智能背景下机器学习在柔性应变传感器中的应用研究进展

doi:10.13475/j.fzxb.20221105502

Abstract

Abstract:

Significance Because of the rapid progress and growth of smart materials and smart textiles, increasing attention hasbeen focused on the research, development, and optimization of flexible strain sensors. Flexible strain sensors for smart textiles are capable of detecting the precise motion trajectory of the human body, mechanical-acoustic characteristics, and information on various physiological indicators. With the continuous optimization of the performance of flexible strain sensors, the flexible sensor devices need to achieve the acquisition and analysis of high-dimensional and high-frequency complex superimposed signals in very complex application environments, which in turn puts forward higher requirements for data processing algorithms. The implementation of machine learning, a more advanced method, has significantly contributed to the improvement in the overall performance of the flexible strain sensing system. This paper presents a systematic review of the research progress of flexible strain sensors based on smart textiles combined with machine learning. The goal of the review is to understand and broaden the application of machine learning in the field of flexible strain sensors.

Progress This paper firstly made an in-depth analysis of the fundamental structure and previous research on a variety of conventional flexible strain sensors such as piezoresistive, piezoelectric, capacitive, optical, magnetic, and triboelectric. In addition, this paper introduced the workflow of machine learning, which can be divided into the following four main steps: data preprocessing, machine learning and model training, model evaluation, and prediction of new data. According to the learning method, machine learning can be classified into supervised learning, unsupervised learning, reinforcement learning, and a mixture of the above three types. This paper then paper provided a detailed description of the information processing process of flexible strain sensors based on machine learning, as well as summarized the advantages and disadvantages of some typical machine learning algorithms for time-frequency analysis, dimensionality reduction, and classification. Furthermore, this paper analyzed the most recent research on flexible strain sensors based on smart textiles combined with machine learning in the fields of healthcare, life assistance, communication and exchange, as well as teaching and entertainment, which placed a significant amount of emphasis on the benefits that can be gained from utilizing machine learning in flexible strain sensors. In the field of healthcare, flexible strain sensing systems can continuously track various mechanical and acoustic features of the human body by combining with specific machine learning algorithms, which can help users to understand their own health status in real time, and thus achieve the purpose of health monitoring. Secondly, in the field of life assistance, the large amount of information provided by the machine learning-based strain sensing system can help in the design of bionic hearing, touch, and prosthetic manipulator, which can greatly improve the convenience of life for the disabled and the blind. Moreover, free-life monitoring by flexible strain sensing systems has the potential advantage of accurately detecting and measuring clinically relevant features, including fall risk and abnormal gait, so that abnormal movement symptoms of the elderly can be detected in a timely manner, which can ensure the safety of the elderly's life to a considerable extent. In the field of communication and exchange, the application of flexible strain sensors based on machine learning can improve the recognition performance of various features, such as sign language recognition, micro-expression detection, and perceptual interaction, thus facilitating human-to-human communication. In addition, the strain sensing system combined with specific machine learning algorithms enriches the application of smart textiles in teaching and entertainment scenarios, which improves the teaching efficiency and enhances the fun of teaching at the same time, and the application in gaming and entertainment greatly enriches people's lives.

Conclusion and Prospect Flexible strain sensors have excellent characteristics, such as high sensitivity, high resolution, and good elasticity. With the help of new sensor structures, new sensitive materials, and cutting-edge machine learning algorithms, smart textiles have been of great value in a variety of different fields. However, in the context of material intelligence, the research on flexible strain sensors based on smart textiles is still in its infancy and still faces many challenges, such as the fact that researchers have carried out little research on the optimal design of flexible strain sensor arrays, that it is difficult to simulate real human touch with flexible strain sensors designed according to existing technologies, and that the process of human pose recognition with flexible strain sensor systems can easily cause confusion in the recognition system. In a word, there is no doubt that machine learning has evolved into a valuable tool in the realm of smart wearables. It is believed that in the near future, with the continuous development of computer science and computing methods, machine learning will play a huge application value in various aspects such as the research and development of smart textile materials, process improvement, device performance evaluation, signal transmission, data processing, etc., and will further promote the intelligent development of the whole material field.

