共查询到20条相似文献,搜索用时 109 毫秒
1.
2.
3.
4.
5.
6.
7.
针对压电陶瓷固有的迟滞非线性,设计了一种基于深度神经网络(DNN)的前馈补偿控制系统。该系统包含1个输入层、7个隐藏层和1个输出层。实验结果表明,开环情况下压电陶瓷的位移线性误差达8.91μm。施加神经网络前馈补偿后,压电陶瓷的最大位移误差降低到80 nm,稳态误差为±20 nm。进一步测试表明,在10~100 Hz输入频率下系统最大误差小于100 nm,均方根误差为0.01μm,验证了深度神经网络能够准确补偿压电陶瓷动态迟滞非线性,具有较好的频率泛化能力。 相似文献
8.
9.
以对称式微位移缩小机构和柔性铰链相结合,压电陶瓷驱动的微进给刀架可实现精密加工,但刀架的迟滞特性影响其定位精度。该文根据非线性Preisach模型的理论知识及压电陶瓷驱动微进给刀架的电压位移特性,将模型进行修改后得到刀架迟滞特性的数学模型,并对数学模型式进行离散化处理。实验结果表明,改进后的迟滞模型形式简单,数据采集简便,模型描述精确,能较好地实现压电驱动微进给刀架的迟滞建模,提高了迟滞模型的实用性。为提高压电陶瓷驱动微进给刀架的定位精度,实现精密控制打下基础。 相似文献
10.
11.
12.
研究了微型三坐标测量仪中由压电陶瓷器件+柔性铰链构成的微动系统.根据该微动系统对定位精度的要求及微动系统具有迟滞、蠕变等强非线性的特点,该文提出一种神经网络自适应模糊推理比例微分积分(PID)位置控制系统,并进行了控制系统结构研究和实验分析.跟踪实验结果表明,智能PID控制能有效改善系统的动态和静态性能;定位精度实验表明两轴双向定位精度较传统PID控制有大的提高,达到了设计要求. 相似文献
13.
《Mechatronics》2006,16(2):97-104
The LuGre model which has been widely used to describe the friction phenomenon for mechanical systems consists of stiffness and viscous terms. The stiffness term of the LuGre model shows the friction torque to act linearly for the internal state of friction dynamics. Thus it cannot represent the hysteresis phenomenon of friction in the pre-sliding phase. Especially the hysteresis has the non-local memory characteristics. In this paper, the non-local memory hysteresis phenomenon is analyzed through experiments and the improved friction model using the Preisach model is proposed. In order to implement the Preisach model, the neural network algorithm is used to increase the efficiency of the Preisach algorithm. Based on the improved friction model, the adaptive back-stepping sliding mode controller (SMC) is designed to improve tracking performance in the sliding and pre-sliding phases. To evaluate the performance of the proposed friction control system, experiments are executed for a ball-screw servo system and the satisfactory results are shown. 相似文献
14.
Hsin-Jang Shieh Faa-Jeng Lin Po-Kai Huang Li-Tao Teng 《Industrial Electronics, IEEE Transactions on》2006,53(3):905-914
An adaptive displacement control with hysteresis modeling for a piezoactuated positioning mechanism is proposed in this paper because the dynamic performance of piezosystems is often severely deteriorated due to the hysteresis effect of piezoelectric elements. First, a new mathematical model based on the differential equation of a motion system with a parameterized hysteretic friction function is proposed to represent the dynamics of motion of the piezopositioning mechanism. As a result, the mathematical model describes a motion system with hysteresis behavior due to the hysteretic friction. Then, by using the developed mathematical model, the adaptive displacement tracking control with the adaptation algorithms of the parameterized hysteretic function and of an uncertain parameter is proposed. By using the proposed control approach on the displacement control of the piezopositioning mechanism, the advantages of the asymptotical stability in displacement tracking, high-performance displacement response, and robustness to the variations of system parameters and disturbance load can be provided. Finally, experimental results are illustrated to validate the proposed control approach for practical applications. 相似文献
15.
In this paper, a parallel adaptive neural network control system applicable to nonlinear dynamical systems of the type commonly encountered in many practical position control servomechanisms is developed. The controller is based on the use of direct adaptive techniques and an approach of using an additional parallel neural network to provide adaptive enhancements to a basic fixed neural network-based nonlinear controller. Properties of the proposed new controller are discussed in the paper and it is shown that if Gaussian radial basis function networks are used for the additional parallel neural network, uniformly stable adaptation is assured and asymptotic tracking of the position reference signal is achieved. The effectiveness of the proposed adaptive neural network control system is demonstrated in real-time implementation experiments for position control in a servomechanism with asymmetrical loading and changes in the load. 相似文献
16.
17.
针对传统 Prandtl-Ishlinskii(PI)模型不能反映压电式气体比例阀迟滞非对称特性而导致其补偿控制精度难以提高的问题,提出了一种改进的 PI模型,通过添加3次多项式使其能拟合压电式气体流量比例控制阀的非对称迟滞曲线。利用改进的自适应粒子群遗传算法辨识所需的模型参数,模型相对误差为0.0073%,并将模型用于前馈补偿控制。实验结果表明,基于迟滞模型的前馈补偿控制可显著提高压电式气体比例阀输出流量控制的快速性,调节时间降低了60%。 相似文献
18.
19.
Position control of Shape Memory Alloy (SMA) actuators has been a challenging topic during the last years due to their nonlinearities in the governing physical equations as well as their hysteresis behaviors. Using the inverse of phenomenological hysteresis model in order to compensate the input–output hysteresis behavior of these actuators shows the effectiveness of this approach. In this paper, in order to control the tip deflection of a large deformation flexible beam actuated by an SMA actuator wire, a feedforward–feedback controller is proposed. The feedforward part of the proposed control system, maps the beam deflection into SMA temperature, is based on the inverse of the generalized Prandtl–Ishlinskii model. An adaptive model reference temperature control system is cascaded to the inverse hysteresis model in order to estimate the SMA electrical current for tracking the reference signal. In addition, a closed-loop proportional–integral controller with position feedback is added to the feedforward controller to increase the accuracy as well as eliminate the steady state error in position control process. Experimental results indicate that the proposed controller has great accuracy in tracking some square wave signals. It is also experimentally shown that the suggested controller has precise tracking performance in presence of environmental disturbances. 相似文献
20.
In this paper, we present a technique for using an additional parallel neural network to provide adaptive enhancements to a basic fixed neural network-based nonlinear control system. This proposed parallel adaptive neural network control system is applicable to nonlinear dynamical systems of the type commonly encountered in many practical position control servomechanisms. Properties of the controller are discussed, and it is shown that if Gaussian radial basis function networks are used for the additional parallel neural network, uniformly stable adaptation is assured and the approximation error converges to zero asymptotically. In the paper, the effectiveness of the proposed parallel adaptive neural network control system is demonstrated in real-time implementation experiments for position control in a servomechanism with asymmetrical loading and changes in the load 相似文献