Journal of the Korean Society for Precision Engineering (한국정밀공학회지)
- Volume 12 Issue 5
- /
- Pages.57-68
- /
- 1995
- /
- 1225-9071(pISSN)
- /
- 2287-8769(eISSN)
The Numerical Solution of Time-Optimal Control Problems by Davidenoko's Method
Davidenko법에 의한 시간최적 제어문제의 수치해석해
Abstract
A general procedure for the numerical solution of coupled, nonlinear, differential two-point boundary-value problems, solutions of which are crucial to the controller design, has been developed and demonstrated. A fixed-end-points, free-terminal-time, optimal-control problem, which is derived from Pontryagin's Maximum Principle, is solved by an extension of Davidenko's method, a differential form of Newton's method, for algebraic root finding. By a discretization process like finite differences, the differential equations are converted to a nonlinear algebraic system. Davidenko's method reconverts this into a pseudo-time-dependent set of implicitly coupled ODEs suitable for solution by modern, high-performance solvers. Another important advantage of Davidenko's method related to the time-optimal problem is that the terminal time can be computed by treating this unkown as an additional variable and sup- plying the Hamiltonian at the terminal time as an additional equation. Davidenko's method uas used to produce optimal trajectories of a single-degree-of-freedom problem. This numerical method provides switching times for open-loop control, minimized terminal time and optimal input torque sequences. This numerical technique could easily be adapted to the multi-point boundary-value problems.
Keywords
- Davidenko's Method;
- Pontryagin's Maximum Principle;
- Time-optimal Control problems;
- Multipoint Boundary-value Problems