DOI QR코드

DOI QR Code

A Study on PCS for ML-Based Electrical Propulsion System

ML 기반의 전기추진시스템을 위한 PCS에 관한 연구

  • Lee, Jong-Hak (Marine Engineering, Korea Maritime and Ocean University) ;
  • Lee, Hun-Seok (Marine Engineering, Korea Maritime and Ocean University) ;
  • Oh, Jin-Seok (Marine Engineering, Korea Maritime and Ocean University)
  • Received : 2019.05.21
  • Accepted : 2019.07.21
  • Published : 2019.09.30

Abstract

This study proposes a PCS that enables efficient operation of seawater pumps for ships by implementing ML-based algorithms. Seawater temperature, RPM and power consumption data are acquired from two ships with PCS, analyzed with regression analysis method, and new algorithms are presented. Using the algorithms presented, Ship A saved about 36% compared to the PCS application, and ML-based algorithms in certain sea temperatures of 19 to 27 degrees Celsius and above 32 degrees Celsius were about 1% lower than Ship A's PCS. Ship B saved about 50% compared to PCS not applied, and about 2% more than Ship B's PCS in waters above $19^{\circ}C$, a specified sea temperature. The derived data can be used to suggest the optimum pump speed and sea route. In addition, the trend of acquired data can be used to infer the performance of the pump or the timing of elimination of the MGPS when efficiency becomes poor.

본 연구는 선박용 해수펌프를 ML 기반으로 한 알고리즘을 구현하여 효율적으로 운용할 수 있는 PCS를 제안한다. PCS가 탑재된 2척의 선박에서 해수온도, RPM, 전력 소모 데이터를 취득하여 회귀 분석법으로 분석하고, 새로운 알고리즘을 제시한다. 제시하는 알고리즘을 적용하였을 때 Ship A는 PCS를 적용하지 않았을 때 대비하여 약 36%를 절감하였고, 특정 해역온도인 $19{\sim}27^{\circ}C$$32^{\circ}C$ 이상의 해역에서 ML 기반의 알고리즘이 Ship A의 PCS보다 약 1% 더 절감하였다. Ship B는 PCS를 적용하지 않았을 때 대비하여 약 50%를 절감하였고, 특정 해역온도인 $19^{\circ}C$ 이상의 해역에서 Ship B의 PCS보다 약 2%더 절감하였다. 도출된 데이터를 이용하여 최적의 펌프 속도와 항로를 제안할 수 있다. 추가적으로, 취득 데이터의 추세를 활용하여 효율이 낮아졌을 시에 펌프의 성능이나 MGPS의 소제 시기를 유추할 수 있다.

Keywords

References

  1. S. G. Lee, Y. S. Jeong, S. Y. Jung, and C. G. Lee, "Characteristic Analysis of Integrated Power System and Propulsion Motor Comparison for Electric Vessels According to the Driving Condition," Journal of IKEEE, vol 15(1), pp. 96-103, Mar. 2011. https://doi.org/10.7471/IKEEE.2011.15.1.096
  2. Y. M. Kang, and J. S. Oh, "Development of Power Energy Management System for Ships including Energy Saving of Separated Load System," Journal of Information and Communication Engineering, vol. 22, no. 1, pp. 131-139, Aug. 2018.
  3. C. L. Su, W. L. Chung, and K. T. Yu, "An Energy-Savings Evaluation Method for Variable-Frequency-Drive Applications on Ship Central Cooling Systems," IEEE Transactions on Industry Applications, vol. 50, no. 2, Mar/Apr. 2014.
  4. S. H. Hong, C. H Kim, K. E. Hong, J. S. Oh, and J. U. Lee, "Application for RPM Control of Cooling Sea Water Pump in Central Cooling System for Ship," Journal of the Korean Society of Marine Engineering, vol. 2007, pp. 29-32, 2007.
  5. Oreilly & Associateslnc, Hands-On Machine Learning with Scikit-Learn and TensorFlow, 4th ed, 2017.
  6. L. Bottou, "Large-Scale Machine Learning with Stochastic Gradient Descent," Proceedings of COMPSTAT'2010, pp. 177-186, 2010.
  7. S. B. Choi, and M. H. Im, "A study on Efficient Capacity Control of a Marine Pump with the Variation of Sea Water Temperature," Journal of the Korean Society of Marine Environment & Safety, vol. 20, no. 6, pp. 788-793, Dec. 2014. https://doi.org/10.7837/kosomes.2014.20.6.788
  8. C. H. Lee, Z. W. Liu, C. N. Chen, M. Y. Cho, F. T. Lin, and J. A. Joang, "Assessment of Energy Savings With Variable Speed Drives in Ship's Cooling Pumps," IEEE TRANSACTIONS ON ENERGY CONVERSION, vol. 30, no. 4, Dec. 2015.
  9. H. G. kwon, and S. G. Choi, "A trended Kriging model with R2 indicator and application to design optimization," Aerospace Science and Technology, vol. 43, pp. 111-125, 2015. https://doi.org/10.1016/j.ast.2015.02.021