Data-driven approach to machine condition prognosis using least square regression tree

다국어 초록 (Multilingual Abstract)

Machine fault prognosis techniques have been profoundly considered in the recent time due to their substantial profit for reducing unexpected faults or unscheduled maintenance. With those techniques, the working conditions of components, the trending of fault propagation, and the time-to-failure are precisely forecasted before they reach the failure thresholds. In this work, we propose the least square regression tree (LSRT) approach, which is an extension of the

classification and regression tree (CART), in association with one-step-ahead prediction of time-series forecasting techniques to predict the future machine condition. In this technique, the number of available observations is first determined by using Cao’s method and LSRT is employed as a prediction model in the next step. The proposed approach is evaluated by real data of a low methane compressor. Furthermore, a comparative study of the predicted results obtained from CART and LSRT are carried out to prove the accuracy. The predicted results show that LSRT offers the potential for machine condition prognosis.

참고문헌 (Reference)

1 R. Johansson, "System modeling and identification" Prentice-Hall International Inc. 1993

2 J. Yang, "Short-term load forecasting with increment regression tree" 76 : 880-888, 2006

3 D. S. Vogel, "Scalable look-ahead linear regression trees" 757-764, 2007

4 R. Huang, "Residual life prediction for ball bearings based on self-organizing map and back propagation neural network methods" 21 : 193-207, 2007

5 C. S. Byington, "Prognostic enhancements to gas turbine diagnostic systems" 3247-3255, 2003

6 W. Q. Wang, "Prognosis of machine health condition using neurofuzzy system" 18 : 813-831, 2004

7 L. Cao, "Practical method for determining the minimum embedding dimension of a scalar time series" 110 : 43-50, 1997

8 J. Luo, "Model-based prognostic techniques" 330-340, 2003

9 V. T. Tran, "Machine condition prognosis based on regression trees and one-step-ahead prediction" 22 : 1179-1193, 2008

10 A. Suárez, "Globally optimal fuzzy decision trees for classification and regression" 21 : 1297-1311, 1999

11 G. Vachtsevanos, "Fault prognosis using dynamic wavelet neural networks" 857-870, 2001

12 M. B. Kennel, "Determining embedding dimension for phase-space reconstruction using a geometrical construction" 45 : 3403-3411, 1992

13 L. Breiman, "Classification and regression trees" Chapman & Hall 1984

14 M. J. Roemer, "An overview of selected prognostic technologies with application to engine health management" 2006

15 W. Wang, "An adaptive predictor for dynamic system forecasting" 21 : 809-823, 2007

16 L. Torgo, "A study on end-cut preference in least squares regression trees" University of Porto

17 C. Huang, "A stepwise regression tree for nonlinear approximation: application to estimating subpixel land cover" 24 : 75-90, 2003