A gradient algorithm for solution of the optimal control problem for hybrid switching systems. (9th September 2020)

• Record Type: Journal Article
• Authors: Salehi, Hojat Allah; Tavassoli, Babak
• Other Names: Yuan Shuai guestEditor.; Wan Yimin guestEditor.; Zhang Lixian guestEditor.; Baldi Simone guestEditor.
• Is Part Of: Optimal control applications and methods. Volume 41:Number 6(2020)
• Page Start: 1854
• Page End: 1874
• Publication Date: 2020-09-09
• Subjects: gradient method -- hybrid minimum principle -- hybrid system -- optimal control problem -- switching system; Control theory -- Periodicals; Mathematical optimization -- Periodicals; 629.8312
• DOI: 10.1002/oca.2673
• Languages: English
• ISSNs: 0143-2087

Abstract

Summary: In this article, an algorithm is presented for solving the optimal control problem for the general form of a hybrid switching system. The cost function comprises terminal, running and switching costs. The controlled system is an autonomous hybrid switching system with jumps either at some switching times or some time varying switching manifolds. The proposed algorithm is an extension of the first‐order gradient method for the conventional optimal control problem. The algorithm requires a low computational effort. The system's dynamical equations together with a set of algebraic equations are solved at each iteration in order to find the descent direction. The convergence of algorithm is proved and examples are provided to demonstrate the efficiency of the algorithm for different types of hybrid switching system optimal control problems.