Wyniki wyszukiwania - Biblioteka Nauki

1

Bearing fault detection using a method involving absolute value spectrum and impulsivity evaluation

100%

Bouaouiche K. , Menasria Y. , Khalifa D.

Diagnostyka

|

2024

|

tom Vol. 25, No. 2

art. no. 2024213

EN

This study analyzes vibration signals related to bearing defects using a method that reconstructs an effective signal. This reconstruction is based on the determination of the instantaneous amplitude and phase. Then, a decomposition method is applied to the amplitude and phase to obtain several simple functions. Once the functions are obtained, an evaluation of impulsivity is performed on each function using the proposed parameter. This selects functions that contain fault data. The important signal is then identified and used. After the creation of the effective signal, filtering by a morphological operator with a structuring element is applied to improve the signal quality. Finally, in the spectrum of the absolute values of this signal, the defect can be detected from the frequency of the peaks. Signals from different databases were analyzed using the proposed method, illustrating the results in the form of high-amplitude peaks in the frequency of bearing component defects.

2

Defect detection in plate structures using wavelet transformation

100%

Knitter-Piątkowska A. , Guminiak M.

Engineering Transactions

|

2016

|

tom Vol. 64, iss. 2

139--156

EN

This paper is concerned with defect detection in plate structures while considering the influence of external loads. The examined structures are based on Kirchhoff plate structures. Rectangular plate structures are considered. Plate bending is described using the boundary element method. The boundary and boundary-domain integral equations are formulated in a modified, simplified approach without the need of using a value known from the classical theory of Kirchhoff plate bending. Constant-type boundary elements in a non-singular approach are introduced. The plates are loaded with a single static concentrated force or dynamic moving force. External loading is applied at selected points along the direction parallel to one dimension of the plate. Defects are introduced by additional edges forming slots or holes in relation to the basic plate domain. Deflections and curvatures are taken into account as structural responses. Analysis of structural responses is conducted using the signal processing tool of wavelet transformation in its discrete form.

3

Application of Two Advanced Vision Methods Based on Structural and Surface Analyses to Detect Defects in the Erichsen Cupping Test

100%

Jasiński C. , Świłło S. , Kocańda A.

Archives of Metallurgy and Materials

|

2019

|

tom Vol. 64, iss. 3

1041--1049

EN

Due to the wide range of various sheet metal grades and the need to verify the material properties, there are numerous methods to determine the material formability. One of them, that allows quick determination of sheet metal formability, is the Erichsen cupping test described in the ISO 20482: 2003 standard. In the presented work, the results of formability assessment for DC04 deepdrawing sheet metal were obtained by means of the traditionally carried out Erichsen cupping test and compared with the resultsobtained by using two advanced methods based on vision analysis. Application of these methods allows extending the traditional scope of analysis during Erichsen cupping test by determination of the necking and strain localization before fracture. The proposed methods were compared in order to dedicate appropriate solution for the industrial application and laboratory tests respectively, where the simplicity and reliability are the mean aspects need to be considered when applied to the Erichsen cupping test.

4

A New Approach to Experimental Testing of Sheet Metal Formability for Automotive Industry

100%

Jasiński C. , Kocańda A. , Morawiński Ł. , Świłło S.

|

tom Vol. 64, iss. 4

1231--1238

EN

Advanced vision method of analysis of the Erichsen cupping test based on laser speckle is presented in this work. This method proved to be useful for expanding the range of information on material formability for two commonly used grades of steel sheets: DC04 and DC01. The authors present a complex methodology and experimental procedure that allows not only to determine the standard Erichsen index but also to follow the material deformation stages immediately preceding the occurrence of the crack. Accurate determination of these characteristics in the sheet metal forming would be an important application, especially for automotive industry. However, the sheet metal forming is a very complex manufacturing process and its success depends on many factors. Therefore, attention is focused in this study on better understanding of the Erichsen index in combination with the material deformation history.

5

Application of discrete wavelet transformation to defect detection in truss structures with rigidly connected bars

100%

Knitter-Piątkowska A. , Guminiak M. , Przychodzki M.

