Algorithm for parametric identification of fuel consumption characteristics by a vessel using neural network technology

The purpose of the study is to enhance methods for computer monitoring and parametric identification of models describing vessels' fuel consumption characteristics. These improvements aim at analyzing and forecasting energy efficiency indicators of water transport facilities and optimizing the operational modes of diesel generator units. The paper proposes an algorithm for parametric identification of input-output characteristics across various technological processes and systems (technical, biological, economic, social, environmental, etc.) based on measurement data using approximate motor (regression) neural networks. The algorithm enables quantitative error assessment of parametric optimization using the Euclidean norm. Unlike traditional methods relying on statistical series for model fitting, the proposed approach trains a multilayer neural network with backpropagation to minimize deviations in output signal values from reference values by adjusting synaptic weight coefficients. The study demonstrates that radial neural networks with fixed structures—comprising one hidden layer with nonlinear activation functions and one output layer with linear activation functions—are suitable for solving problems in this domain. These networks ensure accurate image mapping based on the Euclidean metric while simplifying training modes and maintaining acceptable approximation and identification accuracy. The algorithm has been implemented to estimate parameters of a vessel's fuel consumption model based on statistical series with a predefined initial approximation. It can also be applied to identify energy consumption characteristics in the inland water transport sector when calculating target indicators and developmental metrics.

1. Baryshnikov, S. O., D. V. Dmitrienko, V. V. Sakharov and A. A. Chertkov. Modeli i algoritmy upravleniya ob”ektami vodnogo transporta v usloviyakh tsifrovoy transformatsii SPb: Izd. «Zanevskaya ploschad’», 2022: 520.

2. Sakharov, V. V., A. A. Kuz’min and A. A. Chertkov. Modeli i algoritmy optimizatsii tekhnologicheskikh protsessov na ob”ektakh vodnogo transporta v srede MatLab Sankt- Peterburg: Federal’noe gosudarstvennoe byudzhetnoe obrazovatel’noe uchrezhdenie vysshego obrazovaniya Gosudarstvennyy universitet morskogo i rechnogo flota im. admirala S. O. Makarova, 2015: 436.

3. Chertkov, A. A., C. V. Saburov and Ya. N. Kask. “Algorithm for identifying parameters of production function models using a neural network .” Vestnik gosudarstvennogo universiteta morskogo i rechnogo flota im. admirala S. O. Makarova 15.6 (2023): 1096–1104. DOI: 10.21821/2309-5180-2023-15-6-1096-1104.

4. Gerasimov, B. I., G. I. Terekhova., et al. Osnovy nauchnykh issledovaniy. Second edition. M: Forum: INFRA-M, 2015: 272.

5. Khaikin, Simon. Neural Networks: A Complete Course, 2nd Edition. with anrl. Moscow, Williams Pub lishing House, 2006. 1104 с.: ил.

6. Vakulenko, S. A. and A. A. Zhikhareva. Prakticheskiy kurs po neyronnym setyam SPb: Universitet ITMO, 2018: 71.

7. Per, S. Osovskiy. Neyronnye seti dlya obrabotki informatsii M: Finansy i statistika, 2002: 344.

8. Gashnikov, M. V. et al. Metody komp’yuternoy obrabotki izobrazheniy: Uchebnoe posobie dlya studentov vuzov, obuchayuschikhsya po napravleniyu podgotovki diplomirovannykh spetsialistov “Prikladnaya matematika” Ed. by V. A. Soifer. Moskva: OOO Izdatel’skaya firma “Fiziko- matematicheskaya literatura”, 2003: 784.

9. Fursov, V. A. “Constructing unified identification algorithms using a small number of observations for adaptive control and navigation systems.” Navigation and Control Technologies for Unmanned Systems IISPIE, 1997: 34–44. DOI: 10.1117/12.277217.

10. Ch. Sanjeev Kumar Dash, Ajit Kumar Behera, Satchidananda Dehuri and Sung- Bae Cho “Radial ba sis function neural networks: a topical state-of-the-art survey.” Open Computer Science 6.1 (2016): 33–63. DOI: doi:10.1515/comp-2016-0005.

11. Anikina, O. V., O. M. Guschina, E. V. Panyukova and N. N. Rogova. “Abular artificial neural network implementation of radial basis functions for the samples classification.” Modern Information Technologies And It- Education 14.2 (2018): 436–445. DOI: 10.25559/SITITO.14.201802.436–445.

12. Goodfellow, I., Y. Bengio and A. Courville. Deep Learning London; Cambridge: MIT Press, 2016.