Condition based monitoring of critical airport infrastructure: automated people mover at the Pearson International Airport in Toronto

多伦多的皮尔逊国际机场是加拿大最大的机场，每年处理的旅客超过2500万人次，预计还将大幅增长。机场的自动旅客运输系统对于在候机楼(1号航站楼和3号航站楼)之间运送旅客以及酒店和停车场等场外设施至关重要。这是一项关键的基础设施，对机场的旅客运送至关重要。该系统是由电缆驱动的系统，由轴承、齿轮和其他机电组件等复杂组件组成。为了确保该系统的顺利运行，需要持续或定期进行维护，以便能够及时检测到任何条件的变化，如部件的劣化或损坏。该项目旨在开发一种基于状态的维护系统，该系统可用于检测这些关键部件中的任何一个的早期故障(诊断)，并估计其剩余使用寿命(预测)，以便更有效地进行维护决策。在诊断方面，将开发新的时频变换来可靠地表征瞬时事件和非平稳数据，并使用振动数据的离散表示来检测异常。将使用隐马尔可夫模型和基于贝叶斯理论的模型等统计模型进行预测。

Pearson International Airport in Toronto is the largest airport in Canada, handling over 25 million passengers a year and projected to grow significantly. The automated people mover at the airport is vital to the conveyance of passengers between terminals (Terminal 1 and Terminal 3), and to off-site facilities such as hotel and parking lots. This is a critical infrastructure vital to the conveyance of passengers at the airport. This system is a cable-driven system, consisting of complex assemblages of components such as bearings, gears and other electro-mechanical components. Ensuring smooth operation of this system requires maintenance, either continuously or at regular intervals, so that any change in the condition like deterioration or damage of its components can be detected in a timely manner. This project is aimed at developing a condition based maintenance system, which can be used to detect incipient failures (diagnosis) in any of these critical components and to estimate their remaining useful life (prognosis) such that maintenance decisions can be undertaken more efficiently. For diagnostics, novel time-frequency transforms will be developed to reliably characterize transient events and non-stationary data, and to detect anomalies using discrete representations of vibration data. Statistical models such as hidden Markov models and models based on Bayesian theory will be used for prognosis.