests. The results are as follows, 1. Comparing by the frequency value of hammer tapping, the velocity value of ultrasonic and the temperature difference value after heating, the related trends of more severe hollowing of the tile, it is correspond to the higher frequency value, higher ultrasonic velocity value, and the higher temperature difference value, and this can assess the extent of tile hollowing. 2. The relationship with the tile of hollowing rate at on-site inspection area and different methods is : hammer tapping, the hollowing rate (y) and the frequency value (x), the linear relationship y = 0.0163x + 7.6165 (R2 = 0.78); ultrasonic detection, the hollowing rate (y) and ultrasonic velocityvalue (x), the linear relationship y = 0.0693x - 144.52 (R2 = 0.86); infrared(IR) thermography, the hollowing rate (y) and maximum temperature difference value (x), the linear relationship y = 39.688x - 551.43 (R2 = 0.90). 3. To compare the results of testing by using infrared thermography technique, ultrasonic detection and hammer tapping to detect the hollowing location and extent of wall tiles, the results are consistent, but the ultrasonic detection and hammer tapping have a higher estimate of the situation hollowing. 4. This study uses ultrasonic technology to detect internal defects of wood member, used in accordance with this research method, it can detect the internal hole of wood member over 3.5 cm diameter.
Neves, Lara Souto das. "Automatic defect detection in wind turbine blades: A Deep Learning Model Pipeline for Detection and Classification of Defects in Drone Images." Master's thesis, 2022. http://hdl.handle.net/10362/134713.
Full textThe decarbonisation of the energy industry is key in the global approach to the climate emergency. Wind energy in particular, plays an important role in transitioning the global energy system to more sustainable sources. To do so, it must optimise O&M costs through a data-driven, predictive maintenance approach. When it comes to the maintenance of a wind turbine, the manual inspection of blade photographs - often taken by drones - is a time-consuming and labour intensive process, yet it is fundamental to ensure the turbine’s continued energy production during its lifecycle. This thesis intends to purpose, test, and implement a defect detection pipeline based on the Faster-RCNN deep learning architecture, capable of detecting 6 distinct classes of blade defects to a level of accuracy suitable enough to deploy in A.I.-assisted inspections.
Tendo em vista a emergência climática, é fundamental a descarbonização do sector energético a nível global. A energia eólica, em particular, tem um papel importante na transição do sistema energético atual para fontes de energia inteiramente limpas e sustentáveis. Para tal, é necessário otimizar os custos de operação e manutenção de turbinas eólicas através de uma abordagem preditiva baseada em dados recolhidos regularmente por meio de fontes automáticas, das quais drones estão em primeiro plano. No que toca à manutenção de turbinas eólicas, a inspeção manual de fotografias de pás é um processo muito demorado e de mão-de-obra intensiva sendo, no entanto, fundamental para a continuação de produção de energia ao longo da vida útil da turbina. O objetivo desta tese é propor, testar e implementar uma pipeline de deteção automática de defeitos baseada na arquitetura de modelo de aprendizagem profunda Faster-RCNN. Este modelo de inteligência artificial é capaz de detetar 6 classes distintas de defeitos na pá, a um nível de precisão adequado para auxiliar nas inspeções, reduzindo o tempo de inspeção, a possibilidade de erros de deteção e os custos de mão-de-obra.
WANG, FU-CHING, and 王富慶. "Tire Bubble Defects Detection Using ResNet." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/ph97y5.
Full text國立雲林科技大學
資訊工程系
107
Digital shearography used to detect tire bubble defects that are unobservable by the naked-eye. The tire manufacturer obtains the tire image through digital shearography, and then judges the bubble defect through the experience operate. The determination of the bubble defects depends not only on the experience and observation of the personnel, but also because there is no uniform judgment standard due to different personnel. This thesis proposes a residual network to detect bubble defects. In the training phase, the whole tire image is divided into several blocks. Use the data augmentation method to increase the training sample, and then input into the network for training;In the test phase, the tire image is pre-processed to select suspected bubble defect areas, and then these suspicious areas are input into the network model for bubble defect classification. The final output is in two categories: bubble-defect and non-defect. In the experimental results, the bubble defect detection rate is about 95%, and the non-defect classification accuracy rate is about 85%. For this method which can help tire manufacturers to further achieve automated inspection and save labor costs.
Tuan, Tran Ngoc, and 陳玉俊. "Detection Defects of Bearing by Acoustic Approach." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/85938866248849630879.
Full text明新科技大學
精密機電產業研發碩士外國學生專班
98
ABSTRACT This technical report provides a method, based on classification techniques, for automatic detection defects of rolling element bearings. We used sound pressure measurement by an 824 sound level meter and a real-time analyzer, which is a production of LARSON DAVIS firm. By measuring sound pressure emission from rolling elements bearings on a model with a fixed motor speed for all bearings, one can collect the signatures of the measured signal. We separate the bearings into two groups, which are a good bearing set and a bad bearing set, where the bad bearings are made artificially damage. Through applying a scattering matrix theory find a set of feature, which can distinguish quality of bearings. We further collect the selected features from the table to train a neural network with target output of a good bearing or a bad bearing. After training, the neural network can detect bearing quality accurately.
Y, Lee C., and 李傳玉. "Machine Vision Detection of Monitor Screen Defects." Thesis, 1998. http://ndltd.ncl.edu.tw/handle/13633457480277964566.
Full textWang, Hsuan-Yin, and 王炫尹. "PCB Defects Detection Based on Deep Learning." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/u379ep.
