Analysis and comparison of variable structure fuzzy neural network control and the PID algorithm

The benefits of fuzzy control and neural network control are discussed. A quick learning control algorithm is given. The controlled object has movement characteristics and quickly-varying parameters. Good control effects are obtained. In control solution space, fuzzy control is used for quick primary partition, then neural network control to get the precise control. It gets successful application in electric touch quickly heated industrial process, and show its good control property and application value.

Due to the growth characteristics of the flowers and fruits of camellia in the same period, the vibrating camellia fruit picking machine needs to ensure the constant rotational speed of the vibrating hydraulic motor when the picking mechanism is operating, to achieve a constant vibration frequency, to ensure that the camellia fruit can smoothly fall off the branches through vibration. In contrast, the camellia fruit does not fall off. In this regard, this paper deduced the state space equation of the camellia fruit picking machine’s valve-controlled vibrating hydraulic motor system and designed a fuzzy wavelet neural network PID controller (FWNN PID controller) based on the traditional incremental PID control principle. Then the designed vibration picking manipulator control system was simulated under no-load, 5 s load conditions, and load start conditions with MATLAB/Simulink, a general PID controller and a fuzzy RBF neural network PID controller (FRBFNN PID controller) were used to contrast with it. The results show that the general PID controller has a slow response speed and poor robustness, while fuzzy neural network PID controllers (including FWNN PID controller and FRBFNN PID controller) have a fast response speed and strong robustness, which can well meet the requirements of a specific vibration frequency. Finally, a field test was carried out. The results show that the FWNN PID control is better than the FRBFNN PID control. Furthermore, the FWNN PID controller obviously reduced the drop rate of camellia flowers within 6% while ensuring the picking efficiency above 90%, which can well meet the needs of the camellia fruit picking operation.

This paper presents the design and application of fuzzy neural network control system for the rotary cement kiln system. Due to the dynamic characteristics and reaction process parameters are with features of large inertia, pure hysteresis, nonlinearity and strong coupling, the fuzzy neural network controller combining both the advantages of neural network and fuzzy control was applied. The fuzzy neural network is an adaptive control process whose parameters can be adjusted by learning algorithms automatically which is aimed to eliminate the shortcomings of conventional control methods. The main control system structure includes mainly the pressure control loop, the burning zone control loop and the back-end of kiln temperature control loop. Simulation results show the effectiveness of the control scheme with satisfied dynamic performances on response time and overshoot.

A neural network model and fuzzy neural network controller was designed to control the inner impedance of a proton exchange membrane fuel cell (PEMFC) stack. A radial basis function (RBF) neural network model was trained by the input-output data of impedance. A fuzzy neural network controller was designed to control the impedance response. The RBF neural network model was used to test the fuzzy neural network controller. The results show that the RBF model output can imitate actual output well, the maximal error is not beyond 20 mΩ, the training time is about 1 s by using 20 neurons, and the mean squared errors is 141.9 mΩ2. The impedance of the PEMFC stack is controlled within the optimum range when the load changes, and the adjustive time is about 3 min.

Fuzzy rule-based neural appointed-time control for uncertain nonlinear systems with aperiodic samplings

Because of the existing hybrid fuzzy PID controller does not perform, using electric hydraulic servo system application (SEHS). Therefore, when the system parameters change will require a new adjustment of PID controller variable. Therefore, a hybrid fuzzy and fuzzy self-tuning PID control was put forward. With this control scheme was divided into two parts, and the fuzzy controller and fuzzy self-tuning PID controller. Fuzzy controller is used to control the output of the system of the values of the system away from target value. We proved that the performance of the control scheme through the experiment of the motor speed control SEHS. The experimental results show that the proposed a hybrid fuzzy PID controller and fuzzy self-tuning effect is better than that of a hybrid fuzzy and PID controller.

By integrating fuzzy neural network and PI controller, a fuzzy neural hybrid controller based on PI controller is proposed. The parameters of new controller can be adjusted on line based on the ability of fuzzy neural network. The effectiveness of the proposed controller can be demonstrated by simulation in nonlinear and time variable plant.

The AGC of reheat interconnected two area power systems are characterized by non-linearity and uncertainty. A hybrid neural network and fuzzy control is proposed for automatic generation control in power systems. Recurrent neural network is employed to forecast controller and system's future output, based on the current Area Control Error (ACE) and the predicted change-of-ACE. The Control Performance Standard (CPS) criterion is adapted to the fuzzy controller design, thus improves the dynamic quality of system. The system was simulated and the frequency deviations in area 1 and area 2 and tie-line power deviations for 1% step-load disturbance in area 1 were obtained. The comparison of frequency deviations and tie-line power deviations for the two area interconnected thermal power system integral controller with Redox Flow Batteries (RFB) reveals that the system with hybrid fuzzy neural controller enhances a better stability than that of system without hybrid fuzzy neural controller.

