Neural Network Control Theory Research Articles

Agricultural machinery photoelectric automatic navigation control system based on back propagation neural network

So as to study the influence of speed factors on the stability of tractor automatic navigation system, combined with neural network control theory, the author proposed a dual-objective joint sliding mode control method based on lateral position deviation and heading angle deviation, using back propagation neural network to establish two-wheel tractor-path dynamics model and straight-line path tracking deviation model, the overall system simulation was carried out by using Matlab/Simulink, and the reliability of the control method was verified. The experimental results showed: when the tractor was tracked with the automatic control of linear path under the condition of the variable speed, the maximum deviation of the lateral position deviation was 12.7cm, and the average absolute deviation was kept within 4.88cm; the maximum deviation of the heading angle deviation was 5°, and the average absolute deviation was kept within 2°; the maximum value of the actual rotation angle was 3.13°, and the standard deviation of the fluctuation was within 0.84°. Under the condition of constant speed and variable speed, using the joint sliding mode control method designed by the author, the dual-objective joint control of lateral position deviation and heading angle deviation could be realized, the controlled overshoot was small, the controlled deviation was small after reaching a stable state, and the adaptability to speed factors was strong, which basically could meet the accuracy requirements of farmland operations.

RESEARCH AND APPLICATION OF SEMI-ACTIVE SUSPENSION CONTROL AND PERFORMANCE TESTING SYSTEM

Suspension is one of the important components of automobile products, and the smooth operation of the automobiles is closely related to the structure of the suspension. This paper studies the semi-active suspension control and its performance test by firstly introducing the suspension, then analyzing the neural network control basis and designing the single-chip control system, and finally formulating the performance evaluation criteria of suspension to evaluate its function. The performance of the semi-active suspension built on the basis of neural network control theory is better than that of the passive suspension and active suspension, so it can be promoted in the future application.

An Adaptive Active Queue Management Based on Model Predictive Control

In recent years, active queue management (AQM) has gained more and more attention as an important part of network congestion control. Although there are many AQM algorithms, these algorithms show weaknesses to detect and control congestion due to the complexity and dynamics of the networks. Hence, this paper proposes a new AQM algorithm based on model predictive control (MPC) theory which has been widely applied in nonlinear and time-delay systems. In order to adjust the parameters of the MPC-based AQM algorithm adaptively according to network scenario variations, the adaptive mechanism is introduced into the new algorithm, named PHAQM, by using the Hebb learning rules from the neural network control theory. The simulation results show that the algorithm is effective in avoiding network congestion. Compared to the traditional AQM schemes, such as PI, REM, and GPC algorithm, the PHAQM has a faster convergence rate and smaller queue length fluctuations and outperforms especially under dynamically changing network situations.

Research on four axis manipulator trajectory tracking Based on RBF Neural Network Algorithm

1. According to the characteristics of strong coupling tracking and highly nonlinear of four axis stamping robot, this paper based on neural network control theory proposes a manipulator trajectory tracking method based on RBF neural network. The algorithm is that the neural network as a mechanical arm joint servo controller realizes the fast tracking of mechanical arm movement posture. The simulation results show that this algorithm can improve the effectiveness and accuracy of mechanical arm trajectory tracking.

Parallel robot with fuzzy neural network sliding mode control

With the advancement in research on parallel robots, control theory is increasingly applied in the field of robotics. Owing to its robustness, sliding mode variable structure control is extensively used in parallel robots. This article presents an adaptive sliding mode control method for nonlinear systems. A parallel robot control model with adaptive fuzzy sliding mode control was designed based on a fuzzy neural network control theory, and simulation results demonstrate its effectiveness of the method.

Obstacle Avoidance Strategy of Mobile Robot Based on Wireless Sensor Networks

In order to improve the real time performance, accuracy and stability, an obstacle avoidance strategy of mobile robot based on wireless sensor networks is proposed in this paper. The algorithm is combined with fuzzy control and neural network control theory which can express those rules difficult to describe by using mathematical model. Simulation results show that the obstacle avoidance strategy can improve the overall system performance substantially and is suitable for mobile robot intelligent control.

