Informacja o cookies

Zgadzam się Nasza strona zapisuje niewielkie pliki tekstowe, nazywane ciasteczkami (ang. cookies) na Twoim urządzeniu w celu lepszego dostosowania treści oraz dla celów statystycznych. Możesz wyłączyć możliwość ich zapisu, zmieniając ustawienia Twojej przeglądarki. Korzystanie z naszej strony bez zmiany ustawień oznacza zgodę na przechowywanie cookies w Twoim urządzeniu.

Publikacje Pracowników Politechniki Lubelskiej
Status:
Warianty tytułu:
Predicting the strength of adhesive joints using neural networks
Autorzy: Domińczuk Jacek
Rok wydania: 2010
Wersja dokumentu: Drukowana | Elektroniczna
Język: polski
Numer czasopisma: 2
Strony: 41 - 47
Bazy: BazTech
Efekt badań statutowych NIE
Materiał konferencyjny: NIE
Publikacja OA: NIE
Abstrakty: angielski
This paper presents the results of the analysis of suitability of artificial intelligence for processing of experimental information related to strength of adhesive joints. The efficiency of neuron artificial network was compared with the efficiency of typical methods of statistical analysis such as linear and polynomial regress. The research was conducted, based on a statical, determinated multifactorial program. The list of arguments comprised length of overlap, thickness of adhesive layer, thickness of joined materials, geometrical parameters of surface. The output result was the load capacity as a force needed to destruct an adhesive joint. The research was done in the situation, when other parameters affecting the strength of adhesive joint were stable. The surface answers of network for entrance parameters combination for the defined nodal point, presented in this paper, indicate non-linear influence of testing parameters on adhesive joints strength. The influence of average square ordinates of roughness profile is close to linear. However, its influence changes following the change of other parameters. The presented graphs show, that the highest adhesive joints strength is a function of complicated relations between the geometrical parameters of joints. The example results presented in this paper, enable to state that the artificial neuron network, thanks to the credibility of modeling and predicting the strength of adhesive joints, can serve as a base of knowledge for constructors and technologists, using adhesive joints in designed constructions. These networks can significantly commit to the increased quality of products and decrease the construction cost.