搜索

x

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

通过机器学习实现基于摩擦纳米发电机的自驱动智能传感及其应用

张嘉伟 姚鸿博 张远征 蒋伟博 吴永辉 张亚菊 敖天勇 郑海务

引用本文:
Citation:

通过机器学习实现基于摩擦纳米发电机的自驱动智能传感及其应用

张嘉伟, 姚鸿博, 张远征, 蒋伟博, 吴永辉, 张亚菊, 敖天勇, 郑海务

Self-powered sensing based on triboelectric nanogenerator through machine learning and its application

Zhang Jia-Wei, Yao Hong-Bo, Zhang Yuan-Zheng, Jiang Wei-Bo, Wu Yong-Hui, Zhang Ya-Ju, Ao Tian-Yong, Zheng Hai-Wu
PDF
HTML
导出引用
  • 在物联网时代, 如何开发一种可持续供电、部署方便且使用灵活的智能传感器系统成为了亟待解决的难题. 以麦克斯韦位移电流作为驱动力的摩擦纳米发电机(triboelectric nanogenerator, TENG)可直接将机械刺激转化为电信号, 因此可作为自驱动传感器使用. 基于TENG的传感器拥有结构简单、瞬时功率密度高等优点, 为构建智能传感器系统提供了重要手段. 同时, 机器学习作为一种成本低、开发周期短、数据处理能力和预测能力强的技术, 对TENG产生的大量电学信号处理效果显著. 本文梳理了基于TENG的传感器系统通过采用机器学习技术进行信号处理和智能识别的最新研究进展, 从交通安全、环境监测、信息安全、人机交互和健康运动检测等角度出发, 概述了该研究方向的技术特点与研究现状. 最后, 深入讨论了该领域当前存在的挑战和未来的发展趋势, 并分析了未来如何改进以期开拓更广阔的应用空间. 我们相信机器学习技术与TENG传感器的结合将推动未来智能传感器网络的快速发展.
    In the era of The Internet of Things, how to develop a smart sensor system with sustainable power supply, easy deployment and flexible use has become an urgent problem to be solved. Triboelectric nanogenerator (TENG) driven by Maxwell’s Displacement Current can convert mechanical motion into electrical signals, thus it can be used as a self-powered sensor. Sensors based on TENGs have the advantages of simple structure and high instantaneous power density, which provide an important means to build intelligent sensor systems. Meanwhile, machine learning, as a technique with low cost, short development cycle, and strong data processing capabilities and predictive capabilities, is effective in processing the large amount of electrical signals generated by TENG. This article combines the latest research progress of TENG-based sensor systems for signal processing and intelligent recognition by employing machine learning techniques, and outlines the technical features and research status of this research direction from the perspectives of traffic safety, environmental monitor, information security, human-computer interaction and health motion detection. Finally, this article also in-depth discusses the current challenges and future development trends in this field, and analyzes how to improve in the future to open up a broader application space. It is suggested that the integration of machine learning technology and TENG-based sensors will promote the rapid development of intelligent sensor networks in the future.
      通信作者: 郑海务, zhenghaiw@ustc.edu
    • 基金项目: 国家自然科学基金(批准号: 52072111)、河南省杰出青年科学基金(批准号: 212300410004)、河南大学一流学科培育项目(批准号: 2019YLZDYJ04)、河南省科技攻关项目(批准号: 212102210025, 212102210274)资助的课题
      Corresponding author: Zheng Hai-Wu, zhenghaiw@ustc.edu
    • Funds: Project supported by the National Natural Science Foundation of China (Grant No. 52072111), the Science Fund for Distinguished Young Scholars of Henan Province, China (Grant No. 212300410004), the First-class Discipline Cultivation Project of Henan University, China (Grant No. 2019YLZDYJ04), the Key Science and Technology Program of Henan Province, China (Grant Nos. 212102210025, 212102210274)
    [1]

    解运洲 2020 物联网技术 10 4

    Xie Y Z 2020 Internet Things Technol. 10 4

    [2]

    Portilla J, Mujica G, Lee J S, Riesgo T 2019 IEEE Sens. J. 19 3179Google Scholar

    [3]

    Lin R, Kim H J, Achavananthadith S, Kurt S A, Tan S C, Yao H, Tee B C, Lee J K, Ho J S 2020 Nat. Commun. 11 444Google Scholar

    [4]

    Fan F R, Tian Z Q, Wang Z L 2012 Nano Energy 1 328

    [5]

    Alagumalai A, Mahian O, Aghbashlo M, Tabatabaei M, Wongwises S, Wang Z L 2021 Nano Energy 83 105844Google Scholar

    [6]

    王中林, 林龙, 陈俊, 牛思淼, 訾云龙 2017 摩擦纳米发电机 (北京: 科学出版社) 第11页

    Wang Z L, Lin L, Chen J, Niu S M, Zi Y L 2017 Triboelectric Nanogenerators (Beijing: China Science Publishing & Media) p11 (in Chinese)

    [7]

    吴晔盛, 刘启, 曹杰, 李凯, 程广贵, 张忠强, 丁建宁, 蒋诗宇 2019 物理学报 68 190201Google Scholar

    Wu Y S, Liu Q, Cao J, Li K, Cheng G G, Zhang Z Q, Ding J N, Jiang S Y 2019 Acta Phys. Sin. 68 190201Google Scholar

    [8]

    McCarthy J, Feigenbaum E A 1990 AI Mag. 11 10

    [9]

    Fan F R, Tian Z Q, Wang Z L 2012 Nano Energ. 1 328

    [10]

    Niu S, Wang Z L 2015 Nano Energy 14 161Google Scholar

    [11]