Engineering Transactions

|

2016

|

tom Vol. 64, iss. 2

157--170

EN

The structures examined in this paper are bridge-type trusses that were previously used as railway viaduct support structures. The considered trusses are modelled as 2D and 3D structures. The lower chord bar of the considered structure can be loaded by external forces located outside the rigid nodes (the points where truss bars are connected). Hence, in the numerical experiment in terms of 2D approach, the truss structure consists of the set of two-node beam finite elements with three degrees of freedom per node and exact shape functions. According to 3D approach, the truss is described as the set of two-node beam elements with six degrees of freedom per node. Axial and twisting displacements of the element are described by linear shape functions and the bending is described by polynomials of the third order corresponding to Euler-Bernoulli beam fields of deformation. The defect (damage) in truss structure is modelled as the local stiffness reduction of one or two lower chord bars. The analysis of a structural response is carried out using the discrete wavelet transformation (DWT). The aim if this work is to detect the localization of damage provided that it exists in the considered structure and to examine whether the DWT will prove to be the effective tool to defect detection. It is expected that the disturbance of the response signal will appear in the vicinity of the point where the defect exists. The family of Daubechies 4 wavelet is implemented. Numerical investigation is executed based on signal analysis of structural static response. Some numerical examples are presented.

6

An approach for automated defect detection and neural classification of web textile fabric

88%

Stojanovic R. , Mitropulos P. , Koulamas C. , Karayiannis Y. , Koubias S. , Papadopoulos G.

Machine Graphics and Vision

|

2000

|

tom Vol. 9, No. 3

587-607

EN

This paper presents an automatic vision-based system for quality control of web textile fabrics. A general hardware and software platform developed to solve this problem is presented and a powerful algorithm for defect inspection is proposed. Based on the improved binary, textural and neural network algorithms, the proposed method gives good results in detection of many types of fabric defects under real industrial conditions, where presence of many types of noise is an inevitable phenomenon. A high detection rate with good localization accurancy, low rate of false alarms, compatibility with standard inspection tools and low price are the main advantages of proposed system, as well as of the overall inspection approach.

7

A New Approach to Experimental Testing of Sheet Metal Formability for Automotive Industry

88%

Jasiński C. , Kocańda A. , Morawiński Ł. , Świłło S. , Jasiński C. , Kocańda A. , Morawiński Ł. , Świłło S.

|

8

Application of Artificial Neural Networks for Defect Detection in Ceramic Materials

88%

Akinci T. C. , Nogay H. S. , Yilmaz O.

Archives of Acoustics

|

2012

|

tom Vol. 37, No. 3

279-286

EN

In this study, an artificial neural network application was performed to tell if 18 plates of the same material in different shapes and sizes were cracked or not. The cracks in the cracked plates were of different depth and sizes and were non-identical deformations. This ANN model was developed to detect whether the plates under test are cracked or not, when four plates have been selected randomly from among a total of 18 ones. The ANN model used in the study is a model uniquely tailored for this study, but it can be applied to all systems by changing the weight values and without changing the architecture of the model. The developed model was tested using experimental data conducted with 18 plates and the results obtained mainly correspond to this particular case. But the algorithm can be easily generalized for an arbitrary number of items.

9

Vision-based Online Defect Detection of Polymeric Film via Structural Quality Metrics

88%

Rawashdeh N. , Hazaveh P. , Altarazi S.

|

tom Vol. 14, No. 1

61--71

EN

Nondestructive and contactless online approaches for detecting defects in polymer films are of significant interest in manufacturing. This paper develops vision-based quality metrics for detecting the defects of width consistency, film edge straightness, and specks in a polymeric film production process. The three metrics are calculated from an online low-cost grayscale camera positioned over the moving film before the final collection roller and can be imple mented in real-time to monitor the film manufacturing for process and quality control. The objective metrics are calibrated to correlate with an expert ranking of test samples, and results show that they can be used to detect defects and measure the quality of polymer films with satisfactory accuracy.

10

Analysis of the possibility of using vibration parameters for diagnostics of selected defects in welded joints of the hull plating elements

75%

Muchowski T. , Szeleziński A. , Murawski L. , Muc A. , Kluczyk M.

Journal of KONBiN

|

2022

|

tom Vol. 52, iss. 3

165--174

EN

The article presents results of vibration tests of thin-walled plates used in shipbuilding for plating hulls of vessels. The conducted tests were aimed at determining the possibility of using measurements of vibration acceleration recorded on the tested objects as parameters enabling the detection of damages in the performed welded joints. Seven plates were compared, six of which had joints in different technical conditions, and one was a board without a weld. The quality of the welds was verified using X-ray methods. The adopted research methodology and the obtained results were presented.

