共查询到19条相似文献,搜索用时 125 毫秒
1.
2.
一种自组织模糊神经网络控制器 总被引:12,自引:0,他引:12
采用一种具有结构和参数学习能力的自组织模糊神经网络控制器设计方法。这种控制器无需事先确定模糊控制规则,能在控制过程中通过神经网络的结构及参数学习在线调整模糊神经网络的结构、产生模糊控制规则、调整规则的参数。仿真表明该控制器能用于一定纯滞后时变对象的控制,具有良好的控制性能。 相似文献
3.
一种基于遗传算法的模糊神经网络最优控制 总被引:25,自引:0,他引:25
通过对控制系统的过程模拟,提出一种模糊神经网络最优控制方案。离线化部分基于遗传算法,分三阶段实现模糊神经网络控制器结构和参数的优化。在线优化部分通过重构模糊神经网络控制器的去模糊化部分,进一步调整控制规则,实现在线去模糊优化。仿真结果表明该方案优于常模糊控制方案和基于专家经验的模糊神经网络控制方案。 相似文献
4.
5.
针对在柴油发电机负荷试验中,有关水电阻负载的负荷特点,分析了目前国内关于水电阻模型建立和实际控制的有关研究情况。结合实际工程项目,给出有关负荷电流的方案分析过程。在调节水电阻进而稳定负荷电流的控制中,提出一种自组织模糊控制和常规模糊控制相结合的综合模糊控制器设计方法。该控制器进一步提高了水电阻负载的控制效果。同时给出了该控制器效果分析。 相似文献
6.
基于神经网络的结构,结合模糊控制的理论,提出了一种模糊神经网络在线学习自适应结构,针对模糊神经网络控制器一般存在着在线修正权值计算量大。权值过度修正容易导致系统振荡等缺点,采用变结构变速率的学习方法对网络结构参数权值进行修正。将参数调整后的控制器模型应用于伺服系统中,并与传统的ITAE三阶无静差最优控制进行比较,仿真试验表明该控制器不但能够提高系统的控制品质,同时可以消除输出力矩对被控对象的扰动,具有很好的控制效果。 相似文献
7.
8.
9.
10.
11.
研究多输入–多输出(MIMO)高阶非仿射非线性系统的特征建模问题.首先证明了MIMO高阶非仿射非线性系统的特征模型可用二阶时变差分方程组描述,并给出了特征模型的建模误差.然后设计了基于特征模型的自适应模糊广义预测控制器,利用Lyapunov方法分析了闭环系统的稳定性.由于控制结构中使用了分层模糊逻辑系统,从而极大减少了模糊规则和可调参数的个数,提高了控制的实时性.通过对挠性卫星姿态控制的仿真研究验证了所给控制方案的有效性,可实现高精度的姿态控制,且该方法具有较强的鲁棒性. 相似文献
12.
This article presents a direct adaptive fuzzy control scheme for a class of uncertain continuous-time multi-input multi-output nonlinear (MIMO) dynamic systems. Within this scheme, fuzzy systems are employed to approximate an unknown ideal controller that can achieve control objectives. The adjustable parameters of the used fuzzy systems are updated using a gradient descent algorithm that is designed to minimize the error between the unknown ideal controller and the fuzzy controller. The stability analysis of the closed-loop system is performed using a Lyapunov approach. In particular, it is shown that the tracking errors are bounded and converge to a neighborhood of the origin. Simulations performed on a two-link robot manipulator illustrate the approach and exhibit its performance. 相似文献
13.
A fuzzy logic based supervisory hierarchical control scheme for real time pressure control 总被引:5,自引:4,他引:1
This paper describes a supervisory hierarchical fuzzy controller (SHFC) for regulating pressure in a real-time pilot pressure control system. The input scaling factor tuning of a direct expert controller is made using the error and process input parameters in a closed loop system in order to obtain better controller performance for set-point change and load disturbances. This on-line tuning method reduces operator involvement and enhances the controller performance to a wide operating range. The hierarchical control scheme consists of an intelligent upper level supervisory fuzzy controller and a lower level direct fuzzy controller. The upper level controller provides a mechanism to the main goal of the system and the lower level controller delivers the solutions to a particular situation. The control algorithm for the proposed scheme has been developed and tested using an ARM7 microcontroller-based embedded target board for a nonlinear pressure process having dead time. To demonstrate the effectiveness, the results of the proposed hierarchical controller, fuzzy controller and conventional proportional-integral (PI) controller are analyzed. The results prove that the SHFC performance is better in terms of stability and robustness than the conventional control methods. 相似文献
14.
Hafedh Abid Ahmed Toumi 《Soft Computing - A Fusion of Foundations, Methodologies and Applications》2016,20(2):649-659
In this paper, we propose an adaptive fuzzy controller for a class of nonlinear SISO time-delay systems. The plant model structure is represented by a Takagi–Sugeno (T–S) type fuzzy system. The T–S fuzzy model parameters are adjusted online. The proposed algorithm utilizes the sliding surface to adjust online the parameters of T–S fuzzy model. The controller is based on adjustable T–S fuzzy parameters model and sliding mode theory. The stability analysis of the closed-loop system is based on the Lyapunov approach. The plant state follows asymptotically any bounded reference signal. Two examples have been used to check performances of the proposed fuzzy adaptive control scheme. 相似文献
15.
对受非完整约束且含模型不确定性的移动机器人基于分层模糊系统设计了跟踪期望几何路径的鲁棒间接自适应控制方案.此方法除实现路径跟踪外,还可避免控制器的奇异性并保证跟踪方向.由于控制结构中使用了分层模糊系统,大大减少了模糊规则数目;并用鲁棒控制项对模糊系统逼近误差进行补偿,减少了其对跟踪精度的影响.证明了闭环系统跟踪误差收敛到原点的小邻域内,且可通过适当增大鲁棒控制项的设计参数使跟踪误差进一步减小.最后用实验结果验证了方法的有效性. 相似文献
16.
Sofiane Doudou 《International journal of systems science》2013,44(6):1029-1038
An adaptive fuzzy control approach is proposed for a class of multiple-input–multiple-output (MIMO) nonlinear systems with completely unknown non-affine functions. The global implicit function theorem is first used to prove the existence of an unknown ideal implicit controller that can achieve the control objectives. Within this scheme, fuzzy systems are employed the approximate the unknown ideal implicit controller, and robustifying control terms are used to compensate the approximation errors and external disturbances. The adjustable parameters of the used fuzzy systems are deduced from the stability analysis of the closed-loop system in the sense of Lyapunov. To show the efficiency of the proposed controllers, two simulation examples are presented. 相似文献
17.
Yong-Qing Fan Yin-He Wang Yun Zhang Qin-Ruo Wang 《International Journal of Control, Automation and Systems》2013,11(3):624-629
This paper proposes a novel adaptive fuzzy control design for a class of nonlinear uncertain systems. The definition of compressor and limiter with adjustable parameters is introduced at beginning, and then updated laws of parameters of the compressor and estimate values of fuzzy approximation accuracies are utilized to synthesize stable adaptive controllers. The most advantage of designing adaptive fuzzy controller is neglectful of the logic structure of fuzzy logic systems, which make designer focus on parameters of the compressor, limiter and fuzzy approximation accuracies. This adaptive fuzzy control method can not only reduce the number of on-line updated parameters but also guarantee states of the closed-loop system to be uniformly ultimately bounded (UUB). Simulation results demonstrate the effectiveness of the control scheme in this paper. 相似文献
18.