基于神经网络PID的SMA丝恒输出力控制方法

doi:10.3969/j.issn.0255-8297.2023.04.015

应用科学学报 ›› 2023, Vol. 41 ›› Issue (4): 718-726.doi: 10.3969/j.issn.0255-8297.2023.04.015

• 控制与系统 • 上一篇

基于神经网络PID的SMA丝恒输出力控制方法

王奔, 吕佩伦, 王扬威

东北林业大学机电工程学院, 黑龙江哈尔滨 150040

收稿日期:2021-08-30 发布日期:2023-08-02
通信作者: 王扬威,高级工程师,研究方向为康复机器人、工业机器人与自动化系统、仿生软体机器人、人工智能与智能装备。E-mail:wang.yangwei@nefu.edu.cn E-mail:wang.yangwei@nefu.edu.cn
基金资助:
国家自然科学基金（No. 52075089）；黑龙江省自然科学基金（No. LH2019E008）资助

Control Method of SMA Wire Constant Output Force Based on Neural Network PID

WANG Ben, Lü Peilun, WANG Yangwei

School of Mechanical and Electrical Engineering, Northeast Forestry University, Harbin 150040, Heilongjiang, China

Received:2021-08-30 Published:2023-08-02

摘要/Abstract

摘要： 为了实现形状记忆合金（shape memory alloys,SMA）丝的恒输出力控制，提出了一种基于粒子群优化神经网络比例积分微分（proportion integral differential,PID）的恒输出力控制方法，在研究SMA丝自感知电阻阻值和输出力、SMA丝温度对应关系的基础上，采用SMA丝电阻作为系统反馈，利用粒子群算法和神经网络算法对PID的参数进行优化，实现了SMA丝的恒输出力精确控制，与传统PID控制相比，降低了超调量，提高了响应速度。

关键词: 形状记忆合金, 粒子群优化, 神经网络优化, PID恒力控制

Abstract: To realize the constant output force control of shape memory alloys (SMA) wire, a constant output force control method based on particle swarm optimization neural network proportion integral differential (PID) is proposed. This paper examines the relationship between SMA wire self-perceived resistance value, output force, and temperature, with SMA wire resistance used as system feedback. Particle swarm algorithm is then applied to optimize the parameters of PID, achieving accurate control of constant output force of SMA wire, thereby reducing overshoot and improving response speed compared to traditional PID control.

Key words: shape memory alloy, particle swarm optimization, neural network optimization, PID constant force control

中图分类号:

TP18

王奔, 吕佩伦, 王扬威. 基于神经网络PID的SMA丝恒输出力控制方法[J]. 应用科学学报, 2023, 41(4): 718-726.

WANG Ben, Lü Peilun, WANG Yangwei. Control Method of SMA Wire Constant Output Force Based on Neural Network PID[J]. Journal of Applied Sciences, 2023, 41(4): 718-726.

参考文献

[1] 黄陈兵, 吴松柏, 张凯, 等. 线性超弹性镍钛合金丝材特性[J]. 信息记录材料, 2018, 19(10):1-2. Huang C B, Wu S B, Zhang K, et al. The property of linear superelastic Nickel-Titanium alloy wire[J]. Information Recording Materials, 2018, 19(10):1-2. (in Chinese)
[2] 李晓光, 张弼, 张道辉, 等. 形状记忆合金手指系统的输出力自适应控制[J]. 控制理论与应用, 2021, 38(1):33-43. Li X G, Zhang B, Zhang D H, et al. Adaptive force control of robotic finger actuated by shape memory alloy[J]. Control Theory & Applications, 2021, 38(1):33-43. (in Chinese)
[3] Song G B, Kelly B, Agrawal B N. Active position control of a shape memory alloy wire actuated composite beam[J]. Smart Materials and Structures, 2000, 9(5):711-716.
[4] Abdullah E J, Gaikwad P S, Azid N, et al. Temperature and strain feedback control for shape memory alloy actuated composite plate[J]. Sensors and Actuators A:Physical, 2018, 283:134-140.
[5] Lee S H, Kim S W. Improved position control of shape memory alloy actuator using the self-sensing model[J]. Sensors and Actuators A:Physical, 2019, 297:111529.
[6] Grant D, Hayward V. Constrained force control of shape memory alloy actuators[C]//IEEE International Conference on Robotics and Automation (ICRA), 2000:1314-1320.
[7] Choi S B, Han Y M, Kim J H, et al. Force tracking control of a flexible gripper featuring shape memory alloy actuators[J]. Mechatronics, 2001, 11(6):677-690.
[8] Teh Y H, Featherstone R. An architecture for fast and accurate control of shape memory alloy actuators[J]. The International Journal of Robotics Research, 2008, 27(5):595-611.
[9] 王社良, 苏三庆. 形状记忆合金的超弹性恢复力模型及其结构抗震控制[J]. 工业建筑, 1999, 29(3):49-52. Wang S L, Su S Q. On super-elastic restoring force models of shape memory alloy and its application in aseismic control of structures[J]. Industrial Construction, 1999, 29(3):49-52. (in Chinese)
[10] 周瑛. 基于NiTi形状记忆合金板条的恒力元件设计[J]. 科学技术与工程, 2017, 17(28):187-190. Zhou Y. Design of constant force element based on NiTi shape memory alloy slab[J]. Science Technology and Engineering, 2017, 17(28):187-190. (in Chinese)
[11] Pai A, Riepold M, Trächtler A. Model-based precision position and force control of SMA actuators with a clamping application[J]. Mechatronics, 2018, 50:303-320.
[12] 莫兴福, 李沙. 基于遗传算法优化的增量式PID控制器设计与实现[J]. 现代信息科技, 2020, 4(3):73-75, 80. Mo X F, Li S. Design and implementation of incremental PID controller based on genetic algorithm optimization[J]. Modern Information Technology, 2020, 4(3):73-75, 80. (in Chinese)
[13] 牛豪杰, 林成新. 形状记忆合金的应用现状综述[J]. 天津理工大学学报, 2020, 36(4):1-6. Niu H J, Lin C X. Summary of application status of shape memory alloy[J]. Journal of Tianjin University of Technology, 2020, 36(4):1-6. (in Chinese)
[14] 金江, 刘红梅, 洪俊青. NiTi形状记忆合金的性能测试[J]. 南通工学院学报(自然科学版), 2002, 1(1):23-28. Jin J, Liu H M, Hong J Q. Performance test of NiTi shape memory alloy[J]. Journal of Nantong University (Natural Science Edition), 2002, 1(1):23-28. (in Chinese)
[15] Cho H, Yamamoto T, Takeda Y, et al. Exploitation of shape memory alloy actuator using resistance feedback control and its development[J]. Progress in Natural Science:Materials International, 2010, 20:97-103.
[16] Piccirillo V, Góes L C S, Balthazar J M, et al. Deflection control of an aeroelastic system utilizing an antagonistic shape memory alloy actuator[J]. Meccanica, 2018, 53(4/5):727-745.

