Research Article
BibTex RIS Cite

Ticari gemilerde operasyonel elektriksel gücün tahmininde makine öğrenmesi yaklaşımı: şaft jeneratörü güç tahmini uygulaması

Year 2021, , 165 - 174, 29.11.2021
https://doi.org/10.51513/jitsa.993058

Abstract

Son yıllarda uluslararası denizcilik ve çevre otoritelerince denizcilik sektöründeki emisyonların azaltılması için son derece radikal kararlar alınmaktadır. Şirketler yürürlüğe konulan kuralları uygulamak için fayda-maliyet oranı bakımından etkin yaklaşımlarla enerji verimliliğini arttırmayı amaçlamaktadır. Bu kapsamda gemi enerji verimliliğinin ve emisyonların belirlenmesi için literatürde çeşitli yaklaşımlar oluşturulmuştur. Özellikle son beş yılda makine öğrenmesi yöntemlerinin farklı alanlarda uygulamalarının başarılı sonuçlar vermesi üzerine bu yöntemler denizcilik sektöründe emisyonların belirlenebilmesi adına da kullanılmaya başlanmıştır. Gemide yakıt tüketimi emisyonun büyük bir bölümünü oluşturmaktadır. Bu konuda literatürde çok sayıda çalışma mevcuttur. Bu çalışmada ise gemilerde toplam yakıt tüketiminin yaklaşık %10-15’lik bir kısmını oluşturan, genellikle seyir sırasında birden fazla sayıda jeneratörün çalıştırılması yerine operasyonel iş ve işlemler için kullanılan şaft jeneratörünün gücü makine öğrenmesi uygulamaları vasıtasıyla tespit edilmiştir. Çalışmada bir konteyner gemisinden alınan 750 günlük veri seti kullanılmıştır. Alınan veri seti makine öğrenmesi yöntemleri için uygun hale getirilmiştir. Bu aşamada veri seti eğitim ve test verisi olarak bilgisayar tarafından rastgele seçilerek iki kısma ayrılmıştır. Eğitim verisi ile algoritmalar eğitilmiş, test verisi ise algoritmalara öğretilmemiş ve tahmin işlemi sırasında algoritma başarılarının ölçülebilmesi adına saklanmıştır. Yapılan tahminler sonucunda Çoklu Doğrusal Regresyon algoritmasının şaft jeneratörünün elektriksel gücünün tahmini işleminde çalışmada incelenen diğer algoritmalardan daha başarılı sonuçlar verdiği tespit edilmiştir.

