Adaptive Neural Network Control System Research Articles

Motion Trajectory Error of Robotic Arm Based on Neural Network Algorithm

In order to solve the problems of unstable motion and large trajectory tracking error of the manipulator when it is disturbed by the outside world, the author proposes an adaptive neural network manipulator motion trajectory error method. The author gives the dynamic equation of the manipulator and uses the positive feedback neural network to study the dynamic characteristics of the manipulator. An adaptive neural network control system is designed, and the stability and convergence of the closed-loop system are proved by the Lyapunov function. A schematic diagram of the manipulator model is established, and MATLAB/Simulink software is used to simulate the dynamic parameters of the manipulator. At the same time, it is compared and analyzed with the simulation results of the PID control system. Simulation results show that in robot arm 3, the expected motion trajectory is θ3 = 0.4cos(2πt), the initial condition θ(0) = [000]τ, the control parameter K = diag(40,40),40), the disturbance parameter τ’ = 20cos(πt), robot arm link parameters l1 = 0.62 m, l2 = 0.41 m, l3 = 0.34 m, m1 = 3.5, m2 = 2.5 kg, m3 = 2 kg, g = 9.82 m/s2, under t = 2s, the motion trajectory of the robotic arm is disturbed by the outside world, and the adaptive neural network is used to control the motion trajectory with a small tracking error, input torque ripple is small. Conclusion. The manipulator adopts the adaptive neural network control method, which can improve the control accuracy of the motion trajectory and weaken the jitter phenomenon of the manipulator motion.

Analysis of fault ride through the improvement of PV power plant based on artificial neural network

The increasing adoption of renewable energy sources in industrial areas, driven by the need to both obtain a grid voltage from renewable energy sources and reduce high electricity bills, has led to an increased demand for solutions that can improve the power quality of these systems. A photovoltaic power plant (PVPP) based on a dc-chopper circuit protection system is proposed for the enhancement of the power quality of PVPP. The aim of the presented protection method is to protect the panels in the PVPP from the harmful effects of the high dc voltage that occurs during grid faults. The adaptive neural network control system is applied in both the T-type inverter and the dc-chopper circuit protection system. The proposed protection system is implemented with a 250 kW PVPP to verify its validity with simulation results during grid fault. This approach can potentially improve the reliability and stability of PVPP, and contribute to the maintain of PVPP into the grid.

Accuracy Improvement of Robot Arm Trajectory based on Adaptive Neural Network Algorithm

An adaptive neural network control method was proposed to solve the problems such as unstable motion and large trajectory tracking error when the robot arm was disturbed by the external environment.The dynamic equations of the manipulator were given and the dynamic characteristics of the manipulator were studied by using the positive feedback neural network. Then the adaptive neural network control system was designed, and the stability and convergence of the closed-loop system were proved by the Lyapunov function. Later, the model diagram of the robot arm was established, and the dynamics parameters of the manipulator were simulated by MATLAB /Simulink software.At the same time, they were compared with the simulation results of the PID control system for analysis.The simulation results showed that the trajectory tracking error and input torque fluctuation were smaller when the trajectory of the robot arm was disturbed by the external world. When adopting the control method of the adaptive neural network, the robot arm could improve the control precision of the trajectory, thus reducing the jitter of the robot arm motion.

Contact pressure of high-voltage DC power relay change and life prediction and structure optimization

To effectively predict the life of high voltage dc power relay, the authors design the structure of the relay to extending its life. The contact failure mechanism of relay products is analyzed by observing the appearance of several contact failures. The electromagnetic-thermal field coupling model is established and the state of heat flow and distribution of temperature increase between electrical and thermal coupling contacts are analyzed through simulations and experiments. An adaptive neural network control system is established to conduct sample training, obtain the best stiffness coefficient of the main spring, and optimize the design of the main spring structure composed of composite springs. The action voltage, release voltage, contact resistance, contact pressure, action time, and release time as characteristic parameters, and the relative error, correlation degree, variance ratio, and small error probability of each characteristic parameter, are calculated. The precision grade index of contact resistance and action time is defined as level 1. The two characteristic parameters are selected as the prediction variables to establish the life-prediction model based on gray theory. The relative error between the predicted and test life is 5.31%–5.6%, indicating that the life-prediction model has high accuracy. The test results show that the combined main spring structure can extend the life of a relay by 18.15%.

