Associate Professor Cheng-Lung Wu

Associate Professor Cheng-Lung Wu

Associate Professor
Science
School of Aviation

Dr. Wu is currently an Associate Professor at UNSW Aviation who specialises in airline operations management, scheduling, airport terminal planning, airport retail development, passenger choice behaviour, and airline big data analytics. Many of his past projects helped industry partners save millions of dollars in operating costs or enhance product sales and revenues. Dr. Wu leads a team of researchers who have specialised skills to deliver value for industry partners through world-class av...

Phone
+61-2-9385 4191
E-mail
c.l.wu@unsw.edu.au
Location
School of Aviation Old Main Building UNSW Sydney NSW 2052

My Research Interests
My research focuses on airport operations, airline operations, schedule optimisation and passenger choice behaviour modelling. I also work with industry partners on big data analytics and simulation-based projects. I published a book with Ashgate Publishing, titled 'Airline Operations and Delay Management. This book was first published in March 2010 and is available on Amazon.com. A simplified Chinese version of this book is also available via the Chinese Civil Aviation Publishing House.

My Academic Activities
I joined UNSW Aviation in 2002 after my PhD from Loughborough University (UK). I have spent time both in the public and private sectors in transport and aviation. My research is innovative and highly relevant to the industry; recent projects in my lab include:

  • Aircraft fuel uplift modelling: my team developed a data-driven and risk-based fuel uplift model for Qantas. We used aircraft QAR data and advanced risk-modelling models.
  • Passengers' online booking behaviour: my team worked with the Velocity Frequent Flyer Programme of Virgin Australia on passenger booking data, website cookie data and frequent flyer data. We developed a few models to predict passenger booking likelihood and online booking behaviour.
  • Passenger airport shopping behaviour: my team used an indoor navigation App to explore passenger movement at Taipei Airport. We tested how real-time retail marketing via smartphone push notifications could stimulate passenger shopping. 
  • Aircraft line maintenance scheduling and optimisation: my team worked with Qantas on the scheduling and optimisation of aircraft line maintenance. We also did an in-house test with Qantas on the performance of this optimisation algorithm. The results were quite significant. If you are interested, then please contact me.
  • Customer-centric air cargo network planning: this project focuses on how air cargo networks can adapt to customer demand from the perspective of sustainability.
  • AI-based aircraft maintenance scheduling: this project focuses on developing AI-based methods to solve aircraft maintenance scheduling problems.

My Professional Activities
In the past few years, I have seen the commercial implementation of my earlier Aircraft Turnaround Monitoring System (ATMS) research (article here). This prototype product, ATMS was issued a preliminary Australian patent in 2004, recognising the innovation of this framework/prototype in the airline industry. Recent commercial examples of the ATMS concept include SITA's former Workforce Mobility SolutionAlso, see another example of the ATMS framework in action from Avtura's Real-Time Aircraft Turnaround Tool.

My Research Supervision

Currently, I'm supervising three projects:

1. Customer-centric air cargo network planning on sustainability: this project is on the cross area of aviation sustainability and air cargo planning with a strong focus on customer-driven demand and sustainability drivers.

2. AI-based aircraft maintenance scheduling: this project builds AI models to approach the traditional OR-based aircraft scheduling models. Reinforcement-learning models are in particular the focus of this project.

3. Simulation and AI-based aircraft maintenance scheduling: this project uses a simulation-based model for maintenance task scheduling and uses an AI-based model to optimise task scheduling.