Adaptive RBF Neural Network Research Articles

Active disturbance rejection control with adaptive RBF neural network for a permanent magnet spherical motor

Active disturbance rejection control with adaptive RBF neural network for a permanent magnet spherical motor

An adaptive multi-objective optimization method for structure-connection-performance design of commercial vehicle cab

A variable screening-approximate model-adaptive multi-optimization algorithm integrated method is proposed to solve the high-dimensional nonlinear problems for lightweight optimization of cabs. Firstly, a full-parametric body-in-white model of the cab is established using implicit parameterization technology, and the simulation analysis of the bending and torsional stiffness, natural modal characteristics, and passive safety are established. Then, considering the structure and connection process parameters, the design variables are screened based on a gray relational analysis-TOPSIS (GRA-TOPSIS). Finally, integrated multi-objective optimization of cab structure-connection-performance is carried out by an adaptive RBF neural network optimization method, and the optimal solution is determined by the GRA-TOPSIS method. Compared with the initial model, the mass of cab is reduced by 3.28% after optimization design. It provides guidance for the lightweight design of body.

Fuzzy-type 2 fractional fault tolerant adaptive controller for wind turbine based on adaptive RBF neural network observer

Fuzzy-type 2 fractional fault tolerant adaptive controller for wind turbine based on adaptive RBF neural network observer

Adaptive Multi-Surface Sliding Mode Control with Radial Basis Function Neural Networks and Reinforcement Learning for Multirotor Slung Load Systems

While using multirotor UAVs for transport of suspended payloads, there is a need for stability along the desired path, in addition to avoidance of any excessive payload oscillations, and a good level of precision in maintaining the desired path of the vehicle. However, due to the nonlinear and underactuated nature of the system, in addition to the presence of mismatched uncertainties, the development of a control system for this application poses an interesting research problem. This paper proposes a control architecture for a multirotor slung load system by integrating a Multi-Surface Sliding Mode Control, aided by a Radial Basis Function Neural Network, with a Deep Q-Network Reinforcement Learning agent. The former will be used to ensure asymptotic tracking stability, while the latter will be used to suppress payload oscillations. First, we will present the dynamics of a multirotor slung load system, represented here as a quadrotor with a single pendulum load suspended from it. We will then propose a control method in which a multi-surface sliding mode controller, based on an adaptive RBF Neural Network for trajectory tracking of the quadrotor, works in tandem with a Deep Q-Network Reinforcement Learning agent whose reward function aims to suppress the oscillations of the single pendulum slung load. Simulation results demonstrate the effectiveness and potential of the proposed approach in achieving precise and reliable control of multirotor slung load systems.

Adaptive RBF Neural Network Tracking Control of Stochastic Nonlinear Systems with Actuators and State Constraints

This paper investigates the adaptive neural network (NN) tracking control problem for stochastic nonlinear systems with multiple actuator constraints and full-state constraints. The issue of system full-state constraints is tackled by a generalized barrier Lyapunov function (GBLF), and the output constraints of the system are considered to be in the form of time-varying functions, which are more in line with the needs of real physical systems. The NN approximation technique is utilized to overcome the influence of the uncertainty term on controller design due to randomness. Based on the backstepping technique, a neural adaptive fixed-time tracking control strategy is designed. Under the designed control strategy, the tracking accuracy of the controlled system can reach the expectation in a fixed time. The multi-actuator constraints are converted into a generalized mathematical model to simplify the controller design process. Using the characteristics of the hyperbolic tangent function, a new function called practical virtual control signal is designed using the virtual control signal as the input. Due to the saturation constraint property of the hyperbolic tangent function, it is theoretically ensured that no state of the system exceeds the constraints through to the new form of the virtual controller. Using the adaptive controller constructed in this paper, the controlled system is semi-global fixed-time stabilized in probability (SGFSP). Finally, the effectiveness of the proposed control strategy is further verified by simulation examples.

