高超声速飞行器的模糊CMAC神经网络控制器设计

由于采用机体一体化设计,吸气式高超声速飞行器的气动特性难以准确获知,建立的数学模型是极不准确的;设计了一种模糊CMAC神经网络(FCMAC)控制器及其学习算法,在CMAC神经网络控制器中结合模糊逻辑理论,使得CMAC控制器具有自学习能力;仿真用高超声速飞行器的纵向模型对该控制器进行了验证,证明该控制方法能够有效地跟踪飞行器的高度和速度指令。

基于TMS320F2812无刷直流电机控制系统设计

设计一种基于TMS320F2812的无刷直流电机控制系统;详细介绍了转子位置检测电路、相电流检测电路、驱动电路以及保护电路设计;给出相应的硬件电路。该系统采用三环控制。其中,位置环采用PI调节器;速度环采用参数自整定模糊PID控制;电流环采用电流滞环控制。该设计方案电路简单,可靠性强,具有较高的应用价值。同时,实验结果也验证了该方法的有效性。

无刷直流电机控制策略的仿真研究

为改善无刷直流电机的调速性能,研究了基于模糊控制思想的模糊控制器及其在BLDCM控制系统中的应用。在Matlab仿真平台下,建立了BLDCM的模型,构建了BLDCM转速闭环控制系统,其中转速控制器分别采用了模糊控制器和普通PID控制器。仿真结果表明:与常规PID控制器相比,采用模糊控制器的优势在于转速输出无超调、响应速度快、控制精度高,具有较强的鲁棒性和自适应能力。

基于Fuzzy-PI的BLDCM控制系统设计与仿真

提出了一种无刷直流电机的Fuzzy-PI转速调节器的设计方法。在无刷直流电机的高性能速度跟踪中,采用传统的PI调节器,则难以克服系统超调和短时振荡问题。采用复合Fuzzy-PI的控制方法,并且采用自适应的权值修正方法来修正Fuzzy回路与PI回路的连接权值。最后,在Matlab与Simulink下进行了仿真,结果表明,运用这种设计方法很好地抑制了超调和振荡。

Fuzzy Control Method for Gasoline Engine Idle Speed Control

In order to improve the steady and dynamic characteristic of the idle speed control and study the performance of the fuzzy control method for the idle speed control, a fuzzy control system is developed to control the idle speed of gasoline engine. The construction and working principle of the fuzzy controller are described, and the design procedure of the fuzzy controller is given in detail. The control parameters are determined by computer simulation. The simulation and experiments on the engine test bench show that the idle speed is controlled accurately both in stationary and in dynamic states, and the fuzzy control method is robust to the changes of engine parameters.

FUZZY ADAPTIVE CONTROL OF FLEXIBLE-LINK ROBOT MANIPULATOR

A fuzzy adaptive control method is proposed for a flexible robot manipulator. Due to the structure characteristics of the flexible manipulator, the vibration modes must be controlled to realize the high-precision tip position. The Lagrangian principle is utilized to model the dynamic function of the single-degree flexible manipulator incorporating the assumed modes method. Simulation results of the fuzzy adaptive control method in the location control and the trajectory tracking with different tip disturbances are presented and compared with the results of the classic PD control. It shows that the controller can obtain the stable and robust performance.

Reactive fuzzy controller design by Q-learning for mobile robot navigation

In this paper a learning mechanism for reactive fuzzy controller design of a mobile robot navigating in unknown environments is proposed. The fuzzy logical controller is constructed based on the kinematics model of a real robot. The approach to learning the fuzzy rule base by relatively simple and less computational Q-learning is described in detail. After analyzing the credit assignment problem caused by the rules collision, a remedy is presented. Furthermore, time-varying parameters are used to increase the learning speed. Simulation results prove the mechanism can learn fuzzy navigation rules successfully only using scalar reinforcement signal and the rule base learned is proved to be correct and feasible on real robot platforms.

A Multiple Model Approach to Modeling Based on Fuzzy Support Vector Machines

A new multiple models(MM) approach was proposed to model complex industrial process by using Fuzzy Support Vector Machines(F -SVMs). By applying the proposed approach to a pH neutralization titration experiment, F -SVMs MM not only provides satisfactory approximation and generalization property, but also achieves superior performance to USOCPN multiple modeling method and single modeling method based on standard SVMs.

Intelligent Control Scheme of Engineering Machinery of Cluster Hybrid System

In a hybrid system, the subsystems with discrete dynamics play a central role in a hybrid system. In the course of engineering machinery of cluster construction, the discrete control law is hard to obtain because the construction environment is complex and there exist many affecting factors. In this paper, hierarchically intelligent control, expert control and fuzzy control are introduced into the discrete subsystems of engineering machinery of cluster hybrid system, so as to rebuild the hybrid system and make the discrete control law easily and effectively obtained. The structures, reasoning mechanism and arithmetic of intelligent control are replanted to discrete dynamic, conti- nuous process and the interface of the hybrid system. The structures of three types of intelligent hybrid system are presented and the human experiences summarized from engineering machinery of cluster are taken into account.

