Robust control of three‐degree‐of‐freedom spherical actuator based on deep reinforcement learning
Robust control of three‐degree‐of‐freedom spherical actuator based on deep reinforcement learning
复制标题
基于深度强化学习的三自由度球形执行器鲁棒控制
DOI：
10.1002/tee.23563
复制
发表时间：
2022
影响因子：
1
通讯作者：
Hirata Katsuhiro
中科院分区：
文献类型：
--
作者：
Fusayasu Hirotsugu;Heya Akira;Hirata Katsuhiro
多自由度球面执行器已被广泛应用于机器人和工业机械领域。提出了一种可实现高扭矩密度的外转子三自由度球面作动器。使用基于扭矩常数矩阵的扭矩生成方程来计算每个线圈的输入电流。由于各种制造错误，永磁型致动器存在产生意外齿槽扭矩的问题。制造误差主要是指电机设计阶段的理想尺寸与批量生产中的实际尺寸之间的差异。在这种情况下，执行器将超过经典比例-积分-微分(PID)控制器的限制。因此，通过引入深度神经网络，我们提出了一种基于强化学习的电流补偿器，有望提高球形执行器的鲁棒性。该电流补偿器被应用于齿槽扭矩制造波动等不确定问题。对深度强化学习的主要参数奖励值进行了检验，与经典的PID控制器和简单神经网络(NN)控制器相比，减小了控制误差。©2022日本电气工程师学会。由威利期刊有限责任公司出版。
Multi‐degree‐of‐freedom (multi‐DOF) spherical actuators have been developed for the fields of robotics and industrial machineries. We have proposed an outer rotor type three‐DOF spherical actuator that can realize a high torque density. Each coil input current is calculated using a torque generating equation based on the torque constant matrix. The permanent magnet type actuators have a problem with generating unexpected cogging torque due to various manufacturing errors. Manufacturing errors mainly mean differences between the ideal dimensions at the motor design stage and the actual dimensions in mass production. In this case, the actuator would exceed the limitations of classical proportional‐integral‐differential (PID) controllers. Therefore, we propose a current compensator using reinforcement learning by introducing a deep neural network that is expected to improve the robustness of spherical actuators. This current compensator was applied to uncertainty problems such as manufacturing fluctuations of cogging torque. We examined the reward, which is the main parameter of deep reinforcement learning, and reduced the control error compared to classical PID controller and simple neural network (NN) controller. © 2022 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.
登录
查看更多内容
带辅助极的三自由度球形执行器的提案
DOI：
10.1109/isef45929.2019.9097061
发表时间：
2019
期刊：
2019 19th International Symposium on Electromagnetic Fields in Mechatronics, Electrical and Electronic Engineering (ISEF)
影响因子：
--
作者：
K. Takahara;K. Hirata;N. Niguchi;Tomoya Amazutsumi
通讯作者：
Tomoya Amazutsumi
影响因子：
2.1
作者：
B. V. Ninhuijs;J. Jansen;B. Gysen;Elena A. Lomonova
通讯作者：
Elena A. Lomonova
考虑磁各向异性的永磁同步电机齿槽转矩计算
DOI：
10.1108/03321640410540548
发表时间：
2004
影响因子：
0.7
作者：
S. Yamaguchi;A. Daikoku;N. Takahashi
通讯作者：
N. Takahashi
三自由度球形执行机构定位计算精度分析
影响因子：
2.1
作者：
H. Fusayasu;Yuji Masuyama;K. Hirata;N. Niguchi;K. Takahara
通讯作者：
K. Takahara