FEATURES OF FORECASTING THE CONDITION OF VESSEL EQUIPMENT OF RIVER AND SEA TRANSPORT

Abstract

The main contradiction that underlies scientific research in the direction of improving the efficiency of river and sea transport is, on the one hand, the need to increase the technical readiness of ship equipment for its intended use and its smooth operation.

On the other hand, attempts to maximize the cost of transportation, leads to a reduction in the number of control measures, simplification of their procedure. In this aspect, the development of new methods of technical operation of equipment based on the use of modern automated procedures for determining the frequency and scope of diagnosis is relevant.

Thus, the solution is subject to the actual scientific and applied task of developing a procedure for determining the appropriate timing of technical diagnostics of ship equipment on the basis of forecasting the technical condition of the equipment.

These simulation results confirm the adequacy of the model of the process of operation of ship equipment of river and sea transport, which is based on the idea of ​​predictive control of individual reliability of a sample of ship equipment based on canonical decomposition of a random process taking into account a priori measurement errors.

This idea allows to implement the specified model in the conditions of operation of the vessel at a minimum of diagnostic data, precisely defining random process in control points and providing a minimum of an average square of an error of approach in intervals between these points.

Incomplete a priori information can reduce the accuracy of forecasting, or make it impossible to predict the condition of ship equipment. In this case, there is a need to take into account the incompleteness of control information in the procedure for solving the problem of forecasting, as well as to assess its impact on the accuracy of the results.

The article considers the peculiarities of solving the problem of forecasting outside the a priori knowledge of the process, namely a practical example of individual forecasting of the change of the stem gap and the valve guide sleeve based on a linear canonical representation of the scalar a posteriori process in areas not covered by statistics.