Development of single-chip fuzzy controller based on FFSI in binary

Length and concise structure of fuzzy logic reasoning program and its real-time reasoning characteris-tic have their effect on the performance of a digital single-chip fuzzy controller. The control effect of a digitalfuzzy controller based on looking up fuzzy control responding table is only relative to the table and not relative tothe fuzzy control rules in the practical control process. Aiming at above problem and having combined fuzzy log-ic reasoning with digital operational characteristics of a single-chip microcomputer, functioning-fuzzy-subset in-ference (FFSI) in binary, in which triangle membership functions of error and error-in-change are all represen-ted in binary and singleton membership functions of control variable is binary too, has been introduced. The cir-cuit principle plans of a single-chip fuzzy controller have been introduced for development of its hardware, andthe primary program structure, fuzzy logic reasoning subroutine, serial communication subroutine with PC andreliability design of the fuzzy controller are all discussed in detail. The control of indoor temperature by a fuzzycontroller has been conducted using a testing-room thermodynamic system. Research results show that the FFSIin binary can exercise a concise fuzzy control in a single-chip fuzzy controller, and the fuzzy controller is there-fore reliable and possesses a high performance-price ratio.

Torsional vibration active control of hybrid construction machinery complex shafting

Due to the coaxial connection of engine, motor and pump, the dynamic characteristics of hybrid construction machinery are changed, which generates a new torsional vibration problem of multi-power sources. To reduce the torsional vibration of the hybrid construction machinery complex shafting, torsional vibration active control was proposed. The three-mass model of coaxial shafting of hybrid construction machinery was established. The PID control and the fuzzy sliding mode control were chosen to weaken torsional vibration by controlling the motor speed and torque. The simulation results show that the fuzzy sliding mode control has 12% overshoot of the PID control when the engine torque changes. The active control is effective and can realize smooth power switch.

FUZZY CONTROLLED AUTOMATION SYSTEM FOR THE MAIN COAL BUNKER

A fuzzy control scheme is presented according to the coal quantity in the main coal bunker, this method has a good dynamic response characteristic and is suited for complex nonlin-ear systems. The designation of self-adopting fuzzy controller, the working principle and functions of this system are also proposed, with the hardware and the main flow diagram of this system in-troduced in this paper.

Interval Type-2 fuzzy position control of electro-hydraulic actuated robotic excavator

This paper deals with fuzzy intelligent position control of electro-hydraulic activated robotic excavator for the control of boom, arm and bucket axes. Intelligent control systems are required to overcome unde- sirable stick-slip motion, limit cycles and oscillations. Models of electro-hydraulic servo controlled front end loader excavators are highly nonlinear. The nonlinear model accounts for fluid flow rate of valve, pump hydraulics, and friction forces. The friction forces are modelled by Coulomb, viscous and Stribeck function. Interval Type-2 Fuzzy Logic Controller （IT2FLC） is used to study the time-domain position responses of axes in the presence of external applied load. It has the ability to control the position of each of the three axes with minimum actuator position errors. Models presented are accurate and study the dynamics of the actuator and load. To improve the transient behaviour of the robotic excavator, we elim- inated iitter of the bucket movement in the presence of nonlinearities.

Fuzzy control on automatic frequency tracking of ultrasonic vibration system with high power and high quality factor Q

In order to realize automatic tracking drift of resonance frequency of ultrasonic vibration system with high power and high quality factor Q, adaptive fuzzy control was studied with a self-fabricated ultrasonic plastic welding machine. At first, relations between amplitude of vibration and frequency as well as main loop current and amplitude of vibration were analyzed. From this analysis, we deduced that frequency tracking process of the vibration system can be concluded as an optimizing problem of one dimensional fluctuant extremum of main loop current in vibration system. Then a method of self-optimizing fuzzy control, used for the realization of automatic frequency tracking in vibration system, is presented on the basis of serf-optimizing adaptive control approach and fuzzy control approach. The result of experiments shows that the fuzzy self-optimizing method can solve the problem of tracking frequency drift very well. Response time of tracking in the system is less than 50 ms, which basically meets the requirements of frequency tracking in ultrasonic plastic welding machine.

Integrated yaw and rollover control based on differential braking for off-road vehicles with mechanical elastic wheel

Aiming at the issue of yaw and rollover stability control for off-road vehicles with non-pneumatic mechanical elastic wheel(MEW),an integrated control system based on fuzzy differential braking is developed.By simplifying the structure of the MEW,a corresponding fitting brush tire model is constructed and its longitudinal and lateral tire force expressions are set up,respectively.Then,a nonlinear vehicle simulation model with MEW is established to validate the proposed control scheme based on Carsim.The designed yaw and rollover control system is a two-level structure with the upper additional moment controller,which utilizes a predictive load transfer ratio(PLTR)as the rollover index.In order to design the upper integrated control algorithm,fuzzy proportional-integral-derivative(PID)is adopted to coordinate the yaw and rollover control,simultaneously.And the lower control allocator realizes the additional moment to the vehicle by differential braking.Finally,a Carsim-simulink co-simulation model is constructed,and simulation results show that the integrated control system could improve the vehicle yaw and roll stability,and prevent rollover happening.

