TY - JOUR
T1 - Event-triggered constrained control using explainable global dual heuristic programming for nonlinear discrete-time systems
AU - Sun, Bo
AU - van Kampen, Erik Jan
PY - 2022
Y1 - 2022
N2 - This paper develops an event-triggered optimal control method that can deal with asymmetric input constraints for nonlinear discrete-time systems. The implementation is based on an explainable global dual heuristic programming (XGDHP) technique. Different from traditional GDHP, the required derivatives of cost function in the proposed method are computed by explicit analytical calculations, which makes XGDHP more explainable. Besides, the challenge caused by the input constraints is overcome by the combination of a piece-wise utility function and a bounding layer of the actor network. Furthermore, an event-triggered mechanism is introduced to decrease the amount of computation, and the stability analysis is provided with fewer assumptions compared to most existing studies that investigate event-triggered discrete-time control using adaptive dynamic programming. Two simulation studies are carried out to demonstrate the applicability of the constructed approach. The results present that the developed event-triggered XGDHP algorithm can substantially save the computational load, while maintain comparable performance with the time-based approach.
AB - This paper develops an event-triggered optimal control method that can deal with asymmetric input constraints for nonlinear discrete-time systems. The implementation is based on an explainable global dual heuristic programming (XGDHP) technique. Different from traditional GDHP, the required derivatives of cost function in the proposed method are computed by explicit analytical calculations, which makes XGDHP more explainable. Besides, the challenge caused by the input constraints is overcome by the combination of a piece-wise utility function and a bounding layer of the actor network. Furthermore, an event-triggered mechanism is introduced to decrease the amount of computation, and the stability analysis is provided with fewer assumptions compared to most existing studies that investigate event-triggered discrete-time control using adaptive dynamic programming. Two simulation studies are carried out to demonstrate the applicability of the constructed approach. The results present that the developed event-triggered XGDHP algorithm can substantially save the computational load, while maintain comparable performance with the time-based approach.
KW - Adaptive dynamic programming
KW - Asymmetric input constraints
KW - Event-triggered control
KW - Explainable artificial intelligence
KW - Global dual heuristic programming
UR - http://www.scopus.com/inward/record.url?scp=85118572957&partnerID=8YFLogxK
U2 - 10.1016/j.neucom.2021.10.046
DO - 10.1016/j.neucom.2021.10.046
M3 - Article
AN - SCOPUS:85118572957
SN - 0925-2312
VL - 468
SP - 452
EP - 463
JO - Neurocomputing
JF - Neurocomputing
ER -