On-line Prediction Model of Oil Content in Oil Discharge Monitoring Equipment Using Parallel TSK Fuzzy Modeling

병렬구조 TSK 퍼지 모델을 이용한 선박용 기름배출 감시장치의 실시간 기름농도 예측모델

  • 백경동 (부산대학교 전자전기공학부) ;
  • 조재우 (부산대학교 전자전기공학부) ;
  • 최문호 (부산대학교 전자전기공학부) ;
  • 김성신 (부산대학교 전자전기공학부)
  • Published : 2010.01.01


The oil tanker ship over 150GRT must equip oil content meter which satisfy requirements of revised MARPOL 73/78. Online measurement of oil content in complex samples is required to have fast response, continuous measurement, and satisfaction of ${\pm}10ppm$ or ${\pm}10%$ error in this field. The research of this paper is to develop oil content measurement system using analysis of light transmission and scattering among turbidity measurement methods. Light transmission and scattering are analytical methods commonly used in instrumentation for online turbidity measurement of oil in water. Gasoline is experimented as a sample and the oil content approximately ranged from 14ppm to 600ppm. TSK Fuzzy Model may be suitable to associate variously derived spectral signals with specific content of oil having various interfering factors. Proposed Parallel TSK Fuzzy Model is reasonably used to classify oil content in comparison with other models. Those measurement methods would be effectively applied and commercialized to oil content meter that is key components of oil discharge monitoring control equipment.


  1. IMO MEPC, "How to do it, manual ofthe practical implication of ratifying and implementing MARPOL 73/78," International Maritime Organization, London, 1993.
  2. IMO MEPC, "Revised guidelines and specifications for oil discharge monitoring and control systems for oil tankers," International Maritime Organization, London, 2003.
  3. "해양오염 방지설비 형식 승인을 위한 성능시험 및 검정기준", 국토해양부 고시 제2009-480호, 국토해양부, 2009.
  4. R. Jethra, "Turbidity measurement," ISA Transactions, vol. 32, pp. 397-405, 1993.
  5. D. Bivolaru, P. M. Danehy, and J. W. Lee, "Intracavity Rayleigh/Mie scattering for multi-point two-component velocity measurement," NASA Langley Research Center, 2005.
  6. L. V. Wang, H.-I. Wu, Biomedical Optics: Principles and Imaging, Wiley-Interscience, 2007.
  7. P. J. Huber, "Robust estimation of a location parameter," Annals of Mathematical Statistics, vol. 35, pp. 73-101, 1964.
  8. U. Caydas, A. Hascahk, and S. Ekici, "An adaptive neurofuzzy inference system (ANFIS) model for wire-EDM," Expert Systems with Applications, vol. 36, pp. 6135-6139, 2009.
  9. J. S. R. Jang, "ANFIS: Adaptive-Network-Based Fuzzy Inference System," IEEE Trans. on Systems Man and Cybernetics, vol. 23, no. 3, Jun. 1993.
  10. 조재우, 백경동, 김성신 "적응형 뉴로퍼지(ANFIS) 모델을 이용한 기름농도 능동 검출," 2009 한국자동제어학술회의(KACC2009), pp. 740-743, Sep. 2009.