Force Tracking Control of Lower Extremity Exoskeleton Based on a New Recurrent Neural Network

The lower extremity exoskeleton can enhance the ability of human limbs, which has been used in many fields. It is difficult to develop a precise force tracking control approach for the exoskeleton because of the dynamics model uncertainty, external disturbances, and unknown human–robot interactive force lied in the system. In this paper, a control method based on a novel recurrent neural network, namely zeroing neural network (ZNN), is proposed to obtain the accurate force tracking. In the framework of ZNN, an adaptive RBF neural network (ARBFNN) is employed to deal with the system uncertainty, and a fixed-time convergence disturbance observer is designed to estimate the external disturbance of the exoskeleton electrohydraulic system. The Lyapunov stability method is utilized to prove the convergence of all the closed-loop signals and the force tracking is guaranteed. The proposed control scheme’s (ARBFNN-FDO-ZNN) force tracking performances are presented and contrasted with the exponential reaching law-based sliding mode controller (ERL-SMC). The proposed scheme is superior to ERL-SMC with fast convergence speed and lower tracking error peak. Finally, experimental tests are conducted to verify the efficacy of the proposed controller for solving accurate force tracking control issues.

Dynamic surface adaptive RBF neural network control for a class of non‐linear uncertain systems

AbstractAn adaptive neural network dynamic surface control method for strict feedback non‐linear systems with model uncertainty is proposed in this paper. The uncertain parts are approached by RBF neural network; meanwhile, the virtual controller is designed to make system stable according to dynamic surface control. The method of Lyapunov is used to prove the stability and convergence of the system. The simulation results prove the feasibility of this controller and prove that the controller has an advantage to approach the uncertain non‐linear system and make system have well convergence and traceability.

Adaptive neural network sliding mode controller design for load following of nuclear power plant

The power control and load following of nuclear reactors have always been a research topic of concern in the field of nuclear power. In order to improve the control system performance and load following performance, this paper proposes a sliding mode control method based on adaptive RBF neural network (RBFNN) for pressurized water reactor (PWR) power control and load following. Firstly, based on the operation mechanism and energy transport process of PWR, the PWR power model is established based on the point-reactor equation. Then, based on Lyapunov stability theory, an ideal sliding mode controller is designed for a general nonlinear second-order model. Secondly, considering that some state variables in the actual PWR model cannot be directly measured, which leads to the problem that the actual control law cannot be directly applied, RBFNN is used as the controller, and its output is used to replace the actual control law and approximate the ideal control law. Adaptive algorithm is adopted to improve the approximation effect of RBFNN. Finally, the simulation results show that the proposed control method can achieve the PWR load following task well under the set working conditions, and has good robustness to disturbances. Compared with the traditional sliding mode control (TSMC) method, this method can effectively eliminate chattering phenomenon and greatly improve the control performance of the sliding mode controller.

Adaptive Robust RBF-NN Nonsingular Terminal Sliding Mode Control Scheme for Application to Snake Robot’s Head for Image Stabilization

Image stabilization is important for snake robots to be used as mobile robots. In this paper, we propose an adaptive robust RBF neural network nonsingular terminal sliding mode control to reduce swinging in the snake robot’s head while it is being driven. To avoid complex dynamic problems and reduce interference during driving, we propose a 2-DOF snake robot’s head system. We designed the control system based on the nonsingular terminal sliding mode control, which ensures a fast response and finite time convergence. To reduce chattering, we incorporated an RBF neural network that can compensate for disturbances. Additionally, we included an adaptive robust term to address the disadvantages of neural network-based control. The adaptive robust term generates control inputs based on the error and is used in conjunction with the reverse saturation function to eliminate chattering. The update law of the neural network and the adaptive robust term is designed based on Lyapunov’s theory. We proved the stability of the proposed controller by investigating finite time convergence before and after the reverse saturation function operation section. Finally, we verified the performance of the proposed controller through computer simulation. The simulation evaluates the controllers using a sinusoidal reference signal similar to snake robot movement and a mixed reference signal considering the controller’s waste case. The proposed controller has excellent tracking performance and improved chattering compared with the previous controller.

