DOI QR코드

DOI QR Code

Operation diagnostic based on PCA for wastewater treatment

PCA를 이용한 하폐수처리시설 운전상태진단

  • 전병희 (강원대학교건설방재공학과) ;
  • 박장환 (특허청) ;
  • 전명근 (충북대학교 전기전자 컴퓨터공학부, 컴퓨터 정보통신 연구소)
  • Published : 2006.06.01

Abstract

SBR is one of the most general sewage/wastewater treatment processes and, particularly, has an advantage in high concentration wastewater treatment like sewage wastewater. A Kernel PCA based fault diagnosis system for biological reaction in full-scale wastewater treatment plant was proposed using only common bio-chemical sensors such as ORP(Oxidation-Reduction Potential) and DO(Dissolved Oxygen). During the SBR operation, the operation status could be divided into normal status and abnormal status such as controller malfunction, influent disturbance and instrumental trouble. For the classification and diagnosis of these statuses, a series of preprocessing, dimension reduction using PCA, LDA, K-PCA and feature reduction was performed. Also, the diagnosis result using differential data was superior to that of raw data, and the fusion data show better results than other data. Also, the results of combination of K-PCA and LDA were better than those of LDA or (PCA+LDA). Finally, the fault recognition rate in case of using only ORP or DO was around maximum 97.03% and the fusion method showed better result of maximum 98.02%.

축산폐수는 축사가 대부분 상수원보다 상류지역에 산재하고 있어 이를 효과적으로 관리하기 어려우나, 연속 회분식 반응기(Sequencing Batch Reactor, SBR)는 장치가 간단하고 경제성이 우수하여 축산폐수처리에서 효율적으로 적용될 수 있다. 본 연구에서는 DO(Dissolved Oxygen)과 ORP(Oxidation-Reduction Potential)을 이용하여 지식기반 고장진단 시스템을 제안하였다. 실시간으로 얻어진 ORP, DO값들을 전처리하여, [ORP], [DO]외에 [ORP DO]합성data와 ORP, DO의 특징벡터의 합에서 얻어진 fusion data의 총 4개의 data set을 이용하여 각각에 대한 진단과 분류성능을 검토하였다. 이 값을 이용하여 FCM (fuzzy C-mean) 클러스터링 한 후, K-PCA과 LDA로 차원축소시켜 특징벡터를 추출하였다. 그리고 Hamming distance로 test data와 특징벡터의 거리를 계산하여 각 class를 F1에서 F8까지 분류하였다. 그 결과 데이터를 그대로 이용하는 것 보다 차분데이터형태로 이용하는 것이 우수했으며 그 중 fusion 데이터의 결과가 다른 것들보다 향상된 결과를 보였다. 그리고 K-PCA와 LDA를 결합한 결과가 다른 방법에 비해 우수한 결과를 보였으며 fusion method를 이용한 최고인식율은 98.02%를 나타내었다.

Keywords

References

  1. S. B. Dolines et aI., 'A curve interpretation and diagnosis technique for industrial process,' IEEE Trans. Ind. Applicat., Vol. 28, no. 1, pp. 261-267, January/February 1992 https://doi.org/10.1109/28.120240
  2. J. Sottile et aI., 'An overview of fault monitoring and diagnosis in mining equipment,' IEEE Trans. Ind. Applicat., Vol. 30, no. 5, pp. 1326-1332, September/October 1994 https://doi.org/10.1109/28.315247
  3. D. Diall et aI., 'Fault detection and diagnosis in an induction machine drive: a pattern recognition approach based on Concordia stator mean current vector,' IEMDC'03, Vol. 3, pp. 1448-1453. June 2003
  4. S. Wu, and T. Chow, 'Induction machine fault detection using SOM-based RBF neural network,' IEEE Trans. Ind. Elect., Vol. 51, no. 1, pp.183-194, February 2004 https://doi.org/10.1109/TIE.2003.821897
  5. W. T. Thomson, and M. Fenger, 'Current signature analysis to detect induction motor faults,' IEEE Ind. Applicat. Magazine, pp. 26-34, July/August 2001 https://doi.org/10.1109/2943.930988
  6. Nejjari, M. H. Benbouzid, 'Monitoring and diagnosis of induction motors electrical faults using a current Park's vector pattern learning approach,' IEEE Trans. Ind. Applicat., Vol. 36, no.3, pp. 730-735, May/june 2000 https://doi.org/10.1109/28.845047
  7. Zidani et aI., 'Induction motor stator faults diagnosis by a current Concordia pattern-based fuzzy decision system,' IEEE Trans. Energy Conversion, Vol. 18, no. 4, pp, 469-475, December 2004 https://doi.org/10.1109/TEC.2003.815832
  8. A. Genovesi, J. Harmand and J. Steyer, 'A fuzzy logic based diagnosis system for the on-line supervision of an anaerobic digester pilot-plant,' Biochemical Engineering Journal, Vol. 3, pp. 171-183, 1999 https://doi.org/10.1016/S1369-703X(99)00015-7
  9. K. Szafnicki, C. Narce and J. Bourgois, 'Towards an integrated tool for control, supervision and operator training-application to industrial wastewater detoxication plants,' Control Engineering Practice, Vol. 13, pp. 729-738, 2005 https://doi.org/10.1016/j.conengprac.2004.07.002
  10. K. L. Norcross, 'Sequencing Batch Reactor-An Overview,' Wat. Sci. & Tech., Vol. 26, pp. 2523-2526, 1992
  11. B. H. juri, D. H. Kim, E. H. Choi, H. Bae, S. S. Kim and C. W. Kim, 'Control of SBR Operation for Piggery Wastewater Treatment with DO and ORP,' J. of Kor. Soc. of Env. Eng. Vol. 18, pp. 545-551, 2002
  12. K. M .Poo, J. H. Im, B .H. Jun, J. R. Kim, I. S. Hwang, K. S. Choi and C. W. Kim, 'Full-cyclic control strategy of SBR for nitrogen removal in strong wastewater using common sensors' Wat. Sci. Tech. Vol. 53, No 4-5, pp. 151-160, 2005
  13. B. H. Jun, K. M. Poo, E. H. Choi, H. I. Lee and C. W. Kim, 'High-performance SBR Operation by Optimized Feeding Method of External Carbon Source for Piggery Wastewater Treatment,' J. of Kor. Soc. of Env. Eng. Vol. 24, pp. 1957-1964, 2002
  14. R. O. Duda, P. E. Hart and D. G. Stork, Pattern classification, Wiley Interscience, 2001