Bulletin of scientific research results Bulletin of scientific research results Бюллетень результатов научных исследований 2223-9987 53010 10.20295/2223-9987-2022-3-137-150 Современные технологии - транспорту HIGH TECHNOLOGIES FOR TRANSPORT Современные технологии - транспорту Design Algorithm for Forecasting Model of Transport-Logistic Activity on the Basis of Neuro-Fuzzy Networks Алгоритм построения прогнозной модели транспортно-логистической деятельности на основе применения нечетких нейронных сетей Ламехов Владимир Андреевич Lamehov Vladimir Andreevich Коровяковский Евгений Константинович Korovyakovskiy Evgeny Konstantinovich

кандидат технических наук;

candidate of technical sciences;

 Петербургский государственный университет путей сообщения Императора Александра I Россия Emperor Alexander I St. Petersburg State Transport University Russian Federation Петербургский государственный университет путей сообщения Императора Александра I Россия Emperor Alexander I Petersburg State Transport University Russian Federation 22 09 2022 22 09 2022 2022 3 137 150 22 09 2022 https://atjournal.ru/en/nauka/article/53010/view

Цель: Рассмотреть существующую ситуация на рынке контейнерных перевозок Ленинградской области. Показать необходимость построения новых прогностических моделей. Обосновать применение нейронных нечетких сетей. Рассмотреть существующие ограничения их применения. Предложить способы построения прогностических нейронных нечетких моделей для оценки перспективных количественных показателей логистической деятельности. Методы: ANFIS, R-ANFIS, Fuzzy-Partitions, SCRG, GD, LSE, PSO, ABC, FA. Результаты: Указана необходимость адаптации нейронных нечетких сетей для проведения прогнозов в области логистики, предложена структура перспективной модели, учитывающей использование и анализ множества методов структурной и параметрической идентификации. Указаны недостатки отдельных методов структурной и параметрической идентификации, влияющие на точность получаемых прогнозов. Практическая значимость: Показана значимость построения точных прогностических моделей для ключевых количественных показателей логистической деятельности. Приведены факторы, влияющие на осуществление транспортно-логистической деятельности, достоверный прогноз которых в ситуациях ограниченного времени и ресурсов невозможен. В статье предложены к рассмотрению существующие методы параметрической и структурной идентификации нечетких нейронных сетей. Предложен алгоритм адаптации существующих методов для использования в транспортно-логистическом процессе.

Purpose: To consider the current situation in container transportation market of Leningrad Region. To show the need in the design of new forecasting models. To justify the use of neural fuzzy networks. To consider existing limitations of their application. To suggest the ways to build predictive neural fuzzy models for evaluating promising quantitative indicators of logistics activities. Methods: ANFIS, R-ANFIS, Fuzzy-Partitions, SCRG, GD, LSE, PSO, ABC, FA. Results: The necessity of adaptation of neural fuzzy networks for making forecasts in the field of logistics is pointed on, the structure of a promising model is proposed which takes into account the use and analysis of variety of methods on structural and parametric identification. The shortcomings of particular methods of structural and parametric identification, which affect the accuracy of being obtained forecasts, are indicated. Practical importance: The importance of design of accurate predictive models for key quantitative indicators of logistics activities is shown. The factors influencing the implementation of transport and logistics activities are given which of, reliable forecast is impossible in the situation of limited time and resources. For consideration, the article proposes the existing methods of parametric and structural identification of fuzzy neural networks. An algorithm for adapting existing methods to the use in a transport and logistics process is proposed.

 Нечеткие нейронные сети гибридные нейронные сети методы параметрической и структурной идентификации методы обучения контейнерный терминал логистика прогнозирование Fuzzy neural networks hybrid neural networks parametric and structural identification methods learning methods container terminal logistics forecasting