    Luo J, Wang Z L 2020 EcoMat 2 e12059

    [12]

    Li S, Nie J, Shi Y, Tao X, Wang F, Tian J, Lin S, Chen X, Wang Z L 2020 Adv. Mater. 32 2001307Google Scholar

    [13]

    Nie J, Ren Z, Xu L, Lin S, Zhan F, Chen X, Wang Z L 2020 Adv. Mater. 32 1905696Google Scholar

    [14]

    Wang Z L 2017 Mater. Today 20 74Google Scholar

    [15]

    Wang Z L 2013 ACS Nano 7 9533Google Scholar

    [16]

    Nie J, Wang Z, Ren Z, Li S, Chen X, Wang Z L 2019 Nat. Commun. 10 2264Google Scholar

    [17]

    Wang S, Lin L, Wang Z L 2012 Nano Lett. 12 6339Google Scholar

    [18]

    Zhu G, Lin Z H, Jing Q, Bai P, Pan C, Yang Y, Zhou Y, Wang Z L 2013 Nano Lett. 13 847Google Scholar

    [19]

    Niu S, Wang S, Liu Y, Zhou Y S, Lin L, Hu Y, Pradel K C, Wang Z L 2014 Energy Environ. Sci. 7 2339Google Scholar

    [20]

    Zhu G, Chen J, Liu Y, Bai P, Zhou Y S, Jing Q, Pan C, Wang Z L 2013 Nano Lett. 13 2282Google Scholar

    [21]

    Wang S, Lin L, Xie Y, Jing Q, Niu S, Wang Z L 2013 Nano Lett. 13 2226Google Scholar

    [22]

    Lei R, Shi Y, Ding Y, Nie J, Li S, Wang F, Zhai H, Chen X, Wang Z L 2020 Energy Environ. Sci. 13 2178Google Scholar

    [23]

    Bai P, Zhu G, Liu Y, Chen J, Jing Q, Yang W, Ma J, Zhang G, Wang Z L 2013 ACS Nano 7 6361Google Scholar

    [24]

    Niu S, Zhou Y S, Wang S, Liu Y, Lin L, Bando Y, Wang Z L 2014 Nano Energy 8 150Google Scholar

    [25]

    Wang S, Niu S, Yang J, Lin L, Wang Z L 2014 ACS Nano 8 12004Google Scholar

    [26]

    Wu C, Wang A C, Ding W, Guo H, Wang Z L 2019 Adv. Energy Mater. 9 1802906Google Scholar

    [27]

    Cortes C, Vapnik V 1995 Mach. Learn. 20 273

    [28]

    Kukreja H, Bharath N, Siddesh C, Kuldeep S 2016 Int. J. Adv. Res. Innov. Ideas Educ. 1 27

    [29]

    李彦冬, 郝宗波, 雷航 2016 计算机应用 36 2508

    Li Y, Hao Z, Lei H 2016 J. Comput. Appl. 36 2508

    [30]

    Greff K, Srivastava R K, Koutník J, Steunebrink B R, Schmidhuber J 2016 IEEE Trans. Neural Netw. Learn. Syst. 28 2222

    [31]

    Hinton G E, Osindero S, Teh Y W 2006 Neural Comput. 18 1527Google Scholar

    [32]

    Butler A C 2010 J. Exp. Psychol. Learn. Mem. Cogn. 36 1118Google Scholar

    [33]

    Wang B, Liu Y, Zhou Y, Wen Z 2018 Nano Energy 46 322Google Scholar

    [34]

    Peden M 2005 Int. J. Inj. Control Saf. Promot. 12 85Google Scholar

    [35]

    Abou Elassad Z E, Mousannif H, Al Moatassime H 2020 Transp. Res. Part C Emerg. Technol. 118 102708Google Scholar

    [36]

    Soares S, Monteiro T, Lobo A, Couto A, Cunha L, Ferreira S 2020 Sustainability 12 1971Google Scholar

    [37]

    Moretti L, Palazzi F, Cantisani G 2020 Sustainability 12 4120Google Scholar

    [38]

    Trivedi M M, Cheng S Y 2007 Computer 40 60

    [39]

    Trivedi M M, Gandhi T, McCall J 2007 IEEE Trans. Intell. Transp. Syst. 8 108Google Scholar

    [40]

    Zhang H, Cheng Q, Lu X, Wang W, Wang Z L, Sun C 2021 Nano Energy 79 105455Google Scholar

    [41]

    Ho T K 1995 Proceedings of 3rd international conference on document analysis and recognition Montreal Montreal, QC, Canada, August 14–16,1995 p278

    [42]

    Wu Y, Abdel-Aty M, Park J, Zhu J 2018 Transp. Res. Part C Emerg. Technol. 95 481Google Scholar

    [43]

    Cheng Q, Jiang X, Zhang H, Wang W, Sun C 2020 Sustainability 12 8926Google Scholar

    [44]

    Ma C, Gao S, Gao X, Wu M, Wang R, Wang Y, Tang Z, Fan F, Wu W, Wan H, Wu W 2019 InfoMat 1 116Google Scholar

    [45]

    García-Gonzalo E, Fernández-Muñiz Z, García Nieto P J, Bernardo Sánchez A, Menéndez Fernández M 2016 Materials 9 531Google Scholar

    [46]

    Zhang W, Wang P, Sun K, Wang C, Diao D 2019 Nano Energy 56 277Google Scholar

    [47]

    Yang L, Wang Y, Zhao Z, Guo Y, Chen S, Zhang W, Guo X 2020 ACS Appl. Mater. Interfaces 12 38192Google Scholar

    [48]