Finite-time suspension control based on GFTSM and RBFNN for low-wind-speed MVAWT

For low-wind-speed maglev vertical axis wind turbine (MVAWT), this paper proposes a finite-time suspension control strategy based on global fast terminal sliding mode (GFTSM) and adaptive RBF neural network (RBFNN). Due to the randomness of wind speed and wind direction, the actual working conditions of low-wind-speed wind farms are very complex. In order to ensure the stability of the maglev system in MVAWT and improve its anti-disturbance ability, a finite-time GFTSM controller with small chattering is firstly designed based on the dynamic suspension model considering external wind load disturbance. Secondly, the RBFNN is adopted to approximate system uncertainties and external disturbance, its network weight is adjusted according to the adaptive law, and the finite-time global fast convergence characteristic of GFTSM is also introduced into the adaptive law to improve the convergence speed of the RBFNN. Furthermore, in order to obtain the derivatives of input signals of controller and mitigate the effect of sensors’ noise, a finite-time differentiator is introduced. According to Lyapunov stability theory, the stability and finite-time convergence characteristics of the proposed control strategy are proved. Finally, simulation and experiment results show that the proposed strategy has faster dynamic response speed and stronger anti-disturbance ability.

Finite-time trajectory tracking control of quadrotor UAV via adaptive RBF neural network with lumped uncertainties

The trajectory tracking control of the quadrotor with model uncertainty and time-varying interference is studied. The RBF neural network is combined with the global fast terminal sliding mode (GFTSM) control method to converge tracking errors in finite time. To ensure the stability of the system, an adaptive law is designed to adjust the weight of the neural network by the Lyapunov method. The overall novelty of this paper is threefold, 1) Owing to the use of a global fast sliding mode surface, the proposed controller has no problem with slow convergence near the equilibrium point inherently existing in the terminal sliding mode control. 2) Benefiting from the novel equivalent control computation mechanism, the external disturbances and the upper bound of the disturbance are estimated by the proposed controller, and the unexpected chattering phenomenon is significantly attenuated. 3) The stability and finite-time convergence of the overall closed-loop system are strictly proven. The simulation results indicated that the proposed method achieves faster response speed and smoother control effect than traditional GFTSM.

A Study on the Design of Error-Based Adaptive Robust RBF Neural Network Back-Stepping Controller for 2-DOF Snake Robot’s Head

In this paper, we will propose the controller of a 2-DOF head in a snake robot for effective image data reading when the snake robot is driving, and present an error-based adaptive robust radial base function neural network back-stepping controller. The snake robot head system is a nonlinear system, and there are unmeasurable disturbances that occur while driving. To solve this problem, we use back-stepping controller and radial basis function neural network to compensate for unmeasurable disturbances to improve the steady state. In order to further compensate for the network approximation error that occurs during training or large signal changes, we use adaptive coefficients and error functions to approximate the network approximation error and design adaptive robust terms. Compared to the previous controller, the proposed controller can actively compensate for large signal changes and has the advantage of not generating residual input in a steady state. The proposed controller is based on Lyapunov function candidate to design an adaptive law and prove the system stability. The stability of the control system is proven through Lyapunov analysis and bounded. The proposed controller compared and verified the controller performance for two inputs through simulation and presented the efficiency of the controller.

Lane-Changing Strategy Based on a Novel Sliding Mode Control Approach for Connected Automated Vehicles

Safe and efficient autonomous lane changing is a key step of connected automated vehicles (CAVs), which can greatly reduce the traffic accident rate and relieve the traffic pressure. Aiming at the requirements of the smoothness and efficiency of the lane-changing trajectory of CAVs, it is necessary to design the lane changing controller to integrate the sensing, decision-making, and control tasks in the driving process. Firstly, based on the vehicle dynamics model, this paper proposes a vehicle lane-changing control strategy based on NNTSMC method (neural network enhanced non-singular fast terminal sliding mode control). The designed lane-changing controller can well realize the designed path tracking, and both lateral position and yaw angle can well track the expected value. This method enables the vehicle to control the front wheel steering angle intelligently, and the lateral acceleration during steering changes in the small scope, which ensures the steering stability of the vehicle. In this study, an improved adaptive RBF neural network with bounded mapping is designed to estimate the upper bound of the total disturbance of the system, which effectively reduces the chattering phenomenon of the control force. The Lyapunov function constructed in this study proves that the designed controller can ensure the stability of the controlled system. Finally, a comparative experiment is performed by the MATLAB/Simulink-CarSim co-simulation. Compared with SMC and TSMC (non-singular fast terminal sliding mode control), the proposed method has a performance improvement of at least 58.0% and 34.1%, respectively. The effectiveness and superiority of the proposed control method were confirmed by the experiments on the co-simulation platform.