Транспортная стратегия Российской Федерации на период до 2030 года. Министерство транспорта Российской Федерации. - 2008. Transportnaya strategiya Rossiyskoy Federacii na period do 2030 goda. Ministerstvo transporta Rossiyskoy Federacii. - 2008. Дирекция по развитию транспортной системы Санкт-Петербурга и Ленинградской области. Стратегия развития транспортной системы Санкт-Петербурга и Ленинградской области на период до 2030 года. - 2016. Direkciya po razvitiyu transportnoy sistemy Sankt-Peterburga i Leningradskoy oblasti. Strategiya razvitiya transportnoy sistemy Sankt-Peterburga i Leningradskoy oblasti na period do 2030 goda. - 2016. Pokrovskaya O. Northern Latitudinal Railway Project: Priorities and Drivers / O. Pokrovskaya, R. Fedorenko, A. Kamaletdinov. - 2021. - DOI: 10.1007/978-3-030-60929-0_34. Pokrovskaya O. Northern Latitudinal Railway Project: Priorities and Drivers / O. Pokrovskaya, R. Fedorenko, A. Kamaletdinov. - 2021. - DOI: 10.1007/978-3-030-60929-0_34. Anisimov V. Multimodal Transport Network of the Far Eastern Federal District of Russia / V. Anisimov, L. Bogdanova, O. Morozova, S. Shkurnikov, N. Nesterova. - 2021. - DOI: 10.1007/978-981-33-6208-6_45. Anisimov V. Multimodal Transport Network of the Far Eastern Federal District of Russia / V. Anisimov, L. Bogdanova, O. Morozova, S. Shkurnikov, N. Nesterova. - 2021. - DOI: 10.1007/978-981-33-6208-6_45. Panova Yu. Russian Railways on the Eurasian Market: Issue of Sustainability / Yu. Panova, E. Korovyakovskiy, A. Semerkin et al. // European Business Review. - 2017. - 10.1108/EBR-01-2016-0008. Panova Yu. Russian Railways on the Eurasian Market: Issue of Sustainability / Yu. Panova, E. Korovyakovskiy, A. Semerkin et al. // European Business Review. - 2017. - 10.1108/EBR-01-2016-0008. Goncharova N. Intelligent Transport Systems as a Way to Improve the Quality of the Rail-Truck Multimodal Freight Transportation / N. Goncharova // IEEE East-West Design & Test Symposium (EWDTS). - 2019. - Pp. 1-7. - DOI: 10.1109/EWDTS.2019.8884460. Goncharova N. Intelligent Transport Systems as a Way to Improve the Quality of the Rail-Truck Multimodal Freight Transportation / N. Goncharova // IEEE East-West Design & Test Symposium (EWDTS). - 2019. - Pp. 1-7. - DOI: 10.1109/EWDTS.2019.8884460. Jang J.-S. R. ANFIS: adaptive-network-based fuzzy inference system / J.-S. R. Jang // IEEE Transactions on Systems, Man, and Cybernetics. - Vol. 23. - № 3. - Pp. 665-685. - May-June 1993. - doi: 10.1109/21.256541. Jang J.-S. R. ANFIS: adaptive-network-based fuzzy inference system / J.-S. R. Jang // IEEE Transactions on Systems, Man, and Cybernetics. - Vol. 23. - № 3. - Pp. 665-685. - May-June 1993. - doi: 10.1109/21.256541. Zhang J. Recurrent neuro-fuzzy networks for nonlinear process modeling / J. Zhang, A. J. Morris // IEEE Transactions on Neural Networks. - Vol. 10. - № 2. - Pp. 313-326. - March 1999. - doi: 10.1109/72.750562. Zhang J. Recurrent neuro-fuzzy networks for nonlinear process modeling / J. Zhang, A. J. Morris // IEEE Transactions on Neural Networks. - Vol. 10. - № 2. - Pp. 313-326. - March 1999. - doi: 10.1109/72.750562. Yinghua L. Using fuzzy partitions to create fuzzy systems from input-output data and set the initial weights in a fuzzy neural network / L. Yinghua, G. A. Cunningham III, S. Coggeshall // IEEE Transactions on Fuzzy Systems. - 1997. - № 5. - Pp. 614-621. - DOI: 10.1109/91.649913. Yinghua L. Using fuzzy partitions to create fuzzy systems from input-output data and set the initial weights in a fuzzy neural network / L. Yinghua, G. A. Cunningham III, S. Coggeshall // IEEE Transactions on Fuzzy Systems. - 1997. - № 5. - Pp. 614-621. - DOI: 10.1109/91.649913. Castellano G. A neuro-fuzzy network to generate human-understandable knowledge from data / G. Castellano, A. Fanelli, C. Mencar // Cognitive Systems Research Journal. - 2002. - № 3. - Pp. 125-144. - DOI: 10.1016/S1389-0417(01)00055-9. Castellano G. A neuro-fuzzy network to generate human-understandable knowledge from data / G. Castellano, A. Fanelli, C. Mencar // Cognitive Systems Research Journal. - 2002. - № 3. - Pp. 