    Fukushima K 1980 Biol. Cybern. 36 193Google Scholar

    [49]

    Shao H, Jiang H, Li X, Liang T 2018 Comput. Ind. 96 27Google Scholar

    [50]

    Zhao G, Yang J, Chen J, Zhu G, Jiang Z, Liu X, Niu G, Wang Z L, Zhang B 2019 Adv. Mater. Technol. 4 1800167Google Scholar

    [51]

    Zhang W, Deng L, Yang L, Yang P, Diao D, Wang P, Wang Z L 2020 Nano Energy 77 105174Google Scholar

    [52]

    Tcho I W, Kim W G, Choi Y K 2020 Nano Energy 70 104534Google Scholar

    [53]

    Jin T, Sun Z, Li L, Zhang Q, Zhu M, Zhang Z, Yuan G, Chen T, Tian Y, Hou X, Lee C 2020 Nat. Commun. 11 5381Google Scholar

    [54]

    Shi Y, Wang F, Tian J, Li S, Fu E, Nie J, Lei R, Ding Y, Chen X, Wang Z L 2021 Sci. Adv. 7 eabe2943Google Scholar

    [55]

    Hou C, Geng J, Yang Z, Tang T, Sun Y, Wang F, Liu H, Chen T, Sun L 2021 Adv. Mater. Technol. 6 2000912Google Scholar

    [56]

    Zhang Z, He T, Zhu M, Sun Z, Shi Q, Zhu J, Dong B, Yuce M R, Lee C 2020 NPJ Flex. Electron. 4 29Google Scholar

    [57]

    Wen F, Sun Z, He T, Shi Q, Zhu M, Zhang Z, Li L, Zhang T, Lee C 2020 Adv. Sci. 7 2000261Google Scholar

    [58]

    Lin Z, Wu Z, Zhang B, Wang Y C, Guo H, Liu G, Chen C, Chen Y, Yang J, Wang Z L 2019 Adv. Mater. Technol. 4 1800360Google Scholar

    [59]

    Luo J, Gao W, Wang Z L 2021 Adv. Mater. 33 2004178Google Scholar

    [60]

    Liu S, Zhang J, Zhang Y, Zhu R 2020 Nat. Commun. 11 5615Google Scholar

    [61]

    Luo J, Wang Z, Xu L, Wang A C, Han K, Jiang T, Lai Q, Bai Y, Tang W, Fan F R, Wang Z L 2019 Nat. Commun. 10 5147Google Scholar

    [62]

    Zhou Y, Shen M, Cui X, Shao Y, Li L, Zhang Y 2021 Nano Energy 84 105887Google Scholar

    [63]

    Syu M H, Guan Y J, Lo W C, Fuh Y K 2020 Nano Energy 76 105029Google Scholar

    [64]

    Shi Q, Zhang Z, He T, Sun Z, Wang B, Feng Y, Shan X, Salam B, Lee C 2020 Nat. Commun. 11 4609Google Scholar

    [65]

    Shi Q, Zhang Z, Yang Y, Shan X, Salam B, Lee C 2021 ACS Nano 15 18312Google Scholar

    [66]

    Li S, Fan Y, Chen H, Nie J, Liang Y, Tao X, Zhang J, Chen X, Fu E, Wang Z L 2020 Energy Environ. Sci. 13 896Google Scholar

    [67]

    Zou H, Guo L, Xue H, Zhang Y, Shen X, Liu X, Wang P, He X, Dai G, Jiang P, Zheng H, Zhang B, Xu C, Wang Z L 2020 Nat. Commun. 11 2093Google Scholar

    [68]

    Oliynyk A O, Antono E, Sparks T D, Ghadbeigi L, Gaultois M W, Meredig B, Mar A 2016 Chem. Mater. 28 7324Google Scholar

    [69]

    Ward L, Agrawal A, Choudhary A, Wolverton C 2016 NPJ Comput. Mater. 2 16028Google Scholar

    [70]

    Vergara A, Vembu S, Ayhan T, Ryan M A, Homer M L, Huerta R 2012 Sens. Actuators, B 166 320

    [71]

    Gu L, Cui N, Liu J, Zheng Y, Bai S, Qin Y 2015 Nanoscale 7 18049Google Scholar

    [72]

    Lee K Y, Yoon H J, Jiang T, Wen X, Seung W, Kim S W, Wang Z L 2016 Adv. Energy Mater. 6 1502566Google Scholar

    [73]

    Agrawal A, Lee S K, Silberman J, Ziegler M, Kang M, Venkataramani S, Cao N, Fleischer B, Guillorn M, Cohen M, Mueller S, Oh J, Lutz M, Jung J, Koswatta S, Zhou C, Zalani V, Bonanno J, Casatuta R, Chen C Y, Choi J, Haynie H, Herbert A, Jain R, Kar M, Kim K H, Li Y, Ren Z, Rider S, Schaal M, Schelm K, Scheuermann M, Sun X, Tran H, Wang N, Wang W, Zhang X, Shah V, Curran B, Srinivasan V, Lu P F, Shukla S, Chang L, Gopalakrishnan K 2021 IEEE J Solid-State Circuits San Francisco, California, USA, Feburary, 13–22, 2021 p144

    [74]

    Joung H A, Ballard Z S, Wu J, Tseng D K, Teshome H, Zhang L, Horn E J, Arnaboldi P M, Dattwyler R J, Garner O B, Di Carlo D, Ozcan A 2019 ACS Nano 14 229

  • 图 1  基于TENG的多功能智能传感系统的结构示意图和主要功能展示

    Fig. 1.  Structure diagram of the multifunctional intelligent sensor system based on TENG and its main function display.