A Multi-Axis Synchronization Control Approach Based on Adjacent Cross-Coupling Strategy

The high precision synchronized multi-axis control has become one of the key issues in modern manufacturing industry. As synchronized multi-axis control systems are nonlinear, time-variable and easily affected by disturbances, it is difficult to determine reasonable coupling control law and large amount of on-line calculation just through the existing synchronous control strategies for multi-axis system. In this paper the development status of multi-axis control synchronization control strategy is analyzed and the synchronization control algorithm is proposed based on the adjacent coupling error. The parameters of cross-coupled control are set on the basis of BP neural network control theory, which can not only reduce the tracking error, but also eliminate the synchronization error between adjacent axes. The synchronization performance of this approach is good with simple configuration. With this approach, the synchronization performance is good with simple configuration. Simulation results of the multi-axis synchronous system show that this method can effectively obtain the synchronization with a quick convergence. In the end, the multi-axis cross-coupled control approach based on BP neural networks is applied to a three-axis synchronization control system and its effectiveness is discussed.

Annoyance rate evaluation method on ride comfort of vehicle suspension system

The existing researches of the evaluation method of ride comfort of vehicle mainly focus on the level of human feelings to vibration. The level of human feelings to vibration is influenced by many factors, however, the ride comfort according to the common principle of probability and statistics and simple binary logic is unable to reflect these uncertainties. The random fuzzy evaluation model from people subjective response to vibration is adopted in the paper, these uncertainties are analyzed from the angle of psychological physics. Discussing the traditional evaluation of ride comfort during vehicle vibration, a fuzzily random evaluation model on the basis of annoyance rate is proposed for the human body’s subjective response to vibration, with relevant fuzzy membership function and probability distribution given. A half-car four degrees of freedom suspension vibration model is described, subject to irregular excitations from the road surface, with the aid of software Matlab/Simulink. A new kind of evaluation method for ride comfort of vehicles is proposed in the paper, i.e., the annoyance rate evaluation method. The genetic algorithm and neural network control theory are used to control the system. Simulation results are obtained, such as the comparison of comfort reaction to vibration environments between before and after control, relationship of annoyance rate to vibration frequency and weighted acceleration, based on ISO 2631/1(1982), ISO 2631-1(1997) and annoyance rate evaluation method, respectively. Simulated assessment results indicate that the proposed active suspension systems prove to be effective in the vibration isolation of the suspension system, and the subjective response of human being can be promoted from very uncomfortable to a little uncomfortable. Furthermore, the novel evaluation method based on annoyance rate can further estimate quantitatively the number of passengers who feel discomfort due to vibration. A new analysis method of vehicle comfort is presented.

Intelligent Control of Dynamic Performance of Vehicle Electric Power Steering and Active Suspension Integrated System

Aiming at complexity, uncertainty and non-linearity of electric power steering and active suspension integrated system, the grey prediction fuzzy neural network control strategy of dynamic performance of integrated system is proposed based on the grey prediction theory, fuzzy control theory and neural network control theory. The dynamic response of integrated system is studied. The integrated system controller with chip microprocessor LPC2138 as kernel is designed. Based on the simulation, the real vehicle road test is done. The results show that the grey prediction fuzzy neural network control strategy can carry out real time coordinated control of the integrated system of electric power steering and active suspension, the contradiction between the ride comfort and the handling stability is alleviated and the comprehensive performance is improved.

A Single Neuron Controller for Permanent Magnet Motor Servo Systems

This paper proposes a design of Single Neuron Controller(SNC), which is based on the Neural Network control theory, for a Permanent Magnet Synchronous Motor (PMSM) Servo System. The design includes the control laws decision for SNC and the simulation studies for the robust performance of system and its response behaviors. By comparison of PI Controller and Single Neuron Controller, it is concluded the designed SNC servo system has a more satisfactory performance. It is also concluded the response behaviors of system has a close relationship with the structure and parameters of SNC.