Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: Bayes network

Sortuj według:

Ogranicz wyniki do:

Methods for identifying threats of critical infrastructure systems within Baltic Sea region

Tchórzewska-Cieślak Barbara, Pietrucha-Urbanik Katarzyna, Szpak Dawid

Journal of Polish Safety and Reliability Association

2019

Vol. 10, No. 1

149--166

In the analysis of the operation of critical infrastructure systems it is important to perform the analysis of the safety of the operation. The daily operation of such systems is inherently associated with the occurrence of various types of random undesirable events. Therefore, in the paper the matrix and logical trees methods used in the analysis of the risk of threats in critical infrastructure systems within the Baltic Sea, were presented. The analysis and assessment of the protection of technical system was performed using the FMEA method (Failure Mode and Effect Analysis). As to analyse the cause and effect of undesirable events the method of Bayes' theorem and Java Bayes program were implemented, which allows to identify the probability of the event occurrence.

Platforma do budowania sieci stwierdzeń

Cholewa W., Chrzanowski P., Rogala T., Amarowicz M.

Pomiary Automatyka Kontrola

2011

R. 57, nr 9

1079-1082

W niniejszym artykule przedstawiono wyniki badań związanych z zastosowaniem metod i technik sztucznej inteligencji w obszarze diagnostyki technicznej. Szczególną uwagę zwrócono na możliwość budowania systemów doradczych opartych na wielowarstwowych sieciach stwierdzeń. Przedstawiono ogólną koncepcję platformy do budowania sieci stwierdzeń. Nakreślono plan prac związanych z rozwojem platformy, który umożliwi stosowanie różnego typu sieci w ramach jednego modelu oraz integrację z innymi systemami.

This paper deals with the results of studies relevant to the methods and techniques of artificial intelligence in the field of technical diagnostics. At the beginning, the basic concepts, such as the statement and statement network, are described. Then, the concept of a multilayer statement network (Fig. 1) which is generalization of a single-layer statement network is presented. Special attention is paid to possibility of using the multilayer statement networks for development of multi-scale statement networks. Next, the general concept of a platform for development of the multilayer statement network and description of the main classes of objects resulting from using the platform are given. The choice of R environment for development of the platform is justified and its advantages are emphasized. The data exchange with other systems using XML format and the file structure is described. The process of construction of the multilayer statement network is discussed based on an example of the two-layer network shown in Fig. 2. The obtained results show the correctness of the platform operation. Finally, the main advantages of platforms, such as possibility of development of multilayer statement networks or commenting of the particular objects are discussed. The schedule of the development of platforms, including e.g. extension of the learning process of the network structure and tuning the network parameters basing on the available data sets or extension-training opportunities to construct multilayer network models with different types of networks on a different layers is also presented.