    图 2  描述两个原子间CE和电荷转移现象的重叠电子云通用模型[11]

    Fig. 2.  Overlapped electron-cloud model proposed for explaining CE and charge transfer between two atoms for a general case[11]

    图 3  TENG的4种工作模式及其应用 (a) 垂直接触-分离模式; (b)水平滑动模式; (c) 单电极模式; (d)独立层模式[26]

    Fig. 3.  Four working modes of TENG and applications: (a) Vertical contact-separation (CS) mode; (b) lateral-sliding (LS) mode; (c) single-electrode (SE) mode; (d) freestanding triboelectric-layer(FT) mode[26]

    图 4  机器学习的基本工作流程

    Fig. 4.  Basic workflow of machine learning

    图 5  从基于TENG的传感器收集数据并推送至机器学习模型进行计算分析的过程. 数据在数据中心存储和管理, 用户可以从控制中心与数据中心进行交互. 在预处理阶段将数据分为多元时间序列和多元空间数据, 接着输入机器学习模型分析并做出预测, 最后对结果进行验证和评估

    Fig. 5.  Process of collecting data from TENG-based sensors and pushing it to the machine learning model for computational analysis. Data is stored and managed in the data center. Users can interact with the data center from the control center. In the preprocessing stage, the data is divided into multivariate time series and multivariate spatial data, and then input into the machine. The machine learns the model and analyzes and makes predictions, and finally verifies and evaluates the results

    图 6  纳米发电机产业在中国未来发展的路线图

    Fig. 6.  Roadmap for the future development of the nano-generator industry in China

    图 7  实验平台和TENGs的插图 (a)实验平台; (b)放置在方向盘上的两个TENGs, 尺寸为25 cm × 2 cm × 0.1 cm; (c) 反应时间示意图; (d) RF分类器给出的分类结果的混淆矩阵[40]

    Fig. 7.  Illustrations of experimental platform and TENGs: (a) Experimental platform; (b) two TENGs placed on steering wheel with a size of 25 cm × 2 cm × 0.1 cm. (c) Schematic diagram of reaction time; (d) confusion matrices of the classification result given by RF classifier[40].

    图 8  基于大数据和机器学习技术的智能检测识别系统[46]

    Fig. 8.  Intelligent detection and recognition system based on big data and machine learning technology[46]

    图 9  实时沉积物监测的实验装置和工作机理图 (a) 测试装置示意图; (b)去离子水滴和质量分数为1.00%的含颗粒水滴(颗粒直径117.33 μm) 产生的典型输出短路电流, 插图显示了使用高速摄像机捕捉到的液滴的动态运动; (c)水与PTFE接触通电产生主要电流峰的机理; (d)预带电砂粒与铜电极间静电感应产生小电流峰的机理[47]

    Fig. 9.  Diagram of the experimental setup and working mechanism for real-time sediment monitoring: (a) Schematic diagram of the testing setup. (b) Typical output short-circuit current generated by DI water droplets and particle-laden droplets (particle diameter: 117.33 μm) with a mass fraction of 1.00%. The inset figures show the dynamic motions of the droplets captured using a high-speed camera. (c) Mechanism of the major current peaks induced by the contact electrification between water and PTFE. (d) Mechanism of the minor current peaks induced by the electrostatic induction between the precharged sand particles and the Cu electrode[47].

    图 10  智能键盘的工作原理 (a)当用户开始击键, 带正电的手指接近导致自由电子从底部ITO电极流到顶部电极; (b)手指抬起并发生分离时, 会产生反方向从顶部电极流向底部电极的电流[50]

    Fig. 10.  Operating principle of the intelligent keyboard: (a) When a keystroke is initiated, the approach of positively charged human finger results in free electrons flowing from bottom ITO electron to top electrode; (b) when the finger is up and a separation occurs, it produces another current in the external circuit flowing from the top electrode to bottom electrode[50].

    图 11  TENG在手写识别中的应用 (a) TENG录制手写签名的过程; (b)结合TENG和机器学习方法进行手写签名识别; (c) 由三人书写英文、中文和阿拉伯数字的分类精度[51]

    Fig. 11.  Application of TENG in handwriting recognition: (a) Process of TENG recording handwritten signatures; (b) combining TENG and machine learning methods for handwriting signature recognition; (c) classification accuracy of English, Chinese and Arabic numerals written by three persons[51]

    图 12  CR-TENG的工作原理图 (a) 基于CR-TENG的扫描过程: i) CR-TENG和纸张之间的接触和分离; ii)比较每个单元格的输出电压($ v_{{\rm{max}}} $)和$ v_{\rm{T}} $; iii)将纸上图案转换后的数字图像. 在$ v_{{\rm{max}}} $值大于$ v_{\rm{T}} $ 的单元格中, 确定接触的纸张为已进行墨水打印的纸, 而在$ v_{{\rm{max}}} $值小于$ v_{\rm{T}} $ 的接触纸张被确定为裸纸. (b)根据r扫描图像的清晰度[52]

    Fig. 12.  Working schematic of CR-TENG: (a) The scanning process based on the CR-TENG. i) Contact and separation between the CR-TENG and paper; ii) Comparison of the output voltage ($ v_{{\rm{max}}} $) and $ v_{\rm{T }}$ in each cell; iii) Converted digital image of the pattern on paper. In cells with a $ v_{{\rm{max}}} $ values larger than $ v_{\rm{T}} $, the paper in contact was determined to be ink-printed paper, while in cells with a $ v_{max} $ values smaller than $ v_t $, the paper in contact was determined to be bare paper. (b) Legibility of the scanned image according to r[52]

