然后应用反馈误差学习法修正学习误差。
Then, the feedback error learning is applied to reduce the learning errors.
它通过构造伪输出辨识被控对象参数，引进反馈误差，实现对解耦神经网络的在线训练。
It can identify the parameters of a controlled object by forming a fake output and bring in a feedback error for performing an on-line training to decouple the neural network.
同时提出了一个反馈误差学习算法，用于对模糊检测规则进行改进以求达到识别的最优。
And a feedback study algorithm is proposed, with which it modifies the fuzzy detection rules to get the optimal results of recognition.
DRNN控制器是根据GMA的滞回特性构造的，通过反馈误差学习方案在线学习GMA的逆滞回模型。
The DRNN controller was constructed based on the hysteretic characteristics of the GMA, and on-line learned the inverse hysteresis model of the GMA by the feedback-error learning scheme.
此外，就放大器输入电路及反馈环节的数学模型进行了误差计算与工作稳定性的分析与评价。
In addition, the mathematical model of the input circuit and the feedback link of the amplifier are analyzed on the error computation and stability evaluation.
灯管的亮度能够通过反馈回路，或者设置误差放大器输入端的参考端直流电平来调整。
The lamp dimming can be done through this feedback loop or, by setting the reference DC level of the input of error amplifier.
通过对受控对象模型的并行结构分解，引入多重输出误差反馈，构成了一种新的内模控制结构。
A novel internal model control structure with multiple output error feedbacks is proposed in this paper, by means of multi model decomposition technique.
反馈系统包含了跟踪误差的未来信息，以便改善发电机的跟踪速度和控制效果。
To improve the tracking speed and control effects of the generator, the feedback system includes indirectly the future information of the tracking errors.
本文通过对被控对象模型的传递函数并行结构分解，引入多重输出误差反馈，并根据内模结构来设计系统控制器。
In this paper, multiple output error feedbacks are introduced via the parallel decomposition of the plant transfer function in the internal model control system.
利用非线性系统的线性反馈理论，考虑动力学建模的模型误差和外界干扰等不确定因素，提出了一种鲁棒轨迹跟踪控制策略。
The robust trajectory tracking control strategy accounts for model errors and external disturbances using linear feedback theory for the non-linear system, which ensures system stability and li.
本文导出误差反馈次最优二阶状态空间数字滤波器单位噪声增益的计算公式。
A simple formula of unit noise gain is derived for suboptimal second-order state-space digital filter with error feedback.
在经典控制理论和现代控制理论中，反馈被用来产生作为控制器输入的误差。
In classical control theory and modern control theory, feedback is used to produce errors which is the input of a controller.
本文将最小误差激励(mee)法推广应用于多机电力系统分散输出反馈控制器的设计。
This paper proposes the application of extended minimum error excitation (MEE) method to designing decentralized output feedback controllers for multi-machine power systems.
自抗绕控制器由三部分组成：跟踪微分器、扩张状态观测器和非线性状态误差反馈控制律。
The auto-disturbance rejection controller is composed of three parts: tracking-differentiator, extended state observer and nonlinear state error feedback control law.
本文提出一种新的基于三次样条曲线的面积误差反馈曲线拟合方法。
A new curve fitting method using area error feedback based on cubic splines is presented.
并用方块图与反馈控制理论导出了这种调速回路速度刚性的数学表达式，估算了由负载引起的速度误差。
By block diagram and feedback-control principles expression is derived for speed-stiffness in the loop and speed error due to load calculated.
结合误差反馈同步方法和参数自适应同步方法，使参数不同的两个系统达到同步，数值计算结果也表明同步效果很好。
A method for synchronization of two systems with parameters perturbation is presented, which combines the error feedback approach with the parameter adaptive control way.
结果表明：该方法能够有效地抑制位置反馈元件周期性误差导致的速率波动，提高转台的速率平稳性。
The results show that this method can efficiently restrain the rate ripple of the table caused by the periodic errors of position feedback elements, and can raise the rate stability of tables.
分析表明：最优策略实质上是以零控脱靶作为误差信号的反馈控制。
Our mathematical analysis shows that the optimal strategy is actually a feedback control that takes zero -effect miss as error signal.
在反馈控制器中比例控制器用来调节压电作动器的输出误差。
In the feedback controller design, a proportional controller is used to regulate the output error of piezoelectric actuators.
这种方法比反馈环法定时精度高，定时误差捕获快，并且不需要时钟源，不占用片内硬件资源，适合于全软件化设计要求。
Contrasted with the feedback loop this method is more accurate, the timing error is caught faster, the time resource is not necessary and it does not occupy resources of the hardware in DSP.
除此之外，本文对可行性研究的结论进行了一定的反馈，分析造成误差的实际原因。
In addition, this text carries on the certain feedback to the conclusion that possibility study, the analysis results in actual reason of the error margin.
根据卡尔曼滤波新息过程的统计特点，将新息过程部分反馈到DR方程以抑制DR的误差发散。
Innovations of FKF are partly fed back to DR equations to restrain the accumulation of error according to the characteristic of innovations.
该文针对存在信道估计误差的有限反馈多用户多输入多输出(MIMO)传输性能进行分析。
In this paper, the impact of channel estimation error on the performance of multiuser Multiple-Input Multiple-Output (MIMO) transmission based on limited feedback information is analyzed.
利用计算出来的速度反馈构成了速度闭环系统，并采用低通滤波方法减小误差，同时应用了零矢量调制控制法减小转矩脉动，提高了整个系统的控制性能。
Constituted the speed closed-loop system with the speed feedback, used the low pass filter method to reduce the error, so the overall system control performance is advanced.
反馈计算部分(240)将量化误差进行滤波，并且将滤波结果输出到加法器(250)。
The feedback computing section (240) filters the quantization error and outputs the result of the filtering to the adder (250).
用复合控制把惯导系统测量的炮塔俯仰转动角速度（扰动角速度）反馈到控制前端，进行预先补偿，可保证小的瞬态误差和系统的稳定性。
The stability and small dynamic errors could be confirmed by using the method of composite control in which the pitch angular rate of barbette sensed by INS was feed back and compensated in advance.
最后，给出了一种基于汉字图形轮廓特征的误差估计方法，并利用误差估计初步建立了一套带有反馈的汉字识别系统。
At last, a set of Chinese characters recognition system with reaction are constructed, based on and using the error estimation approach of Chinese characters Outlines feature.
利用神经网络具有自学习的优点，可以大大减少误差反馈问题对工艺数据的需求，并且便于系统的扩展。
Utilize the neural network to have advantage taught oneself to practise, can reduce the error and feedback the demand for the craft data of the question greatly, and benefit systematic expansion.
利用神经网络具有自学习的优点，可以大大减少误差反馈问题对工艺数据的需求，并且便于系统的扩展。
Utilize the neural network to have advantage taught oneself to practise, can reduce the error and feedback the demand for the craft data of the question greatly, and benefit systematic expansion.
应用推荐