Adaptive sliding mode control of switched linear systems using disturbance observer based on the RBF neural network

This study deals with analyze of an adaptive sliding model controller for a class of switched linear systems in the context of model reference adaptive control (MRAC) using RBF neural network (RBFNN) with the aid of disturbance observer (DO). For this purpose, adaptive laws and switching rules are designed. These are constructed based on tracking error and sliding mode control, together with using time-dependent switching conceptualizations. A DO is used to estimate the external disturbance with an adaptive RBFNN which is applied to obtain the external disturbance upper bound estimation, combined with an adaptive sliding mode control (ASMC) under the identic Lyapunov stability framework. The switching rules are based on dwell time (DT) and average dwell time (ADT) switching. The ASMC updates the system dynamics so that it assures the proposed closed-loop switched linear system stability via fast switching, resulting in the form of globally uniformly ultimately bounded (GUUB) stability. The convergence of the process of updating the weights in the adaptive RBFNN and the boundedness of updated estimates of weights are satisfied. Achieving the state tracking, robustness, reducing the chattering problem and anti-disturbance performance are the main objectives. Moreover, switching rules based on the mode-dependent approaches have been developed, which can allow faster switching as compared to switching rules based on the DT and ADT. Finally, to evaluate the efficiency of the obtained theoretical results, the controller and the proposed method have been tested on the electro-hydraulic system (EHS).

Adaptive RBF Neural Network Backstepping Control for Two-Link Robot Manipulators

In this paper, an adaptive radial basis function neural network(RBFNN) backstepping controller is presented for a two-link robot manipulator in the presence of uncertainty and external interferences. RBFNNs are applied to approximate uncertain nonlinear functions, and considering the backstepping technique, an adaptive RBFNN backstepping control strategy is proposed. It is proved by the Lyapunov function that tracking errors converge to a small neighborhood of the equilibrium point and the closed-loop system variables are bounded. The simulation results demonstrate the effectiveness of the presented design method.

Adaptive neural synchronized impedance control for cooperative manipulators processing under uncertain environments

In robotic cooperation manufacturing occasions, like grinding, assembling, welding, etc., the position-force synchronization tracking control for robotic cooperative manipulators is critical to improve the comprehensive manufacturing quality with high-precision and high-adaptability. In terms of these problems, this paper proposes an adaptive neural synchronized impedance controller (ANSIC) for cooperative manipulators processing. The proposed method includes two non-parallel control loops of the cooperative system to achieve and guarantee the desired movement trajectory and manufacturing force of the cooperation task. In the inner position tracking loop, an adaptive RBF-neural network based synchronization sliding controller is designed to simultaneously estimate the uncertain dynamic parameters of the robotic manipulators and improve the cooperative position tracking precision. In the outer force tracking loop, another RBF-neural network is applied to reform the impedance control model automatically and compensate the position and stiffness errors of the uncertain workpiece environment. Mathematical proof and experiments under various conditions are conducted. The results demonstrate the effective convergences of both the cooperative processing trajectory and force despite the uncertain environments.

Soft Sensor Modeling Method Based on Improved KH-RBF Neural Network Bacteria Concentration in Marine Alkaline Protease Fermentation Process.