PL

W artykule przedstawiono wyniki badań drganiowych płyt cienkościennych wykorzystywanych w okrętownictwie jako poszycie kadłubów jednostek pływających. Przeprowadzone badania miały na celu określenie możliwości stosowania pomiarów przyspieszeń drgań rejestrowanych na badanych obiektach jako parametrów umożliwiających wykrycie uszkodzeń w wykonanych połączeniach spawanych. Porównano siedem płyt, z czego sześć miało spoiny w różnym stanie technicznym, a jedna była bez spawu. Jakość spoin zweryfikowana została metodami RTG. Przedstawiono przyjętą metodykę badawczą oraz uzyskane wyniki.

11

Fabric Defect Detection Using a Hybrid and Complementary Fractal Feature Vector and FCM-based Novelty Detector

75%

Zhou J. , Wang J. , Bu H.

Fibres & Textiles in Eastern Europe

|

2017

|

tom Vol. 25, no. 6 (126)

46--52

EN

Automated detect detection in woven fabrics for quality control is still a challenging novelty detection problem. This work presents five novel fractal features based on the box-counting dimension to address the novelty detection of fabric defect. Making use of the formation of woven fabric, the fractal features are extracted in a one-dimension series obtained by projecting a fabric image along the warp and weft directions, where their complementarity in discriminating defects is taken into account. Furthermore a new novelty detector based on fuzzy c-means (FCM) is devised to deal with one-class classification of the features extracted. Finally, by jointly applying the features proposed and the FCM based novelty detector, we evaluate the method proposed for eight datasets with different defects and textures, where satisfying results are achieved with a low overall missing detection rate.

PL

Automatyczne wykrywanie defektów tkanin w celu kontroli ich jakości mimo wielu dotychczasowych badań nadal stanowi wyzwanie. Mając na celu opracowanie nowatorskiej metody wykrywaniem wad tkanin przedstawiono pięć cech fraktalnych. W celu klasyfikacji wyodrębnionych cech opracowano detektor wad tkanin oparty na zbiorze rozmytym wartości średnich (FCM). Poprzez wspólne zastosowanie proponowanych cech i opartego na FCM detektorze sprawdzono proponowaną metodę dla ośmiu zestawów danych z różnymi defektami i teksturami. Stwierdzono, że otrzymane wyniki są na satysfakcjonującym poziomie.

12

Wykrywanie defektów z wykorzystaniem termografii aktywnej i algorytmu k-średnich

75%

Dudzik S.

Pomiary Automatyka Robotyka

|

2019

|

tom R. 23, nr 3

11--15

PL

W pracy przedstawiono nową metodę wykrywania defektów materiałowych z wykorzystaniem termografii aktywnej. W celu zwiększenia kontrastu cieplnego dokonano przetwarzania wstępnego zarejestrowanej sekwencji termogramów metodami morfologii matematycznej. Do wykrywania defektów zastosowano algorytm k-średnich. W pracy zbadano wpływ miary odległości używanej w opisywanym algorytmie oraz doboru danych wejściowych na efektywność opisywanej metody. Eksperyment przeprowadzono dla próbki wykonanej z kompozytu zbrojonego włóknem węglowym (CFRP). W badaniach stwierdzono, że najmniejsze błędy wykrywania defektów za pomocą opisywanej metody uzyskuje się dla kwadratowej odległości euklidesowej.

EN

The paper presents a new method of detecting material defects using active thermography. In order to increase the thermal contrast, preprocessing of the recorded sequence of thermograms was carried out using mathematical morphology methods. The k-means algorithm was used to detect defects. The work examined the impact of distance measure used in the described algorithm and the selection of input data on the effectiveness of the described method. The experiment was carried out for a sample made of carbon fiber reinforced composite (CFRP). Studies have shown that the smallest errors in defect detection using the described method are obtained for the square Euclidean distance.

13

Fabric Defect Detection and Classifier via Multi-Scale Dictionary Learning and an Adaptive Differential Evolution Optimized Regularization Extreme Learning Machine

75%

Zhou Z. , Wang C. , Gao X. , Zhu Z. , Hu X. , Zheng X. , Jiang L.

