Neural Network Models to Anticipate Failures of Airport Ground Transportation Vehicle Doors

作者：Smith Alice E^*; Coit David W; Liang Yun Chia

来源：IEEE Transactions on Automation Science and Engineering, 2010, 7(1): 183-188.

DOI：10.1109/TASE.2009.2020508

• Condition monitoring
• neural network
• predictive maintenance
• preventive maintenance
• transportation

This paper describes a case study of the development and testing of a prototype system to support condition-based maintenance of the door systems of airport transportation vehicles. Every door open/close cycle produces a "signature" that can indicate the current degradation level of the door system. A combined statistical and neural network approach was used. Time, electrical current and voltage signals from the open/close cycles are processed in real-time to estimate, using the neural network, the condition of the door set relative to maintenance needs. Data collection hardware for the vehicle was designed, developed and tested to monitor door characteristics to quickly predict degraded performance, and to anticipate failures. The prototype system was installed on vehicle door sets at the Pittsburgh International Airport and tested for several months under actual operating conditions.
Note to Practitioners-This paper describes the development of an automated system that consists of hardware and software to monitor the condition of a mechanical door set on board airport ground transportation vehicles. The aim is to use the current and past conditions to estimate (using neural network predictions) when the door set is in need of scheduled maintenance. This will allowairports to achieve very high availability rates (near 100%) for these vehicles, while also achieving cost effective maintenance policies. Currently, vehicles tend to be over-maintained because of the availability levels mandated by airport authorities. This system, although in prototype form, shows the viability of an automated condition-based maintenance approach. The drawback proved to be the variability among door sets from vehicle to vehicle, which means the predictive software of the system would need to be customized for each vehicle. Several patents, both U. S. and foreign, have been granted to this automated system.

• 出版日期2010-1