    图 13  用于软夹具及其数字孪生应用的低成本TENG的结构图 (a) TENG传感器及其基本结构. (i)长度TENG (l-TENG)传感器; (ii) 触觉TENG (t-TENG)传感器. (b)集成TENG 传感器的机械爪; (c)智能感官数据处理. $ {\rm{E}}_1 $$ {\rm{E}}_4 $, ${\rm{E}}_L$表示t-TENG传感器的电极; (d) AIoT传感系统的数字孪生应用[53]

    Fig. 13.  Construction drawing of the low-cost TENG for soft gripper and its digital twin applications: (a) As-fabricated TENG sensors and their basic structures. (i) Length TENG (L-TENG) sensor. (ii) Tactile TENG (T-TENG) sensor. (b) Soft gripper integrated with TENG sensors. (c) Intelligent sensory data processing strategies. $ {\rm{E}}_1 $$ {\rm{E}}_4 $, and ${\rm{E}}_L$ represent the electrodes in the T-TENG sensor. (d) Digital twin applications based on AIoT sensory system[53]

    图 14  DT-HMI的示意图. 主要功能单元有 (a) 基于齿轮旋转及其输出信号的DT-HMI的TENG; (b)在正向旋转和反向旋转的过程中, 布置在齿轮(TENG感应齿轮)两侧的TENG输出不同的信号; (c)布置在移动平台中间圆柱上的模式开关传感器和触发识别传感器[55]

    Fig. 14.  Schematics of the DT-HMI for diversified applications. The major functional units: (a) TENGs of the DT-HMI based on gear rotation and its output signals; (b) TENGs arranged on both sides of the gear (TENG sensing gears) output different signals during forward rotation and reverse rotation; (c) Two triboelectric sensors arranged on the middle cylindrical of the mobile platform are the mode switch sensor and trigger discriminating sensor[55]

    图 15  W-TENG在智能运动中的应用 (a) 基于W-TENG 的智能乒乓球台的结构; (b) 基于W-TENG的自供电跌落点分布统计系统的操作流程; (c)自供电跌落点分布统计系统; (d)不同球速下的传感器输出电压; (e) W-TENG传感器阵列分析乒乓球运动轨迹和落点的原理[61]

    Fig. 15.  Application of the W-TENG in intelligent sports: (a) Structure of intelligent ping-pong table based on W-TENG; (b) operation procedure of statistical system of self-powered drop point distribution based on W-TENG; (c) self-powered drop point distribution statistical system; (d) sensor output voltage at different ball velocity; (e) principle of W-TENG sensor array to analyze the trajectories and drop points of table tennis[61]

    图 16  用机器学习演示棒球比赛场景 (a)手势识别和控制流程图; (b) CNN模型的结构; (c) 手势的信号模式; (d)投球3种常见手势的混淆矩阵; (e) 3 个手势的照片(左), 以及在Unity中使用手势实现VR控制的对应截图(右)[57]

    Fig. 16.  Demonstration of baseball game scenario with machine learning: (a) Flow chart for gesture recognition and control; (b) structure of CNN model; (c) signal patterns of 3 gestures; (d) confusion matrix for 3 common gestures of pitching ball; (e) photographs of 3 gestures (left), and corresponding screenshot of using gestures to achieve VR control in Unity (right)[57].

    图 17  可以识别人类活动的智能袜 (a)在VR游戏中从感官信息采集到实时预测的过程; (b)智能袜对不同动作(跳跃、奔跑、滑行、跳跃和行走)输出的3D 曲线图; (c)混淆矩阵; (d) 在数字人体系统中的虚拟角色运动和真实人类运动的对应关系[56]

    Fig. 17.  Human activities recognition of deep learning-enabled socks: (a) Process flow from sensory information collection to the real-time prediction in VR fitness game; (b) 3D plots of the deep learning sock outputs responding to different motions (leap, run, slide, jump, and walk); (c) confusion map for deep learning outcome; (d) motion of the virtual character corresponding to real motion in a proposed digital human system[56].

    图 18  结合机器学习技术的TENG传感器在未来面临的挑战 (a) 机器学习辅助制作TENG传感器材料; (b)优化TENG传感器信号处理结果; (c) 优化TENG 传感器设备的封装; (d)使机器学习技术和TENG传感器深度融合

    Fig. 18.  Future challenges by TENG sensors combined with machine learning technology: (a) Production of TENG sensor materials assist by machine learning; (b) optimize results of TENG sensor signal processing; (c) Optimize the encapsulation of TENG sensor equipment; (d) combine deeply machine learning technology and TENG sensors

  • [1]

    解运洲 2020 物联网技术 10 4

    Xie Y Z 2020 Internet Things Technol. 10 4

    [2]

    Portilla J, Mujica G, Lee J S, Riesgo T 2019 IEEE Sens. J. 19 3179Google Scholar

    [3]

    Lin R, Kim H J, Achavananthadith S, Kurt S A, Tan S C, Yao H, Tee B C, Lee J K, Ho J S 2020 Nat. Commun. 11 444Google Scholar

    [4]

    Fan F R, Tian Z Q, Wang Z L 2012 Nano Energy 1 328

    [5]

    Alagumalai A, Mahian O, Aghbashlo M, Tabatabaei M, Wongwises S, Wang Z L 2021 Nano Energy 83 105844Google Scholar

    [6]

    王中林, 林龙, 陈俊, 牛思淼, 訾云龙 2017 摩擦纳米发电机 (北京: 科学出版社) 第11页

    Wang Z L, Lin L, Chen J, Niu S M, Zi Y L 2017 Triboelectric Nanogenerators (Beijing: China Science Publishing & Media) p11 (in Chinese)

    [7]

