A fuzzy control and neural network based rotor speed controller for maximum power point tracking in permanent magnet synchronous wind power generation system

When the wind speed changes significantly in a permanent magnet synchronous wind power generation system,the maximum power point cannot be easily determined in a timely manner.This study proposes a maximum power reference signal search method based on fuzzy control,which is an improvement to the climbing search method.A neural network-based parameter regulator is proposed to address external wind speed fluctuations,where the parameters of a proportional-integral controller is adjusted to accurately monitor the maximum power point under different wind speed conditions.Finally,the effectiveness of this method is verified via Simulink simulation.

Fuzzy Control System of Hydraulic Roll Bending Based on Genetic Neural Network

For nonlinear hydraulic roll bending control, a new fuzzy intelligent control method was proposed based on the genetic neural network. The method taking account of dynamic and static characteristics of control system has settled the problems of recognizing and controlling the unknown, uncertain and nonlinear system successfully, and has been applied to hydraulic roll bending control. The simulation results indicate that the system has good performance and strong robustness, and is better than traditional PID and neural-fuzzy control. The method is an effective tool to control roll bending force with increased dynamic response speed of control system and enhanced tracking accuracy.

Neural-networks-based Modelling and a Fuzzy Neural Networks Controller of MCFC

Molten Carbonate Fuel Cells (MCFC) are produced with a highly efficient and clean power generation technology which will soon be widely utilized. The temperature characters of MCFC stack are briefly analyzed. A radial basis function (RBF) neural networks identification technology is applied to set up the temperature nonlinear model of MCFC stack, and the identification structure, algorithm and modeling training process are given in detail. A fuzzy controller of MCFC stack is designed. In order to improve its online control ability, a neural network trained by the I/O data of a fuzzy controller is designed. The neural networks can memorize and expand the inference rules of the fuzzy controller and substitute for the fuzzy controller to control MCFC stack online. A detailed design of the controller is given. The validity of MCFC stack modelling based on neural networks and the superior performance of the fuzzy neural networks controller are proved by Simulations.

Intelligent Home Using Fuzzy Control Based on AIoT

The Internet of Things has grown rapidly in recent years,and the technologies related to it have been widely used in various fields.The idea of this paper is to build a set of Internet of Things systems in a smart home wireless network environment,with the purpose of providing people with a more comfortable,convenient,and safe life.In the sensing layer of the Internet of Things,we discuss the uses of common sensing technologies on the Internet and combine these with Arduino microprocessors to integrate temperature sensing modules,humidity sensing modules,gas sensing modules,and particulate matter 2.5(PM2.5)sensing modules.In the network layer,we discuss using the Wi-Fi wireless networking function composed of a home router and a wireless Wi-Fi chip Espressif system 8266(ESP8266)to transmit the collected home-sensing data to the ThingSpeak cloud database.Finally,in the application layer part,the system uses a mobile device with fuzzy calculation optimization software.The system is also connected remotely for home environment monitoring,so the home environment can be optimized anytime,anywhere.

Application of neural networks and fuzzy control to the welding robot

Intelligent control is applied in welding robot. The neural network was used for detecting the deviation of the torch from the center of the gap. The robot tracing the welding line with the fuzzy controller. The proposed method was successfully used to seam tracking in V groove weld configuration .

A three-dimensional probabilistic fuzzy control system for network queue management

A novel probabilistic fuzzy control system is proposed to treat the congestion avoidance problem in transmission control protocol （TCP） networks. Studies on traffic measurement of TCP networks have shown that the packet traffic exhibits long range dependent properties called self-similarity, which degrades the network performance greatly. The probabilistic fuzzy control （PFC） system is used to handle the complex stochastic features of self-similar traffic and the modeling uncertainties in the network system. A three-dimensional （3-D） membership function （MF） is embedded in the PFC to express and describe the stochastic feature of network traffic. The 3-D MF has extended the traditional fuzzy planar mapping and further provides a spatial mapping among ＂fuzziness-randomness-state＂. The additional stochastic expression of 3-D MF provides the PFC an additional freedom to handle the stochastic features of self-similar traffic. Simulation experiments show that the proposed control method achieves superior performance compared to traditional control schemes in a stochastic environment.

