Machine failure forewarning via phase-space dissimilarity measures.

We present a model-independent, data-driven approach to quantify dynamical changes in nonlinear, possibly chaotic, processes with application to machine failure forewarning. From time-windowed data sets, we use time-delay phase-space reconstruction to obtain a discrete form of the invariant distribution function on the attractor. Condition change in the system's dynamic is quantified by dissimilarity measures of the difference between the test case and baseline distribution functions. We analyze time-serial mechanical (vibration) power data from several large motor-driven systems with accelerated failures and seeded faults. The phase-space dissimilarity measures show a higher consistency and discriminating power than traditional statistical and nonlinear measures, which warrants their use for timely forewarning of equipment failure.

[1]  M. Rustici,et al.  Onset of chaotic dynamics in a ball mill: Attractors merging and crisis induced intermittency. , 2002, Chaos.

[2]  J. S. Lin,et al.  A nonlinear dynamic model of cutting , 1990 .

[3]  Chun Liu,et al.  An Analytical Model of Cutting Dynamics. Part 1: Model Building , 1985 .

[4]  Fraser,et al.  Independent coordinates for strange attractors from mutual information. , 1986, Physical review. A, General physics.

[5]  Takens,et al.  Estimation of the dimension of a noisy attractor. , 1994, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[6]  J. D. Smith,et al.  Machine-Tool Dynamics: An Introduction , 1970 .

[7]  Robert I. King,et al.  Handbook of High-Speed Machining Technology , 1986 .

[8]  Takens,et al.  Maximum-likelihood estimation of the entropy of an attractor. , 1994, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[9]  D. Ruelle,et al.  Ergodic theory of chaos and strange attractors , 1985 .

[10]  Lee M. Hively,et al.  Data-driven nonlinear technique for condition monitoring , 1997 .

[11]  Luis A. Aguirre,et al.  Investigating nonlinear dynamics from time series: The influence of symmetries and the choice of observables. , 2002, Chaos.

[12]  Sergiu T. Chiriacescu.  Stability in the dynamics of metal cutting , 1990 .

[13]  Lee M. Hively,et al.  ROBUST DETECTION OF DYNAMICAL CHANGE IN SCALP EEG , 1999 .

[14]  Lee M. Hively,et al.  Sensitive Measures of Condition Change in EEG Data , 1999 .

[15]  S. Lenhart,et al.  RKH Space Methods for Low Level Monitoring and Control of Nonlinear Systems II. A Vector-Case Example: The Lorenz System , 1997 .

[16]  Lm Hively,et al.  Annual Report for NERI Proposal No.2000-0109 on Forewarning of Failure in Critical Equipment at Next-Generation Nuclear Power Plants , 2001 .

[17]  Friedrich Pfeiffer,et al.  Unsteady processes in machines. , 1994, Chaos.

[18]  F. Koenigsberger,et al.  Machine Tool Structures , 1969 .

[19]  Xiao Li,et al.  Study and performance evaluation of some nonlinear diagnostic methods for large rotating machinery , 1993 .

[20]  C. E. SHANNON,et al.  A mathematical theory of communication , 1948, MOCO.

[21]  G. Stépán.  Retarded dynamical systems : stability and characteristic functions , 1989 .

[22]  Igor Grabec,et al.  Chaos generated by the cutting process , 1986 .

[23]  V. Protopopescu,et al.  Timely detection of dynamical change in scalp EEG signals. , 2000, Chaos.

[24]  Henry D. I. Abarbanel,et al.  Analysis of Observed Chaotic Data , 1995 .

[25]  D. W. Wu,et al.  An Analytical Model of Cutting Dynamics. Part 2: Verification , 1985 .

[26]  J. Tlusty,et al.  Basic Non-Linearity in Machining Chatter , 1981 .

[27]  J. S. Lin,et al.  Nonlinear dynamics of the cutting process , 1991 .

[28]  Krzysztof Jemielniak,et al.  The development of frequency and amplitude of chatter vibration , 1989 .

[29]  M. Rustici,et al.  Hyperchaotic qualities of the ball motion in a ball milling device. , 1999, Chaos.

[30]  S. Smith,et al.  Stabilizing chatter by automatic spindle speed regulation , 1992 .

[31]  Irene A. Stegun,et al.  Handbook of Mathematical Functions. , 1966 .

[32]  Steven R. Bishop,et al.  Nonlinearity and Chaos in Engineering Dynamics , 1994 .

[33]  Floris Takens,et al.  On the numerical determination of the dimension of an attractor , 1985 .

[34]  Claude E. Shannon,et al.  A mathematical theory of communication , 1948, MOCO.

[35]  Ioannis Minis,et al.  The nonlinear dynamics of metal cutting , 1992 .

[36]  I. Grabec.  Chaotic dynamics of the cutting process , 1988 .

[37]  H. Kantz,et al.  Nonlinear time series analysis , 1997 .

[38]  Lee M. Hively,et al.  Epileptic Event Forewarning From Scalp EEG , 2001, Journal of clinical neurophysiology : official publication of the American Electroencephalographic Society.

[39]  Lakhtakia,et al.  Analysis of sensor signals shows turning on a lathe exhibits low-dimensional chaos. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[40]  Giacomelli,et al.  Relationship between delayed and spatially extended dynamical systems. , 1996, Physical review letters.

[41]  S. A. Tobias.  Machine-tool vibration , 1965 .

[42]  Yoshisuke Ueda,et al.  Bifurcations in a system described by a nonlinear differential equation with delay. , 1994, Chaos.

[43]  V. Protopopescu,et al.  Detecting dynamical change in nonlinear time series , 1999 .

[44]  Lee M. Hively,et al.  Channel-consistent forewarning of epileptic events from scalp EEG , 2003, IEEE Transactions on Biomedical Engineering.