共查询到19条相似文献,搜索用时 62 毫秒
1.
给出了一种基于神经网络广义逆系统的汽轮发电机汽门开度控制策略,在无需系统模型参数和状态反馈的情况下,可实现非线性系统的大范围线性化,从而实现非线性系统的线性化控制。对单机无穷大系统的仿真表明,应用该控制策略可显著地增强电力系统的暂态稳定性。 相似文献
2.
神经网络在线学习模糊自适应控制及其应用 总被引:10,自引:6,他引:4
基于反馈误差学习法,提出了一种神经网络在线学习模糊自适应控制结构。利用模糊推理机产生的分目标学习误差训练神经网络,避免了控制器的输出产生振荡或进入饱和状态。工程应用表明,该方法将模糊推理引入神经网络学习中,可有效地提高系统的控制品质。 相似文献
3.
基于RBF神经网络的模糊自适应控制 总被引:7,自引:0,他引:7
在对一些复杂系统进行模糊控制时,由于对系统的不了解,很难得到适合的控制规则。基于模糊控制器的一种解析结构,提出了模糊控制器与径向基函数(Radial Basis Function)神经网络相结合的方法。由RBF神经网络对系统进行辨识,并为学习系统提供必要的信息,根据信息对经验规则进行修改,从而改善模糊控制系统动态响应。仿真结果表明该控制器对模型参数变化具有较好的适应能力,能够较快地修改系统的原控制规则,使对象输出较快地跟踪系统的输入。 相似文献
4.
5.
快关汽门控制的模糊神经网络方法 总被引:1,自引:0,他引:1
将模糊控制与神经网络相结合,设计了一种基于模糊神经网络的快关汽门控制器。该控制器 一方面避免了建立数学模型及信号失真带来的麻烦,另一方面又具有自学习、自组织能力。 数字仿真结果表明,使用这种快关汽门控制器控制效果好,具有较强的鲁棒性。 相似文献
6.
7.
基于神经网络在线学习的过热汽温自适应控制系统 总被引:6,自引:5,他引:6
将反馈误差学习控制与径向基函数神经网络相结合,提出了一种基于神经网络在线学习的自适应控制方法,神经网络控制器利用常规控制器的输出增量作为误差信号进行在线学习,实现对常规PID控制器的补偿,使控制系统能够适应对象的非线性和时变特性。将该方法应用于电厂过热汽温控制系统进行仿真研究,结果表明该方法能较好地适应对象特性的变化,且控制系统的性能比常规串级控制系统有较大的提高。 相似文献
8.
基于RBF神经网络的热工过程在线自适应建模算法研究 总被引:3,自引:8,他引:3
传统的各种神经网络建模方法由于自身的局限性不能很好地应用于复杂的热工过程建模。该文提出了一种新型的基于RBF网络的热工过程在线自适应建模算法:近似相关性网络(ACN)建模和阶层补偿式网络结构(HCN)建模。文中与资源分配网络(RAN)进行了详细的算例比较,并进一步计算了实际的热工非线性模型。计算结果表明:该文提出的建模算法不仅能提高模型的输出精度,而且也可有效地减小网络的规模,较好地解决了神经网络超界空间的自适应构造问题,为热工过程全局非线性模型的建立提供了一个新的解决方法。 相似文献
9.
采用本地信号的可控串联电容补偿神经网络逆系统控制方法 总被引:3,自引:4,他引:3
选取可控串联电容补偿(TCSC)上传输的有功功率作为被控量,本文提出了采用本地信号的TCSC神经网络逆系统控制方法。该方法基于较完整的TCSC非线性动态模型,实现了TCSC系统的精确线性化,同时所设计的控制策略适用于任意的电力系统结构。控制器的设计使用神经网络逆系统方法,使得所设计的控制策略不依赖于系统的精确模型和参数。针对两区域四机电力系统的仿真结果表明所设计的控制策略能达到直接控制TCSC传输功率,间接控制远端发电机功角的目的。 相似文献
10.