基于神经网络PID的SMA丝恒输出力控制方法

Control Method of SMA Wire Constant Output Force Based on Neural Network PID

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	李晗, 孟顺梅, 蔡志成. 基于博弈论和粒子群优化的移动边缘计算任务卸载方法[J]. 应用科学学报, 2023, 41(3): 405-418.
[2]	曾磊, 白金明, 刘琦. 多群落粒子群优化供应链数据中心任务调度[J]. 应用科学学报, 2023, 41(3): 419-430.
[3]	邹倩颖, 陈晖阳, 李永生, 胡力雯, 王小芳. 粒子群优化的深海图像暗边缘检测优化算法[J]. 应用科学学报, 2023, 41(1): 153-169.
[4]	王光艳, 耿艳香, 陈雷. 改进粒子群算法在水下盲语音分离中的应用研究[J]. 应用科学学报, 2018, 36(4): 589-600.
[5]	姜长泓, 张永恒, 王盛慧. 基于改进粒子群优化算法的PID控制器参数优化[J]. 应用科学学报, 2017, 35(5): 667-674.
[6]	董莉, 宋晓勤, 韩杰. 基于遗传粒子群优化的认知OFDM网络资源分配算法[J]. 应用科学学报, 2017, 35(3): 288-298.
[7]	杨洪涛，耿金华，丁小瑞，喻曹丰，禹斌. 数控机床力-几何误差的PSO-SVM建模[J]. 应用科学学报, 2014, 32(3): 325-330.
[8]	刘立昕，卞红雨. 用于水下目标跟踪的多特征融合PSOPF 算法[J]. 应用科学学报, 2013, 31(6): 564-568.
[9]	张树银，郭英，齐子森，苏令华. 共形阵列LFM信号DOA和极化参数的联合估计[J]. 应用科学学报, 2013, 31(3): 252-258.
[10]	陈志敏，薄煜明，吴盘龙，宋公飞，段文勇. 一种新型自适应粒子群优化粒子滤波算法及应用[J]. 应用科学学报, 2013, 31(3): 285-293.
[11]	王建青，李帆，赵建辉. 基于混合粒子群优化的巡航导弹低空突防航迹规划[J]. 应用科学学报, 2012, 30(3): 317-323.
[12]	靳一，王继武，吴乐南. 基于IM-SAPSO和SVM的EBPSK检测器设计[J]. 应用科学学报, 2012, 30(2): 141-145.
[13]	张民，陈欣，陆宇平. PSO算法用于导弹鲁棒控制器性能权函数优化[J]. 应用科学学报, 2011, 29(6): 650-654.
[14]	麻海圆1;2，孟相如1，马志强1，马森2. 多目标粒子群优化的复合型组播拥塞控制[J]. 应用科学学报, 2011, 29(5): 459-466.
[15]	李洪波1，董新民1，李婷婷2，郭军1. 飞机环控/发动机系统多目标优化[J]. 应用科学学报, 2011, 29(4): 435-440.