针对非线性过程,提出了一种基于自构建神经网络的内模控制方法(Internal Model Control,IMC)。采用自构建算法实现神经网络的结构学习和参数学习,在被控过程内部模型和控制器模型的辨识过程中,该网络能够根据给定的判定条件自动增加神...针对非线性过程,提出了一种基于自构建神经网络的内模控制方法(Internal Model Control,IMC)。采用自构建算法实现神经网络的结构学习和参数学习,在被控过程内部模型和控制器模型的辨识过程中,该网络能够根据给定的判定条件自动增加神经元节点,以满足辨识精度的要求;为了防止网络学习过拟合,基于灵敏度方法对神经网络隐层节点进行修剪删除;网络的参数学习采用梯度下降法。自构建算法可以有效地避免普通神经网络内模控制方案中网络结构难以确定的问题,仿真结果表明,该控制系统有良好的跟踪性、鲁棒性和抗干扰性。展开更多
Tracking precision of pre-planned trajectories is essential for an auto-guided vehicle (AGV). The purpose of this paper is to design a self-constructing wavelet neural network (SCWNN) method for dynamical modeling and...Tracking precision of pre-planned trajectories is essential for an auto-guided vehicle (AGV). The purpose of this paper is to design a self-constructing wavelet neural network (SCWNN) method for dynamical modeling and control of a 2-DOF AGV. In control systems of AGVs, kinematical models have been preferred in recent research documents. However, in this paper, to enhance the trajectory tracking performance through including the AGV’s inertial effects in the control system, a learned dynamical model is replaced to the kinematical kind. As the base of a control system, the mathematical models are not preferred due to modeling uncertainties and exogenous inputs. Therefore, adaptive dynamic and control models of AGV are proposed using a four-layer SCWNN system comprising of the input, wavelet, product, and output layers. By use of the SCWNN, a robust controller against uncertainties is developed, which yields the perfect convergence of AGV to reference trajectories. Owing to the adaptive structure, the number of nodes in the layers is adjusted in online and thus the computational burden of the neural network methods is decreased. Using software simulations, the tracking performance of the proposed control system is assessed.展开更多
To improve the reliability and accuracy of the global po- sitioning system （GPS）/micro electromechanical system （MEMS）- inertial navigation system （INS） integrated navigation system, this paper proposes two diff...To improve the reliability and accuracy of the global po- sitioning system （GPS）/micro electromechanical system （MEMS）- inertial navigation system （INS） integrated navigation system, this paper proposes two different methods. Based on wavelet threshold denoising and functional coefficient autoregressive （FAR） model- ing, a combined data processing method is presented for MEMS inertial sensor, and GPS attitude information is also introduced to improve the estimation accuracy of MEMS inertial sensor errors. Then the positioning accuracy during GPS signal short outage is enhanced. To improve the positioning accuracy when a GPS signal is blocked for long time and solve the problem of the tra- ditional adaptive neuro-fuzzy inference system （ANFIS） method with poor dynamic adaptation and large calculation amount, a self-constructive ANFIS （SCANFIS） combined with the extended Kalman filter （EKF） is proposed for MEMS-INS errors modeling and predicting. Experimental road test results validate the effi- ciency of the proposed methods.展开更多
文摘针对非线性过程,提出了一种基于自构建神经网络的内模控制方法(Internal Model Control,IMC)。采用自构建算法实现神经网络的结构学习和参数学习,在被控过程内部模型和控制器模型的辨识过程中,该网络能够根据给定的判定条件自动增加神经元节点,以满足辨识精度的要求;为了防止网络学习过拟合,基于灵敏度方法对神经网络隐层节点进行修剪删除;网络的参数学习采用梯度下降法。自构建算法可以有效地避免普通神经网络内模控制方案中网络结构难以确定的问题,仿真结果表明,该控制系统有良好的跟踪性、鲁棒性和抗干扰性。
文摘Tracking precision of pre-planned trajectories is essential for an auto-guided vehicle (AGV). The purpose of this paper is to design a self-constructing wavelet neural network (SCWNN) method for dynamical modeling and control of a 2-DOF AGV. In control systems of AGVs, kinematical models have been preferred in recent research documents. However, in this paper, to enhance the trajectory tracking performance through including the AGV’s inertial effects in the control system, a learned dynamical model is replaced to the kinematical kind. As the base of a control system, the mathematical models are not preferred due to modeling uncertainties and exogenous inputs. Therefore, adaptive dynamic and control models of AGV are proposed using a four-layer SCWNN system comprising of the input, wavelet, product, and output layers. By use of the SCWNN, a robust controller against uncertainties is developed, which yields the perfect convergence of AGV to reference trajectories. Owing to the adaptive structure, the number of nodes in the layers is adjusted in online and thus the computational burden of the neural network methods is decreased. Using software simulations, the tracking performance of the proposed control system is assessed.
基金supported by the National Natural Science Foundation of China (60902055)
文摘To improve the reliability and accuracy of the global po- sitioning system （GPS）/micro electromechanical system （MEMS）- inertial navigation system （INS） integrated navigation system, this paper proposes two different methods. Based on wavelet threshold denoising and functional coefficient autoregressive （FAR） model- ing, a combined data processing method is presented for MEMS inertial sensor, and GPS attitude information is also introduced to improve the estimation accuracy of MEMS inertial sensor errors. Then the positioning accuracy during GPS signal short outage is enhanced. To improve the positioning accuracy when a GPS signal is blocked for long time and solve the problem of the tra- ditional adaptive neuro-fuzzy inference system （ANFIS） method with poor dynamic adaptation and large calculation amount, a self-constructive ANFIS （SCANFIS） combined with the extended Kalman filter （EKF） is proposed for MEMS-INS errors modeling and predicting. Experimental road test results validate the effi- ciency of the proposed methods.