Key words: flexible strain sensor, machine learning, signal processing, smart textile, smart material

CLC Number:

TP212

LU Yan, HONG Yan, FANG Jian. Research progress on applications of machine learning in flexible strain sensors in context of material intelligence[J].Journal of Textile Research, 2024, 45(05): 228-238.

Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks

URL: http://www.fzxb.org.cn/EN/10.13475/j.fzxb.20221105502

http://www.fzxb.org.cn/EN/Y2024/V45/I05/228

Figures/Tables 3

Fig.1

Fig.2

Tab.1

Advantages and disadvantages of machine learning algorithms for time-frequency analysis, dimensionality reduction, and classification"

用途	算法	优点	缺点	参考文献
时频分析	傅里叶变换(FT)	可解释时域难以解释的滤波问题;可将线性时不变(LTI)系统分析问题中的卷积积分运算简化为乘积运算	无法实现时频联合分析	[36]
	希尔伯特-黄变换(HHT)	能分析非线性非平稳信号,且具有完全自适应性;不受海森堡测不准原理制约——适合突变信号	在经验模态分解(EMD)过程中会产生最终效应和模混合	[37]
	小波变换(WT)	能够以自适应分辨率在时域和频域中提取和分析信息	容易受到噪声频率分布变化的影响	[38]
	时间序列分析(TSA)	简单易行,便于掌握	准确性差,一般只适用于短期预测	[39]
降维	主成分分析(PCA)	减少了事件驱动应用中传感器节点或簇头的缓冲区溢出,避免了拥塞问题	当PCA的因子负荷的符号有正有负时,综合评价函数意义就不明确;命名清晰性低	[40]
	独立成分分析(ICA)	可消除高阶依赖关系	幅值、分离信号的排列具有不确定性	[41]
	因子分析(FA)	能很好地涵盖原始数据的各个项,同时将分析过程简化为因子项的分析	只能面对综合性的评价,同时对数据的数据量和成分有一定要求,需要先进行比较变量间简单相关系数(KOM)检测数据是否可以运用此方法	[42]
	自编码器(AE)	可增强神经网络模型的学习能力	该方法的性能很大程度上取决于数据的质量,可能无法处理对于带有噪声数据的极端情况	[43]
分类	决策树(DT)	透明,减少决策中的歧义,并允许进行全面的分析;测试数据集时,运行速度比较快,能够在大型数据源上实现切实可行、效果较好的结果	易发生过拟合、忽略数据集中属性的相互关联	[44]
	层次聚类分析(HCA)	无需预先知道聚类的数量,且易于实现	算法的时间复杂度大、不可逆性;聚类终止的条件具有不精确性	[45]
	偏最小二乘判别分析 (PLS-DA)	具有多功能性,可用于预测和描述建模以及判别变量选择	需要优化大量参数才能获得可靠和有效的结果	[46]
	支持向量机(SVM)	通过非线性映射将低维非线性函数映射到高维空间,无需知道非线性映射的具体形式	核函数的选择是该方法研究的核心问题,目前缺乏有效的方法来选择核函数	[47]
	人工神经网络(ANN)	擅于分类复杂和非线性的数据集,且对输入没有限制;算法可以快速调整以适应新的问题	对计算量的要求较高	[48]

