Tribology and Lubricants

Korean Tribology Society (한국트라이볼로지학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Neural Network Diagnostic System for Rotating Machinery Failure Diagnosis

신경망을 이용한 회전축의 이상상태 진단에 관한 연구

  • 유송민 (경희대학교 기계산업시스템 공학부) ;
  • 박상신 (영남대학교 기계공학부)
  • Published : 2000.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, a neural network based diagnostic system of a rotating spindle system supported by ball bearings was introduced. In order to create actual failure situations, two exemplary abnormal status were made. Out of several possible data source locations, ten measurement spots were chosen. In order to discriminate multiple abnormal status, a neural network system was introduced using back propagation algorithm updating connecting weight between each nodes. In order to find the optimal structure of the neural network system reducing the information sources, magnitude of the weight of the network was referred. Hinton diagram was used to visually inspect the least sensitive weight connecting between input and hidden layers. Number of input node was reduced from 10 to 7 and prediction rate was increased to 100%.

Keywords

References

  1. 서울대학교 박사학위 논문 축경사가 볼 베어링의 피로수명에 끼치는 영향에 관한 연구 김완두
  2. '91 대한기계학회 추계학술대회 논문집(Ⅰ) On the Monitoring of Single Crystal Diamond Tool Wear in Ultra-Precision Machining by Fuzzy Pattern Recognition Technique Tae Jo Ko;Dong Woo Cho
  3. 한국정밀공학회 논문 가공공정의 이상상태 진단을 위한 진단전문가 시스템의 개발 유송민;김영진
  4. Pattern Recognition: Statistical, Structural and Neural Approcahes R.J. Schalkoff
  5. J of Eng for Ind v.112 Sensor integration using neural network for intelligent tool conditioningmonitoring Rangwala S.;Dornfeld D,
  6. Neural Networks v.4 Back-propagation algorithm which varies the number of hydden units Hirose Y.;Yamashita K.;Hijiya S.
  7. International Workshop on Artificial Neural Networks Determining the Significance of Input Parameters Using Sensitivity Analysis A.P. Engelbrecht;I Cloete;J.M. Zurada
  8. Measurement Science and Technology v.6 no.9 Sensor Optimization using Neural Network Sensitivity R. Naimunohasses;D.M. Barnett;D.A. Green;P.R. Smith
  9. International Conference on Neural Networks Feature Extraction of Machinery Diagnosis Using Neural Network Y. Shao;K. Nezu;K. Chen;X. Pu
  10. Computers Math. Applic. v.33 no.8 Feature Saliency Measures J.M. Steppe;K.W. Bauer, Jr.
  11. IEICE Trans. INF & SYST. v.E80-D no.1 A Learning Algorithm for Fault Tolerance Feedforward Neural Networks N.C. Hammadi;H. Ito
  12. Chemometrics and Intelligent Laboratory Systems v.40 no.2 Variable Selection for Neural Networks in Multivariate Calibration F. Despagne;D. Massart