References

  • Alexey V. P. (2014). Innovation and design of cruise ships, Pacific Science Review, 16, 4, 280-282, 1229-5450, doi: 10.1016/j.pscr.2015.02.001.
  • Aline F. S., Nicolau A. C., André D. S. B., José E. S., Amauri G., Noé C., Bismarck L. S. (2021). Multiple linear regression approach to predict tensile properties of Sn-Ag-Cu (SAC) alloys, Materials Letters, 304, 130587, 0167-577X, doi: 10.1016/j.matlet.2021.130587.
  • Andrea C., Luca O., Francesco B., Francesca C., Mehmet A., Stefano S. (2019). Data-driven ship digital twin for estimating the speed loss caused by the marine fouling, Ocean Engineering, 186, 106063, 0029-8018, doi: 10.1016/j.oceaneng.2019.05.045.
  • Andrew C. T., Irina H., Vasco S. R., Joseph S. (2020). Maritime container shipping: Does coopetition improve cost and environmental efficiencies?. Transportation Research Part D: Transport and Environment, 87, 102507, 1361-9209, doi: 10.1016/j.trd.2020.102507.
  • Aris P., Anders H. M., Tim C. M. (2017). Applying Multi-Class Support Vector Machines for performance assessment of shipping operations: The case of tanker vessels, Ocean Engineering, 140, 1-6, 0029-8018, doi: 10.1016/j.oceaneng.2017.05.001.
  • Bilgili L. (2021). Life cycle comparison of marine fuels for IMO 2020 Sulphur Cap. Science of The Total Environment, Volume 774, 145719, 0048-9697, doi: 10.1016/j.scitotenv.2021.145719.
  • Chengpeng W., Yinxiang Z., Di Z., Tsz L. Y. (2021). Identifying important ports in maritime container shipping networks along the Maritime Silk Road. Ocean & Coastal Management, 211, 105738, 0964-5691, doi: 10.1016/j.ocecoaman.2021.105738.
  • Chi Z., Di Z., Mingyang Z., Wengang M., (2019). Data-driven ship energy efficiency analysis and optimization model for route planning in ice-covered Arctic waters, Ocean Engineering, 186, 106071, 0029-8018, doi: 10.1016/j.oceaneng.2019.05.053.
  • Dai X., Chen H., Seyed A. B., Masoud S., Mohammad A. (2019). Statistical estimation the thermal conductivity of MWCNTs-SiO2/Water-EG nanofluid using the ridge regression method, Physica A: Statistical Mechanics and its Applications, 537, 122782, 0378-4371, doi: 10.1016/j.physa.2019.122782.
  • Harilaos N. P., Thalis Z., Sotiria L. (2021). A comparative evaluation of market based measures for shipping decarbonization. Maritime Transport Research, 2, 100019, 2666-822X, doi: 10.1016/j.martra.2021.100019.
  • Jan K. (2014). Ship's Propulsion Neural Controller Main Engine-Pitch Propeller-Shaft Generator, IFAC Proceedings Volumes, 47, 1, 905-912, 1474-6670, 9783902823601, doi: 10.3182/20140313-3-IN-3024.00067
  • Jin S. P., Young-Joon S., Min-Ho H. (2019). The role of maritime, land, and air transportation in economic growth: Panel evidence from OECD and non-OECD countries. Research in Transportation Economics, 78, 100765, 0739-8859, doi: 10.1016/j.retrec.2019.100765.
  • Kanka G., Samuel G. L. (2021). Support vector machine regression for predicting dimensional features of die-sinking electrical discharge machined components, Procedia CIRP, 99, 508-513, 2212-8271, doi: 10.1016/j.procir.2021.03.109.
  • Laura F. P., Fermin M., Martín G. R., Teresa L. (2018). Dynamic mean absolute error as new measure for assessing forecasting errors, Energy Conversion and Management, 162, 176-188, 0196-8904, doi: 10.1016/j.enconman.2018.02.030.
  • Martin Ć., Shady H. E. A. A., Ahmed F. Z. (2020). On the root mean square error (RMSE) calculation for parameter estimation of photovoltaic models: A novel exact analytical solution based on Lambert W function, Energy Conversion and Management, 210, 112716, 0196-8904, doi: 10.1016/j.enconman.2020.112716.
  • Nitin D., Babita S., Chalak H.D. (2021). Gradient boosting-based regression modelling for estimating the time period of the irregular precast concrete structural system with cross bracing, Journal of King Saud University- Engineering Sciences, 1018-3639, doi: 10.1016/j.jksues.2021.08.004.
  • Pavlos K., Nikos T. (2021), Data-driven modelling of ship propulsion and the effect of data pre-processing on the prediction of ship fuel consumption and speed loss. Ocean Engineering, 222, 108616, 0029-8018, doi: 10.1016/j.oceaneng.2021.108616.
  • Paula S. Á. (2021). From maritime salvage to IMO 2020 strategy: Two actions to protect the environment, Marine Pollution Bulletin, 170, 112590, 0025-326X, doi: 10.1016/j.marpolbul.2021.112590.
  • Saim T.K., Yercan F. (2021). Comparative Cost-Effectiveness Analysis of Arctic and International Shipping Routes: A Fuzzy Analytic Hierarchy Process, Transport Policy, 0967-070X, doi: 10.1016/j.tranpol.2021.08.015.
  • Tariku S. T., Gang X., Zhishuai L., Hao T., Zhen S., Bin H., Heruye M. M. (2021). Traffic Congestion Prediction using Decision Tree, Logistic Regression and Neural Networks, IFAC-Papers On Line, 53, 5, 512-517, 2405-8963, doi: 10.1016/j.ifacol.2021.04.138.
  • Yuanqiao W., Zhongyi S., Chunhui Z., Changshi X., Qianqian C., Dong H., Yimeng Z. (2020). Automatic ship route design between two ports: A data-driven method, Applied Ocean Research, 96, 102049, 0141-1187, doi: 10.1016/j.apor.2019.102049.
  • Zhen G., Bin Y., Mengyan H., Wensi W., Yu J., Fang Z. (2021). A novel hybrid method for flight departure delay prediction using Random Forest Regression and Maximal Information Coefficient, Aerospace Science and Technology, 116, 106822, 1270-9638, doi: 10.1016/j.ast.2021.106822.
Year 2021, , 165 - 174, 29.11.2021
https://doi.org/10.51513/jitsa.993058

