Expert Systems Used in Aviation
Expert systems often develop around core industries where planning
and/or diagnosing complexities make human resource acquisition and
retention a major issue. The aviation industry is a perfect example.
The schedulling flights based on economics, environmental, regulatory
requirements and airway traffic parameters is extremely complex.
And mistakes extremely costly.
So too in aircraft maintenance, and once you enter the world of
military aviation - it just gets down right non-sensible to most
Expert systems typically found in the avaition industry include:
- The Aviation Expert System - used to clarify psychological assessment
issues in the field of aviation.
- GAPATS - General Aviation Pilot Advisor
and Training System
- AMES - Aircraft Maintenance Expert Systems
- Operations Management - Flights Schedulling,
Crew Rostering, Airline Gate Allocation Schedulling. See
JAL Case Study
- CASRAP - Civil Aviation Security Risk
- Anti-G control schedule for jet fighter
The General Aviation Pilot Advisor and Training System (GAPATS)
is a computerized airborne expert system developed jointly by Knowledge
Based Systems, Inc. (KBSI) and Texas A&M University (TAMU).
This system uses AI fuzzy logic to infer the flight mode of an
- sensed flight parameters
- an embedded knowledge base, and
- pilot inputs
This data is then used to assess the pilot’s flying performance
and issue recommendations for pilot actions.
GPATS improves safety by enhancing the pilot’s situational
awareness and by reducing the cost and time required to achieve
and maintain pilot proficiency, without adding to pilot workload.
information on GPATS
Aircraft Maintenance Expert Systems
AMES have been used since the early 1990's. Manual proceduresaround
aircraft maintenance are very strenuous and time consuming. Diagnosis
of aircraft malfunctions is an ideal candidate for an expert system
to assist in the diagnosis of aircraft problems.
Operations Management Decision Suppport
Airline operational planning, scheduling and controlling [OPSC]
is one of the most demanding operational scenarios. For details
on JAL Scheduling Case
Flight operational control decision-making operates within the
structured flight schedule planning [long and short run] developed
by airline competitive strategy. It must then manage the pre-described
flight schedule on a daily basis, in a highly dynamic environment.
Affects such as weather, unscheduled equipment maintenance, crew
shortages, regulatory factors, and aircraft loading can make the
profitable deployment and management of a pre-determined flight
schedule very complex.
Airline operational management systems are heuristic, experience-based
tools that apply the above factors in a real-time decision support
systems [DSS]. To stay economically competitive, airlines need decision-making
tools that can provide qualified, if not quantified information
rapidly. Examples of such systems include:
Singapore Airlines installed a commercial off the shelf AI based
DSS platform to support scheduling, crew, maintenance decisions.
In the interim, they have implemented a Crew Management System [ICMS]
- a stand alone AI based DSS, with limited integration of other
management considerations. Unix based, written in C, and supported
by an Oracle database.
Southwest developed their own Integrated Flight Tracking System
[Swift] in 1995. SWIFT allows 37 dispatchers the ability to track
2,200 daily flights, in just 45 seconds [previously a 15 minute
calculation]. Swift provides AI decision-making, removing the need
to manually filter through irrelevant information. Maintenance,
planning, and other functions have since been integrated to Swift.
Delta Airlines commissioned Transquest to develop an AI-DSS system.
This AI-DSS automatically determines the solutions to problems such
as: Which aircraft in a large holding pattern should land first?
Or; Which flight(s) should be canceled or re-routed as a result
of ATC flow control?
United Airlines initiated an AI-DSS called System Operations Advisor
[SOA] in 1992. During the next 12 month period, the SOA reduced
potential delays, on the deployment of over 2,000 flights a day
on over five continents, by 27,000 minutes, which apart from customer
convenience, translated into savings of approximately $540,000 in
related delay costs.
SOA allows the operational manager to use a "solve button"
on module programs that integrate and provide real-time decision
support for delaying a flight, swapping and canceling. Each module
acts as an ES and provides a graphical user interface (GUI) that
may be used to set up models for solving specific real-time problems.
SOA uses a mixed nodal hierarchy model, consisting of nodes and
- Nodes represent arrival, ground and departure
- Arcs indicates the direction of specific aircraft
flight flow, a direct route, maintenance, cancellation or the
swap of alternate aircraft.
Allocated costs are assigned to each arch created within each model
set calculated by SOA. The slope and flow direction of each arc
determines the overall affect of the incident on the final solution.
After pushing the solve button, SOA provides the optimal cost solution
along with other [ranked] alternatives.
Thereafter, United developed additional integrated AI-DSS modules
to assist with the management of gates, passenger flow, and overall
Cathay Pacifics hierarchy for strategic planning was structured
- Long term strategy - includes analysis of new
aircraft type, evaluation of fleet plan, effects of aircraft on
deployed routes, and new route studies
- Medium and short run planning - consist of
the same considerations conducted in long range planning with
the addition of seasonal and weekly ad hoc modifications.
For short term planning Cathay developed an AI-DSS platform called
'Interactive Flight Scheduling System' [IFSS].
IFSS is a short term planning tool that employs a rules base and
- Rules - include maintenance, ad hoc reports,
training flights, charter flights, and many other factors translated
into computational values.
- Symbolic values - are generated by the IFSS
upon the user’s request, based on commands such as: Shift
Flight, Best Fit, Exchange Flights, Cancel Flight, Upgrade Flight
(larger aircraft) or Downgrade Flight (smaller aircraft).
The IFSS also allows the user to manually Add, Delete, Move, Exchange,
and Search various flights.
A utility function on the IA processor allows the airline to pre-define
the probabilities for utility of affected operational attributes
for each calculated solution. This allows the user to determine
the highest probability of economic utility when deciding between
solutions that will all solve the defined problem. This allows the
operational manager to refine the IFSS selected solution within
real-time decision making.
Anti-G Fighter Pilot System
The high maneuverability of modern jet fighters often subjects
the pilots to high Gz acceleration. One of the adverse effects of
Gz acceleration is loss of consciousness. The Anti-G Fighter Pilot
System presents an alternative to the current protection pressure
mask and pressurized G-suit. The system used expert knowledge and
pilots' anthropometric and physiologic data to generate control
schedules of the G-suit and mask pressures of jet fighter pilots.
Civil Aviation Security Risk Assessment
AKELA has developed an expert system program [CASRAP] which enables
users to examine and assess the three major elements of risk - threats,
vulnerabilities, and assets - and then determine the impact of mitigating
measures on overall security risk. The system allows comparison
between airports in widely varying operating environments.
The program leads the user through a vulnerability assessment
which includes: physical, operational, and technical elements of
security in each of the major areas of an airport. Full
details on CASRAP [pdf]
NEXT: JAL Scheduling
Case Study Using Expert System
Back To Top