Neural Network and Fuzzy Control Based 11-Level Cascaded Inverter Operation

This paper presents a combined control and modulation technique to enhance the power quality(PQ)and power reliability(PR)of a hybrid energy system(HES)through a single-phase 11-level cascaded H-bridge inverter(11-CHBI).The controller and inverter specifically regulate the HES and meet the load demand.To track optimum power,a Modified Perturb and Observe(MP&O)technique is used for HES.Ultra-capacitor(UCAP)based energy storage device and a novel current control strategy are proposed to provide additional active power support during both voltage sag and swell conditions.For an improved PQ and PR,a two-way current control strategy such as the main controller(MC)and auxiliary controller(AC)is suggested for the 11-CHBI operation.MC is used to regulate the active current component through the fuzzy controller(FC),and AC is used to regulate the dc-link voltage of CHBI through a neural network-based PI controller(ANN-PI).By tracking the reference signals fromMC and AC,a novel hybrid pulse widthmodulation(HPWM)technique is proposed for the 11-CHBI operation.To justify and analyze the MATLAB/Simulink software-based designed model,the robust controller performance is tested through numerous steady-state and dynamic state case studies.

Application of Improved Fuzzy Controller in Networked Control System

Aiming at the problem of network-induced delay and data dropout in networked control system, an improved fuzzy controller is proposed in this paper. Considering the great influence of a controller on the performance of control system, an improved controller with a second order fuzzy controller and network-induced delay compensator being added to the basic fuzzy controller is proposed to realize self-regulation on-line. For this type of controller, neither plant model nor measurement of network delay is required. So it is capable of automatically adjusting quantified factor, pro- portional factor, and integral factor according to the control system error and its derivative. The design makes full use of the advantages of quickness in operation and reduction of steady state error because of its integral function. The con- troller has a good control effect on time-delay and can keep a better performance by self-regulation on-line in the net- work with data dropout and interference. It is good in quickness, adaptability, and robustness, which is favorable for controlling the long time-delay system.

A Fuzzy Control Based Intelligent Control System for Flower Greenhouse

In order to realize intelligent control of flower greenhouse＇ s parameters of atmospheric temperature and humidity, lighting intensity, CO2 concentration and soil water content, it carries out design with ZigBee network, embedded controller and intelligent fuzzy control algorithm as core. With advantages of high precision and stability, the design of sensor circuit mainly employs digital module sensors. In order to save energy, the sensor circuit is controlled by relay switch to work at the proper time. The gateway node is designed by employing high performance 32-digit embedded controller and WinCE6.0 embedded OS is self customized. And embedded SQlite database is realized on WinCE6.0 for effectively managing data. The closed loop control is realized by employing fuzzy control algorithm and the test result shows that the deviation of atmospheric temperature is controlled within ± 0.5° C, the deviation of illumination intensity is controlled within ± 283 LUX, the deviation of CO2 concentration is controlled within ± 24 PPM, the deviation of atmospheric humidity is controlled within ± 13% and that of soil water content is controlled within ± 0.9%, thus all parameters fully meet practical requirements of flower greenhouse.

Neural network-based TIG weld width fuzzy controller

A netal network-based fuzzy self-tuning PID controller theh is prope to control the dynamic process ofpulse TIG welding uses fuzzy logic and neural network to adjust the parameters of PID controller on line, and simula-tion results show that the controller has not only simple nonlinear control of tfuzzy control, but also the learning capabil-ity and adaptability of neural netwrk.

Novel method for the evaluation of data quality based on fuzzy control

One of the goals of data collection is preparing for decision-making, so high quality requirement must be satisfied. Rational evaluation of data quality is an effective way to identify data problem in time, and the quality of data after this evaluation is satisfactory with the requirement of decision maker. A fuzzy neural network based research method of data quality evaluation is proposed. First, the criteria for the evaluation of data quality are selected to construct the fuzzy sets of evaluating grades, and then by using the learning ability of NN, the objective evaluation of membership is carried out, which can be used for the effective evaluation of data quality. This research has been used in the platform of ＇data report of national compulsory education outlay guarantee＇ from the Chinese Ministry of Education. This method can be used for the effective evaluation of data quality worldwide, and the data quality situation can be found out more completely, objectively, and in better time by using the method.

Thickness and Shape Synthetical Adjustment for DC Mill Based on Dynamic Nerve-Fuzzy Control

Due to the complexity of thickness and shape synthetical adjustment system and the difficulties to build a mathematical model,a thickness and shape synthetical adjustment scheme on DC mill based on dynamic nerve-fuzzy control was put forward,and a self-organizing fuzzy control model was established.The structure of the network can be optimized dynamically.In the course of studying,the network can automatically adjust its structure based on the specific questions and make its structure the optimal.The input and output of the network are fuzzy sets,and the trained network can complete the composite relation,the fuzzy inference.For decreasing the off-line training time of BP network,the fuzzy sets are encoded.The simulation results indicate that the self-organizing fuzzy control based on dynamic neural network is better than traditional decoupling PID control.

