Output Tracking Control via Neural Networks for High-Order Stochastic Nonlinear Systems with Dynamic Uncertainties

Adaptive neural network finite‐time command filter tracking control for nonlinear systems with multiple coupling high‐order terms and disturbances

“…Assuming that V T is stable in a small neighborhood of an ideal value, it can be regarded as a constant. Choose (𝜏, 𝛽, q) as the state variables, and introduce state transition: x 1 = 𝜏, x 2 = 𝛽, x 3 = q, u = 𝜌. then by introducing the external disturbance, then (34) can be converted into the following system:…”

“…In order to generalize the studied nonlinear systems, the nonlinear function of the system is relaxed to be an unknown smooth nonlinear function but without a upper‐bound function of a fixed structure. Then, using the approximation characteristics of RBF neural network to approach this unknown nonlinear term makes the design of controller possible. Although kinds of literature have solved the problem of unknown nonlinear terms in some systems by combining neural network control with backstepping, such as [32–34], they have not considered the differential explosion problem of high‐order systems and the problem of finite time convergence, and the tracking error accuracy caused by the introduction of filters has not been considered. However, simplifying the design process of the controller and ensuring the good performance of the system is our goal.…”

Adaptive finite-time command filter tracking control of nonlinear system with multiple high-order coupling terms and disturbances

“…(iii) Although some literatures, such as [31]- [33], have solved the problem of unknown nonlinear terms in some systems by combining neural network control with backstepping and recursion technology, but, they have not considered the differential explosion problem of high-order systems and the problem of finite time convergence, and the tracking error accuracy caused by the introduction of filters has not been considered. Therefore, this paper not only introduces command filter to solve the differential explosion problem, but also redesigns the compensation signal to make the tracking accuracy very good.…”

Adaptive Fixed-Time Control of Strict-Feedback High-Order Nonlinear Systems

“…In [20], the unknown function in the system is described by the mathematical model of an online neural network. In addition to this pioneering result, high-order system control based on neural networks has been widely developed and applied [24][25][26].…”