| Abstrakt: |
The article is devoted to the issue of building decision-making models for the classification and forecasting of communication, navigation and surveillance equipment. The analysis of theoretical results and the practice of operation of modern devices of communication, navigation and surveillance testify to the need for wide application of information technologies for processing operational data regarding the operation of these devices and further modernization of the operation system. At this time, there is a need to apply adequate methods of processing statistical data and building special adaptive algorithms of models for making decisions on operational reliability management of specific types of equipment. The implementation of modern maintenance regulations involves the application of the tools of the theory of controlled random processes in the conditions of stochastic uncertainty of information about equipment parameters, creates the necessary conditions for the development of models for the classification of the technical condition with further forecasting of events in the system operation. The object classification process is considered in the article as a set of elementary operations designed to perform certain functions in a certain sequence according to the chosen classification algorithm. The degree of detailing into elementary operations is determined by the purpose of the study. In the proposed model, classification is considered as a sequence of transformation of a vector of states into a vector of realizations as a result of the joint action of a set of elementary operations. The quality of performance of the classification of communication, navigation and surveillance equipment is determined by the quality of performance of each of the studied set of elementary operations, and the mathematical model of decision-making during classification will be based on the mathematical model of each of the studied operations. When performing predictive control in the process of classifying the researched devices, a decision about the technical condition is made at a certain forecasting interval. Predictive control eliminates a significant drawback of current control, which consists of the discrepancy between the time of making a decision about the condition of equipment and the time of its use as intended, thus increasing the effectiveness of control and, accordingly, the effectiveness of the use of equipment. The article has developed a systematic method for determining the probabilities of making a decision based on the results of classification with forecasting, about the belonging of a devices to a certain classified state. The stochastic graphs of decision formation with the chosen classification algorithm with forecasting and taking into account errors were analyzed. Analytical ratios describing the process of classification of the technical condition of the means with subsequent forecasting were obtained. Such ratios can generally be used to solve the problems of increasing the reliability of decision-making during the implementation of predictive control. The results of the research can be used in the process of designing and improving the system of operation of communication, navigation and surveillance equipment during the processes of monitoring the technical condition. [ABSTRACT FROM AUTHOR] |