Design of robust fuzzy controller for ship course-tracking based on RBF network and backstepping approach

This study presents an adaptive fuzzy neural network (FNN) control system for the ship steering autopilot. For the Norrbin ship steering mathematical model with the nonlinear and uncertain dynamic characteristics, an adaptive FNN control system is designed to achieve high-precision track control via the backstepping approach. In the adaptive FNN control system, a FNN backstepping controller is a principal controller which includes a FNN estimator used to estimate the uncertainties, and a robust controller is designed to compensate the shortcoming of the FNN backstepping controller. All adaptive learning algorithms in the adaptive FNN control system are derived from the sense of Lyapunov stability analysis, so that system-tracking stability can be guaranteed in the closed-loop system. The effectiveness of the proposed adaptive FNN control system is verified by simulation results.

Traffic Signals Control with Adaptive Fuzzy Controller in Urban Road Network

An adaptive fuzzy logic controller (AFC) is presented for the signal control of the urban traffic network. The AFC is composed of the signal control system-oriented control level and the signal controller-oriented fuzzy rules regulation level. The control level decides the signal timings in an intersection with a fuzzy logic controller. The regulation level optimizes the fuzzy rules by the Adaptive Rule Module in AFC according to both the system performance index in current control period and the traffic flows in the last one. Consequently the system performances are improved. A weight coefficient controller (WCC) is also developed to describe the interactions of traffic flow among the adjacent intersections. So the AFC combined with the WCC can be applied in a road network for signal timings. Simulations of the AFC on a real traffic scenario have been conducted. Simulation results indicate that the adaptive controller for traffic control shows better performance than the actuated one.

Two-layer networked learning control using self-learning fuzzy control algorithms

Since the existing single-layer networked control systems have some inherent limitations and cannot effectively handle the problems associated with unreliable networks, a novel two-layer networked learning control system (NLCS) is proposed in this paper. Its lower layer has a number of local controllers that are operated independently, and its upper layer has a learning agent that communicates with the independent local controllers in the lower layer. To implement such a system, a packet-discard strategy is firstly developed to deal with network-induced delay and data packet loss. A cubic spline interpolator is then employed to compensate the lost data. Finally, the output of the learning agent based on a novel radial basis function neural network (RBFNN) is used to update the parameters of fuzzy controllers. A nonlinear heating, ventilation and air-conditioning (HVAC) system is used to demonstrate the feasibility and effectiveness of the proposed system.

Finite-time Prescribed Performance Time-Varying Formation Control for Second-Order Multi-Agent Systems With Non-Strict Feedback Based on a Neural Network Observer

This paper studies the problem of time-varying formation control with finite-time prescribed performance for nonstrict feedback second-order multi-agent systems with unmeasured states and unknown nonlinearities.To eliminate nonlinearities,neural networks are applied to approximate the inherent dynamics of the system.In addition,due to the limitations of the actual working conditions,each follower agent can only obtain the locally measurable partial state information of the leader agent.To address this problem,a neural network state observer based on the leader state information is designed.Then,a finite-time prescribed performance adaptive output feedback control strategy is proposed by restricting the sliding mode surface to a prescribed region,which ensures that the closed-loop system has practical finite-time stability and that formation errors of the multi-agent systems converge to the prescribed performance bound in finite time.Finally,a numerical simulation is provided to demonstrate the practicality and effectiveness of the developed algorithm.

Time-varying parameters estimation with adaptive neural network EKF for missile-dual control system

In this paper, a filtering method is presented to estimate time-varying parameters of a missile dual control system with tail fins and reaction jets as control variables. In this method, the long-short-term memory(LSTM) neural network is nested into the extended Kalman filter(EKF) to modify the Kalman gain such that the filtering performance is improved in the presence of large model uncertainties. To avoid the unstable network output caused by the abrupt changes of system states,an adaptive correction factor is introduced to correct the network output online. In the process of training the network, a multi-gradient descent learning mode is proposed to better fit the internal state of the system, and a rolling training is used to implement an online prediction logic. Based on the Lyapunov second method, we discuss the stability of the system, the result shows that when the training error of neural network is sufficiently small, the system is asymptotically stable. With its application to the estimation of time-varying parameters of a missile dual control system, the LSTM-EKF shows better filtering performance than the EKF and adaptive EKF(AEKF) when there exist large uncertainties in the system model.

Direct-Torque Neuro-Fuzzy Control of Induction Motor

Fuzzy systems are currently being used in a wide field of industrial and scientific applications.Since the design and especially the optimization process of fuzzy systems can be very time consuming,it is convenient to have algorithms which construct and optimize them automatically.In order to improve the system stability and raise the response speed,a new control scheme,direct-torque neuro-fuzzy control for induction motor drive,was put forward.The design and tuning procedure have been described.Also,the improved stator flux estimation algorithm,which guarantees eccentric estimated flux has been proposed.