• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

使用在线训练神经网络对线性执行器进行定位的自整定控制。

Self-Tuning Control Using an Online-Trained Neural Network to Position a Linear Actuator.

作者信息

Hernandez-Alvarado Rodrigo, Rodriguez-Abreo Omar, Garcia-Guendulain Juan Manuel, Hernandez-Diaz Teresa

机构信息

Industrial Technologies Division, Universidad Politecnica de Queretaro, Carretera Estatal 420, El Marques 76240, Mexico.

Center for Engineering and Industrial Development, Av. Playa Pie de la Cuesta No. 702, Queretaro 76125, Mexico.

出版信息

Micromachines (Basel). 2022 Apr 29;13(5):696. doi: 10.3390/mi13050696.

DOI:10.3390/mi13050696
PMID:35630163
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC9144629/
Abstract

Linear actuators are widely used in all kinds of industrial applications due to being devices that convert the rotation motion of motors into linear or straight traction/thrust motion. These actuators are ideal for all types of applications where inclination, lifting, traction, or thrust is required under heavy loads, such as wheelchairs, medical beds, and lifting tables. Due to the remarkable ability to exert forces and good precision, they are used classic control systems and controls of high-order. Still, they present difficulties in changing their dynamics and are designed for a range of disturbances. Therefore, in this paper, we present the study of an electric linear actuator. We analyze the positioning in real-time and attack the sudden changes of loads and limitation range by the control. It uses a general-purpose control with self-tuning gains, which can deal with the essential uncertainties of the actuator and suppress disturbances, as they can change their weights to interact with changing systems. The neural network combined with PID control compensates the simplicity of this type of control with artificial intelligence, making it robust to drastic changes in its parameters. Unlike other similar works, this research proposes an online training network with an advantage over typical neural self-adjustment systems. All of this can also be dispensed with the engine model for its operation. The results obtained show a decrease of 42% in the root mean square error (RMSE) during trajectory tracking and saving in energy consumption by 25%. The results were obtained both in simulation and in real tests.

摘要

线性执行器由于能够将电机的旋转运动转换为线性或直线牵引/推力运动，因此广泛应用于各种工业领域。这些执行器适用于所有需要在重负载下进行倾斜、提升、牵引或推力的应用类型，如轮椅、医疗床和升降台。由于其出色的力施加能力和良好的精度，它们被用于经典控制系统和高阶控制。然而，它们在改变动力学方面存在困难，并且是为一系列干扰而设计的。因此，在本文中，我们介绍了对电动线性执行器的研究。我们分析实时定位，并通过控制应对负载的突然变化和限制范围。它使用具有自整定增益的通用控制，能够处理执行器的基本不确定性并抑制干扰，因为它们可以改变权重以与变化的系统相互作用。神经网络与PID控制相结合，用人工智能弥补了这类控制的简单性，使其对参数的剧烈变化具有鲁棒性。与其他类似工作不同，本研究提出了一种在线训练网络，它比典型的神经自调整系统具有优势。其运行也无需发动机模型。所获得的结果表明，在轨迹跟踪期间均方根误差（RMSE）降低了42%，能耗节省了25%。这些结果在模拟和实际测试中均得到了验证。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/4923d9674a63/micromachines-13-00696-g022.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/9ddc2a89cef8/micromachines-13-00696-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/29aaa152f4da/micromachines-13-00696-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/ad4de37aebee/micromachines-13-00696-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/bc1e381a6e6b/micromachines-13-00696-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/8ecd84940886/micromachines-13-00696-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/6702d47dc46d/micromachines-13-00696-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/c9b3abcf3b5f/micromachines-13-00696-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/6db69d9894ce/micromachines-13-00696-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/f8825146cd85/micromachines-13-00696-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/0562a9b329cc/micromachines-13-00696-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/4dd24972049b/micromachines-13-00696-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/1217d69303db/micromachines-13-00696-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/215b6df940e8/micromachines-13-00696-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/4fb9fcebca35/micromachines-13-00696-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/7caac52cbe00/micromachines-13-00696-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/b4025445133f/micromachines-13-00696-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/39879c278bc6/micromachines-13-00696-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/dfde442633ca/micromachines-13-00696-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/efb3b08259b8/micromachines-13-00696-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/2779ddad4cab/micromachines-13-00696-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/4c5b4c46d510/micromachines-13-00696-g021.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/4923d9674a63/micromachines-13-00696-g022.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/9ddc2a89cef8/micromachines-13-00696-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/29aaa152f4da/micromachines-13-00696-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/ad4de37aebee/micromachines-13-00696-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/bc1e381a6e6b/micromachines-13-00696-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/8ecd84940886/micromachines-13-00696-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/6702d47dc46d/micromachines-13-00696-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/c9b3abcf3b5f/micromachines-13-00696-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/6db69d9894ce/micromachines-13-00696-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/f8825146cd85/micromachines-13-00696-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/0562a9b329cc/micromachines-13-00696-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/4dd24972049b/micromachines-13-00696-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/1217d69303db/micromachines-13-00696-g012.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/215b6df940e8/micromachines-13-00696-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/4fb9fcebca35/micromachines-13-00696-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/7caac52cbe00/micromachines-13-00696-g015.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/b4025445133f/micromachines-13-00696-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/39879c278bc6/micromachines-13-00696-g017.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/dfde442633ca/micromachines-13-00696-g018.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/efb3b08259b8/micromachines-13-00696-g019.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/2779ddad4cab/micromachines-13-00696-g020.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/4c5b4c46d510/micromachines-13-00696-g021.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/3f70/9144629/4923d9674a63/micromachines-13-00696-g022.jpg

