Nowa wersja platformy, zawierająca wyłącznie zasoby pełnotekstowe, jest już dostępna.
Przejdź na https://bibliotekanauki.pl
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 1

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
1
100%
EN
Sticking of abrasive grains into the surface is the effect of abrasive jet machining processing. For prosthetic works burnt the clay, it may deteriorate the quality of metal-clay connection. Parameters of sandblasting have the significant influence on the amount of stubble elements stuck into the base. The aim of the research is examining possibilities of applying neuron networks for modeling this process. Examples were sandblasted using alternating parameters (pressure of working factor, angle of sandblasting, size of grains). As a next the amount of stubble elements stuck into the base were calculated. Study results allowed to work out a set of 180 standardized teaching patterns. Next, a group of 150 randomly selected neuron networks was submitted to teaching process. The aim was to select net architecture with the highest adjustment for discussed issue. Finally, a MLP (Multi Layer Perception) was chosen. Training process of the net involved presentation of process entrance parameters to the net, followed by presentation of researched proportional partaking of stuck elements. In following training cycles the error was decreasing systematically. After finishing the training, the average medium error between the real measurement and the one anticipated by the net was about 5 per cent. Additional number of abrasive jet machining processing was done to verification experiments. As the study shows, designed artificial neuron net stimulates real dependencies appearing during abrasive jet machining-processing in a proper way and can be used for estimating proportional part of grains stuck into base after this processing. It turns out that this phenomenon can be modeled, and its model can be used in a practical way without using mathematical or physical equations.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.