Skip to Main Content
A Complex Adaptive System (CAS) is a network of communicating, intelligent agents where each agent adapts its behavior in order to collaborate with other agents to achieve overall system goals. A VFR airport is modeled where each aircraft is an intelligent agent that communicates with other aircraft in order to decide when to enter the approach corridor. The control problem to be solved in this general aviation VFR airport is the variation in aircraft speed, which results in faster aircraft overtaking slower aircraft in the approach corridor. A graphical simulation library called Operational Evaluation Modeling for Context-Sensitive Systems (OpEMCSS) has been developed to simulate complex systems, including CAS. This simulation library includes a Classifier Event Action block that is a forward chaining, expert system controller used in intelligent agent decision-making. The Classifier Event Action block can implement both crisp and fuzzy rules. In one version of the model an equation is used to predict how long an aircraft is required to wait to enter the approach corridor in order to achieve the proper time and distance separation at final approach. Comparison of the required and actual performance is used to guide rule learning in the Classifier Event Action block. This paper discusses the performance of the proposed control strategy and the fuzzy rule-learning problem.