Adaptive neural network and nonlinear electrohydraulic active suspension control system

In this article, an adaptive neural network control system is proposed for a quarter car electrohydraulic active suspension system coping with dynamic nonlinearities and uncertainties. The proposed control system is primarily designed to stabilize a sprung mass position of the quarter car electrohydraulic active suspension. Linear controllers such as the proportional–integral–differential controller have limited control performances. The limited control performances are caused by dynamic phenomena such as nonlinearity, parametric uncertainties, and stiff external disturbances. To overcome these dynamic phenomena, we propose a combined adaptive radial basis function neural network with a backstepping control system for a quarter car active suspension system. This setup can handle the unmatched model uncertainty of the system, while the adaptive neural network can take care of its unknown smoothing functions. In general, radial basis function neural network can represent a complicated function, and therefore, semi-strict-feedback dynamic systems are considered to simplify the adaptive neural network control design. Simulation results are indicated to illustrate adaptive neural network control effectiveness.

Adaptive neural network control for a nonlinear Euler‐Bernoulli beam in three‐dimensional space with unknown control direction

SummaryIn this paper, an adaptive neural network control system is developed for a nonlinear three‐dimensional Euler‐Bernoulli beam with unknown control direction. The Euler‐Bernoulli beam is modeled as a combination of partial differential equations (PDEs) and ordinary differential equations (ODEs). Adaptive radial basis function–based neural network control laws are designed to determine approximation of disturbances. A projection mapping operator is adopted to realize bounded approximation of disturbances. A Nussbaum function is introduced to compensate for the unknown control direction. The goal of this study is to suppress the vibrations of the Euler‐Bernoulli beam in three‐dimensional space. In addition, unknown control direction problem and bounded disturbances are considered to guarantee that the signals of the system are uniformly bounded. Numerical simulations demonstrate the effectiveness of the proposed method.

Improving the energy efficiency of oil production using identification and prediction of operating modes of production wells based on data analysis methods, machine learning and neural networks

Currently, there is a need to improve the systems and control of pumping equipment in the oil and gas production and oil and gas transport industries. Therefore, an adaptive neural network control system for an electric drive of a production well was developed. The task of expanding the functional capabilities of asynchronous electric motors control of the oil and gas production system using the methods of neural networks is solved. We have developed software modules of the well drive control system based on the neural network, an identification system, and a scheme to adapt the control processes to changing load parameters, that is, to dynamic load, to implement the entire system for real-time control of the highspeed process. In this paper, based on a model of an identification block that includes a multilayered neural network of direct propagation, the control of the well system was implemented. The neural network of the proposed system was trained on the basis of the error back-propagation algorithm, and the identification unit works as a forecaster of system operation modes based on the error prediction. In the initial stage of the model adaptation, some fluctuations of the torque are observed at the output of the neural network, which is associated with new operating conditions and underestimated level of learning. However, the identification object and control system is able to maintain an error at minimum values and adapt the control system to a new conditions, which confirms the reliability of the proposed scheme.

Adaptive Neural Network Control of Robot Based on a Unified Objective Bound

In the conventional adaptive neural network control of robotic manipulator, the desired position of robot end effector is specified as a point or trajectory. In addition, it is usually difficult to guarantee the transient performance of adaptive neural network control system due to the initialization error of the weight of neural network. In this paper, a new control formulation is proposed for the adaptive neural network control of robotic manipulator, which unifies existing neural network control tasks such as setpoint control, trajectory tracking control, and trajectory tracking control with prescribed performance bound. The proposed method also includes a new adaptive neural network control scheme where the objective for the robot end effector can be specified as a dynamic region, instead of the desired position or trajectory. The stability of the closed-loop system is analyzed using Lyapunov-like analysis. Experimental results are presented to illustrate the performance of the proposed approach and the energy-saving property of the proposed neural network controller with dynamic region.

Research on Adaptive Neural Network Control System Based on Nonlinear U-Model with Time-Varying Delay

U-model can approximate a large class of smooth nonlinear time-varying delay system to any accuracy by using time-varying delay parameters polynomial. This paper proposes a new approach, namely, U-model approach, to solving the problems of analysis and synthesis for nonlinear systems. Based on the idea of discrete-time U-model with time-varying delay, the identification algorithm of adaptive neural network is given for the nonlinear model. Then, the controller is designed by using the Newton-Raphson formula and the stability analysis is given for the closed-loop nonlinear systems. Finally, illustrative examples are given to show the validity and applicability of the obtained results.

