Intelligent system for predicting parameters of fuel and lubricants.

Abstract

The article considers an intelligent forecasting system for monitoring fuel volumes on a ship. The system solves the following monitoring tasks: data analysis and evaluation, model building and forecasting values for decision-making. The information system consists of the following subsystems: information collection and storage subsystem, data preparation subsystem, data analysis and pre-processing subsystem, modelling subsystem and forecasting subsystem. The forecasting subsystem provides a forecast value combination module, which implements seven different methods of combining forecast values. In most cases, combination helps to improve the quality of forecasts. The experimental part of the study considers the problem of predicting the volumes of possible filling of fuel storage systems based on a report on regular data collection on the level and amount of fuel in the tanks on a ship. The following machine learning methods were used for forecasting: ARIMA/SARIMA models, exponential smoothing, regression neural network models and BSTS models. The quality assessment of the obtained forecast values was carried out using the following quality metrics: MAE, MSE, RMSE. The information system allows you to obtain high-quality fuel quantity forecasts for tanks of various types, as well as generalized indicators.