Full text國立暨南國際大學
資訊工程學系
107
The annual output value of printed circuit board (PCB) related industry is more than 21 billion US dollars which implies that the quantity of the produced PCBs per year is extremely large. However, the yield rate of PCBs is limited and if defective PCBs cannot be detected and discarded in the early stage of producing an electronic system, then they will lead to large amount of profit loss. Nowadays, many high speed automatic optical inspection systems can be used to classify defective PCBs. However, a closer inspection of the discarded PCBs will reveal that almost 70\% of them are actually misclassified. In this work, we develop an accurate PCB defect re-identification system based on deep learning techniques. We tested the performance of ResNet (Residual Network), DenseNet (Densely Connected Convolutional Network), GoogLeNet (Google Inception Net), and EFMNet (Extremal Feature Map Network) developed by us. A 98\% PCB defect re-identification accuracy is achieved. The developed system can dramatically reduce the false-defect rate.
Tu, Wei-Shan, and 杜瑋珊. "Resonance frequency assessment ofdental implant detecting defect." Thesis, 2009. http://ndltd.ncl.edu.tw/handle/39086715308231031334.
Full text國立中央大學
機械工程研究所
97
The dental implant is generally used in patients who are edentulous and missing natural tooth. This study is based on the resonant frequency response to specify criteria for examining the defect direction and defect severity in the bone of dental implant. Both the finite element analysis and the experimental modal analysis are applied to compare the differences between experiment and simulation. In the first stage, resonance frequency analysis (RFA) was applied to estimate stability of bone-implant structure in full size. The variation of RF was used to locate the direction of bone that was non-ossestintegration. The resonance frequency (RF) increased substantially as better stability of bone-implant structure was achieved. In the second stage, The boundary condition was varied to simulate different mandible. The RF with different boundary was used to decide defect type. Then, we collated those data and defined a criterion to detect the defect bone depth with dental implant. The three detection steps include that using the severe RF to decide the mandible type, locating the direction of defect bone, and deciding the defect type. In the end, we prove that RFA was effective method for examining the defect direction and defect severity in the bone of dental implant.
Chen, Yu-Ping, and 陳育屏. "Video Defect Detection and Inpainting." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/86206764654466115122.
Full text淡江大學
資訊工程學系碩士班
93
Video inpainting uses spatial-temporal information to repair defects such as spikes and lines on aged films. We propose a series of new algorithms based on adjustable thresholds to repair different varieties of aged films. The main contribution is an automatic spike and dirt detection mechanism. We prove that if appropriate threshold is once decided by the author, almost all damages in an aged video clip can be detected. In addition, the repairing procedure first estimates temporal information and obtain replacement blocks among several frames. Spatial information is then used to repair damages that can not be fixed by temporal information due to fast motion. The results are visually pleasant with most defects removed.
Hsieh, Wenlung, and 謝汶龍. "Solder Ball Defect Detection Algorithm." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/10016529977572684747.
Full text國立聯合大學
光機電整合產業專班
101
In the paper, an automatic detection algorithm is proposed to detect the defects of solder ball in ball grid array (BGA). The defects include polluted solder ball and lack of boundary smoothness in the solder ball. The algorithm applies the color characteristics of pollutants to segment them, computes pollutants’ areas, and judges the results by criteria. Moreover, after finding the solder ball boundary by applying the techniques of color characteristics, morphology, and boundary enhancement, the algorithm adopts fractal dimension to measure the complexity of the segmented boundary and judges the result by criteria. The simulation result shows the ratios of correct defect decision are more than 90%.
Hau, Huang Shr, and 黃士豪. "Detection of Lens Defects Using LED Lighting Systems." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/2c4f5n.
Full text國立高雄應用科技大學
光電與通訊工程研究所
102
This paper aims to do a series of exploration on the flawed lenses according to the different wavelength’s LED(Light-Emitting-Diode), and finds out the best way for detecting the flawed lenses. This paper combines the optical simulation software TracePro and the graphic software SolidWorksfordesigning the solid model in accordance with defect lenses. This paper adopts one kind of double gauss lens group which is most often used on photos taking and the camera lens, this sort of the lens design can raise the effect of focusing, eliminate the chromatism, and design the detection system of defect in lenses that is invisible easily by human eyes through controlling the LED’s wavelength and the focal distance, then bring up one kind of the way for doing lenses defect detection that used on LED lighting system. This way of detection uses the principle that the difference of refraction coefficient between the material and the medium, and the other principle that LED’s beam of light gets into the material interface and causes partial lights refracting back and forming light’s loss, and the dark point on the formation of image, to detect the defect on the lenses. The finding reveals that the effect of lenses defect detection on monochromatic light is better than the polychromatic light, in the monochromatic light, the red-ray LED’s contrast is higher than the other monochromatic light, and it can find out the lenses defect’ location and size, and also can recognize whether the tiny object on the lenses is thedefect bubble or not, or just the dust, fingerprint, and the spot. The contribution in this paper is: the technique for current lenses defect detection all uses the direct detection in appearance, as a result of the detective model’s quantity is large, variety is much, the precision is high, and by using this method not only consumes much time, the efficiency is low, the prime cost is high, and the mis-detected rate for using human eyes to do the detection is high, but for using the LED illumination system that we designed as the lenses defect detection instrument can be effective and find out every location’s defect promptly, and this detective system has some advantages such as low prime cost, easily being gotten, the manipulation is easy and shooting lenses’ defect is rapid.