Assessing the impact of active guidance for defect detection: a replicated experiment

The silicon panel is the core component of photovoltaic power generation, whose surface quality is related to its service life and power generation efficiency. However, microcracks, fragments, incomplete welding, broken grids, and other defects often occur in industrial production. The edge detection algorithm is usually used to detect defects in silicon panels, but the common edge detection algorithm has an impact on defect detection because of the grid shadow of the panel. The current mainstream defect detection algorithm based on convolutional neural network requires a large number of positive and negative samples of image data sets for pretraining the model, which consumes a lot of time and GPU computing power, and the steps are cumbersome. To solve the problem, a defect detection method based on Prewitt and Canny operators is proposed in this article. In this method, Prewitt and Canny operators are combined to eliminate the effect of grids on the detection. The microcrack defects and their specific positions can be detected efficiently and intuitively, therefore improving the detection accuracy. The experimental results indicate that the purity and integrity of the defect profile of the image processed by the algorithm are greatly improved. The foreground edge is clear, and the defect recognition accuracy is higher, which effectively prevent the impact of grid shadow on weld testing.

Download Full-text

Grouting Defect Detection of Lapped Bar Connections Based on Impact-Echo Method

Shock and Vibration ◽

10.1155/2019/1934240 ◽

2019 ◽

Vol 2019 ◽

pp. 1-14

Author(s):

Yun-Lin Liu ◽

Jing-Jing Shi ◽

Jun-Qi Huang ◽

Guang-Shuo Wei ◽

Zhi-Xin Wu

Keyword(s):

Frequency Response ◽

Defect Detection ◽

Precast Concrete ◽

Amplitude Spectrum ◽

Fe Model ◽

Impact Echo ◽

Lap Splice ◽

Good Potential ◽

The Impact ◽

Impact Echo Method

Grouted lap-splice connections are widely used for connecting precast concrete components. Grouting defects in the connections significantly influence the structural performance of the whole connection, which leads to the need for grouting defect detection. In this study, the impact-echo (IE) method was used for detecting defects in grouted lap-splice connections. Grouted connections with different levels of artificial grout defects were prepared in a shear wall, and the IE method was used to measure the frequency response. In addition, finite element (FE) analysis based on ABAQUS was conducted to simulate the tests. Based on the validated FE model, a parametric study was conducted to investigate the effect of the depth of the grout hole on the amplitude spectrum. The results indicated that (1) the IE method offered a good potential for grouting defect detection in grouted lap-splice connections; (2) the proposed FE model could well predict the frequency response of the grouting hole; and (3) the measured frequency and amplitude of the grouting hole in an impact-echo test would be considerably influenced by the hole depth.

Download Full-text

The Impact of a Number of Samples on Unsupervised Feature Extraction, Based on Deep Learning for Detection Defects in Printed Circuit Boards

Future Internet ◽

10.3390/fi14010008 ◽

2021 ◽

Vol 14 (1) ◽

pp. 8

Author(s):

Ihar Volkau ◽

Abdul Mujeeb ◽

Wenting Dai ◽

Marius Erdt ◽

Alexei Sourin

Keyword(s):

Deep Learning ◽

Defect Detection ◽

Printed Circuit Boards ◽

Learning Model ◽

Circuit Boards ◽

Printed Circuit ◽

Unsupervised Deep Learning ◽

The Impact ◽

Deep Learning Model ◽

Unsupervised Feature Extraction

Deep learning provides new ways for defect detection in automatic optical inspections (AOI). However, the existing deep learning methods require thousands of images of defects to be used for training the algorithms. It limits the usability of these approaches in manufacturing, due to lack of images of defects before the actual manufacturing starts. In contrast, we propose to train a defect detection unsupervised deep learning model, using a much smaller number of images without defects. We propose an unsupervised deep learning model, based on transfer learning, that extracts typical semantic patterns from defect-free samples (one-class training). The model is built upon a pre-trained VGG16 model. It is further trained on custom datasets with different sizes of possible defects (printed circuit boards and soldered joints) using only small number of normal samples. We have found that the defect detection can be performed very well on a smooth background; however, in cases where the defect manifests as a change of texture, the detection can be less accurate. The proposed study uses deep learning self-supervised approach to identify if the sample under analysis contains any deviations (with types not defined in advance) from normal design. The method would improve the robustness of the AOI process to detect defects.

