Airline Scheduling Case Study
Case Study Using Expert Systems For Aircraft Crew Scheduling (JAL)
Japan Airlines (JAL), developed a KB system for crew scheduling
(Onodera and Mori 1991).
Fleet: Over 100 wide-body aircraft
Staff: 2200 flight crew members (pilots, co-pilots, and flight
Scheduling: The airline must produce a monthly crew allocation
Key Scheduling Constraints
- Crew training: (for aircraft and route qualification)
- Restrictions on maximum number of takeoffs and landings
- Vacation and meeting needs
- Crew turnaround times at various destinations
- Timing: The schedule for a given month needs to be produced
by the 25th of the preceding month to give adequate warning to
crew and maintenance personnel.
Before the development of the KB scheduling system, called COSMOS/AI:
- Resource - about 25 human schedulers were involved in solving
the crew allocation problem.
- Time - The JAL 747 schedule took 20 days to prepare (with overtime).
- Expertise - Schedulers needed about a year to become expert
in the problem.
- Maintenance of scheduling knowledge - updating information
on planes, crews, government regulations, etc.
In the summer of 1986, JAL investigated automated systems for
crew scheduling, resulting in:
a traditional operations research-based scheduling system (in
cooperation with Hitachi),
a knowledge-based [KB] systems approach (with NEC).
Testing of both systems began in the summer of 1988.
The KB system was selected for two major reasons:
- it produced better schedules because it was far better able
to represent complex, yet informal constraints on crew preferences
and other related factors.
- it was much easier to maintain.
The JAL scheduling system uses straightforward heuristic scheduling
It builds crew pattern blocks that include pre-flight rest time,
flight time, mandatory time at the destination, and a return flight.
These blocks are then placed on the flight schedule, along with
other time allocations like crew testing, vacations, and training,
in order of most-constrained allocations first.
When a problem occurs, time allocations are shuffled, moving the
least constrained blocks first.
The most complicated problems (the 747s) take two to three hours
for a single scheduling run.
Constraining factors which must be considered in producing the
schedule are shown in Figure 2.6. The human experts still make final
adjustments to the schedule.
The JAL system has an excellent human interface and full integration
with a mainframe-based corporate database that provides constant
updates to the KB system.
The scheduling system itself is distributed among workstations
specialized to the different aircraft types, although the workstations
themselves share information on crews trained on multiple aircraft
The KB system became fully operational in February, 1990.
- It has reduced the number of human schedulers from 25 to 19
[when JAL operations increased by five to ten percent].
- These 19 schedulers are now also assisting in other crew management
tasks, reducing the actual scheduling manpower effectively to
the equivalent of 14.
- The 747 schedule now takes a maximum of 15 days to produce,
with no overtime required, compared with 20 or more days, including
overtime, to do the job previously.
- Training time has been reduced to two months.
Overall, scheduling productivity has approximately doubled.
The system cost about 500 million yen ($3.9 million at 128 yen/$)
to build and paid for itself in direct cost savings in about 18
JAL views the harder-to-measure savings in increased crew satisfaction
and ease of maintenance as equally important.
Back To Top