    吴晔盛, 刘启, 曹杰, 李凯, 程广贵, 张忠强, 丁建宁, 蒋诗宇 2019 物理学报 68 190201Google Scholar

    Wu Y S, Liu Q, Cao J, Li K, Cheng G G, Zhang Z Q, Ding J N, Jiang S Y 2019 Acta Phys. Sin. 68 190201Google Scholar

    [8]

    McCarthy J, Feigenbaum E A 1990 AI Mag. 11 10

    [9]

    Fan F R, Tian Z Q, Wang Z L 2012 Nano Energ. 1 328

    [10]

    Niu S, Wang Z L 2015 Nano Energy 14 161Google Scholar

    [11]

    Luo J, Wang Z L 2020 EcoMat 2 e12059

    [12]

    Li S, Nie J, Shi Y, Tao X, Wang F, Tian J, Lin S, Chen X, Wang Z L 2020 Adv. Mater. 32 2001307Google Scholar

    [13]

    Nie J, Ren Z, Xu L, Lin S, Zhan F, Chen X, Wang Z L 2020 Adv. Mater. 32 1905696Google Scholar

    [14]

    Wang Z L 2017 Mater. Today 20 74Google Scholar

    [15]

    Wang Z L 2013 ACS Nano 7 9533Google Scholar

    [16]

    Nie J, Wang Z, Ren Z, Li S, Chen X, Wang Z L 2019 Nat. Commun. 10 2264Google Scholar

    [17]

    Wang S, Lin L, Wang Z L 2012 Nano Lett. 12 6339Google Scholar

    [18]

    Zhu G, Lin Z H, Jing Q, Bai P, Pan C, Yang Y, Zhou Y, Wang Z L 2013 Nano Lett. 13 847Google Scholar

    [19]

    Niu S, Wang S, Liu Y, Zhou Y S, Lin L, Hu Y, Pradel K C, Wang Z L 2014 Energy Environ. Sci. 7 2339Google Scholar

    [20]

    Zhu G, Chen J, Liu Y, Bai P, Zhou Y S, Jing Q, Pan C, Wang Z L 2013 Nano Lett. 13 2282Google Scholar

    [21]

    Wang S, Lin L, Xie Y, Jing Q, Niu S, Wang Z L 2013 Nano Lett. 13 2226Google Scholar

    [22]

    Lei R, Shi Y, Ding Y, Nie J, Li S, Wang F, Zhai H, Chen X, Wang Z L 2020 Energy Environ. Sci. 13 2178Google Scholar

    [23]

    Bai P, Zhu G, Liu Y, Chen J, Jing Q, Yang W, Ma J, Zhang G, Wang Z L 2013 ACS Nano 7 6361Google Scholar

    [24]

    Niu S, Zhou Y S, Wang S, Liu Y, Lin L, Bando Y, Wang Z L 2014 Nano Energy 8 150Google Scholar

    [25]

    Wang S, Niu S, Yang J, Lin L, Wang Z L 2014 ACS Nano 8 12004Google Scholar

    [26]

    Wu C, Wang A C, Ding W, Guo H, Wang Z L 2019 Adv. Energy Mater. 9 1802906Google Scholar

    [27]

    Cortes C, Vapnik V 1995 Mach. Learn. 20 273

    [28]

    Kukreja H, Bharath N, Siddesh C, Kuldeep S 2016 Int. J. Adv. Res. Innov. Ideas Educ. 1 27

    [29]

    李彦冬, 郝宗波, 雷航 2016 计算机应用 36 2508

    Li Y, Hao Z, Lei H 2016 J. Comput. Appl. 36 2508

    [30]

    Greff K, Srivastava R K, Koutník J, Steunebrink B R, Schmidhuber J 2016 IEEE Trans. Neural Netw. Learn. Syst. 28 2222

    [31]

    Hinton G E, Osindero S, Teh Y W 2006 Neural Comput. 18 1527Google Scholar

    [32]

    Butler A C 2010 J. Exp. Psychol. Learn. Mem. Cogn. 36 1118Google Scholar

    [33]

    Wang B, Liu Y, Zhou Y, Wen Z 2018 Nano Energy 46 322Google Scholar

    [34]

    Peden M 2005 Int. J. Inj. Control Saf. Promot. 12 85Google Scholar

    [35]

    Abou Elassad Z E, Mousannif H, Al Moatassime H 2020 Transp. Res. Part C Emerg. Technol. 118 102708Google Scholar

    [36]

    Soares S, Monteiro T, Lobo A, Couto A, Cunha L, Ferreira S 2020 Sustainability 12 1971Google Scholar

    [37]

    Moretti L, Palazzi F, Cantisani G 2020 Sustainability 12 4120Google Scholar

    [38]

    Trivedi M M, Cheng S Y 2007 Computer 40 60

    [39]

    Trivedi M M, Gandhi T, McCall J 2007 IEEE Trans. Intell. Transp. Syst. 8 108Google Scholar

    [40]

    Zhang H, Cheng Q, Lu X, Wang W, Wang Z L, Sun C 2021 Nano Energy 79 105455Google Scholar

    [41]

    Ho T K 1995 Proceedings of 3rd international conference on document analysis and recognition Montreal Montreal, QC, Canada, August 14–16,1995 p278

    [42]

    Wu Y, Abdel-Aty M, Park J, Zhu J 2018 Transp. Res. Part C Emerg. Technol. 95 481Google Scholar

    [43]

    Cheng Q, Jiang X, Zhang H, Wang W, Sun C 2020 Sustainability 12 8926Google Scholar

    [44]