Download Full-text

A Machine Learning Framework for Predicting Bridge Defect Detection Cost

Infrastructures ◽

10.3390/infrastructures6110152 ◽

2021 ◽

Vol 6 (11) ◽

pp. 152

Author(s):

Chongjiao Wang ◽

Changrong Yao ◽

Bin Qiang ◽

Siguang Zhao ◽

Yadong Li

Keyword(s):

Machine Learning ◽

Cost Analysis ◽

Prediction Model ◽

Defect Detection ◽

Cost Prediction ◽

Factors Affecting ◽

Gdp Growth Rate ◽

Economic Developments ◽

The Impact ◽

Detection Cost

Evaluating the cost of detecting bridge defects is a difficult task, but one that is vital to the lifecycle cost analysis of bridges. In this study, a detection cost sample database was established based on practical engineering data, and a bridge defect detection cost prediction model and software were developed using machine learning. First, the random forest method was adopted to evaluate the importance of the seven main factors affecting the detection cost. The most important indicators were selected, and the recent GDP growth rate was employed to account for the impact of social and economic developments on the detection cost. Combining a genetic algorithm with a multilayer neural network, a detection cost prediction model was established. The predictions given by this model were found to have an average relative error of 3.41%. Finally, an intelligent prediction software for bridge defect detection costs was established, providing a reliable reference for bridge lifecycle cost analysis and the evaluation of defect detection costs during the operation period.

Download Full-text

Research of Diagnostic Models of Radioelectronic Equipment

Èlektronnoe modelirovanie ◽

10.15407/emodel.43.03.064 ◽

2021 ◽

Vol 43 (3) ◽

pp. 64-74

Author(s):

L. Sakovych ◽

◽

S. Gnatiuk ◽

O. Hodych ◽

Y. Martusenko ◽

...

Keyword(s):

Defect Detection ◽

Labor Costs ◽

Detection Algorithms ◽

Radio Electronic ◽

Diagnostic Models ◽

Diagnostic Software ◽

The Impact ◽

First Time ◽

Comprehensive Indicator

A comprehensive indicator of the reliability of electronic means - the coefficient of readiness, significantly depends on the average recovery time. At the same time, the largest labor costs are spent by repair specialists on finding a faulty element. Diagnostic repair support depends on the models used in the development of defect detection algorithms. The most common use of diag-nostic models is in the form of a graph of information and energy connections, which consists of three types of structures: sequential connection of elements, converging and diverging. The latter did not receive the necessary research. In the article as a result of research of influence of the form of the graph of information and power communications on indicators of quality of di-agnostic maintenance of radio electronic means analytical dependences of an estimation of deviation of the diagnosis at an expert error for converging and diverging structures are received for the first time. This allows to improve the quality of diagnostic software and to minimize di-agnostic errors when using current repairs by the aggregate method by assessing the impact of controlled variables at the stage of creating algorithms for finding defects. It is expedient to use the received results at improvement of diagnostic maintenance of existing radio electronic means and its development for perspective samples for the purpose of increase of quality of current repair irrespective of structure of a product.

Download Full-text

Formation of Lunar Craters and Bright Rays as a Result of Meteorite Impacts

Symposium - International Astronomical Union ◽

10.1017/s0074180900178404 ◽

1962 ◽

Vol 14 ◽

pp. 415-418

Author(s):

K. P. Stanyukovich ◽

V. A. Bronshten

Keyword(s):

Explosive Charge ◽

The Moon ◽

Meteorite Impacts ◽

The Earth ◽

Lunar Craters ◽

The Impact

The phenomena accompanying the impact of large meteorites on the surface of the Moon or of the Earth can be examined on the basis of the theory of explosive phenomena if we assume that, instead of an exploding meteorite moving inside the rock, we have an explosive charge (equivalent in energy), situated at a certain distance under the surface.