基于RBF神经网络的伺服系统自适应自抗扰控制 总被引:1,自引:0,他引:1
针对伺服系统中存在的非线性,提出了一种基于RBF神经网络的自适应自抗扰控制(ADRC)方法,设计了基于RBF神经网络的自适应自抗扰ADRC控制器。通过仿真和实验验证了该方法能有效地克服采用PD控制时系统的超速超回现象和爬行现象,在参数变化时具有较好的稳态性能和较强的鲁棒性。 相似文献
11.
多机电力系统附加NNPSS的在线学习神经网络逆励磁控制器 总被引:1,自引:0,他引:1
为提高发电机机端电压和转速的综合控制性能,设计了附加神经网络电力系统稳定器(NNPSS)的在线学习神经网络逆(OLANNI)励磁控制器。针对多机系统同步发电机组模型,根据逆系统方法得到发电机励磁系统的逆系统的表达形式,并通过离线训练得到发电机励磁系统的神经网络逆系统。借鉴传统的AVR/PSS控制方法,并考虑到其对电力系统不确定性的自适应能力的不足,在离线训练的基础上分别设计了自适应的OLANNI、NNPSS以取代传统的AVR、PSS,给出了基于在线梯度算法的OLANNI和NNPSS的在线学习算法,并根据Lyapunov稳定性理论证明了OLANNI和NNPSS在线学习的收敛性。将设计的控制器应用于一个典型的2区域4机系统,仿真研究结果表明:在系统遭受扰动时,所设计的控制器较AVR/PSS和OLANNI控制器具有更好的综合控制性能。 相似文献
12.
Takenori Kobayashi Akihiko Yokoyama Yasuo Morioka 《Electrical Engineering in Japan》1995,115(5):38-51
Control equipment of synchronous generators such as automatic voltage regulators, speed governors and power system stabilizers have been developed to maintain stability and to improve damping of power systems. When an operating condition changes greatly, however, such controllers may become less effective because of nonlinearity of the power system. In this paper, a nonlinear adaptive generator control system using neural networks is proposed. The proposed neurocontrol system consists of two neural networks which work as an identifier and a controller, respectively, and generates supplementary control signals to the conventional controllers. An essential feature of the proposed system is that the internal connection weights of both neural networks are adjusted adaptively so as to generate appropriate control signals for transient stability and damping enhancement in response to changes of the operating conditions and the network configuration. To investigate the control performance of the proposed neurocontrol system, digital time simulations are carried out for a one-machine infinite bus model system. As a result, it is clarified that the proposed adaptive neurocontrol system effectively improves the system damping and shows adaptability against the wide changes of the operating conditions. 相似文献
13.
In this paper, a model reference adaptive sliding mode (MRASMC) using a radical basis function (RBF) neural network (NN) is proposed to control the single-phase active power filter (APF). The RBF NN is utilized to approximate the nonlinear function and eliminate the modeling error in the APF system. The model reference adaptive current controller in AC side not only guarantees the globally stability of the APF system but also the compensating current to track the harmonic current accurately. Moreover, a sliding mode voltage controller based on an exponential approach law is designed to improve the tracking performance of DC side voltage. Simulation results demonstrate strong robustness and outstanding compensation performance with the proposed APF control system. In conclusion, MRASMC using RBF NN can improve the adaptability and robustness of the APF system and track the given instructional signal quickly. 相似文献
14.
针对区域互联电力系统受到风电及负荷扰动后,系统频率会出现大幅度波动的问题,提出一种基于云神经网络自适应逆系统的多区域互联电力系统负荷频率控制方法。在分析单一区域电力系统有功输出特性的基础上,建立计及多区域有功输出的互联电力系统负荷频率控制模型。采用自适应逆控制有效解决系统响应和扰动抑制的矛盾。将云模型引入自适应逆系统构建云神经网络辨识器。利用云模型在处理模糊性和随机性等不确定性方面的优势,进一步提高神经网络的辨识能力。仿真结果表明,所设计的云神经网络自适应逆系统不仅可以得到好的动态响应,还可以使风电及负荷引起的扰动减小到最小。 相似文献
15.