Abstract

References

  • Alexey V. P. (2014). Innovation and design of cruise ships, Pacific Science Review, 16, 4, 280-282, 1229-5450, doi: 10.1016/j.pscr.2015.02.001.
  • Aline F. S., Nicolau A. C., André D. S. B., José E. S., Amauri G., Noé C., Bismarck L. S. (2021). Multiple linear regression approach to predict tensile properties of Sn-Ag-Cu (SAC) alloys, Materials Letters, 304, 130587, 0167-577X, doi: 10.1016/j.matlet.2021.130587.
  • Andrea C., Luca O., Francesco B., Francesca C., Mehmet A., Stefano S. (2019). Data-driven ship digital twin for estimating the speed loss caused by the marine fouling, Ocean Engineering, 186, 106063, 0029-8018, doi: 10.1016/j.oceaneng.2019.05.045.
  • Andrew C. T., Irina H., Vasco S. R., Joseph S. (2020). Maritime container shipping: Does coopetition improve cost and environmental efficiencies?. Transportation Research Part D: Transport and Environment, 87, 102507, 1361-9209, doi: 10.1016/j.trd.2020.102507.
  • Aris P., Anders H. M., Tim C. M. (2017). Applying Multi-Class Support Vector Machines for performance assessment of shipping operations: The case of tanker vessels, Ocean Engineering, 140, 1-6, 0029-8018, doi: 10.1016/j.oceaneng.2017.05.001.
  • Bilgili L. (2021). Life cycle comparison of marine fuels for IMO 2020 Sulphur Cap. Science of The Total Environment, Volume 774, 145719, 0048-9697, doi: 10.1016/j.scitotenv.2021.145719.
  • Chengpeng W., Yinxiang Z., Di Z., Tsz L. Y. (2021). Identifying important ports in maritime container shipping networks along the Maritime Silk Road. Ocean & Coastal Management, 211, 105738, 0964-5691, doi: 10.1016/j.ocecoaman.2021.105738.
  • Chi Z., Di Z., Mingyang Z., Wengang M., (2019). Data-driven ship energy efficiency analysis and optimization model for route planning in ice-covered Arctic waters, Ocean Engineering, 186, 106071, 0029-8018, doi: 10.1016/j.oceaneng.2019.05.053.
  • Dai X., Chen H., Seyed A. B., Masoud S., Mohammad A. (2019). Statistical estimation the thermal conductivity of MWCNTs-SiO2/Water-EG nanofluid using the ridge regression method, Physica A: Statistical Mechanics and its Applications, 537, 122782, 0378-4371, doi: 10.1016/j.physa.2019.122782.
  • Harilaos N. P., Thalis Z., Sotiria L. (2021). A comparative evaluation of market based measures for shipping decarbonization. Maritime Transport Research, 2, 100019, 2666-822X, doi: 10.1016/j.martra.2021.100019.
  • Jan K. (2014). Ship's Propulsion Neural Controller Main Engine-Pitch Propeller-Shaft Generator, IFAC Proceedings Volumes, 47, 1, 905-912, 1474-6670, 9783902823601, doi: 10.3182/20140313-3-IN-3024.00067
  • Jin S. P., Young-Joon S., Min-Ho H. (2019). The role of maritime, land, and air transportation in economic growth: Panel evidence from OECD and non-OECD countries. Research in Transportation Economics, 78, 100765, 0739-8859, doi: 10.1016/j.retrec.2019.100765.