125-144. - DOI: 10.1016/S1389-0417(01)00055-9. Lee Shie-Jue. A neuro-fuzzy system modeling with self-constructing rule generationand hybrid SVD-based learning / Shie-Jue Lee, Chen-Sen Ouyang // Fuzzy Systems, IEEE Transactions on. - 2003. № 11. - Pp. 341-353. - DOI: 10.1109/TFUZZ.2003.812693. Lee Shie-Jue. A neuro-fuzzy system modeling with self-constructing rule generationand hybrid SVD-based learning / Shie-Jue Lee, Chen-Sen Ouyang // Fuzzy Systems, IEEE Transactions on. - 2003. № 11. - Pp. 341-353. - DOI: 10.1109/TFUZZ.2003.812693. Jiang H. Modeling customer satisfaction for new product development using a PSO-based ANFIS approach / H. Jiang, C. K. Kwong, W. H. Ip, T. C. Wong // Appl. Soft Comput. 2012. - № 12. - Pp. 726-734. - DOI: 10.1016/j.asoc.2011.10.020. Jiang H. Modeling customer satisfaction for new product development using a PSO-based ANFIS approach / H. Jiang, C. K. Kwong, W. H. Ip, T. C. Wong // Appl. Soft Comput. 2012. - № 12. - Pp. 726-734. - DOI: 10.1016/j.asoc.2011.10.020. Catalão J. Hybrid Wavelet-PSO-ANFIS approach for short-term electricity prices forecasting / J. Catalão, H. M. I. Pousinho, V. M. F. Mendes // Power Systems, IEEE Transactions on. - 2011. - № 26. - Pp. 137-144. - DOI: 10.1109/TPWRS.2010.2049385. Catalão J. Hybrid Wavelet-PSO-ANFIS approach for short-term electricity prices forecasting / J. Catalão, H. M. I. Pousinho, V. M. F. Mendes // Power Systems, IEEE Transactions on. - 2011. - № 26. - Pp. 137-144. - DOI: 10.1109/TPWRS.2010.2049385. Turki M. Adaptive Control of Nonlinear System Using Neuro-Fuzzy Learning by PSO Algorithm / M. Turki, S. Bouzaida, A. Sakly, M'Sahli Faouzi. - 2012. Turki M. Adaptive Control of Nonlinear System Using Neuro-Fuzzy Learning by PSO Algorithm / M. Turki, S. Bouzaida, A. Sakly, M'Sahli Faouzi. - 2012. Pousinho H. M. I. A hybrid PSO-ANFIS approach for short-term wind power prediction in Portugal / H. M. I. Pousinho, V. M. F. Mendes, J. P. S. Catalão // Energy Conversion and Management. - 2011- Vol. 52. - Iss. 1. - Pp. 397-402. - ISSN 0196-8904. Pousinho H. M. I. A hybrid PSO-ANFIS approach for short-term wind power prediction in Portugal / H. M. I. Pousinho, V. M. F. Mendes, J. P. S. Catalão // Energy Conversion and Management. - 2011- Vol. 52. - Iss. 1. - Pp. 397-402. - ISSN 0196-8904. Peilin L. Training ANFIS Model with an Improved Quantum-Behaved Particle Swarm Optimization Algorithm / L. Peilin, L. Wenhao, W. Fang // Mathematical Problems in Engineering. - 2013. - DOI: 10.1155/2013/595639. Peilin L. Training ANFIS Model with an Improved Quantum-Behaved Particle Swarm Optimization Algorithm / L. Peilin, L. Wenhao, W. Fang // Mathematical Problems in Engineering. - 2013. - DOI: 10.1155/2013/595639. Bagheri A. Financial forecasting using ANFIS networks with Quantum-behaved Particle Swarm Optimization / A. Bagheri, H. Peyhani, M. Akbari // Expert Systems with Applications. - № 41. - Pp. 6235-6250. - DOI: 10.1016/j.eswa.2014.04.003. Bagheri A. Financial forecasting using ANFIS networks with Quantum-behaved Particle Swarm Optimization / A. Bagheri, H. Peyhani, M. Akbari // Expert Systems with Applications. - № 41. - Pp. 6235-6250. - DOI: 10.1016/j.eswa.2014.04.003. Soto J. Optimization of the Fuzzy Integrators in Ensembles of ANFIS Model for Time Series Prediction: The case of Mackey-Glass / J. Soto, P. Melin. - 2015. - DOI: 10.2991/ifsa-eusflat-15.2015.140. Soto J. Optimization of the Fuzzy Integrators in Ensembles of ANFIS Model for Time Series Prediction: The case of Mackey-Glass / J. Soto, P. Melin. - 2015. - DOI: 10.2991/ifsa-eusflat-15.2015.140. Malleswaran M. Genetically optimized ANFIS based Intelligent Navigation System / M. Malleswaran, V. Vaidehi and R. A. Joseph // Third International Conference on Advanced Computing. - 2011. - Pp. 390-395. - DOI: 10.1109/ICoAC.2011.6165207. Malleswaran M. Genetically optimized ANFIS based Intelligent Navigation System / M. Malleswaran, V. Vaidehi and R. A. Joseph // Third International Conference on Advanced Computing. - 2011. - Pp. 390-395. - DOI: 10.1109/ICoAC.2011.6165207. Cárdenas J. J. Evolutive ANFIS training for