Yongping Pan Chenguang Yang Mahardhika Pratama Haoyong Yu 《International Journal of Adaptive Control and Signal Processing》2019,33(12):1726-1738
The ability to learn is crucial for neural network (NN) control as it is able to enhance the overall stability and robustness of control systems. In this study, a composite learning control strategy is proposed for a class of strict‐feedback nonlinear systems with mismatched uncertainties, where raised‐cosine radial basis function NNs with compact supports are applied to approximate system uncertainties. Both online historical data and instantaneous data are utilized to update NN weights. Practical exponential stability of the closed‐loop system is established under a weak excitation condition termed interval excitation. The proposed approach ensures fast parameter convergence, implying an exact estimation of plant uncertainties, without the trajectory of NN inputs being recurrent and the time derivation of plant states. The raised‐cosine radial basis function NNs applied not only reduces computational cost but also facilitates the exact determination of a subregressor activated along any trajectory of NN inputs so that the interval excitation condition is verifiable. Numerical results have verified validity and superiority of the proposed approach. 相似文献
16.
为了更好地实现电力系统暂态稳定预防控制,提出了基于卷积神经网络(Convolutional Neural Network, CNN)的电力系统暂态稳定预防控制方法。通过CNN模型输出变量灵敏度选择控制发电机并确定控制量,然后采用CNN和时域仿真相结合的暂态稳定评估方法进行控制方案校核,得到使系统在预想故障下稳定的控制方案。采用某省级电网算例进行预防控制效果验证。结果表明,采用所提出的预防控制方法,可以找到使系统恢复稳定的预防控制策略。 相似文献
17.
故障期间形成的暂态能量造成发电机的摇摆振荡,故障切除后,该暂态能量(TE)是增加还是减少将决定发电机的振荡是增幅还是减幅,TE反映了发电机稳定性受到危害的程度.以单机无穷大系统为例,给出了不同故障类型下TE随时间变化的曲线,分析了汽轮机模型、水轮机模型以及调速系统附加鲁棒控制(GAHC)对TE的影响.通过理论分析和对比仿真实验得到的TE和转速曲线表明:汽轮机调速系统有助于TE衰减,水轮机的水锤效应在故障开始后的一段时间内不利于TE的衰减;从理论上证明了GAHC加快TE衰减提高同步发电机稳定性的作用;利用TE能够定量直观地评价控制方法对发电机稳定性的控制效果。 相似文献
18.
19.
It is well known that the angle-dependent disturbance in a servo motor caused by nonuniformity of field windings, armature cogging, rotor imbalance, nonuniform load and so on, may influence the speed control performance greatly. This often leads to large speed fluctuations which are undesired in practical situations. Therefore speed fluctuation reduction techniques in the presence of angle-dependent disturbances are strongly required and have been studied by many researchers. In this paper, the authors propose a new approach to this problem via adaptive control with the aid of a radial basis function (RBF) network composed of Gaussian basis functions. The angle-dependent disturbance, viewed as a periodic non-linear function with a period of 2π radians in the angular domain, is approximated by an RBF network in (0, 2π) radians. Then an adaptive linearization control system employing the RBF network which compensates for the disturbance is proposed. The RBF network has the advantage that it is linear in the parameters and hence parameter adaption is very fast and easy to implement. It is proved through theoretical analysis that the stability of adaptive control is guaranteed by Lyapunov stability theory. Finally, simulation and experimental results are included in the paper to show the excellent performance of the proposed method. © 1997 Scripta Technica, Inc. Electr Eng Jpn, 119(4): 77–86, 1997 相似文献