相似文献

1
Self-Tuning Control Using an Online-Trained Neural Network to Position a Linear Actuator.使用在线训练神经网络对线性执行器进行定位的自整定控制。
Micromachines (Basel). 2022 Apr 29;13(5):696. doi: 10.3390/mi13050696.
2
Neural Network-Based Self-Tuning PID Control for Underwater Vehicles.基于神经网络的水下航行器自整定PID控制
Sensors (Basel). 2016 Sep 5;16(9):1429. doi: 10.3390/s16091429.
3
Neural Network Self-Tuning Control for a Piezoelectric Actuator.神经网络自整定控制压电执行器。
Sensors (Basel). 2020 Jun 12;20(12):3342. doi: 10.3390/s20123342.
4
Implementation of ANN-Based Auto-Adjustable for a Pneumatic Servo System Embedded on FPGA.基于人工神经网络的可自动调节的FPGA嵌入式气动伺服系统的实现。
Micromachines (Basel). 2022 May 31;13(6):890. doi: 10.3390/mi13060890.
5
Adaptive fuzzy neural network control design via a T-S fuzzy model for a robot manipulator including actuator dynamics.基于T-S模糊模型的机器人机械手自适应模糊神经网络控制设计，包括执行器动力学。
IEEE Trans Syst Man Cybern B Cybern. 2008 Oct;38(5):1326-46. doi: 10.1109/TSMCB.2008.925749.
6
Nonlinear Tracking Control of a Conductive Supercoiled Polymer Actuator.超弹性螺旋聚合物驱动器的非线性跟踪控制
Soft Robot. 2018 Apr;5(2):190-203. doi: 10.1089/soro.2017.0023. Epub 2017 Nov 30.
7
Single Neural Adaptive PID Control for Small UAV Micro-Turbojet Engine.单神经元自适应 PID 控制在小型无人机微涡轮喷气发动机中的应用。
Sensors (Basel). 2020 Jan 8;20(2):345. doi: 10.3390/s20020345.
8
Interpretable PID parameter tuning for control engineering using general dynamic neural networks: An extensive comparison.使用广义动态神经网络进行可解释的 PID 参数整定在控制工程中的应用：广泛比较。
PLoS One. 2020 Dec 10;15(12):e0243320. doi: 10.1371/journal.pone.0243320. eCollection 2020.
9
Individual deformability compensation of soft hydraulic actuators through iterative learning-based neural network.基于迭代学习的神经网络对软液压致动器的个体变形补偿。
Bioinspir Biomim. 2021 Nov 2;16(5). doi: 10.1088/1748-3190/ac1b6f.
10
Defining a neural network controller structure for a rubbertuator robot.为橡胶驱动器机器人定义一种神经网络控制器结构。
Neural Netw. 2000 May-Jun;13(4-5):533-44. doi: 10.1016/s0893-6080(00)00020-4.

引用本文的文献

1
The Integration of Artificial Intelligence with Micro-Nano-Systems: Perspectives, Challenges and Future Prospects.人工智能与微纳系统的融合：观点、挑战与未来展望。
Micromachines (Basel). 2025 Mar 4;16(3):301. doi: 10.3390/mi16030301.
2
Effect of Local Annealing on Magnetic Flux Distribution and Noise in a Micro-Generator with Amorphous Shell.局部退火对具有非晶外壳的微型发电机中磁通分布和噪声的影响。
Micromachines (Basel). 2022 Nov 26;13(12):2086. doi: 10.3390/mi13122086.

本文引用的文献

1
A Design of FPGA-Based Neural Network PID Controller for Motion Control System.一种用于运动控制系统的基于现场可编程门阵列的神经网络比例积分微分控制器设计。
Sensors (Basel). 2022 Jan 24;22(3):889. doi: 10.3390/s22030889.
2
AutoTune: Automatically Tuning Convolutional Neural Networks for Improved Transfer Learning.AutoTune：自动调整卷积神经网络以提高迁移学习性能。
Neural Netw. 2021 Jan;133:112-122. doi: 10.1016/j.neunet.2020.10.009. Epub 2020 Oct 27.
3
A Hybrid Control with PID⁻Improved Sliding Mode for Flat-Top of Missile Electromechanical Actuator Systems.
一种用于导弹机电执行器系统平顶的 PID 改进滑模混合控制。
Sensors (Basel). 2018 Dec 15;18(12):4449. doi: 10.3390/s18124449.
4
Neural Network-Based Self-Tuning PID Control for Underwater Vehicles.基于神经网络的水下航行器自整定PID控制
Sensors (Basel). 2016 Sep 5;16(9):1429. doi: 10.3390/s16091429.