Fuzzy iterative learning control of electro-hydraulic servo system for SRM direct-drive volume control hydraulic press

A new kind of volume control hydraulic press that combines the advantages of both hydraulic and SRM(switched reluctance motor) driving technology is developed.Considering that the serious dead zone and time-variant nonlinearity exist in the volume control electro-hydraulic servo system,the ILC(iterative learning control) method is applied to tracking the displacement curve of the hydraulic press slider.In order to improve the convergence speed and precision of ILC,a fuzzy ILC algorithm that utilizes the fuzzy strategy to adaptively adjust the iterative learning gains is put forward.The simulation and experimental researches are carried out to investigate the convergence speed and precision of the fuzzy ILC for hydraulic press slider position tracking.The results show that the fuzzy ILC can raise the iterative learning speed enormously,and realize the tracking control of slider displacement curve with rapid response speed and high control precision.In experiment,the maximum tracking error 0.02 V is achieved through 12 iterations only.

Applying machine learning for cars’semi-active air suspension under soft and rigid roads

To improve the ride quality and enhance the control efficiency of cars’semi-active air suspensions(SASs)under various surfaces of soft and rigid roads,a machine learning(ML)method is proposed based on the optimized rules of the fuzzy control(FC)method and car dynamic model for application in SASs.The root-mean-square(RMS)acceleration of the driver’s seat and car’s pitch angle are chosen as the objective functions.The results indicate that a soft surface obviously influences a car’s ride quality,particularly when it is traveling at a high-velocity range of over 72 km/h.Using the ML method,the car’s ride quality is improved as compared to those of FC and without control under different simulation conditions.In particular,compared with those cars without control,the RMS acceleration of the driver’s seat and car’s pitch angle using the ML method are respectively reduced by 30.20% and 19.95% on the soft road and 34.36% and 21.66% on the rigid road.In addition,to optimize the ML efficiency,its learning data need to be updated under all various operating conditions of cars.

Fuzzy Logic Control of a Robotic Manipulator for Obstacles Avoidance

This work presents a Fuzzy Logic Controller （FLC） assigned to control a robotic arm motion while avoiding the obstacles that may face the robotic arm in its movement from the initial point to the final point in an optimized manner, in addition to avoid the singularity phenomenon, and without any exceeding of the physical constraints of the robot arm. A real platform （5 DOF ＂Degree Of Freedom＂ Lab Volt 5150 Robotic Arm） is used to carry this work practically, in addition to providing it by a vision sensor, where a new approach is proposed to inspect the robot work environment using a designed integrated MATLAB program having the ability to recognize the changeable locations of each of the robotic arm＇s end-effector, the goal, and the multi existed obstacles through a recorded film taken by a webcam, then these information will be treated using the FLC where its outputs represent the values that must be delivered to the robot to adopt them in its next steps till reaching to the goal in collision-free movements. The experimental results showed that the developed robotic ann travels successfully from Start to Goal where a high percentage of accuracy in arriving to Goal was achieved, and without colliding with any obstacle ensuring the harmonization between the theoretical part and the experimental part in achieving the best results of controlling the robotic arm＇s motion.

Fuzzy-immune control strategy of a hydro-viscous soft start device of a belt conveyor

Considering the control difficulties of a hydro-viscous trol algorithm was derived. A fuzzy-immune PID controller was soft start （HVSS） device of a belt conveyor, a fuzzy-immune con- designed based on immune feedback regulations and adaptability of the fuzzy logic inference. Using MATLAB software, we simulated the controller and compared the HVSS device with a conven- tional PID controller and a fuzzy PID controller. The simulation results show that the controller is not only very reliable as a PID controller, robust and requires only a short adjustment time of fuzzy control, but possesses also capacity of global optimization of the immune algorithm. To verify our theoretical analysis and simulation, a HVSS test-bed was developed. The experimental results demonstrate that the fuzzy-immune PID controller managed to start the belt conveyor softly and to follow an S-shaped curve while the output speed correctly followed the preset speed with only small fluctuations in speed.

Double-Fed Asynchronous Wind Power Generator by Fuzzy Logic

The objective of this study is the simulation of the fuzzy control of a double-fed induction wind generator （DFIG） and oriented stator flux using MATLAB/S[MULINK. The system consists of a horizontal wind turbine, coupled to a DFIG and driven by a feed consisting of two three＋phase PWM converters in double bridge in order to maximize the delivered power at different wind speeds. We used a traditional regulator and a fuzzy controller. A model of the wind speed and the wind turbine is presented followed by the modeling of double-fed asynchronous generator DFIG controlled by fuzzy logic is performed according to two scenarios： with and without MPPT.