The hydraulic roll bending control system usually has the dynamic characteristics of nonlinearity, slow time variance and strong outside interference in the roiling process, so it is difficult to establish a precise m...The hydraulic roll bending control system usually has the dynamic characteristics of nonlinearity, slow time variance and strong outside interference in the roiling process, so it is difficult to establish a precise mathemati- cal model for control. So, a new method for establishing a hydraulic roll bending control system is put forward by cerebellar model articulation controller （CMAC） neural network and proportional-integral-derivative （PID） coupling control strategy. The non-linear relationship between input and output can be achieved by the concept mapping and the actual mapping of CMAC. The simulation results show that, compared with the conventional PID control algo- rithm, the parallel control algorithm can overcome the influence of parameter change of roll bending system on the control performance, thus improve the anti jamming capability of the system greatly, reduce the dependence of con- trol performance on the accuracy of the analytical model, enhance the tracking performance of hydraulic roll bending loop for the hydraulic and roll bending force and increase system response speed. The results indicate that the CMAC-P1D coupling control strategy for hydraulic roll bending system is effective.展开更多
In order to overcome the system non-linearity and uncertainty inherent in magnetic bearing systems, a GA（genetic algnrithm）-based PID neural network controller is designed and trained tO emulate the operation of a c...In order to overcome the system non-linearity and uncertainty inherent in magnetic bearing systems, a GA（genetic algnrithm）-based PID neural network controller is designed and trained tO emulate the operation of a complete system （magnetic bearing, controller, and power amplifiers）. The feasibility of using a neural network to control nonlinear magnetic bearing systems with unknown dynamics is demonstrated. The key concept of the control scheme is to use GA to evaluate the candidate solutions （chromosomes）, increase the generalization ability of PID neural network and avoid suffering from the local minima problem in network learning due to the use of gradient descent learning method. The simulation results show that the proposed architecture provides well robust performance and better reinforcement learning capability in controlling magnetic bearing systems.展开更多
为提高氮化炉温度控制精度,提出一种基于模糊神经网络PID的氮化炉温度控制方法。即采用模糊神经网络对PID控制的K_(p)、K_(i)、K_( d )3个控制参数进行优化整定,而考虑到模糊神经网络的局限,采用改进后的CS算法对模糊神经网络的初始权...为提高氮化炉温度控制精度,提出一种基于模糊神经网络PID的氮化炉温度控制方法。即采用模糊神经网络对PID控制的K_(p)、K_(i)、K_( d )3个控制参数进行优化整定,而考虑到模糊神经网络的局限,采用改进后的CS算法对模糊神经网络的初始权值和阈值进行优化;最后,根据设计的基于模糊神经网络的PID控制方法搭建新的氮化炉温度控制器,并进行试验测试。试验结果表明:采用FA算法的吸引力机制对CS算法进行改进的方法可以有效提高CS算法的搜索能力和收敛速度;而改进后的CS算法在经过6次迭代后适应度值趋近于零,快速达到平稳,获取最优模糊神经网络的初始权值和阈值;优化后PNN-PID控制曲线在110 s后便达到稳定,与传统PID控制曲线相比,调整时间大幅下降;优化后PNN-PID控制器输出的氮化炉温度控制阶跃信号,其调整时间为960 s左右,与传统PID控制曲线相比,响应速度明显提升,且与系统给出预期温度控制信号曲线几乎完全重叠,控制误差极小,实现了提高氮化炉温度控制精度的目的。展开更多
基金Item Sponsored by National High-Tech Research and Development Program(863Program)of China(2009AA04Z143)Natural Science Foundation of Hebei Province of China(E2006001038)Hebei Provincial Science and Technology Project of China(10212101D)
文摘The hydraulic roll bending control system usually has the dynamic characteristics of nonlinearity, slow time variance and strong outside interference in the roiling process, so it is difficult to establish a precise mathemati- cal model for control. So, a new method for establishing a hydraulic roll bending control system is put forward by cerebellar model articulation controller （CMAC） neural network and proportional-integral-derivative （PID） coupling control strategy. The non-linear relationship between input and output can be achieved by the concept mapping and the actual mapping of CMAC. The simulation results show that, compared with the conventional PID control algo- rithm, the parallel control algorithm can overcome the influence of parameter change of roll bending system on the control performance, thus improve the anti jamming capability of the system greatly, reduce the dependence of con- trol performance on the accuracy of the analytical model, enhance the tracking performance of hydraulic roll bending loop for the hydraulic and roll bending force and increase system response speed. The results indicate that the CMAC-P1D coupling control strategy for hydraulic roll bending system is effective.
基金This project is supported by National Natural Science Foundation of China (No. 5880203).
文摘In order to overcome the system non-linearity and uncertainty inherent in magnetic bearing systems, a GA（genetic algnrithm）-based PID neural network controller is designed and trained tO emulate the operation of a complete system （magnetic bearing, controller, and power amplifiers）. The feasibility of using a neural network to control nonlinear magnetic bearing systems with unknown dynamics is demonstrated. The key concept of the control scheme is to use GA to evaluate the candidate solutions （chromosomes）, increase the generalization ability of PID neural network and avoid suffering from the local minima problem in network learning due to the use of gradient descent learning method. The simulation results show that the proposed architecture provides well robust performance and better reinforcement learning capability in controlling magnetic bearing systems.
文摘为提高氮化炉温度控制精度,提出一种基于模糊神经网络PID的氮化炉温度控制方法。即采用模糊神经网络对PID控制的K_(p)、K_(i)、K_( d )3个控制参数进行优化整定,而考虑到模糊神经网络的局限,采用改进后的CS算法对模糊神经网络的初始权值和阈值进行优化;最后,根据设计的基于模糊神经网络的PID控制方法搭建新的氮化炉温度控制器,并进行试验测试。试验结果表明:采用FA算法的吸引力机制对CS算法进行改进的方法可以有效提高CS算法的搜索能力和收敛速度;而改进后的CS算法在经过6次迭代后适应度值趋近于零,快速达到平稳,获取最优模糊神经网络的初始权值和阈值;优化后PNN-PID控制曲线在110 s后便达到稳定,与传统PID控制曲线相比,调整时间大幅下降;优化后PNN-PID控制器输出的氮化炉温度控制阶跃信号,其调整时间为960 s左右,与传统PID控制曲线相比,响应速度明显提升,且与系统给出预期温度控制信号曲线几乎完全重叠,控制误差极小,实现了提高氮化炉温度控制精度的目的。