  • Kanka G., Samuel G. L. (2021). Support vector machine regression for predicting dimensional features of die-sinking electrical discharge machined components, Procedia CIRP, 99, 508-513, 2212-8271, doi: 10.1016/j.procir.2021.03.109.
  • Laura F. P., Fermin M., Martín G. R., Teresa L. (2018). Dynamic mean absolute error as new measure for assessing forecasting errors, Energy Conversion and Management, 162, 176-188, 0196-8904, doi: 10.1016/j.enconman.2018.02.030.
  • Martin Ć., Shady H. E. A. A., Ahmed F. Z. (2020). On the root mean square error (RMSE) calculation for parameter estimation of photovoltaic models: A novel exact analytical solution based on Lambert W function, Energy Conversion and Management, 210, 112716, 0196-8904, doi: 10.1016/j.enconman.2020.112716.
  • Nitin D., Babita S., Chalak H.D. (2021). Gradient boosting-based regression modelling for estimating the time period of the irregular precast concrete structural system with cross bracing, Journal of King Saud University- Engineering Sciences, 1018-3639, doi: 10.1016/j.jksues.2021.08.004.
  • Pavlos K., Nikos T. (2021), Data-driven modelling of ship propulsion and the effect of data pre-processing on the prediction of ship fuel consumption and speed loss. Ocean Engineering, 222, 108616, 0029-8018, doi: 10.1016/j.oceaneng.2021.108616.
  • Paula S. Á. (2021). From maritime salvage to IMO 2020 strategy: Two actions to protect the environment, Marine Pollution Bulletin, 170, 112590, 0025-326X, doi: 10.1016/j.marpolbul.2021.112590.
  • Saim T.K., Yercan F. (2021). Comparative Cost-Effectiveness Analysis of Arctic and International Shipping Routes: A Fuzzy Analytic Hierarchy Process, Transport Policy, 0967-070X, doi: 10.1016/j.tranpol.2021.08.015.
  • Tariku S. T., Gang X., Zhishuai L., Hao T., Zhen S., Bin H., Heruye M. M. (2021). Traffic Congestion Prediction using Decision Tree, Logistic Regression and Neural Networks, IFAC-Papers On Line, 53, 5, 512-517, 2405-8963, doi: 10.1016/j.ifacol.2021.04.138.
  • Yuanqiao W., Zhongyi S., Chunhui Z., Changshi X., Qianqian C., Dong H., Yimeng Z. (2020). Automatic ship route design between two ports: A data-driven method, Applied Ocean Research, 96, 102049, 0141-1187, doi: 10.1016/j.apor.2019.102049.
  • Zhen G., Bin Y., Mengyan H., Wensi W., Yu J., Fang Z. (2021). A novel hybrid method for flight departure delay prediction using Random Forest Regression and Maximal Information Coefficient, Aerospace Science and Technology, 116, 106822, 1270-9638, doi: 10.1016/j.ast.2021.106822.
There are 22 citations in total.

Details

Primary Language Turkish
Subjects Engineering
Journal Section Articles
Authors

Tayfun Uyanık 0000-0003-2371-8894

Publication Date November 29, 2021
Submission Date September 8, 2021
Acceptance Date September 16, 2021
Published in Issue Year 2021

Cite

APA Uyanık, T. (2021). Ticari gemilerde operasyonel elektriksel gücün tahmininde makine öğrenmesi yaklaşımı: şaft jeneratörü güç tahmini uygulaması. Akıllı Ulaşım Sistemleri Ve Uygulamaları Dergisi, 4(2), 165-174. https://doi.org/10.51513/jitsa.993058