Tab.1

References 61

[1]	LIU K, TEBYETEKERWA M, JI D, et al. Intelligent Materials[J]. Matter, 2020, 3(3): 590-593.
[2]	方剑, 任松, 张传雄, 等. 智能可穿戴纺织品用电活性纤维材料[J]. 纺织学报, 2021, 42(9): 1-9.
	FANG Jian, REN Song, ZHANG Chuanxiong, et al. Electroactive fibrous materials for intelligent wearable textiles[J]. Journal of Textile Research, 2021, 42(9): 1-9.
[3]	房翔敏, 曲丽君, 田明伟. 自供电纺织基柔性应变传感器研究进展[J]. 丝绸, 2022, 59(8): 36-47.
	FANG Xiangmin, QU Lijun, TIAN Mingwei. Research progress of self-powered textile-based flexible stress sensors[J]. Journal of Silk, 2022, 59(8): 36-47.
[4]	汤健, 闫涛, 潘志娟. 导电复合纤维基柔性应变传感器的研究进展[J]. 纺织学报, 2021, 42(5): 168-177.
	TANG Jian, YAN Tao, PAN Zhijuan. Research progress of flexible strain sensors based on conductive composite fibers[J]. Journal of Textile Research, 2021, 42(5): 168-177.
[5]	WANG Y, ZHU L, MEI D, et al. A highly flexible tactile sensor with an interlocked truncated sawtooth structure based on stretchable graphene/silver/silicone rubber composites[J]. Journal of Materials Chemistry C, 2019, 7(28): 8669-8679.
[6]	WIEDERHOLD G, MCCARTHY J. Arthur samuel: pioneer in machine learning[J]. IBM Journal of Research and Development, 1992, 36(3): 329-331.
[7]	CAI G, WANG J, QIAN K, et al. Extremely stretchable strain sensors based on conductive self-healing dynamic cross-links hydrogels for human-motion detection[J]. Advanced Science, 2017. DOI: 10.1002/advs.201600190.
[8]	SURESH KUMAR V, KRISHNAMOORTHI C. Development of electrical transduction based wearable tactile sensors for human vital signs monitor: fundamentals, methodologies and applications[J]. Sensors and Actuators A: Physical, 2021. DOI: 10.1016/j.sna.2021.112582.
[9]	HUANG J, LI D, ZHAO M, et al. Flexible electrically conductive biomass-based aerogels for piezoresistive pressure/strain sensors[J]. Chemical Engineering Journal, 2019, 373: 1357-1366.
[10]	PUNEETHA P, MALLEM S P R, LEE Y W, et al. Strain-controlled flexible graphene/GaN/PDMS sensors based on the piezotronic effect[J]. ACS Applied Materials & Interfaces, 2020, 12(32): 36660-36669.
[11]	QIU A, JIA Q, YU H, et al. Highly sensitive and flexible capacitive elastomeric sensors for compressive strain measurements[J]. Materials Today Communications, 2021, 26: 1-11.
[12]	GUO J, ZHOU B, ZONG R, et al. Stretchable and highly sensitive optical strain sensors for human-activity monitoring and healthcare[J]. ACS Applied Materials & Interfaces, 2019, 11(37): 33589-33598.
[13]	TANG X, MIAO Y, CHEN X, et al. A flexible and highly sensitive inductive pressure sensor array based on ferrite films[J]. Sensors (Basel), 2019, 19(10): 1-12.
[14]	MA S, TANG J, YAN T, et al. Performance of flexible strain sensors with different transition mechanisms: a review[J]. IEEE Sensors Journal, 2022, 22(8): 7475-7498.
[15]	FIORILLO A S, CRITELLO C D, PULLANO S A. Theory, technology and applications of piezoresistive sensors: a review[J]. Sensors and Actuators A: Physical, 2018, 281: 156-175.
[16]	MITSUHIRO Shikidaa T S, KAZUO Satob, KOICHI Itoigawa. Active tactile sensor for detecting contact force and hardness of an object[J]. Sensors and Actuators A (Physical), 2003, 103(1/2): 213-218.
[17]	PARK K I, SON J H, HWANG G T, et al. Highly-efficient, flexible piezoelectric PZT thin film nanogenerator on plastic substrates[J]. Advanced Materials, 2014, 26(16): 2514-2520.
[18]	MAKIHATA M, MUROYAMA M, TANAKA S, et al. Design and fabrication technology of low profile tactile sensor with digital interface for whole body robot skin[J]. Sensors (Basel), 2018. DOI: 10.3390/s18072374.
[19]	赵利端, 刘丽妍, 何崟, 等. 基于碳纳米管的柔性应变传感器研究进展[J]. 材料科学与工程学报, 2022, 40(5): 883-889,908.
	ZHAO Liduan, LIU Liyan, HE Yin, et al. Research progress on carbon nanotube flexible sensors[J]. Journal of Materials Science & Engineering, 2022, 40(5): 883-889,908.