    Ma C, Gao S, Gao X, Wu M, Wang R, Wang Y, Tang Z, Fan F, Wu W, Wan H, Wu W 2019 InfoMat 1 116Google Scholar

    [45]

    García-Gonzalo E, Fernández-Muñiz Z, García Nieto P J, Bernardo Sánchez A, Menéndez Fernández M 2016 Materials 9 531Google Scholar

    [46]

    Zhang W, Wang P, Sun K, Wang C, Diao D 2019 Nano Energy 56 277Google Scholar

    [47]

    Yang L, Wang Y, Zhao Z, Guo Y, Chen S, Zhang W, Guo X 2020 ACS Appl. Mater. Interfaces 12 38192Google Scholar

    [48]

    Fukushima K 1980 Biol. Cybern. 36 193Google Scholar

    [49]

    Shao H, Jiang H, Li X, Liang T 2018 Comput. Ind. 96 27Google Scholar

    [50]

    Zhao G, Yang J, Chen J, Zhu G, Jiang Z, Liu X, Niu G, Wang Z L, Zhang B 2019 Adv. Mater. Technol. 4 1800167Google Scholar

    [51]

    Zhang W, Deng L, Yang L, Yang P, Diao D, Wang P, Wang Z L 2020 Nano Energy 77 105174Google Scholar

    [52]

    Tcho I W, Kim W G, Choi Y K 2020 Nano Energy 70 104534Google Scholar

    [53]

    Jin T, Sun Z, Li L, Zhang Q, Zhu M, Zhang Z, Yuan G, Chen T, Tian Y, Hou X, Lee C 2020 Nat. Commun. 11 5381Google Scholar

    [54]

    Shi Y, Wang F, Tian J, Li S, Fu E, Nie J, Lei R, Ding Y, Chen X, Wang Z L 2021 Sci. Adv. 7 eabe2943Google Scholar

    [55]

    Hou C, Geng J, Yang Z, Tang T, Sun Y, Wang F, Liu H, Chen T, Sun L 2021 Adv. Mater. Technol. 6 2000912Google Scholar

    [56]

    Zhang Z, He T, Zhu M, Sun Z, Shi Q, Zhu J, Dong B, Yuce M R, Lee C 2020 NPJ Flex. Electron. 4 29Google Scholar

    [57]

    Wen F, Sun Z, He T, Shi Q, Zhu M, Zhang Z, Li L, Zhang T, Lee C 2020 Adv. Sci. 7 2000261Google Scholar

    [58]

    Lin Z, Wu Z, Zhang B, Wang Y C, Guo H, Liu G, Chen C, Chen Y, Yang J, Wang Z L 2019 Adv. Mater. Technol. 4 1800360Google Scholar

    [59]

    Luo J, Gao W, Wang Z L 2021 Adv. Mater. 33 2004178Google Scholar

    [60]

    Liu S, Zhang J, Zhang Y, Zhu R 2020 Nat. Commun. 11 5615Google Scholar

    [61]

    Luo J, Wang Z, Xu L, Wang A C, Han K, Jiang T, Lai Q, Bai Y, Tang W, Fan F R, Wang Z L 2019 Nat. Commun. 10 5147Google Scholar

    [62]

    Zhou Y, Shen M, Cui X, Shao Y, Li L, Zhang Y 2021 Nano Energy 84 105887Google Scholar

    [63]

    Syu M H, Guan Y J, Lo W C, Fuh Y K 2020 Nano Energy 76 105029Google Scholar

    [64]

    Shi Q, Zhang Z, He T, Sun Z, Wang B, Feng Y, Shan X, Salam B, Lee C 2020 Nat. Commun. 11 4609Google Scholar

    [65]

    Shi Q, Zhang Z, Yang Y, Shan X, Salam B, Lee C 2021 ACS Nano 15 18312Google Scholar

    [66]

    Li S, Fan Y, Chen H, Nie J, Liang Y, Tao X, Zhang J, Chen X, Fu E, Wang Z L 2020 Energy Environ. Sci. 13 896Google Scholar

    [67]

    Zou H, Guo L, Xue H, Zhang Y, Shen X, Liu X, Wang P, He X, Dai G, Jiang P, Zheng H, Zhang B, Xu C, Wang Z L 2020 Nat. Commun. 11 2093Google Scholar

    [68]

    Oliynyk A O, Antono E, Sparks T D, Ghadbeigi L, Gaultois M W, Meredig B, Mar A 2016 Chem. Mater. 28 7324Google Scholar

    [69]

    Ward L, Agrawal A, Choudhary A, Wolverton C 2016 NPJ Comput. Mater. 2 16028Google Scholar

    [70]

    Vergara A, Vembu S, Ayhan T, Ryan M A, Homer M L, Huerta R 2012 Sens. Actuators, B 166 320

    [71]

    Gu L, Cui N, Liu J, Zheng Y, Bai S, Qin Y 2015 Nanoscale 7 18049Google Scholar

    [72]

    Lee K Y, Yoon H J, Jiang T, Wen X, Seung W, Kim S W, Wang Z L 2016 Adv. Energy Mater. 6 1502566Google Scholar

    [73]

    Agrawal A, Lee S K, Silberman J, Ziegler M, Kang M, Venkataramani S, Cao N, Fleischer B, Guillorn M, Cohen M, Mueller S, Oh J, Lutz M, Jung J, Koswatta S, Zhou C, Zalani V, Bonanno J, Casatuta R, Chen C Y, Choi J, Haynie H, Herbert A, Jain R, Kar M, Kim K H, Li Y, Ren Z, Rider S, Schaal M, Schelm K, Scheuermann M, Sun X, Tran H, Wang N, Wang W, Zhang X, Shah V, Curran B, Srinivasan V, Lu P F, Shukla S, Chang L, Gopalakrishnan K 2021 IEEE J Solid-State Circuits San Francisco, California, USA, Feburary, 13–22, 2021 p144