Marine alkaline protease (MAP) fermentation is a complex multivariable, multi-coupled, and nonlinear process. Some unmeasured parameters will affect the quality of protease. Aiming at the problem that some parameters are difficult to be detected online, a soft sensing modeling method based on improved Krill Herd algorithm RBF neural network (LKH-RBFNN) is proposed in this paper. Based on the multi-parameter RBFNN model, the adaptive RBF neural network algorithm and control law are used to approximate the unknown parameters. The adaptive Levy flight strategy is used to improve the traditional Krill Herd algorithm, improve the global search ability of the algorithm, and avoid falling into local optimization. At the same time, the location update formula of Krill Herd algorithm is improved by using the calculation methods of similarity and agglomeration degree, and the parameters of adaptive RBFNN are optimized to improve its over correction and large amount of calculation. Finally, the soft sensing prediction model of bacterial concentration and relative active enzyme in map process based on LKH-RBFNN is established. The root mean square error and maximum absolute error of this model are 0.938 and 0.569, respectively, which are less than KH-RBFNN and PSO-RBFNN prediction models. It proves that the prediction error of LKH-RBFNN model is smaller and can meet the needs of online prediction of key parameters of map fermentation.

Research on Thermal-Hydraulic Parameter Prediction Method of the Small Lead–Bismuth Fast Reactor Core Based on Adaptive RBF Neural Network

In this study, a cladding surface temperature prediction method based on an adaptive RBF neural network was proposed. This method can significantly improve the accuracy and efficiency of the thermal safety evaluation of the lead–bismuth fast reactor. First, based on the sub-channel analysis program SUBCHANFLOW, the core sub-channel model of the small lead–bismuth fast reactor SPALLER-100 was established. Second, the calculated 2000 groups of core power distribution and coolant flow distribution data were used as training samples. The adaptive RBF neural network model was trained to predict the surface temperature of fuel elements in the lead–bismuth fast reactor. Finally, by comparison, the effectiveness and superiority of the adaptive RBF neural network method were proved. The results indicate that the relative error of the maximum temperature of the fuel cladding predicted using the adaptive RBF neural network method was less than 0.5%, which can be used for the rapid prediction of the thermal and hydraulic parameters of the lead–bismuth fast reactor.

Multi-Terrain Velocity Control of the Spherical Robot by Online Obtaining the Uncertainties in the Dynamics

One controller cannot work on multiple and unknown terrains in the velocity control of the spherical robot, because the dynamic models of the robot vary on different terrains, and unmodeled dynamics and uncertainties exist in estimated dynamic models. Based on the above problem, a new velocity controller for spherical robot is designed. This controller combines a hierarchical sliding mode controller (HSMC), an adaptive RBF neural network (RBFNN) and a variable step-size algorithm. The RBFNN is used to online estimate the uncertainties, and the Lyapunov function is utilized to design the adaptive law for the RBFNN. In order to learn the uncertainties faster, while minimizing overshoot and preventing velocity oscillations, a variable step-size algorithm is proposed. The practical experiments demonstrate that, this controller of the spherical robot achieves velocity tracking on multiple and complex terrains, while eliminating steady-state error, having a good control effect, and maintaining high stability.

An α‐variable model‐free prescribed‐time control for nonlinear system with uncertainties and disturbances

AbstractIn this article, an ‐variable model‐free prescribed‐time controller (‐MFPTC) is proposed for a nonlinear system with uncertainties and disturbances. First, an ultra‐local model is employed to formulate the plant dynamic by using input and output data. Second, to observe the state variables and compensate for the lumped uncertainties, a linear extended state observer (LESO) is designed. Then, a corresponding LESO‐based ‐fixed model‐free controller (LESO‐iPD) is proposed. Third, based on LESO‐iPD, a prescribed‐time sub‐controller (PTC) is adopted to converge tracking error within a prescribed finite time. Furthermore, an adaptive RBF neural network compensator is constructed to approximate and compensate for LESO error. Correspondingly, an ‐fixed model‐free prescribed‐time controller (‐MFPTC) is proposed. Fourth, based on ‐MFPTC, a tracking error‐based ‐variable method is applied to improve the controller performance, and an ‐variable model‐free prescribed‐time controller (‐MFPTC) is subsequently proposed. Moreover, stability and prescribed‐time convergence of closed‐loop system with ‐MFPTC are analyzed by using the Lyapunov theorem. Ultimately, to demonstrate the performance and effectiveness of the proposed control strategy, the numerical simulation with sliding mode control, LESO‐iPD, ‐MFPTC, and ‐MFPTC and co‐simulation results on quadrotor have been obtained.