Wyniki wyszukiwania - BazTech

1

Deep learning correction for image reconstruction in electrical impedance tomography using UNet model

Maciura Łukasz, Rymarczyk Tomasz, Wójcik Dariusz, Gauda Konrad, Kowalski Marcin

Przegląd Elektrotechniczny

|

2023

|

R. 99, nr 6

134--137

EN

This article was inspired by a similar Deep DBar algorithm, where a modified UNet convolutional model was used to correct the output of the DBar algorithm using the UNet model. However, instead of the DBar algorithm, another deterministic electrical impedance tomography reconstruction algorithm was used in this solution. The modified UNet model was used to successfully correct the initial reconstructions, which were computed using Kotre regularities using pseudo-inversion of the sensitivity matrix.

PL

Ten artykuł został inspirowany podobnym algorytmem Deep DBar, w którym zmodyfikowany model splotowy UNet został użyty do skorygowania danych wyjściowych algorytmu DBar przy użyciu modelu UNet. Jednak zamiast algorytmu DBar w tym rozwiązaniu zastosowano inny deterministyczny algorytm rekonstrukcji elektrycznej tomografii impedancyjnej. Zmodyfikowany model UNet został wykorzystany do skutecznej korekcji wstępnych rekonstrukcji, które zostały obliczone przy użyciu regularności Kotrego z wykorzystaniem pseudo-inwersji macierzy czułości.

2

Indentation Hardness and Tribological Wear under the Conditions of Sliding Friction of the Surface Layer of Composites Based on Methacrylate Resins with Ceramic Nanofiller

Pieniak Daniel, Gauda Konrad

Advances in Science and Technology. Research Journal

|

2020

|

Vol. 14, no 2

112--119

EN

The biomaterials, which are the subject of this work, are the dental restorative materials classified as light cured polymer matrix ceramic composites or resin based composites. The dental composite materials are needed for the repairment of human teeth. Fillings and other dental applications are exposed to the biomechanical loading in the chewing process. The wear resistance and hardness are important functional properties. Currently, nanofiller composites play an important role among dental composites. The objective of this paper was to study and analyze the friction, mechanical and wear properties of the surface of polymer matrix ceramic filed nanocomposites. Three material groups were used, one commercial composite Filek Z550 (3M ESPE, USA) and two experimental composites Ex-nano(G) and Ex-flow(G). The microindentation tests were conducted on the Micro Combi Tester device (Anton Paar GmbH, Germany). Rotating sliding ball-on-disc friction tests were performed against an alumina ball on 5 N load at 1 Hz in the bath of artificial saliva at 37°C. The linear wear and friction coefficients were evaluated. In the light of the obtained results of contact and friction strength tests, it was found that the performance depends on the production technology of the polymer-ceramic composites. The test results indicate that the share of filler nanoparticles the in experimental composites is advantageous due to the tribological wear.

3

Application of optical profilometry in the analysis of the destruction process of renovation organic coatings for the automotive industry

Gauda Konrad, Pasierbiewicz Kamil

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2019

|

T. 9, nr 4

22--25

EN

The article concerns the evaluation of the possibility of using the optical profilometry method in the analysis of the destruction process of acrylic coatings exposed at a climate station in an industrial-urban atmosphere. It was found that the observed changes do not allow to clearly assess the durability of the tested coatings. It seems that the method used may play a supporting role in assessing the quality of the coatings because the surface maps show the number and size of pores in the coating. Therefore, this method can be used, for example, to help determine the optimal parameters of the coating process (e.g. spray pressure).

PL

Artykuł dotyczy oceny możliwości wykorzystania metody profilometrii optycznej w analizie procesu destrukcji renowacyjnych powłok akrylowych przeznaczonych dla przemysłu motoryzacyjnego eksponowanych na stacji klimatycznej w atmosferze przemysłowo-miejskiej. Stwierdzono, że zaobserwowane zmiany nie pozwalają jednoznacznie ocenić trwałości badanych powłok. Wydaje się, że zastosowana metoda może odgrywać rolę pomocniczą w ocenie jakości powłok, ponieważ mapy powierzchni wyraźnie pokazują liczbę i wielkość porów w powłoce. Można więc zastosować tę metodę przykładowo jako wspomagającą ustalenie optymalnych parametrów procesu nakładania powłok (np. ciśnienia natrysku).

4

Application of artificial neural network in the process of selection of organic coatings

Popko Artur, Gauda Konrad

Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska

|

2019

|

T. 9, nr 4

18--21

EN

The structure of the artificial neural network (ANN) to support the selection of organic coatings was developed and verified, and its learning process was carried out. A simulation of the operation of the network was also carried out, which showed that programming of the coating system selection process can be much faster and more accurate, which is important for a system used in industrial conditions.

PL

Opracowano i zweryfikowano strukturę sztucznej sieci neuronowej (SSN) służącej do wspomagania procesu doboru powłok organicznych oraz przeprowadzono jej proces uczenia. Dokonano również symulacji działania przedmiotowej sieci, która wykazała, że programowanie procesu doboru systemu powłokowego może być o wiele szybsze i dokładniejsze, co ma istotne znaczenie dla systemu użytkowanego w warunkach przemysłowych.

5

Wear Characteristics of Hardfacing Coatings Obtained by Tungsten Inert Gas Method

Dziedzic Krzysztof, Józwik Jerzy, Barszcz Marcin, Gauda Konrad

Advances in Science and Technology. Research Journal

|

2019

|

Vol. 13, no 4

8--14

EN

This paper evaluates the wear characteristics of hardfacing coatings. Regenerative hardfacing coatings were applied with the TIG (Tungsten Inert Gas) method. The solid welding wires were used to obtain the coatings marked as: EL-500 HB, EL-650 HB, and EL-3348. The tribological analysis of samples was conducted at room temperature. The wear rate was evaluated with a THT 1000 Anton Parr ball-on-disc tribotester, in accordance with the ASTM G-133 standard. The counterbody (static partner) consisted of balls with the diameter of 6 mm made of Al2O3. The test was performed with the sliding speed of the friction pair 0.4 m/s, track radius 10 mm, normal load 20 N, acquisition rate 10 Hz and sliding distance 2000 m. During the test, the friction coefficient and wear rate were recorded. The multi-criteria assessment of the construction materials discussed, while taking into account five criteria, showed that EL-3348 HB is the best material. Computer applications were used for multi-criteria assessment and statistical processing of data.