A Neural Network Approach to Condition Based Maintenance : Case Study of Airport Ground Transportation Vehicles

Abstract This paper describes a joint industry/university collaboration to develop a prototype system to provide real time monitoring of an airport ground transportation vehicle with the objectives of improving availability and minimizing field failures by estimating the proper timing for condition-based maintenance. Hardware for the vehicle was designed, developed and tested to monitor door characteristics (voltage and current through the motor that opens and closes the doors and door movement time and position), to quickly predict degraded performance, and to anticipate failures. A combined statistical and neural network approach was implemented. The neural network “learns” the differences among door sets and can be tuned quite easily through this learning. Signals are processed in real time and combined with previous monitoring data to estimate, using the neural network, the condition of the door set relative to maintenance needs. The prototype system was installed on several vehicle door sets at the Pittsburgh International Airport and successfully tested for several months under simulated and actual operating conditions. Preliminary results indicate that improved operational reliability and availability can be achieved.

[1]  William J. Kolarik,et al.  Multivariate performance reliability prediction in real-time , 2001, Reliab. Eng. Syst. Saf..

[2]  Araceli Sanchis,et al.  Hydroelectric power plant management relying on neural networks and expert system integration , 2000 .

[3]  Michael J. Roemer,et al.  Advanced diagnostics and prognostics for gas turbine engine risk assessment , 2000, 2000 IEEE Aerospace Conference. Proceedings (Cat. No.00TH8484).

[4]  Tamas Szecsi,et al.  A DC motor based cutting tool condition monitoring system , 1999 .

[5]  Vijay K. Jain,et al.  On-line monitoring of tool wear in turning using a neural network , 1999 .

[6]  MengChu Zhou,et al.  On-line robust identification of tool-wear via multi-sensor neural-network fusion , 1998 .

[7]  D. E. Dimla,et al.  Neural network solutions to the tool condition monitoring problem in metal cutting—A critical review of methods , 1997 .

[8]  A. Louis-Charles,et al.  Modeling Component Placement Errors In Surface Mount Technology Using Neural Networks , 1997, 1997 Proceedings 47th Electronic Components and Technology Conference.

[9]  T. I. El-Wardany,et al.  Tool condition monitoring in drilling using vibration signature analysis , 1996 .

[10]  Hsu-Pin Wang,et al.  Performance analysis of rotating machinery using enhanced cerebellar model articulation controller (E-CMAC) neural networks , 1996 .

[11]  J. Sottile,et al.  An overview of fault monitoring and diagnosis in mining equipment , 1994 .

[12]  Elie Bienenstock,et al.  Neural Networks and the Bias/Variance Dilemma , 1992, Neural Computation.

[13]  Mo-Yuen Chow,et al.  A neural network approach to real-time condition monitoring of induction motors , 1991 .

[14]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.

[15]  Ken-ichi Funahashi,et al.  On the approximate realization of continuous mappings by neural networks , 1989, Neural Networks.

[16]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[17]  R. A. Pawlowski,et al.  Gas Turbine Engine Health Monitoring and Prognostics , 1999 .

[18]  A. Chattopadhyay,et al.  Neural-networks-based tool wear monitoring in turning medium carbon steel using a coated carbide tool , 1997 .

[19]  D. Rumelhart.  Learning Internal Representations by Error Propagation, Parallel Distributed Processing , 1986 .