Minrui Fei

Genetic algorithm based neuro-fuzzy network adaptive PID control and its applications

It is difficult to satisfy most of the performance targets by using the PID control law only, if the plants are the processes with uncertain time-delay, varying parameters and non-linearity. For this reason a genetic algorithm based neuro-fuzzy network adaptive PID controller is proposed in this paper. The neuro-fuzzy network is used to amend the parameters of the PID controller online, the global optimal parameters of the network are found with a high speed, and the improved genetic algorithm is introduced to overcome the local optimum defect of the BP algorithm. Finally, the simulation experiment of the control method on the tobacco-drying control process is performed. The simulation results demonstrate that this kind of control method is effective.

Analysis on network-induced delays in networked learning based control systems

Local controller and remote learning device are connected through communication network in Networked Learning based Control Systems (NLCSs). Network-induced delays are inevitable during data transmission, and will deteriorate the real-time transmission of learning result from learning device to controller and even destabilize the entire system. This paper deals with the delays in NLCSs. The sources of delays are discussed and the possibility of reducing all delays into an equivalent delay is proposed. Finally, experimental measurements for that equivalent delay on Ethernet are conducted.

Fuzzy supervisor based multiple model adaptive controller for systems with uncertain parameters

This paper presents a kind of multiple model adaptive controller based on fuzzy supervisor for the control system of robots with uncertain parameters. The controller uses the structure of model reference control system and adopts a fuzzy supervisor who controls the switching of respective control models instead of tuning dynamically the parameters of controller to tune control input. So a lot of calculations are avoided for tuning the parameters of controller dynamically and the dynamic response characteristics of common multiple model adaptive controller are optimized. Also performance of the whole system is improved by using the optimization based GA. Simulation results are shown to demonstrate the effectiveness of that this kind of control scheme.

Investigation and Implementation of Field Communication Open Policy

Abstract This paper presents latest research, development and realization of the Field Communication Open Policy (FCOP) during latest fast and strong development of open protocol tendency of lowest layer network (fieldbus) for factory automation, CIMS, DCCS and PLC systems etc. nowadays. The FCOP and its support techniques consist of two main parts: a) the technique of Graphic-oriented Programmable Protocol Interface(GPPI); b) the technique of multiprotocol configuration Field Communication Control Device(FCCD). The practical operation shows that FCOP has correct philosophy and realistic policy.

Tuning parameters of PID controller based on fuzzy logic controlled genetic algorithms

To solve the problem of tuning parameters of PID controller using the conventional genetic algorithm, an improved genetic algorithm based on fuzzy inference is proposed. On the basis of generalizing heuristic knowledge about crossover and mutation operations, a fuzzy controller is designed to adaptively adjust the crossover rate and mutation rate. The fuzzy logic controlled genetic algorithm (FCGA) improves global optimization ability of the standard genetic algorithm. We apply it to adaptive PID controller. The comparison between the FCGA and the SGA is performed, which demonstrates that the FCGA has much better capability of parameters optimization and convergent speed, and it can also fulfill the requirement of real-time control.

Design of Fuzzy-logic-control System Based on Gaussian-basis-function Neural Network

ABSTRACT In this paper, a fuzzy logic system is constructed by Gaussian basis function neural network. In the process of design, a learning rate self-adjusting algorithm is presented to guarantee that the basis function has a reasonable distribution, meantime to reduce the disturbance of noise and improve the control precision. Finally, a non linear object is simulated by this approach. The results demonstrate that: compared vith normal fuzzy logic control system, this self-learning fuzzy logic control system has stronger learning ability and better control performance.

Application of Fuzzy Neural Network Predictive Control in Material Proportioning System

In accordance with the technique features of material proportioning belt system in the cement production, e.g., inertia, time lag, non-linearity and frequent disturbance in work field, a fuzzy neural network predictive controller based on neural network prediction model is designed. By combining fuzzy control, neural network and predictive control, it can enhance self-studying, tracking and anti-interference capabilities of the algorithm, and the neural network can compensate with the limitation of conventional predictive control that based on linear model. With this algorithm the weigh belt is controlled, and the simulation experimental curves show that the control effect of the material flow is effective, and the precision of ingredient proportion has evidently improved

Optimization of fuzzy controller based on genetic algorithm

It is pivotal to choose the parameters of control rules, membership function in designing a fuzzy controller. Genetic Algorithm is an effective method to optimize it. Based on hardly to find the best solution when the number of parameters to be optimized is too large, a step-by-step method to optimize the parameters of fuzzy controller is proposed. After discussion, only a quarter of control rules need to be optimized. To eliminate the system error, an integrator is connected with the fuzzy controller in parallel. Simulation results show that proposed design scheme can acquire the satisfied dynamic performance by learning and genetic optimization even for lack of any prior knowledge.

Intelligent Fuzzy Control Method for Soaking PIT Economical Combustion

Abstract In this paper, based on the feature of the soaking pit heating and combustion process, economical combustion is realized by using fuzzy control theory. According to technology of heating, the system model with delay and non-linear blocks is established. In the process of soaking pit heating, the control layout is proposed that using the fuzzy control in the period of heating and holding temperature in order to raise heating efficiency of soaking pit combustion in the process of control. At last, by the simulation figures, it is validated that tracking effect is better, anti jamming is stronger and robustness is better. This control scheme can be used in soaking pit economical combustion system.

Research of intelligent control method for the temperature of fermentation

Fermentation process of the microorganism is a comprehensive course of organism growth and chemical reaction and the fermentation temperature is one of its most important parameters. Though an analysis of the fermented mechanism, this paper has introduced an intelligent control method for the fermentation temperature based on the apery intelligent control algorithm. During control processes, the function of humans control behavior is mimiced by the computer, and the characteristic information obtained from the dynamic processes of the control system is fully used to analyze, judge and decide so that the effective control of the object lacking of accurate model can be made. The system that adopted the apery intelligent control algorithm has been applied to a bio-pharmaceutical enterprise and has achieved a satisfied result.