然后，以这些数据为基础训练倒立摆的神经网络逆模型；
Then the neural network based inverse model of the inverted pendulum is trained.
由SVM辨识的逆模型作为前馈控制器，形成直接逆模型控制器。
SVM based inverse model of nonlinear system is used as feed-forward controller to form direct inverse model controller.
首先，根据被控对象传递函数和灵敏度分析，简化被控对象逆模型。
Firstly, according to analyzing both the transfer function of the object and the sensitivity, the inverse model of the object is simplified.
采用支持向量回归在线辨识算法作为建模方法建立被控对象的逆模型。
Online identification algorithm of support vector regression is used to build the inverse model for the plant.
由SVM辨识非线性系统的逆模型作为前馈控制器，形成直接逆控制。
SVM were used to identify the inverse model of nonlinear system, and this inverse model was used as feed-forward controller to design direct inverse control.
在使用神经网络完成非线性对象的模型和逆模型时，选择的训练方法很重要。
Choosing a training method is very important when using neural network to obtain the model and the inverse model of the nonlinear object.
提出基于逼近逆模型及趋近律的综合控制方法来综合一类非线性系统的控制律。
An integrated control method based on approximate inverse model and tendency rate for a class of nonlinear system is presented.
介绍了用自适应LMS滤波器离线辨识六面体单元柔性结构模型和逆模型的方法。
A method of adaptive LMS filter is presented in this paper to identify the model and inverse model of the hexahedral unit of flexible truss.
可准确描述其非线性特性的磁流变阻尼器正模型通常非常复杂，难以直接得到逆模型。
It is quite difficult to describe the direct model of the MR damper, however, it is much more difficult for the inverse model.
同时以探测器特定时刻输出电压作为观测量，建立了称之为模型2的探测器光路逆模型。
At the same time, a model called model 2 is modeled using the voltages of the output of photodetector at special time as observed quantities.
为了进行迟滞非线性补偿，提出了相位补偿与迟滞逆模型相结合来补偿迟滞特性的控制方法。
In order to mitigate the effect of the hysteresis, the control method for compensating hysteresis was proposed by combining the inverse model and phase-angle compensation.
从系统逆模型补偿出发，基于神经网络提出一种更加完备的热敏电阻测温系统非线性校正方法。
Based on the property of the system inverse model, an integral approach to nonlinear compensation of temperature measuring system with thermistor based on neural network is presented.
初始过程的逆模型，建立了基于最小二乘支持向量机，并通过剪枝算法将支持向量的数量减少。
The initial inverse model of process is built based on least squares support vector machine, and the Numbers of support vector is reduced through pruning algorithm.
考虑到某些模糊系统的万能逼近能力，本文提出用模糊系统来逼近磁流变阻尼器逆模型的新思路。
The paper presents a novel train of thoughts to approach to the inverse model of the MR damper by using the universal approximation of a kind of fuzzy system.
根据自适应神经模糊推理系统原理，设计两个模糊系统分别逼近磁流变阻尼器的正模型和逆模型。
Then two different fuzzy systems are designed to approximate the direct model and the inverse one on the basis of adaptive neuro-fuzzy inference system(ANFIS).
此方法把有源滤波器及主电路部分看作广义有源滤波器并利用其逆模型作为控制器对其进行控制。
The active filter and the main circuit are look as the generalized active filter and the inverse of its model is used as the controller to control the active filter.
在这种自适应逆控制机制中，逆模型通过递归最小二乘算法更新，控制器依据-滤波进行在线调整。
In this adaptive inverse control mechanism, the inverse model is updated through recursive least squares algorithm, and controller is adjusted online according to method of filter.
非线性动态系统的内模控制要求建立精确的对象正模型和逆模型，这对于大多数实际对象是难以做到。
In the internal model control design for nonlinear systems, the precise forward and inverse models of plant are required, but it is impossible in the majority of practical plants.
仿真结果表明，在没有被控对象先验知识的情况下，利用该方法能准确地建立连续非线性系统的逆模型。
Simulation results show that the presented method can accurately construct the inverse dynamic model of the continuous nonlinear system even without prior knowledge about the controlled plant.
该控制器的正模型和逆模型都以三层BP神经网络为主体，实现对SVC及电网的动态描述和对SVC的控制。
Three-layer BP neural network models are used for the internal model and the reverse model of the controlled system in the controller.
由于纯延迟离散系统仅存在延时的逆模型，因而对该系统进行自适应逆控制时，扰动消除会产生一定的延迟误差。
There only exists delay inversion model in pure-delay discrete system which causes delay error when adaptive inverse control is used for canceling noise.
最后比较了逆模型控制和反s变换控制，逆模型控制有更好的效果，可以很好控制酸性到弱酸和碱性到弱碱的情况。
At last, compared with anti-S transform control, the inverse control has a better effect on the process changing from strong acid to weak acid or from strong base to weak base.
本文提出一种基于T -S模型的变结构模糊神经网络直接逆模型控制器，并将其应用于移动机器人的运动控制中。
A direct inverse model controller of fuzzy neural network with changeable structure based on t s inference is presented in this paper and it is used to the motion control of mobile robot.
研究了特征值反问题求解的几种神经网络模型：直接逆模型，间接逆模型，优化方法模型，指出了各种方法的应用范围。
In this paper, several artificial neural network based models of solving inverse eigenvalue problem and their characters are studied. These models are direct, indirect and optimization inverse models.
针对桥式起重机运行过程中载荷摆动造成的运行精度差和工作效率低下问题，提出了一种神经网络直接逆模型控制方法，以降低载荷摆动。
The model of a rotary crane was derived to know the reason of load swing, and as a result, the load swing could be well controlled.
仿真研究表明，SVM具有优良的逆模型辨识能力，基于模糊控制补偿的支持向量机逆控制系统的动态性能好、跟踪精度高、鲁棒稳定性强。
Simulations demonstrate that SVM has good nonlinear approximation capability for inverse model, and the proposed control system has good dynamic and static performances as well as good robustness.
仿真研究表明，只要恰当地选择神经网络正、逆模型的结构和辨识数据的长度等参数，实现加热炉神经网络内模自校正控制的结果是令人满意的。
Simulation shows that if chosen the appropriate ANN structure and training data quantity, its ANN internal model self-tuning control can be realized and the results can be acceptable.
仿真研究表明，只要恰当地选择神经网络正、逆模型的结构和辨识数据的长度等参数，实现加热炉神经网络内模自校正控制的结果是令人满意的。
Simulation shows that if chosen the appropriate ANN structure and training data quantity, its ANN internal model self-tuning control can be realized and the results can be acceptable.
应用推荐