Introduction to Composite Learning

In the proposed control method, an interval type-2 fuzzy neural network (IT2FNN) is first developed for each UA to approximate the unknown term associated with the loss-of-effectiveness faults in the distributed error dynamics, and then a disturbance observer (DO) is proposed to compensate for the approximation error and bias fault encountered by each UA, such that the composite learning strategy composed of the IT2FNN and the DO is obtained for each UA.

In the adaptive learning control design, to obtain the evaluation information of uncertain learning, the prediction error is constructed based on the composite learning scheme.

Besides, the detailed implementation process of the composite learning laws adopted for enhancing the radial basis function neural network is presented.

A composite learning factor (CLF) was employed which assigned different learning factor to three types of layers: frozen layers, middle layers, and new layers.

To address the uncertainty, considering the periodic tracking property of MEMS gyroscopes, a composite learning mechanism driven by the learning performance evaluation signal is applied to learn the system dynamics.

In addition, a novel composite learning-based controller for each turbine is designed to achieve closed-loop yaw tracking, which can guarantee the exponential convergence of tracking errors in the presence of uncertainties of yaw actuators.

,is paper investigates a composite learning prescribed performance control (PPC) scheme for uncertain strict-feedback system.

Once the states run out of the domain of intelligent control, the robust item will pull the states back while inside the neural working domain, the composite learning is developed to achieve higher approximation precision by building the prediction error for the weight update.

In this paper, a composite learning tracking control scheme is developed for underactuated autonomous underwater vehicles (AUVs) in the presence of unknown dynamics and time-varying disturbances.

In this paper, we propose a learning approach for interval Fuzzy Logic Systems (FLSs) to end up with models that are capable to cover an expected amount of uncertainty with a high accuracy by exploiting a composite learning method with quantile regression.

This article investigates the composite learning fuzzy control for a class of stochastic nonlinear strict-feedback systems subject to dynamics uncertainty.

This paper investigates the robust adaptive neural control of nonminimum phase hypersonic flight vehicle using composite learning.

Yet we propose a composite learning model (CLM) that combines the strength of broad learning and conventional deep learning techniques to identify the fault types of underactuated surface vessels (USV).

The proposed scheme can guarantee at least the similar control performance compared with its continuous alternatives while it importantly reduces the communication burden through the ETC and can enhance the estimation accuracy of the observer by applying the composite learning.

This paper proposes a composite learning adaptive position tracking controller with improved parameter convergence for electro-hydraulic servo systems.

In this article, a novel composite learning control scheme based on nonlinear disturbance observer (NDOB), neural network (NN), and model-based state observer (MSOB) is investigated for the manned submersible vehicle.

In this brief, a novel OHD-driven parameter estimation scheme that exploits only partial OHD is presented to improve parameter convergence and is incorporated with direct adaptive control to construct a composite learning control strategy.

This paper considers the tracking control of fractional-order nonlinear systems (FONSs) in triangular form with actuator faults by means of sliding mode control (SMC) and composite learning SMC (CLSMC).

This paper investigates a fault-tolerant control of the hypersonic flight vehicle using back-stepping and composite learning.

Furthermore, the composite learning, which combines nonlinear disturbance observer and direct adaptive neural control, is applied to improve the approximation performance and enhance system robustness.

To improve the NNs learning rapidity, the prediction error which reflect the learning performance is constructed, further the updating law is designed utilizing the composite learning technique.

In this study, a composite learning control strategy is proposed for a class of strict-feedback nonlinear systems with mismatched uncertainties, where raised-cosine radial basis function NNs with compact supports are applied to approximate system uncertainties.

Moreover, the composite learning method is utilized to estimate unknown nonlinear functions.

Considering that the estimated parameters convergence cannot be achieved in the absence of persistent excitation (PE) conditions, the composite learning update law of the weight matrix in the NN is adopted to guarantee the parameters convergence under interval excitation (IE) conditions which is easier to reach.

The modeling accuracy is theoretically guaranteed by a composite learning technique, it explores both online historical data and instantaneous data to achieve NN weight convergence under a much weaker interval-excitation condition than the stringent persistent-excitation condition.