Русская версия English version

Forecasting technical condition of ship electric power systems

A.S. Steklov, A.V. Serebryakov, V.G. Titov

Vestnik IGEU, 2016 issue 5, pp. 21—26

Download PDF

Abstract in English: 

Background: At present, autoregressive analysis and artificial neural networks are the most frequently used methods in forecasting problems. However, it is not easy to use neural network techniques to predict the residual life of equipment as the network can only be trained if there is an accurate training sample, including changes in the equipment technical condition in the past. Besides, to study the problem of predicting the technical condition of ship electric power systems requires the creation of working conditions that are close to industrial ones, as well as long-term continuous monitoring. These requirements can hardly be fulfilled in a laboratory. The objective of this research is to solve the problem of forecasting the technical condition of the electrical system by autoregressive analysis.

Materials and methods: Predicting the condition of a ship electric power system is based on the analysis of a time series by applying the integrated moving average autoregression model that takes account of external factors, such as the operating conditions and equipment wear. The model development employed the apparatus of differential equations.

Results: A model has been developed to analyse the time series of ship electric power system efficiency degree. The model is different from the existing ones as it allows accounting not only for the value of the integral damage parameter but also for the factors that influence the rate with which the equipment technical condition changes, such as the process conditions and the equipment life cycle. Unlike the neural network forecasting methods, this model does not require a training sample.

Conclusions: The results obtained can be used in expert systems of forecasting technical condition of ship power systems. For example, the last 12 monthly observations (1 year) show that the developed model of the autoregressive integrated moving average forecasts a series. The proposed model is aimed at predicting technical condition of ship power systems.

Key words: electric power systems of ships, efficiency, forecasting, Box-Jenkins model, autoregression model.

References in English: 

1. Daryenkov, A.B., Khvatov, O.S. Avtonomnaya vysokoeffektivnaya elektrogeneriruyushchaya stantsiya [Autonomous highly efficient power generating station]. Trudy Nizhegorodskogo gosudarstvennogo tekhnicheskogo universiteta, 2009, vol. 77, pp. 68–72.

2. Dubrovin, V.I., Subbotin, S.A., Boguslaev, A.V., Yatsenko, V.K. Intellektual'nye sredstva diagnostiki i prognozirovaniya nadezhnosti aviadvigateley [Intelligent diagnostics and prediction of aircraft engines reliability]. Zaporozh'e, OAO «Motor-Sich», 2003. 279 p.

3. Kalyavin, V.P., Rybakov, L.M. Nadezhnost' i diagnostika elementov elektroustanovok [Reliability and diagnostics of electrical elements]. Saint-Petersburg, Elmor, 2009. 336 p.

4.   Steklov, A.S., Titov, V.G., Serebryakov, A.V. Sistema diagnostiki tekhnicheskogo sostoyaniya sudovogo sinkhronnogo generatora [System of diagnosing marine synchronous generator technical condition]. Trudy Nizhe-gorodskogo gosudarstvennogo tekhnicheskogo uni-versiteta, 2016, no. 1, pp. 60–64.

5.   Steklov, A.S., Titov, V.G., Serebryakov, A.V. Opredelenie stepeni rabotosposobnosti sudovykh sinkhronnykh generatorov s primeneniem iskusstvennykh neironechetkikh setey [Determining of ship synchronous generator efficiency by using artificial fuzzy-neural networks]. Vestnik Chuvashskogo universiteta, 2016, no. 1, pp. 97–104.

6. Deyi, Li, Yi, Du. Artificial intelligence with uncertainty. Tsinghua University, Beijing, China. Chapman & Hall. CRC, 2008. 347 p.

7. Espinosa, J., Vandewalle, J., Wertz, V. Fuzzy logic, identification and predictive control. London, Springer–Verlag, 2005. 263 p.

8. Kosko, B. Fuzzy systems as universal approximators. IEEE Trans. Comput, 1994, v. 43.

9. Sivanandam, S.N., Sumathi, S., Deepa, S.N. Introduction to fuzzy logic using MATLAB. Springer, 2007. 441 p.

10. Shtovba, S.D. Proektirovanie nechetkikh sistem sredstvami MATLAB [Designing of fuzzy systems by MATLAB tools]. Moscow, Telekom, 2007.

Ключевые слова на русском языке: 
судовые электроэнергетические системы, работоспособность, прогнозирование, модель Бокса-Дженкинса, модель авторегрессии, скользящее среднее, техническое состояние, временной ряд
Ключевые слова на английском языке: 
electric power systems of ships, efficiency, forecasting, Box-Jenkins model, autoregression model
The DOI index: 
10.17588/2072-2672.2016.5.021-026
Downloads count: 
32