Fibres & Textiles in Eastern Europe

|

2019

|

tom Vol. 27, no. 1 (133)

67--77

EN

To develop an automatic detection and classifier model for fabric defects, a novel detection and classifier technique based on multi-scale dictionary learning and the adaptive differential evolution algorithm optimised regularisation extreme learning machine (ADE-RELM) is proposed. Firstly in order to speed up dictionary updating under the condition of guaranteeing dictionary sparseness, k-means singular value decomposition (KSVD) dictionary learning is used. Then multi-scale KSVD dictionary learning is presented to extract texture features of textile images more accurately. Finally a unique ADE-RELM is designed to build a defect classifier model. In the training ADE-RELM classifier stage, a self-adaptive mutation operator is used to solve the parameter setting problem of the original differential evolution algorithm, then the adaptive differential evolution algorithm is utilised to calculate the optimal input weights and hidden bias of RELM. The method proposed is committed to detecting common defects like broken warp, broken weft, oil, and the declining warp of grey-level and pure colour fabrics. Experimental results show that compared with the traditional Gabor filter method, morphological operation and local binary pattern, the method proposed in this paper can locate defects precisely and achieve high detection efficiency.

PL

W celu opracowania automatycznego modelu wykrywania i klasyfikowania defektów tkanin, zaproponowano nowatorską technikę wykrywania i klasyfikowania opartą na zastosowaniu maszyny uczącej się (ADE-RELM). Proponowana metoda ma na celu wykrywanie powszechnych defektów, takich jak przerwana osnowa i wątek oraz zabrudzenia po oleju. Wyniki eksperymentalne pokazują, że w porównaniu z tradycyjną metodą filtrów Gabora, operacją morfologiczną i lokalnym wzorcem binarnym, proponowana w artykule metoda pozwala na precyzyjne zlokalizowanie defektów i osiąga wysoką skuteczność ich wykrywania.

14

The method of detecting inhomogeneities and defects in materials using sensors based on the fiber Bragg optic structures

75%

Zychowicz Ł.

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2019

|

tom T. 9, nr 3

62--65

EN

The article presents the possibilities of detecting defect in materials using the fiber Bragg gratings (FBG). Steel belts with a thickness of 1 mm were used for the tests: one standard and the others were damaged. The damage was in the form of incisions. The FBG was glued to the sample with epoxy glue along its entire length and elongation by outside force. Based on the transmission spectrum obtained on the Optical Spectrum Analyzer (OSA) the processing characteristics: the main minimum on the transmission characteristics, total width of the spectrum and the full width at half maximum FWHM depending on the FBG strain was determine.

PL

W artykule przedstawiono możliwości wykrywania defektu w materiałach przy użyciu światłowodowych siatek Bragga (FBG). Do testów użyto kilka stalowych pasków: jeden wzorcowy, pozostałe uszkodzone w różny sposób. Uszkodzenia miały postać nacięć. FBG przyklejono do próbki klejem epoksydowym na całej długości i wydłużano. Widmo transmisji uzyskane na analizatorze widma wykorzystano do określenia charakterystyk przetwarzania: główne minimum charakterystyki transmisji całkowita szerokość widma i szerokość połówkowa FWHM w zależności od odkształcenia siatki.

15

Detekcja defektów cienkich struktur elektroprzewodzących z wykorzystaniem termografii

75%

Korzeniewska E. , Murawski P. , Krawczyk A. , Pawlak R.

Przegląd Elektrotechniczny

|

2016

|

tom R. 92, nr 1

93--95

PL

W artykule zaprezentowano metodę wykrywania defektów warstw cienkich elektroprzewodzących powstałych w procesie ich wytwarzania lub użytkowania za pośrednictwem analizy zdjęć termograficznych. Warstwy te zostały wytworzone na elastycznym podłożu kompozytowym z wykorzystaniem technologii osadzania próżniowego PVD. W wyniku przepływu prądu elektrycznego przez próbki, dochodzi do ich nierównomiernego nagrzewania, a to stanowi podstawę do detekcji niejednorodności struktur w analizie termograficznej.

EN

The paper presents a method for detecting defects of thin electroconductive layers formed during their manufacturing or using via thermographic images analysis. These layers are formed on a flexible composite substrate with using vacuum deposition PVD technology. As a result of the electric current flow through the samples it comes to the uneven heating, and this is the basis for detection of inhomogenity in structures via thermographic analysis.

