Detection and Prognostics on Low-Dimensional Systems

This paper describes the application of known and novel prognostic algorithms on systems that can be described by low-dimensional, potentially nonlinear dynamics. The methods rely on estimating the conditional probability distribution of the output of the system at a future time given knowledge of the current state of the system. We show how to estimate these conditional probabilities using a variety of techniques, including bagged neural networks and kernel methods such as Gaussian process regression (GPR). The results are compared with standard method such as the nearest neighbor algorithm. We demonstrate the algorithms on a real-world dataset and a simulated dataset. The real-world dataset consists of the intensity of an NH3 laser. The laser dataset has been shown by other authors to exhibit low-dimensional chaos with sudden drops in intensity. The simulated dataset is generated from the Lorenz attractor and has known statistical characteristics. On these datasets, we show the evolution of the estimated conditional probability distribution, the way it can act as a prognostic signal, and its use as an early warning system. We also review a novel approach to perform GPR with large numbers of data points.

[1]  Byoung-Tak Zhang,et al.  Evolving neural trees for time series prediction using Bayesian evolutionary algorithms , 2000, 2000 IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks. Proceedings of the First IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks (Cat. No.00.

[2]  Eric A. Wan,et al.  Time series prediction by using a connectionist network with internal delay lines , 1993 .

[3]  M. Way,et al.  Novel Methods for Predicting Photometric Redshifts from Broadband Photometry Using Virtual Sensors , 2006 .

[4]  Leo Breiman,et al.  Bagging Predictors , 1996, Machine Learning.

[5]  Ashok Srivastava,et al.  Improved Linear Algebra Methods for Redshift Computation from Limited Spectrum Data - II , 2008 .

[6]  Ekaterina Pavlovskaia,et al.  Chaos caused by fatigue crack growth , 2003 .

[7]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[8]  V. V. Matveev,et al.  Some Aspects of Vibration of an Elastic Body with a "Breathing" Discontinuity of Material , 2000 .

[9]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[10]  N..  DISCOVERING SYSTEM HEALTH ANOMALIES USING DATA MINING TECHNIQUES , 2006 .

[11]  Robert Tibshirani,et al.  The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd Edition , 2001, Springer Series in Statistics.

[12]  David Mackay,et al.  Gaussian Processes - A Replacement for Supervised Neural Networks? , 1997 .

[13]  Pfister,et al.  Optimal delay time and embedding dimension for delay-time coordinates by analysis of the global static and local dynamical behavior of strange attractors. , 1992, Physical review. A, Atomic, molecular, and optical physics.

[14]  A. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[15]  Olivier J. J. Michel,et al.  Comparison of several methods to predict chaotic time series , 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[16]  G. U. Yule,et al.  The Foundations of Econometric Analysis: On a Method of Investigating Periodicities in Disturbed Series, with Special Reference to Wolfer's Sunspot Numbers ( Philosophical Transactions of the Royal Society of London , A, vol. 226, 1927, pp. 267–73) , 1995 .

[17]  David Draper,et al.  Assessment and Propagation of Model Uncertainty , 2011 .

[18]  David He,et al.  Hidden semi-Markov model-based methodology for multi-sensor equipment health diagnosis and prognosis , 2007, Eur. J. Oper. Res..

[19]  J. Juang.  Applied system identification , 1994 .

[20]  Ashok N. Srivastava,et al.  Data Mining for Features Using Scale-Sensitive Gated Experts , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[21]  Tsuyoshi Mihara,et al.  Evaluation of Closed Cracks by Model Analysis of Subharmonic Ultrasound , 2004 .

[22]  Ashok Srivastava,et al.  Stable and Efficient Gaussian Process Calculations , 2009, J. Mach. Learn. Res..

[23]  Jörg D. Wichard,et al.  Iterated Time Series Prediction with Ensemble Models , 2004 .

[24]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[25]  James McNames,et al.  Local averaging optimization for chaotic time series prediction , 2002, Neurocomputing.

[26]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[27]  Geoffrey E. Hinton,et al.  Evaluation of Gaussian processes and other methods for non-linear regression , 1997 .

[28]  I. A. Viktorov.  Rayleigh and Lamb Waves , 1967 .

[29]  A. P. Bovsunovskii.  Vibrations of a Nonlinear Mechanical System Simulating a Cracked Body , 2001 .

[30]  Hans C. van Houwelingen,et al.  The Elements of Statistical Learning, Data Mining, Inference, and Prediction. Trevor Hastie, Robert Tibshirani and Jerome Friedman, Springer, New York, 2001. No. of pages: xvi+533. ISBN 0‐387‐95284‐5 , 2004 .

[31]  C. O. Weiss,et al.  Comparison of NH3 laser dynamics with the extended lorenz model , 1989 .

[32]  Tsuyoshi Mihara,et al.  Evaluation of closed cracks by analysis of subharmonic ultrasound , 2004 .

[33]  D. Worlton,et al.  ULTRASONIC TESTING WITH LAMB WAVES , 1956 .

[34]  Dmitri M. Donskoy,et al.  N-SCAN: new vibromodulation system for detection and monitoring of cracks and other contact-type defects , 2003, SPIE Smart Structures and Materials + Nondestructive Evaluation and Health Monitoring.

[35]  M. Ogorzalek,et al.  Time series prediction with ensemble models , 2004, 2004 IEEE International Joint Conference on Neural Networks (IEEE Cat. No.04CH37541).

[36]  Neal B. Abraham,et al.  Lorenz-like chaos in NH3-FIR lasers , 1995 .

[37]  R. J. Shuford,et al.  Acoustic emission signal detection by ceramic/polymer composite piezoelectrets embedded in glass‐epoxy laminates , 1996 .

[38]  Eamonn J. Keogh,et al.  A symbolic representation of time series, with implications for streaming algorithms , 2003, DMKD '03.

[39]  Eamonn J. Keogh,et al.  Dimensionality Reduction for Fast Similarity Search in Large Time Series Databases , 2001, Knowledge and Information Systems.

[40]  David He,et al.  A segmental hidden semi-Markov model (HSMM)-based diagnostics and prognostics framework and methodology , 2007 .

[41]  Tsuyoshi Mihara,et al.  FATIGUE CRACK CLOSURE ANALYSIS USING NONLINEAR ULTRASOUND , 2004 .

[42]  I. A. Viktorov.  Rayleigh and Lamb Waves: Physical Theory and Applications , 1967 .

[43]  F. Takens.  Detecting strange attractors in turbulence , 1981 .