Projects

 


ChinaUSAirTrafficNetwork-web

Air Traffic Network Analysis and Delay Modeling Based on Aircraft Tracking Data

Air travel demand increases steadily in the past ten years worldwide, while Asia-Pacific registered the strongest growth among all regions. Rapid growth in flights crowded the airspace in Asia; frequent flight delay wastes time, fuel and takes its toll on economic activities and the environment.

A key limitation for existing methods and their further developments lies in availability of complete operational data. New opportunities arise from the implementation of Automatic Dependent Surveillance – Broadcast (ADS-B), a satellite-based surveillance technology which tracks and broadcasts the location of each aircraft via satellite. With ADS-B adopted by eight countries and growing, it is possible to track and analyze aircraft movement data at global scale.

The aim of this research is to develop novel methods to analyze airspace congestion in a national air traffic network using real-time aircraft tracking data.  We expect the results will allow air traffic service providers to identify existing bottlenecks and establish benchmarks for real-time monitoring; decision-makers can predict risks of flight delays under various operational scenarios, such as network structure modifications, infrastructure improvements, or changes in air traffic management.

Related papers:

Ren, P., & Li, L. (2018). Characterizing air traffic networks via large-scale aircraft tracking data: A comparison between China and the US networks. Journal of Air Transport Management, 67, 181–196. https://doi.org/10.1016/j.jairtraman.2017.12.005

Murça, MCR., Hansman, R. J., Li, L. & Ren, P., (2018). Flight Trajectory Data Analytics for Characterization of Air Traffic Flows: A Comparative Analysis of Terminal Area Operations between New York, Hong Kong and Sao Paulo. Transportation Research Part C: Emerging Technologies, 97, 324-347. https://doi.org/10.1016/j.trc.2018.10.021


ClusterAD-web

Proactive Flight Operations Monitoring Using Onboard Recorded Flight Data

Despite continuous efforts to improve safety, accidents are still occurring. Unlike decades earlier, safety incidents have been traced to the operation of the aircraft systems, or to human errors in particular, which continue to occur even as the development of hardware has advanced.

To improve pilot operations, airlines have begun an extensive monitoring of flight operations, thanks to an abundance of data recorded by the digital Flight Data Recorder (the Black Box). However, traditional data analytics methods are quickly becoming obsolete and largely irrelevant for proactive safety management. For instance, Exceedance Detection, widely used by the airline industry, can only detect hazardous behaviors from a pre-defined list comprised of “known issues of safety concerns”; it cannot respond to emerging, previously unidentified issues that are yet potentially dangerous. Another flaw is that this list is only updated after accidents, if at all, usually at the cost of lives and airline reputations.

In light of abundantly available datasets and recent advances in data analytics, there is a critical need to revamp the analytics toolset to enable the monitoring of flight operations to achieve proactive safety management. Yet, research advances in this area have been sparse due to the fact that current approaches are ill-equipped to deal with the emerging “systems” perspective of flight operations. Existing model-based or rule-based techniques focus on monitoring equipment performance but not other critical aspects of flights such as the pilot, weather, or aircraft systems. New holistic informatics approaches that treat flight operations from a systems perspective are urgently called for.

In response, this research proposes a system informatics-based approach to proactively monitor flight operations using Black Box data. With the rapid development of information technologies and the big data collected by ubiquitous sensors, system informatics are transforming how data is used for the sensing, learning, monitoring, diagnosis and prognosis of the structures as well as dynamics of systems. Thus research aims to offer tools that can identify deficiencies in flight operations, including new data-mining methods for pattern identification and anomaly detection, procedures to validate proposed methods and cross-check with existing tools, and case studies to apply these methods at airlines for safety management.