[20]	CHEN T, QIAO X, WEI P, et al. Tough gel-fibers as strain sensors based on strain-optics conversion induced by anisotropic structural evolution[J]. Chemistry of Materials, 2020, 32(22): 9675-9687.
[21]	YANG H, FU J, CAO R, et al. A liquid lens-based optical sensor for tactile sensing[J]. Smart Materials and Structures, 2022. DOI: 10.1088/1361-665x/ac4d64.
[22]	CHI C, SUN X, XUE N, et al. Recent progress in technologies for tactile sensors[J]. Sensors (Basel), 2018, 18(4): 1-29.
[23]	TAO J, BAO R, WANG X, et al. Self-powered tactile sensor array systems based on the triboelectric effect[J]. Advanced Functional Materials, 2018. DOI: 10.1002/adfm.201806379.
[24]	YANG H L, XIE X Z, KADOCH M. Machine learning techniques and a case study for intelligent wireless networks[J]. IEEE Network, 2020, 34(3): 208-215.
[25]	JORDAN M I, MITCHELL T M. Machine learning:trends, perspectives, and prospectsing of nano-fibres[J]. Science, 2015, 349(6245): 255-260.
[26]	WANG M, CUI Y, WANG X, et al. Machine learning for networking: workflow, advances and opportuni-ties[J]. IEEE Network, 2018, 32(2): 92-99.
[27]	DUAN L, CUI S, QIAO Y, et al. Clustering based on supervised learning of exemplar discriminative information[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020, 50(12): 5255-5270.
[28]	NIKBAKHT R, JONSSON A, LOZANO A. Unsupervised learning for parametric optimization[J]. IEEE Communications Letters, 2021, 25(3): 678-681.
[29]	MATSUO Y, LECUN Y, SAHANI M, et al. Deep learning, reinforcement learning, and world models[J]. Neural Networks, 2022. DOI: 10.1016/j.neunet.2022.03.037.
[30]	LIU Z, HUANG S, JIN W, et al. Broad learning system for semi-supervised learning[J]. Neurocomputing, 2021, 444: 38-47.
[31]	WU J, SHENG V S, ZHANG J, et al. Multi-label active learning algorithms for image classification: overview and future promise[J]. ACM Computing Surveys, 2020. DOI: 10.1145/3379504.
[32]	MANIA H, JORDAN M I, RECHT B. Active learning for nonlinear system identification with guarantees[J]. Journal of Machine Learning Research, 2022, 23(32): 1-30.
[33]	DEN HENGST F, FRANçOIS-LAVET V, HOOGENDOORN M, et al. Planning for potential: efficient safe reinforcement learning[J]. Machine Learning, 2022, 111(6): 2255-2274.
[34]	SHIRMOHAMMADLI V, BAHREYNI B. Machine learning for sensing applications: a tutorial[J]. IEEE Sensors Journal, 2022, 22(11): 10183-10195.
[35]	JEON H, JUNG Y, LEE S, et al. Area-efficient short-time fourier transform processor for time-frequency analysis of non-stationary signals[J]. Applied Sciences, 2020. DOI: 10.3390/app10207208.
[36]	HIRSCHBERG V, RODRIGUE D. Fourier trans-form (ft) analysis of the stress as a tool to follow the fatigue behavior of metals[J]. Applied Sciences, 2021, 11(8): 1-15.
[37]	JI Y, WANG H. A revised Hilbert-Huang transform and its application to fault diagnosis in a rotor system[J]. Sensors (Basel), 2018. DOI: 10.3390/s18124329.
[38]	GRADOLEWSKI D, MAGENES G, JOHANSSON S, et al. A wavelet transform-based neural network denoising algorithm for mobile phonocardiography[J]. Sensors (Basel), 2019, 19(4): 1-18.
[39]	DONATELLI R E, PARK J A, MATHEWS S M, et al. Time series analysis[J]. American Journal of Orthodontics and Dentofacial Orthopedics, 2022, 161(4): 605-608. doi: 10.1016/j.ajodo.2021.07.013 pmid: 35337650
[40]	JIANG H, XIONG H, WU D, et al. AgFlow: fast model selection of penalized PCA via implicit regularization effects of gradient flow[J]. Machine Learning, 2021, 110(8): 2131-2150.
[41]	PRAVEEN KUMAR D, AMGOTH T, ANNAVARAPU C S R. Machine learning algorithms for wireless sensor networks: a survey[J]. Information Fusion, 2019, 49: 1-25. doi: 10.1016/j.inffus.2018.09.013
