|
|
High data rate image processing using CUDA/OpenCL
Sedláček, Filip ; Klečka, Jan (referee) ; Honec, Peter (advisor)
The main objective of this research is to propose optimization of the defect detection algorithm in the production of nonwoven textile. The algorithm was developed by CAMEA spol. s.r.o. As a consequence of upgrading the current camera system to a more powerful one, it will be necessary to optimize the current algorithm and choose the hardware with the appropriate architecture on which the calculations will be performed. This work will describe a usefull programming techniques of CUDA software architecture and OpenCL framework in details. Using these tools, we proposed to implement a parallel equivalent of the current algorithm, describe various optimization methods, and we designed a GUI to test these methods.
|
|
|
Reliable visual systems
Honec, Peter ; Janáková, Ilona (advisor)
The Doctoral thesis demonstrates the design of reliable industrial visual systems. The special emphasis is dedicated to the detection of defects on webs in industrial applications based on line-scan cameras. This system makes possible detection and classification of defects originating during the real production conditions. This work covers a theoretical study of a visual system for the defect detection on endless bands as well as of appropriate lighting and the scene arrangement. Further to that have been selected, adjusted and designed key components of hardware. Following the design and optimization of algorithms a system prototype had been installed on non-woven textiles production line. Eight visual systems implemented into real-life industrial conditions based on this prototype
|
|
|
Deep Neural Networks for Defect Detection
Juřica, Tomáš ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
The goal of this work is to bring automatic defect detection to the manufacturing process of plastic cards. A card is considered defective when it is contaminated with a dust particle or a hair. The main challenges I am facing to accomplish this task are a very few training data samples (214 images), small area of target defects in context of an entire card (average defect area is 0.0068 \% of the card) and also very complex background the detection task is performed on. In order to accomplish the task, I decided to use Mask R-CNN detection algorithm combined with augmentation techniques such as synthetic dataset generation. I trained the model on the synthetic dataset consisting of 20 000 images. This way I was able to create a model performing 0.83 AP at 0.1 IoU on the original data test set.
|
|
|
Inovation of system for electroluminiscence defect detection of solar cells
Lepík, Pavel ; Křivík, Petr (referee) ; Vaněk, Jiří (advisor)
This master thesis analyses the existing methods both practically and theoretically used to detect defected surface area in solar cells. Various methods were used but by using an upgraded CMOS camera without IR filter to implement the electroluminescence method, this has proven to have a very crucial impact on the results. Given the overall results and the acquired information, a procedure with a simple parameter can be setup to carry out the measurements. In addition to this a catalog was formed showing the defects occurring in mono and polycrystalline solar cells.
|
|
|
Response analysis of train track laboratory model
Heteš, Marek ; Věchet, Stanislav (referee) ; Kšica, Filip (advisor)
In terms of safety, railway tracks have to be kept in good condition. Early and accurate detection of track defects can save both time and money. This thesis deals with simulation of a passing train on laboratory apparatus, and the measurement of the generated response. Apparatus represents scaled down section of a railway track, and allows the simulation of defect formation. With the help of the obtained data, a suitable method for defect detection was created.
|
|
|
Classification of board defects in semiconductor manufacturing
Jašek, Filip ; Vágner, Martin (referee) ; Dřínovský, Jiří (advisor)
This diploma thesis focuses on detecting defects in semiconductor wafer manufacturing. It explores methods for identifying faulty chips and controlling yield during production. To classify defects machine learning techniques are used. Initially, ResNet18 architecture was used for inference, but low accuracy was attributed to limited input data. Transfer learning with ResNet50v2 was then attempted, resulting in improved metric with different dataset. Hyperparameter tuning and data augmentations were also explored. The study found that autoencoders for data compression during inference increased speed but led to degraded evaluation metrics.
|
|
|
Design of load mechanism for laboratory model of rail track
Čech, Vít ; Lošák, Petr (referee) ; Kšica, Filip (advisor)
This bachelor thesis deals with the design of the loading of the similarity model of the track and the subsequent implementation and verification of the functionality of the designed device. The thesis is divided into three parts. In the first part of the thesis, the theoretical knowledge related to the effects acting on the track and a research of available methods and equipment that allow the investigation of the individual effects in a controlled laboratory environment are presented. The second part then focuses on the design and construction of the loading mechanism. This had to be designed in accordance with all the loading requirements of the model. The last part covers the testing of the designed loading mechanism and the results are compared with those from a real railway line and also with those measured during the original loading of the model using pneumatic pistons.
|
|
|
Automation of nuclear fuel visual inspection
Knotek, Jaroslav ; Blažek, Jan (advisor) ; Horáček, Jan (referee)
The safety and performance of nuclear plant relies, among others, on the quality of nuclear fuel. The quality fulfilling designed criteria of the fuel in use is inspected and reported on periodically. Visual inspection focuses on the condition of the fuel based on its visual properties. During the inspection, the fuel is being recorded and analysed by the inspector. The current state of the fuel assemblies is compared to the historical statistics which helps do decide whether this particular assembly remains or gets replaced. This thesis describe a project initiated by Centrum Výzkumu Řež focusing on digital image processing methods application to visual inspection process. The result of the project is a tool that accelerates the process of report making. Firstly, it transforms the inspection video into one image overview and highlight a significant part (more than 95%) of possible defects to the inspector. 1
|
|
|
Detection of infill defects in 3D printed structures using the DIC method
Doležal, Tomáš ; Halabuk, Dávid (referee) ; Ščerba, Bořek (advisor)
Additive manufacturing offers wide range of advantages. However various internal defects are likely to be formed during the manufacturing process which negatively affect mechanical properties. Detection of those defects is critical to ensure that the manufactured component stays reliable and maintains its dependability throughout its whole life. The potential of the digital image correlation (DIC) method for detect detection in components manufactured using additive technologies has not yet been investigated in the literature. In this master thesis a novel non-destructive defectoscopic method for the internal defect detection in 3D printed structures is presented, based on the evaluation of the strain field obtained by the DIC method. The method was experimentally evaluated on samples with artificial internal defects fabricated by FDM technology. The samples containing defects were successfully visually detected. A convolutional neural network was then used for the defect detection and achieved a classification accuracy of 94,5 %. This methodology has a potential to provide cheap and fast detection of internal defects formed in additive manufactured components in the future although future research is still required.
|
|
|
Classification of board defects in semiconductor manufacturing
Jašek, Filip ; Vágner, Martin (referee) ; Dřínovský, Jiří (advisor)
This diploma thesis focuses on detecting defects in semiconductor wafer manufacturing. It explores methods for identifying faulty chips and controlling yield during production. To classify defects machine learning techniques are used. Initially, ResNet18 architecture was used for inference, but low accuracy was attributed to limited input data. Transfer learning with ResNet50v2 was then attempted, resulting in improved metric with different dataset. Hyperparameter tuning and data augmentations were also explored. The study found that autoencoders for data compression during inference increased speed but led to degraded evaluation metrics.
|
guest ::