Related papers:

Zhao, W., Li, L., He, F., & Xiao, G. (2018). An Adaptive Online Learning Model for Flight Data Cluster Analysis. In the 2018 IEEE/AIAA 37th Digital Avionics Systems Conference (DASC), London, United Kingdom, 2018, pp. 1-7. https://doi.org/10.1109/DASC.2018.8569600  [PDF]

He, F., Li, L., Zhao, W., & Xiao, G. (2018). Aircraft Weight Estimation Using Quick Access Recorder Data. In the 2018 IEEE/AIAA 37th Digital Avionics Systems Conference (DASC), London, United Kingdom, 2018, pp. 1-5. https://doi.org/10.1109/DASC.2018.8569866 [PDF]

Hong, N., & Li, L. (2018). A Data-Driven Fuel Consumption Estimation Model for Airspace Redesign Analysis. In the 2018 IEEE/AIAA 37th Digital Avionics Systems Conference (DASC), London, United Kingdom, 2018, pp. 1-8. https://doi.org/10.1109/DASC.2018.8569564 [PDF] Best of Session (ATM-D: Analytics) Award

Li, L., Hansman, R. J., Palacios, R., & Welsch, R. (2016). Anomaly detection via a Gaussian Mixture Model for flight operation and safety monitoring. Transportation Research Part C: Emerging Technologies, 64, 45–57. https://doi.org/10.1016/j.trc.2016.01.007 [PDF]

Charruaud, F., & Li, L. (2015). Flight Operations Monitoring through Cluster Analysis: A Case Study. IEEE Intelligent Systems, 30(6), 24–29. https://doi.org/10.1109/MIS.2015.111 [PDF]

Li, L., Das, S., John Hansman, R., Palacios, R., & Srivastava, A. N. (2015). Analysis of Flight Data Using Clustering Techniques for Detecting Abnormal Operations. Journal of Aerospace Information Systems, 12(9), 587–598. https://doi.org/10.2514/1.I010329 [PDF]


HSR-web.png

Health Monitoring of High-Speed Train Components Using Multi-Location Sensor Vibration Data

Condition monitoring, as part of the intelligent infrastructure concept, can significantly improve the reliability, safety and efficiency of rail operations. Degradation in infrastructure can be detected before a problem occurs, without interrupting normal operations. This research contributes to the development of analytics tools and methods for condition monitoring using sensor data. The objective is to develop data-driven methods that are easy to implement and do not rely on sophisticated physics-based models, while making the methods and their results interpretable.

Related papers:

Hong, N., Li, L., Yao, W., Zhao, Y., Yi, C., Lin, J., & Tsui, K. L. (2019). High-Speed Rail Suspension System Health Monitoring Using Multi-Location Vibration Data. IEEE Transactions on Intelligent Transportation Systems. Accepted

Xu, P., Yao, W., Zhao, Y., Yi, C., Li, L., Lin, J., & Tsui, K. L. (2018). Condition monitoring of wheel wear for high-speed trains: A data-driven approach. In 2018 IEEE International Conference on Prognostics and Health Management (ICPHM) (pp. 1–8). Seattle, WA. https://doi.org/10.1109/ICPHM.2018.8448864

 


 MTRTOD-web

Urban Transportation and Social Media Data Analysis

The rise of social media and user-generated contents provided new opportunities to study the impact of urban transport system on people. Massive user data, mood, together with their geo-spatial coordinates can be easily accessed. Existing studies looked at people’s commute and activity patterns or analytics of epidemic diseases using social media data. Little has been done using geo-coded social media data to study the impact of transport systems on public sentiment. The objective of this research is to quantify the impact of urban rail transit system on occupant mood and behaviors using geo-coded social media data as well as GIS information. This research will contribute to the development of new tools to support the urban transport system planning in the digital age.

Related papers:

Huang, J., Zhang, Q., Li, L., Yang, Y., Chiaradia, A., Pryor, M., & Webster C. (2016). Happiness and High-rise Living: Sentiment Analysis of Geo-Located Twitter Data in Hong Kong’s Housing Estates. In the 52nd ISOCARP Congress. (pp. 380 – 387). Durban. South Africa.