[42]	UNO K, ADACHI K, TRENDAFILOV N T. Clustered common factor exploration in factor analysis[J]. Psychometrika, 2019, 84(4): 1048-1067. doi: 10.1007/s11336-019-09666-5 pmid: 30847650
[43]	LI Z, LI S. Neural network model-based control for manipulator: an autoencoder perspective[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021. DOI: 10.1109/tnnls.2021.3109953.
[44]	KRAWCZYK B. Tensor decision trees for continual learning from drifting data streams[J]. Machine Learning, 2021, 110: 3015-3035.
[45]	HU X, LI Y, CHEN G, et al. Identification of balance recovery patterns after slips using hierarchical cluster analysis[J]. Journal of Biomechanics, 2022. DOI: 10.1016/j.jbiomech.2022.111281.
[46]	LEE L C, LIONG C Y, JEMAIN A A. Partial least squares-discriminant analysis (PLS-DA) for classification of high-dimensional (HD) data: a review of contemporary practice strategies and knowledge gaps[J]. Analyst, 2018, 143(15): 3526-3539. doi: 10.1039/c8an00599k pmid: 29947623
[47]	HUANG J-C, KO K-M, SHU M-H, et al. Application and comparison of several machine learning algorithms and their integration models in regression problems[J]. Neural Computing and Applications, 2019, 32(10): 5461-5469.
[48]	KONG P-Y. Distributed sensor clustering using artificial neural network with local information[J]. IEEE Internet of Things Journal, 2022, 9(21): 21851-21861.
[49]	NGUYEN T D, LEE J S. Recent development of flexible tactile sensors and their applications[J]. Sensors (Basel), 2021, 22(1): 1-24.
[50]	FANG Y, ZOU Y, XU J, et al. Ambulatory cardiovascular monitoring via a machine-learning-assisted textile triboelectric sensor[J]. Advanced Materials, 2021. DOI:10.1002/adma.202104178.
[51]	ZHANG Q, JIN T, CAI J, et al. Wearable triboelectric sensors enabled gait analysis and waist motion capture for iot-based smart healthcare applications[J]. Advanced Science, 2022. DOI:10.1002/advs.202103694.
[52]	GHOLAMI M, NAPIER C, PATINO A G, et al. Fatigue monitoring in running using flexible textile wearable sensors[J]. Sensors (Basel), 2020, 20(19): 1-11.
[53]	SUNDARAM S, KELLNHOFER P, LI Y, et al. Learning the signatures of the human grasp using a scalable tactile glove[J]. Nature, 2019, 569(7758): 698-702.
[54]	RAVENSCROFT D, PRATTIS I, KANDUKURI T, et al. Machine learning methods for automatic silent speech recognition using a wearable graphene strain gauge sensor[J]. Sensors (Basel), 2021, 22(1): 1-13.
[55]	ZHANG Z, HE T, ZHU M, et al. Deep learning-enabled triboelectric smart socks for IoT-based gait analysis and VR applications[J]. npj Flexible Electronics, 2020, 4(1): 1-12.
[56]	荣百川. 基于机器学习的摔倒识别研究[D]. 南京: 南京信息工程大学, 2021: 19-34.
	RONG Baichuan. Research on fall recognition based on machine learning[D]. Nanjing: Nanjing Univeristy of Information Science & Technology, 2021: 19-34.
[57]	WANG Z, BU M, XIU K, et al. A flexible, stretchable and triboelectric smart sensor based on graphene oxide and polyacrylamide hydrogel for high precision gait recognition in parkinsonian and hemiplegic patients[J]. Nano Energy, 2022. DOI: 10.1016/j.nanoen.2022.107978.
[58]	ZHOU Z, CHEN K, LI X, et al. Sign-to-speech translation using machine-learning-assisted stretchable sensor arrays[J]. Nature Electronics, 2020, 3(9): 571-578.
[59]	WU X, LUO X, SONG Z, et al. Ultra-robust and sensitive flexible strain sensor for real-time and wearable sign language translation[J]. Advanced Functional Materials, 2023. DOI:10.1002/adtm.202303504.
[60]	WOJCIK K, PIEKARCZYK M. Machine learning methodology in a system applying the adaptive strategy for teaching human motions[J]. Sensors (Basel), 2020, 20(1): 1-23.
[61]	CHEN M, OUYANG J, JIAN A, et al. Imperceptible, designable, and scalable braided electronic cord[J]. Nat Commun, 2022, 13(1): 7097. doi: 10.1038/s41467-022-34918-x pmid: 36402785