16

A nested autoencoder approach to automated defect inspection on textured surfaces

63%

Oz M. A. N. , Kaymakci O. T. , Mercimek M.

International Journal of Applied Mathematics and Computer Science

|

2021

|

tom Vol. 31, no. 3

515--523

EN

In recent years, there has been a highly competitive pressure on industrial production. To keep ahead of the competition, emerging technologies must be developed and incorporated. Automated visual inspection systems, which improve the overall mass production quantity and quality in lines, are crucial. The modifications of the inspection system involve excessive time and money costs. Therefore, these systems should be flexible in terms of fulfilling the changing requirements of high capacity production support. A coherent defect detection model as a primary application to be used in a real-time intelligent visual surface inspection system is proposed in this paper. The method utilizes a new approach consisting of nested autoencoders trained with defect-free and defect injected samples to detect defects. Making use of two nested autoencoders, the proposed approach shows great performance in eliminating defects. The first autoencoder is used essentially for feature extraction and reconstructing the image from these features. The second one is employed to identify and fix defects in the feature code. Defects are detected by thresholding the difference between decoded feature code outputs of the first and the second autoencoder. The proposed model has a 96% detection rate and a relatively good segmentation performance while being able to inspect fabrics driven at high speeds.

17

Image analysis for apple defect detection

63%

Puchalski C. , Gorzelany J. , Zagula G. , Brusewitz G.

Teka Komisji Motoryzacji i Energetyki Rolnictwa

|

2008

|

tom 08

18

A Method for Defect Detection of Yarn-Dyed Fabric Based on Frequency Domain Filtering and Similarity Measurement

63%

Zhang B. , Tang C.

Autex Research Journal

|

2019

|

tom Vol. 19, no. 3

257--262

EN

The detection of defects in yarn-dyed fabric is one of the most difficult problems among the present fabric defect detection methods. The difficulty lies in how to properly separate patterns, textures, and defects in the yarn-dyed fabric. In this paper, a novel automatic detection algorithm is presented based on frequency domain filtering and similarity measurement. First, the separation of the pattern and yarn texture structure of the fabric is achieved by frequency domain filtering technology. Subsequently, segmentation of the periodic units of the pattern is achieved by using distance matching function to measure the fabric pattern. Finally, based on the similarity measurement technology, the pattern’s periodic unit is classified, and thus, automatic detection of the defects in the yarn-dyed fabric is accomplished.

19

Defect Detection of Printed Fabric Based on RGBAAM and Image Pyramid

63%

Jing J. , Ren H.

Autex Research Journal

|

2021

|

tom Vol. 21, no. 2

135--141

EN

To solve the problem of defect detection in printed fabrics caused by abundant colors and varied patterns, a defect detection method based on RGB accumulative average method (RGBAAM) and image pyramid matching is proposed. First, the minimum period of the printed fabric is calculated by the RGBAAM. Second, a Gaussian pyramid is constructed for the template image and the detected image by using the minimum period as a template. Third, the similarity measurement method is used to match the template image and the detected image. Finally, the position of the printed fabric defect is marked in the image to be detected by using the Laplacian pyramid restoration. The experimental results show that the method can accurately segment the printed fabric periodic unit and locate the defect position. The calculation cost is low for the method proposed in this article.

20

Diagnostic methods of detecting defects within the material with the use of active infrared thermovision

63%

Grochalski K. , Peta K.

Archives of Mechanical Technology and Materials

|

2017

|

tom Vol. 37

41--44

EN

Article presents the methods of detecting defects within material with the use of active infrared thermovision. During the study ABS and PVC samples were used inside which internal structure defects and defects of glue conjunction between components were modeled. During combining composite materials with the use of glue joints, there is a problem with homogenous distribution of the glue layer on the surface of an element, which results in the creation of defects in joint structure and the decline of active surface of adhesion forces on the combined materials. It is then necessary to control the quality of the conjunction between the glued surfaces. The use of non-contact diagnostic methods allows to analyze a larger surface which conditions in more efficient quality control process. In the study, external heat excitation was used - optical excitation with periodic variable signal (LockIn method) and unit step excitation (Pulse method). The methods of analysis of the obtained thermograms are presented.