Application of Neural Networks in the Tests of Hand Grenade Fuses

Journal Title: Bulletin of the Military University of Technology - Year 2019, Vol 68, Issue 1

Abstract

The neural networks, which find currently use in the unusually wide range of problems, in such fields as: finance, medicine, geology or physics, were characterized in the article. It was accent, that neural networks are very sophisticated technique of modelling, able to map extremely complex functions. It was noticed particularly, that neural networks had a non-linear character, what very essentially improve the possibilities of their applications. Some previous applications of neural networks were introduced, both in the area of domestic and foreign, including also military applications. The fuse of UZRGM type (Universal Modernized Fuse of Hand Grenades) was characterized, describing his building and way of action, special attention-getting on the tested features during laboratory diagnostic tests. Necessary technical parameters for the first and the second laboratory diagnostic tests, whose purpose was to build two independent neural networks, on the basis of existing test results and undertaken post-diagnostic decisions were designed. A few artificial neural networks were made and finally the best two independent neural networks were chosen. The main parameters of the chosen active neural networks were introduced in the pictures. Concise information, relating to the built artificial neural networks, for the first and the second laboratory diagnostic tests of the fuses of UZRGM type, was presented in the end of the article. In the summary, clearly distinguished are advantages of the applications of the proposed evaluation method, which significantly shortens an evaluation process of new empirical test results and causes complex automatization of an evaluation process of the tested fuses. Keywords: artificial intelligence, neural networks, activation function, hidden neurons, fuse.<br/><br/>

Authors and Affiliations

Dariusz Ampuła

Keywords

Related Articles

Aktywne obrazowanie w monitoringu i diagnostyce technicznej

Aktywne kamery oferują ponad standardowe możliwości pozyskiwania informacji o obserwowanej scenie m.in. w zakresie definiowania przestrzeni i czasu obserwacji czy też obrazowania przy ograniczonej widoczności. Z kolei ak...

Analysis of occurrence of guided disorders in selected railway equipment — impact of load on measurement results

The parameter of interfering signals, determining the type of coupling, is the disturbing frequency. For frequencies less than 30 MHz, main impact comes by conducted emissions. The article presents an analysis of the occ...

Obiekty lekkiego typu w ochronie zbiorowej

W artykule przedstawiono analizę stanu aktualnego w dziedzinie obiektów ochrony zbiorowej typu lekkiego. Przedstawiono podstawowe wyposażenie zespołu Nr-1 będącego elementem zestawu ochrony zbiorowej typu lekkiego dla SD...

Diagnostyka techniczna obiektów z wykorzystaniem aktywnego obrazowania

Pomiary diagnostyczne trudno mierzalnych parametrów wymagają użycia niestandardowych technik pomiarowych. Jedną z takich technik jest tzw. aktywne obrazowanie metodą kadrowania przestrzenno-czasowego. Unikalną własnością...

Resistance of reinforced concrete beams in explosive charges

The paper presents an analysis of the dynamic interaction on reinforced concrete beams, caused by the outbreak of not-direct contact with the design. Depending on the distance of the source of the outbreak, the structure...

Download PDF file
  • EP ID EP519308
  • DOI 10.5604/01.3001.0013.1480
  • Views 76
  • Downloads 0

How To Cite

Dariusz Ampuła (2019). Application of Neural Networks in the Tests of Hand Grenade Fuses. Bulletin of the Military University of Technology, 68(1), 197-212. https://europub.co.uk/articles/-A-519308