Incontrol theory,gain scheduling is an approach to control ofnonlinear systems that uses a family of linearcontrollers, each of which provides satisfactory control for a differentoperating point of the system.
One or moreobservable variables, called thescheduling variables, are used to determine what operating region the system is currently in and to enable the appropriate linear controller. For example, in an aircraftflight control system, thealtitude andMach number might be the scheduling variables, with different linear controller parameters available (and automatically plugged into the controller) for various combinations of these two variables. In brief, gain scheduling is a control design approach that constructs a nonlinear controller for a nonlinear plant by patching together a collection of linear controllers.
A relatively large scope state of the art about gain scheduling has been published in (Survey of Gain-Scheduling Analysis & Design, D.J.Leith, WE.Leithead).[1]
Recently, new methodologies using Machine learning, such as Adaptive control based onArtificial Neural Networks (ANN) andReinforcement Learning,[2][3][4] have been studied.