Fault prediction in aircraft tires using Bayesian Networks

Aircraft tire condition and maintenance is of utmost importance since it is a part that withstands a great variety of operational conditions during the different stages of a flight. When a tire displays wear or damage signs that might compromise the aircraft’s safety, it is removed and replaced by a repaired tire. However, in order to avoid delays in the operation, it is critical that a replacement tire is readily available for installation, and that relies on the management of the resources of different maintenance sections. The management decisions of these sections are often challenged by unexpected tire failures, and the task schedules are repeatedly modified, resulting in an inefficient use of the available resources. To improve this situation, the present thesis proposes a tire failure prediction tool based on Bayesian networks. This tool outputs the amount of tires of each size that is predicted to fail in a specified three day, week of month period. The analysis is divided into two parts: firstly, an analysis of relevance using ANOVA is performed to investigate which variables impact the most the number of cycles a tire performs between failures; and secondly, a Bayesian network regression model is selected and used to perform the predictions of interest.

[1]  John K. Williams,et al.  Using random forests to diagnose aviation turbulence , 2013, Machine Learning.

[2]  Ashok N. Srivastava,et al.  Anomaly Detection and Diagnosis Algorithms for Discrete Symbol Sequences with Applications to Airline Safety , 2009, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[3]  David Heckerman,et al.  A Tutorial on Learning with Bayesian Networks , 1999, Innovations in Bayesian Networks.

[4]  G. Norman.  Likert scales, levels of measurement and the “laws” of statistics , 2010, Advances in health sciences education : theory and practice.

[5]  Thomas G. Dietterich.  What is machine learning? , 2020, Archives of Disease in Childhood.

[6]  D. Boos,et al.  How Large Does n Have to be for Z and t Intervals? , 2000 .

[7]  Trevor Hastie,et al.  An Introduction to Statistical Learning , 2013, Springer Texts in Statistics.

[8]  S. Shapiro,et al.  A Comparative Study of Various Tests for Normality , 1968 .

[9]  Michel Verleysen,et al.  Fault Prediction in Aircraft Engines Using Self-Organizing Maps , 2009, WSOM.

[10]  Ahmed Z. Al-Garni.  Neural Network-Based Failure Rate for Boeing-737 Tires , 1997 .

[11]  Stan Matwin,et al.  Data mining to predict aircraft component replacement , 1999, IEEE Intell. Syst..

[12]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[13]  A. M. Turing,et al.  Computing Machinery and Intelligence , 1950, The Philosophy of Artificial Intelligence.

[14]  Roger E. Kirk,et al.  Experimental design: Procedures for the behavioral sciences (3rd ed.). , 1995 .

[15]  Adrien-Marie Legendre,et al.  Nouvelles méthodes pour la détermination des orbites des comètes , 1970 .

[16]  Nir Friedman,et al.  Probabilistic Graphical Models - Principles and Techniques , 2009 .

[17]  D. W. Scott,et al.  Multivariate Density Estimation, Theory, Practice and Visualization , 1992 .

[18]  E. Parzen.  On Estimation of a Probability Density Function and Mode , 1962 .

[19]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[20]  Constantin F. Aliferis,et al.  An evaluation of machine-learning methods for predicting pneumonia mortality , 1997, Artif. Intell. Medicine.

[21]  Richard Honeck,et al.  Experimental Design and Analysis , 2006 .

[22]  Arthur L. Samuel,et al.  Some Studies in Machine Learning Using the Game of Checkers , 1967, IBM J. Res. Dev..

[23]  F. J. Anscombe,et al.  Distribution of the Kurtosis Statistic b2 for Normal Samples. , 1983 .

[24]  R. D'Agostino,et al.  A Suggestion for Using Powerful and Informative Tests of Normality , 1990 .

[25]  J. Bernardo.  Expected Information as Expected Utility , 1979 .

[26]  R. D'Agostino.  Transformation to normality of the null distribution of g1 , 1970 .

[27]  Raj Reddy,et al.  Automatic Speech Recognition: The Development of the SPHINX System , 2013 .

[28]  Gregory F. Cooper,et al.  A Bayesian method for the induction of probabilistic networks from data , 1992, Machine Learning.

[29]  Ahmed Z. Al-Garni,et al.  Neural network-based failure rate prediction for De Havilland Dash-8 tires , 2006, Eng. Appl. Artif. Intell..

[30]  Babak Saleh,et al.  Toward automated discovery of artistic influence , 2014, Multimedia Tools and Applications.

[31]  Dean Pomerleau,et al.  ALVINN, an autonomous land vehicle in a neural network , 2015 .

[32]  W. Hays.  Statistical theory. , 1968, Annual review of psychology.