energy load profile forecast for an IEMS in an automated factory / J. J. Cárdenas, A. García, J. L. Romeral, K. Kampouropoulos // ETFA 2011. - 2011. - Pp. 1-8. - DOI: 10.1109/ETFA.2011.6059079. Cárdenas J. J. Evolutive ANFIS training for energy load profile forecast for an IEMS in an automated factory / J. J. Cárdenas, A. García, J. L. Romeral, K. Kampouropoulos // ETFA 2011. - 2011. - Pp. 1-8. - DOI: 10.1109/ETFA.2011.6059079. Zhou Y. Explore an evolutionary recurrent ANFIS for modelling multi-step-ahead flood forecasts / Y. Zhou, S. Guo, F. Chang // Journal of Hydrology. - 2019. Zhou Y. Explore an evolutionary recurrent ANFIS for modelling multi-step-ahead flood forecasts / Y. Zhou, S. Guo, F. Chang // Journal of Hydrology. - 2019. Wei C. k-NN Based Neuro-fuzzy System for Time Series Prediction / C. Wei, T. Chen, S. Lee // 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing. - 2013. - Pp. 569-574. - DOI: 10.1109/SNPD.2013.68. Wei C. k-NN Based Neuro-fuzzy System for Time Series Prediction / C. Wei, T. Chen, S. Lee // 14th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing. - 2013. - Pp. 569-574. - DOI: 10.1109/SNPD.2013.68. Karaboga D. Training ANFIS using artificial bee colony algorithm / D. Karaboga, E. Kaya // IEEE International Symposium on Innovations in Intelligent Systems and Applications, IEEE INISTA. - 2013. № 1-5. - DOI: 10.1109/INISTA.2013.6577625. Karaboga D. Training ANFIS using artificial bee colony algorithm / D. Karaboga, E. Kaya // IEEE International Symposium on Innovations in Intelligent Systems and Applications, IEEE INISTA. - 2013. № 1-5. - DOI: 10.1109/INISTA.2013.6577625. Wang R. Assessment of human operator functional state using a novel differential evolution optimization based adaptive fuzzy model / R. Wang, J. Zhang, Y. Zhang, X. Wang // Biomedical Signal Processing and Control. - 2012. - Vol. 7. - Iss. 5. - Pp. 490-498. Wang R. Assessment of human operator functional state using a novel differential evolution optimization based adaptive fuzzy model / R. Wang, J. Zhang, Y. Zhang, X. Wang // Biomedical Signal Processing and Control. - 2012. - Vol. 7. - Iss. 5. - Pp. 490-498. Orouskhani M. A hybrid method of modified cat swarm optimization and gradient descent algorithm for training anfis / M. Orouskhani, M.Manthouri, Y. Orouskhani, M. Teshnehlab // International Journal of Computational Intelligence and Applications. - 2013. - DOI: 12. 10.1142/S1469026813500077. Orouskhani M. A hybrid method of modified cat swarm optimization and gradient descent algorithm for training anfis / M. Orouskhani, M.Manthouri, Y. Orouskhani, M. Teshnehlab // International Journal of Computational Intelligence and Applications. - 2013. - DOI: 12. 10.1142/S1469026813500077. Badetsky A. Improving the Stability of the Train Formation Plan to Uneven Operational Work / A. Badetsky, O. Medved // Transportation Research Procedia. - 2021. - № 54. - Pp. 559-567. - DOI: 10.1016/j.trpro.2021.02.108. Badetsky A. Improving the Stability of the Train Formation Plan to Uneven Operational Work / A. Badetsky, O. Medved // Transportation Research Procedia. - 2021. - № 54. - Pp. 559-567. - DOI: 10.1016/j.trpro.2021.02.108. Dolgopolov P. Optimization of train routes based on neuro-fuzzy modeling and genetic algorithms / P. Dolgopolov, D. Konstantinov, L. Rybalchenko, R. Muhitovs // Procedia Comput Sci. - 2019. - № 149. - Pp. 11-18. - DOI: 10.1016/j.procs.2019.01.101 Dolgopolov P. Optimization of train routes based on neuro-fuzzy modeling and genetic algorithms / P. Dolgopolov, D. Konstantinov, L. Rybalchenko, R. Muhitovs // Procedia Comput Sci. - 2019. - № 149. - Pp. 11-18. - DOI: 10.1016/j.procs.2019.01.101 Yang L. Railway freight transportation planning with mixed uncertainty of randomness and fuzziness / L. Yang, Z. Gao, K. Li // Appl. Soft Comput. J. - 2011. - № 11.1. - Pp. 778-792. - DOI: 10.1016/j.asoc.2009.12.039. Yang L. Railway freight transportation planning with mixed uncertainty of randomness and fuzziness / L. Yang, Z. Gao, K. Li // Appl. Soft Comput. J. - 2011. - № 11.1. - Pp. 778-792. - DOI: 10.1016/j.asoc.2009.12.039.