Download Full-text

The Geosciences Applied to Lunar Exploration

Symposium - International Astronomical Union ◽

10.1017/s0074180900178222 ◽

1962 ◽

Vol 14 ◽

pp. 169-257 ◽

Cited By ~ 9

Author(s):

J. Green

Keyword(s):

Lunar Surface ◽

Probable Mechanism ◽

Point Of View ◽

Lunar Exploration ◽

Geological Model ◽

Apply Geophysics ◽

Surface Features ◽

The Impact

The term geo-sciences has been used here to include the disciplines geology, geophysics and geochemistry. However, in order to apply geophysics and geochemistry effectively one must begin with a geological model. Therefore, the science of geology should be used as the basis for lunar exploration. From an astronomical point of view, a lunar terrain heavily impacted with meteors appears the more reasonable; although from a geological standpoint, volcanism seems the more probable mechanism. A surface liberally marked with volcanic features has been advocated by such geologists as Bülow, Dana, Suess, von Wolff, Shaler, Spurr, and Kuno. In this paper, both the impact and volcanic hypotheses are considered in the application of the geo-sciences to manned lunar exploration. However, more emphasis is placed on the volcanic, or more correctly the defluidization, hypothesis to account for lunar surface features.

Download Full-text

Asteroid and Comet Impact Speeds upon Mars: Significance for Panspermia and the Supply of Organics

International Astronomical Union Colloquium ◽

10.1017/s0252921100014718 ◽

1997 ◽

Vol 161 ◽

pp. 197-201 ◽

Cited By ~ 1

Author(s):

Duncan Steel

Keyword(s):

Probability Distributions ◽

Regions Of Interest ◽

Significant Fraction ◽

Organic Chemicals ◽

Impact Speed ◽

The Mean ◽

The Impact

AbstractWhilst lithopanspermia depends upon massive impacts occurring at a speed above some limit, the intact delivery of organic chemicals or other volatiles to a planet requires the impact speed to be below some other limit such that a significant fraction of that material escapes destruction. Thus the two opposite ends of the impact speed distributions are the regions of interest in the bioastronomical context, whereas much modelling work on impacts delivers, or makes use of, only the mean speed. Here the probability distributions of impact speeds upon Mars are calculated for (i) the orbital distribution of known asteroids; and (ii) the expected distribution of near-parabolic cometary orbits. It is found that cometary impacts are far more likely to eject rocks from Mars (over 99 percent of the cometary impacts are at speeds above 20 km/sec, but at most 5 percent of the asteroidal impacts); paradoxically, the objects impacting at speeds low enough to make organic/volatile survival possible (the asteroids) are those which are depleted in such species.

Download Full-text

Organic Syntheses During the Impact of a Comet with a Gaseous Planet

International Astronomical Union Colloquium ◽

10.1017/s0252921100014706 ◽

1997 ◽

Vol 161 ◽

pp. 189-195

Author(s):

Cesare Guaita ◽

Roberto Crippa ◽

Federico Manzini

Keyword(s):

Polymeric Material ◽

Molecular Form ◽

Parent Compound ◽

Blue Filter ◽

Organic Syntheses ◽

The Impact

AbstractA large amount of CO has been detected above many SL9/Jupiter impacts. This gas was never detected before the collision. So, in our opinion, CO was released from a parent compound during the collision. We identify this compound as POM (polyoxymethylene), a formaldehyde (HCHO) polymer that, when suddenly heated, reformes monomeric HCHO. At temperatures higher than 1200°K HCHO cannot exist in molecular form and the most probable result of its decomposition is the formation of CO. At lower temperatures, HCHO can react with NH3 and/or HCN to form high UV-absorbing polymeric material. In our opinion, this kind of material has also to be taken in to account to explain the complex evolution of some SL9 impacts that we observed in CCD images taken with a blue filter.

Download Full-text