Control system design and optimisation via genetic programming
Anna Bourmistrova · 2011
This paper describes a stochastic approach to comprehensive design of control system architecture for Unmanned Aerial Vehicle (UAV). Design and optimisation of the flight controllers is a demanding task which usually requires deep engineering knowledge of intrinsic aircraft behaviour. Evolutionary Algorithms (EAs) are known for their robustness for a wide range of optimising functions, when no a priori knowledge of the search space is available. Thus it makes evolutionary approach a promising technique to design the task controllers for complex dynamic systems such as an aircraft. This paper presents two examples of design. Firstly, design, optimisation and validation of control system for a six-degree-of-freedom nonlinear F-16 model via a combination of Genetic Algorithm (GA) and Genetic Programming (GP). Although the capability of the algorithm is enormous, the architecture of the system is limited to only proportional, integral and derivative (PID) structure because it is simple, verifiable and most applicable from control system engineer point of view. The need of a well defined approach to the control system validation is dictated by the nature of UAV application, where the major source of mission success is based on autonomous control system architecture reliability. The results show that an effective controller can be designed with little knowledge of the aircraft dynamics using appropriate evolutionary techniques. An evolved controller is evaluated and a set of reliable algorithm parameters is validated.