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

Research progress on applications of machine learning in flexible strain sensors in context of material intelligence

RichHTML

PDF (PC)

Abstract

Cite this article

share this article

Figures/Tables 3

References 61

Related Articles 15

Metrics

Comments

Recommended 0

[1]	JU Yu, WANG Zhaohui, LI Boyi, YE Qinwen. Employee efficiency prediction of garment production line based on machine learning [J]. Journal of Textile Research, 2024, 45(05): 183-192.
[2]	PENG Laihu, HOU Liangmei, QI Yubao, RU Xin, LIU Jianting. Yarn tension signal processing method based on adaptive Loess principle [J]. Journal of Textile Research, 2024, 45(02): 246-254.
[3]	DONG Kai, LÜ Tianmei, SHENG Feifan, PENG Xiao. Advances in smart textiles oriented to personalized healthcare [J]. Journal of Textile Research, 2024, 45(01): 240-249.
[4]	WANG Hanchen, WU Jiayin, HUANG Biao, LU Qilin. Fabrication and properties of biocompatible nanocellulose self-healing hydrogels [J]. Journal of Textile Research, 2023, 44(12): 17-25.
[5]	WANG Menglei, WANG Jing'an, GAO Weidong. Research progress in computer aided cotton blending technology [J]. Journal of Textile Research, 2023, 44(08): 225-233.
[6]	WANG Zhongyu, SU Yun, WANG Yunyi. Development of personal comfort models based on machine learning and their application prospect in clothing engineering [J]. Journal of Textile Research, 2023, 44(05): 228-236.
[7]	PENG Yangyang, SHENG Nan, SUN Fengxin. Scalable construction and performance of fiber-based flexible moisture-responsive actuators [J]. Journal of Textile Research, 2023, 44(02): 90-95.
[8]	NIU Li, LIU Qing, CHEN Chaoyu, JIANG Gaoming, MA Pibo. Fabrication and performances of self-powering knitted sensing fabric with bionic scales [J]. Journal of Textile Research, 2023, 44(02): 135-142.
[9]	WU Jing, HAN Chenchen, GAO Weidong. Properties and applications of yarn-based actuators based on skeletalmuscle-like structure [J]. Journal of Textile Research, 2023, 44(02): 128-134.
[10]	PU Haihong, HE Pengxin, SONG Baiqing, ZHAO Dingying, LI Xinfeng, ZHANG Tianyi, MA Jianhua. Preparation of cellulose/carbon nanotube composite fiber and its functional applications [J]. Journal of Textile Research, 2023, 44(01): 79-86.
[11]	XIAO Yuan, LI Qian, ZHANG Wei, HU Hanchun, GUO Xinlei. Influencing factors on flexible fabric-based electrical circuit formation by micro-jet printed primary cell replacement deposition [J]. Journal of Textile Research, 2022, 43(10): 89-96.
[12]	LIU Huanhuan, WANG Zhaohui, YE Qinwen, CHEN Ziwei, ZHENG Jingjin. Progress and trends in application of wearable technology for emotion recognition [J]. Journal of Textile Research, 2022, 43(08): 197-205.
[13]	LI Ruikai, LI Ruichang, ZHU Lin, LIU Xiangyang. System of seven-lead electrocardiogram monitoring based on graphene fabric electrodes [J]. Journal of Textile Research, 2022, 43(07): 149-154.
[14]	WANG Chengcheng, GONG Xiaodan, WANG Zhen, MA Qunwang, ZHANG Liping, FU Shaohai. Preparation of binary thermochromic microcapsules and application in smart textiles [J]. Journal of Textile Research, 2022, 43(05): 38-42.
[15]	SUN Chunhong, DING Guangtai, FANG Kun. Cashmere and wool classification based on sparse dictionary learning [J]. Journal of Textile Research, 2022, 43(04): 28-32.