Aiming at the network control system with time delay and packet loss, this paper designs a fuzzy adaptive PID controller to realize the adjustment of the network control system. Through the design of wavelet neural algorithm to predict the time delay, the fuzzy adaptive PID can realize the online adjustment of Kp, Ki and Kd, which overcomes the problem of constant input parameter adjustment of the traditional PID controller. Fuzzy control is realized by designing fuzzy rules, and finally through comparison The Matlab simulation renderings of traditional PID controller and fuzzy adaptive PID controller show that the robustness and accuracy of fuzzy adaptive PID controller are better.

An efficient Q-learning paradigm implemented on a fuzzy CMAC network is proposed. The fuzzy CMAC network topological architecture is described. First, the continuous states of the system are partitioned into a number of fuzzy boxes. Second, the proposed fuzzy CMAC evaluates the Q-values of agents in the fired fuzzy boxes and chooses control actions with maximum Q-values. Then a critic generates an external reinforcement signal according to the outcome or the effect of the control at every time-step, which is used later for further improving the estimation of these Q-values. To speed up the convergence of reinforcement learning, the traditional PID controller with several groups of different parameters is adopted so as to collect a number of taught-lessons. These taught-lessons together with the experienced lessons generated automatically, are sequentially replayed and learned, respectively, under the guidance of different reinforcement mechanisms. The hybrid adaptive and learning control system is applied to the control of a pH-neutralization process. Simulation investigations show that the fuzzy connectionist Q-learning control system has more adaptive, higher intelligence, and stronger generalization ability compared to neural network or fuzzy neural network control techniques using supervised learning.

EAF steelmaking is a complex physical and chemical reactions，has Highly nonlinearity, time variability and strong coupling. As the electrode's contact with the charging circuit, charging the collapse of the gasification furnace components and liquid metal boiling and other factors, often result in dramatic fluctuations in arc current. At this point we need to quickly adjust the location of electrodes, so that arc current stable base on this within a certain range. This article in the fuzzy control and neural network’s foundation,will study a kind based on three-phase consciousness electric arc furnace predictive control new method, Using the fuzzy neural network control adjusting electrode, further enhancing the effectiveness of electric arc furnace’synthesis movement.

Active vibration isolation technology can overcome the defects of passive vibration isolation technology that the poor vibration isolation performance in low and resonant frequencies. Compared with other active vibration isolation technologies, magnetic suspension isolation technology has shown useful characteristics, such as wide response frequency range, fast response, high reliability and long-life. However, the control of MSVI is still one of the areas that require further investigation. This paper presents a Fuzzy Neural Networks(FNN) control algorithm for a magnetic suspension isolation vibration system, which is optimized by improved Genetic Algorithm(GA). The output force responses of the FNN and passive vibration isolation system under same excitation are simulated. The simulation results show that the fuzzy control system has much better performance in vibration isolation.

In accordance with the technique features of Active Power Filter control in harmonics suppression, e.g., time lag, non-linearity and frequent disturbance in work field, a fuzzy neural network predictive controller based on genetic algorithm 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 compensating current is controlled, and the simulation experimental curves show that the proposed method is more effective and feasible than PI control or digit adaptive control.

A fuzzy neural network based system was developed to control the quality of resistance spot welding. A fuzzy neural controller (FNC) was designed to realize the memory of the fuzzy neural control bases on a back propagation (BP) network, accordingly achieve the mapping of fuzzy input and output. The experiment results show that this method can compensate the multi-crossfire’s influence on the welding currency, keep a high control precision, and fulfill the demand of high precision quality monitoring to the resistance spot welding.

To decrease the influence of friction on torque tracking accuracy and improve the rapidity of system response when load simulator works at low frequency and low speed, a novel method based on fuzzy neural network (FNN) PID controller and friction torque compensation is put forward. The FNN PID consists of FNN and neural network (NN) PID. The parameters of the controller were optimized by the mixed learning method integrating of offline genetic algorithm (GA) and online error back propagation (BP) algorithm. The friction torque model is identified by LuGre model. The loading motor is a double-stator motor in which the outer stator system serves as compensating the friction torque and the inner stator system as loading torque. Simulation results show that the control system has good dynamic and static performance.