Adaptive Neural Network-Based Event-Triggered Control of Single-Input Single-Output Nonlinear Discrete-Time Systems

Abstract

This paper presents a novel adaptive neural network (NN) control of single-input and single-output uncertain nonlinear discrete-time systems under event sampled NN inputs. In this control scheme, the feedback signals are transmitted, and the NN weights are tuned in an aperiodic manner at the event sampled instants. After reviewing the NN approximation property with event sampled inputs, an adaptive state estimator (SE), consisting of linearly parameterized NNs, is utilized to approximate the unknown system dynamics in an event sampled context. The SE is viewed as a model and its approximated dynamics and the state vector, during any two events, are utilized for the event-triggered controller design. An adaptive event-trigger condition is derived by using both the estimated NN weights and a dead-zone operator to determine the event sampling instants. This condition both facilitates the NN approximation and reduces the transmission of feedback signals. The ultimate boundedness of both the NN weight estimation error and the system state vector is demonstrated through the Lyapunov approach. As expected, during an initial online learning phase, events are observed more frequently. Over time with the convergence of the NN weights, the inter-event times increase, thereby lowering the number of triggered events. These claims are illustrated through the simulation results.

Strictly dissipative stabilization of multiple‐memory Markov jump systems with general transition rates: A novel event‐triggered control strategy

“…Therefore, a core problem is to achieve a controller that less transmission burden can be carried. Event‐triggered communication scheme (ETCS), in which the transmission of sampled signals between the controller and the plant occurs only when a predefined condition is satisfied rather than periodically as the case of traditional setups, has thus been introduced since it efficiently utilizes the network bandwidth, and a wealth of literature has appeared for this topic . To mention a few, in the work of Cheng et al, the problem of event‐triggered control (ETC) for a class of fuzzy MJSs with general switching policies has been investigated.…”

“…Event-triggered communication scheme (ETCS), in which the transmission of sampled signals between the controller and the plant occurs only when a predefined condition is satisfied rather than periodically as the case of traditional setups, has thus been introduced since it efficiently utilizes the network bandwidth, and a wealth of literature has appeared for this topic. [28][29][30][31][32][33][34][35][36] To mention a few, in the work of Cheng et al, 14 the problem of event-triggered control (ETC) for a class of fuzzy MJSs with general switching policies has been investigated. By designing a controller via an ETCS, Shen et al 37 have studied the stabilization problem of T-S fuzzy MJSs over a finite time interval.…”

Composite adaptive control with fast convergence for multilayer neural network

“…The most prominent benefit of NN approximation is the ease of modeling an unknown nonlinearity in many difficult practical control problems, which then results in the simplification of control synthesis. Adaptive neural control has received wide attention in recent years and applied in many applications, such as flight control, n‐link robot control, and reentry vehicle control . Furthermore, multilayer NNs have stronger representation capacity than single‐layer NNs, which have been widely used in most adaptive neural control applications.…”

A novel triggering condition of event‐triggered control based on heuristic dynamic programming for discrete‐time systems

“…Decentralized control for wireless sensor/actuator networks based on event‐triggered control was studied in the work of Mazo . In the works of Eqtami et al and Sahoo et al, event‐triggered control methods for discrete‐time systems were given. Analysis of event‐triggered control methods for linear systems was presented in the work of Heemels et al In 2012, an event‐triggered control algorithm was studied for multiagent systems in the work of Dimarogonas et al Besides, the event‐triggered scheme was used for tracking control systems in the works of Tallapragada and Chopra and Liu et al…”