Scalable Statistical Monitoring of Fleet Data

This paper considers the problem of fitting regression models to historical fleet data with mixed effects, which arises in the context of statistical monitoring of data from a fleet (population) of similar units. A fleet-wide extension of the multivariable statistical process control approach is used to monitor for three different types of faults: a performance anomaly, a performance shift, and an anomalous unit. Our formulation requires the solution of a least- squares problem with very large numbers of both regressors (variables) and data measurements. For problems of interest, this least-squares problem cannot be solved using standard methods. We propose a method for solving the problem that is scalable to extremely large datasets, even ones that do not fit in to the memory of a single computer system. Our method can be parallelized, but also works serially on a single processor. This approach is demonstrated in a simulated example for monitoring a fleet of aircraft from historical cruise flight data.

[1]  Michael A. Saunders,et al.  LSQR: An Algorithm for Sparse Linear Equations and Sparse Least Squares , 1982, TOMS.

[2]  Cheng Hsiao,et al.  Analysis of Panel Data , 1987 .

[3]  H. Goldstein.  Multilevel Statistical Models , 2006 .

[4]  Lois W. Sayrs.  Pooled Time Series Analysis , 1990 .

[5]  S. Rabe-Hesketh,et al.  Generalized linear latent and mixed models , 2000 .

[6]  J. Fox.  Nonparametric Regression Appendix to An R and S-PLUS Companion to Applied Regression , 2002 .

[7]  K. Meyer.  "RRGibbs" - a program for simple random regression analyses via Gibbs sampling. , 2002 .

[8]  M. Cowles.  An R and S-PLUS Companion to Applied Regression , 2003 .

[9]  Samuel Madden,et al.  Distributed regression: an efficient framework for modeling sensor network data , 2004, Third International Symposium on Information Processing in Sensor Networks, 2004. IPSN 2004.

[10]  Fugee Tsung,et al.  Using Profile Monitoring Techniques for a Data‐rich Environment with Huge Sample Size , 2005 .

[11]  Willis A. Jensen,et al.  Profile Monitoring via Linear Mixed Models , 2006 .

[12]  P. Allison.  Fixed Effects Regression Methods In SAS ® , 2006 .

[13]  H. Chipman,et al.  Profile Monitoring Using Mixed-Effects Models , 2006 .

[14]  Hillol Kargupta,et al.  A Scalable Local Algorithm for Distributed Multivariate Regression , 2008, Stat. Anal. Data Min..

[15]  Harvey Goldstein,et al.  Handbook of multilevel analysis , 2008 .

[16]  Willis A. Jensen,et al.  Profile Monitoring via Nonlinear Mixed Models , 2009 .

[17]  J. H. Shiau,et al.  Monitoring Nonlinear Profiles with Random Effects by Nonparametric Regression , 2009 .

[18]  W. Greene,et al.  计量经济分析 = Econometric analysis , 2009 .

[19]  Gonzalo Mateos,et al.  Distributed Lasso for in-network linear regression , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[20]  Peter Dalgaard,et al.  R Development Core Team (2010): R: A language and environment for statistical computing , 2010 .

[21]  Stephen P. Boyd,et al.  Detecting Aircraft Performance Anomalies from Cruise Flight Data , 2010 .