Adaptive neural network control system for laser surface heat treatments

This article introduces an innovative real-time model reference neural control system developed specifically for laser surface heat treatments, which allows one to improve significantly the uniformity and final quality of the process, reducing the rejection rate and increasing the productivity and efficiency of the treatment. Basically, the proposed neural controller allows one to assimilate the complex system dynamics to a simple first order linear system, which can be easily controlled by a conventional proportional, integral and derivative controller, PID, providing exceptional results.

Adaptive Vibration Control by a Variable-Damping Dynamic Absorber Using ER Fluid

This paper describes a variable-damping dynamic absorber applying Electrorheological (ER) fluid to the damping element of a conventional-type dynamic absorber. A prototype of variable-damping dynamic absorber was constructed and its performance was verified with a three-story structural model. The special ability of the present dynamic absorber is to reduce the vibration amplitude at several frequencies by a single dynamic absorber. ER fluid is functional fluid whose yield shear stress can be changed by the applied electric field strength. Because of its peculiar property, ER fluid has been applied to various mechanical components such as shock absorbers and engine mounts for vehicles, clutches, valves, etc. One of the practical ways in applying ER fluid to mechanical components may be to expand the performance of conventional mechanical components by combining ER fluid effectively with them. In this sense, this paper shows a successful application of ER fluid to a conventional-type dynamic absorber. An adaptive neural network control system composed of a forward model network for system identification and a controller network was introduced to control the variable-damping element of the dynamic absorber. The numerical simulations show good agreements with the experimental results.

Adaptive Vibration Control System by Variable-Damping Dynamic Damper using ER Fluid.

This paper describes a variable-damping dynamic damper applying Electrorheological (ER) fluid to the damping element of a conventional-type dynamic damper. A prototype of variable-damping dynamic damper was constructed and its performance was verified with a three-story structural model. The special ability of the present dynamic damper is to reduce the vibration amplitude at several frequencies by a single dynamic damper. ER fluid is functional fluid whose yield shear stress can be changed by the applied electric field strength. Because of its peculiar property, ER fluid has been applied to various mechanical components such as shock absorbers and engine mounts for vehicles, clutches, valves, etc. One of the practical ways in applying ER fluid to mechanical components may be to expand the performance of conventional mechanical components by combining ER fluid effectively with them. In this sense, this paper shows a successful application of ER fluid to a conventional-type dynamic absorber. An adaptive neural network control system composed of a forward model network for system identification and a controller network was introduced to control the variable-damping element of the dynamic damper. The numerical simulations show good agreements with the experimental results.

A neural network control system with parallel adaptive enhancements applicable to nonlinear servomechanisms

In this paper, we present a technique for using an additional parallel neural network to provide adaptive enhancements to a basic fixed neural network-based nonlinear control system. This proposed parallel adaptive neural network control system is applicable to nonlinear dynamical systems of the type commonly encountered in many practical position control servomechanisms. Properties of the controller are discussed, and it is shown that if Gaussian radial basis function networks are used for the additional parallel neural network, uniformly stable adaptation is assured and the approximation error converges to zero asymptotically. In the paper, the effectiveness of the proposed parallel adaptive neural network control system is demonstrated in real-time implementation experiments for position control in a servomechanism with asymmetrical loading and changes in the load. >

Real-time parallel adaptive neural network control for nonlinear servomechanisms—an approach using direct adaptive techniques

In this paper, a parallel adaptive neural network control system applicable to nonlinear dynamical systems of the type commonly encountered in many practical position control servomechanisms is developed. The controller is based on the use of direct adaptive techniques and an approach of using an additional parallel neural network to provide adaptive enhancements to a basic fixed neural network-based nonlinear controller. Properties of the proposed new controller are discussed in the paper and it is shown that if Gaussian radial basis function networks are used for the additional parallel neural network, uniformly stable adaptation is assured and asymptotic tracking of the position reference signal is achieved. The effectiveness of the proposed adaptive neural network control system is demonstrated in real-time implementation experiments for position control in a servomechanism with asymmetrical loading and changes in the load.