    [74]

    Joung H A, Ballard Z S, Wu J, Tseng D K, Teshome H, Zhang L, Horn E J, Arnaboldi P M, Dattwyler R J, Garner O B, Di Carlo D, Ozcan A 2019 ACS Nano 14 229

  • [1] 宋睿, 刘雪梅, 王海滨, 吕皓, 宋晓艳. 机器学习辅助的硬质合金硬度预测. 物理学报, 2024, 0(0): . doi: 10.7498/aps.73.20240284
    [2] 张嘉晖. 蛋白质计算中的机器学习. 物理学报, 2024, 73(6): 069301. doi: 10.7498/aps.73.20231618
    [3] 邓浩程, 李祎, 田双双, 张晓星, 肖淞. 面向高性能摩擦纳米发电机的电介质材料. 物理学报, 2024, 73(7): 070702. doi: 10.7498/aps.73.20240150
    [4] 张逸凡, 任卫, 王伟丽, 丁书剑, 李楠, 常亮, 周倩. 机器学习结合固溶强化模型预测高熵合金硬度. 物理学报, 2023, 72(18): 180701. doi: 10.7498/aps.72.20230646
    [5] 郭唯琛, 艾保全, 贺亮. 机器学习回归不确定性揭示自驱动活性粒子的群集相变. 物理学报, 2023, 72(20): 200701. doi: 10.7498/aps.72.20230896
    [6] 刘烨, 牛赫然, 李兵兵, 马欣华, 崔树旺. 机器学习在宇宙线粒子鉴别中的应用. 物理学报, 2023, 72(14): 140202. doi: 10.7498/aps.72.20230334
    [7] 管星悦, 黄恒焱, 彭华祺, 刘彦航, 李文飞, 王炜. 生物分子模拟中的机器学习方法. 物理学报, 2023, 72(24): 248708. doi: 10.7498/aps.72.20231624
    [8] 康俊锋, 冯松江, 邹倩, 李艳杰, 丁瑞强, 钟权加. 基于机器学习的非线性局部Lyapunov向量集合预报订正. 物理学报, 2022, 71(8): 080503. doi: 10.7498/aps.71.20212260
    [9] 梁帅博, 袁涛, 邱扬, 张震, 妙亚宁, 韩竞峰, 刘秀童, 姚春丽. 钛酸钡介电调控提升纸基摩擦纳米发电机输出性能. 物理学报, 2022, 71(7): 077701. doi: 10.7498/aps.71.20212022
    [10] 万新阳, 章烨辉, 陆帅华, 吴艺蕾, 周跫桦, 王金兰. 机器学习加速搜寻新型双钙钛矿氧化物光催化剂. 物理学报, 2022, 71(17): 177101. doi: 10.7498/aps.71.20220601
    [11] 王坤, 段高燕, 郎佩琳, 赵玉芳, 刘尖斌, 宋钢. 基于银纳米链的马赫-曾德干涉仪结构的生物传感器. 物理学报, 2022, 71(1): 017301. doi: 10.7498/aps.71.20211420
    [12] 丁子平, 廖健飞, 曾泽楷. 基于表面等离子体共振的新型超宽带微结构光纤传感器研究. 物理学报, 2021, 70(7): 074207. doi: 10.7498/aps.70.20201477
    [13] 林键, 叶梦, 朱家纬, 李晓鹏. 机器学习辅助绝热量子算法设计. 物理学报, 2021, 70(14): 140306. doi: 10.7498/aps.70.20210831
    [14] 陈江芷, 杨晨温, 任捷. 基于波动与扩散物理系统的机器学习. 物理学报, 2021, 70(14): 144204. doi: 10.7498/aps.70.20210879
    [15] 庞慧中, 王鑫, 王俊林, 王宗利, 刘苏雅拉图, 田虎强. 双频带太赫兹超材料吸波体传感器传感特性. 物理学报, 2021, 70(16): 168101. doi: 10.7498/aps.70.20210062
    [16] 曹杰, 顾伟光, 曲召奇, 仲艳, 程广贵, 张忠强. 基于变化静电场的非接触式摩擦纳米发电机设计与研究. 物理学报, 2020, 69(23): 230201. doi: 10.7498/aps.69.20201052
    [17] 丁亚飞, 陈翔宇. 基于摩擦纳米发电机的可穿戴能源器件. 物理学报, 2020, 69(17): 170202. doi: 10.7498/aps.69.20200867
    [18] 杨自欣, 高章然, 孙晓帆, 蔡宏灵, 张凤鸣, 吴小山. 铅基钙钛矿铁电晶体高临界转变温度的机器学习研究. 物理学报, 2019, 68(21): 210502. doi: 10.7498/aps.68.20190942
    [19] 吴晔盛, 刘启, 曹杰, 李凯, 程广贵, 张忠强, 丁建宁, 蒋诗宇. 收集振动能的摩擦纳米发电机设计与输出性能. 物理学报, 2019, 68(19): 190201. doi: 10.7498/aps.68.20190806
    [20] 廖文英, 范万德, 李海鹏, 隋佳男, 曹学伟. 准晶体结构光纤表面等离子体共振传感器特性研究. 物理学报, 2015, 64(6): 064213. doi: 10.7498/aps.64.064213
计量
  • 文章访问数:  9961
  • PDF下载量:  291
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-09-02
  • 修回日期:  2021-11-14
  • 上网日期:  2022-01-26
  • 刊出日期:  2022-04-05

/

返回文章
返回