Journal Home > Online First
Nano Research https://doi.org/10.1007/s12274-024-6613-6
Research Article | Online first | Published: 20 April 2024

A machine learning-guided design and manufacturing of wearable nanofibrous acoustic energy harvesters

Show Author's Information Negar Hosseinzadeh Kouchehbaghi1,2,  Maryam Yousefzadeh2( ),  Aliakbar Gharehaghaji2( ),  Safoora Khosravi1,3,  Danial Khorsandi1,  Reihaneh Haghniaz1,  Ke Cao4,  Mehmet R. Dokmeci1,  Mohammad Rostami5,  Ali Khademhosseini1( ),  Yangzhi Zhu1( )
Terasaki Institute for Biomedical Innovation, Los Angeles, CA 91367, USA
Department of Textile Engineering, Amirkabir University of Technology (Tehran Polytechnic), Hafez Avenue, 1591634311 Tehran, Iran
Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC V6T1Z4, Canada
Chemical Sciences Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831, USA
Department of Computer Science, University of Southern California, Los Angeles, CA 90007, USA
Keywords:
machine learning, wearable electronics, electrospun nanofiber, piezoelectric nanogenerator, acoustic energy harvester
Topics:
Devices
Cite this article:
Kouchehbaghi NH, Yousefzadeh M, Gharehaghaji A, et al. A machine learning-guided design and manufacturing of wearable nanofibrous acoustic energy harvesters. Nano Research, 2024, https://doi.org/10.1007/s12274-024-6613-6
Download citation
EndNote(RIS)
BibTeX

560

Views

232

Downloads

Citations

0

Crossref

0

WoS

0

Scopus

0

CSCD

Abstract Full text Electronic supplementary material About this article

Nanofibrous acoustic energy harvesters (NAEHs) have emerged as promising wearable platforms for efficient noise-to-electricity conversion in distributed power energy systems and wearable sound amplifiers for assistive listening devices. However, their real-life efficacy is hampered by low power output, particularly in the low-frequency range (< 1 kHz). This study introduces a novel approach to enhance the performance of NAEHs by applying machine learning (ML) techniques to guide the synthesis of electrospun polyvinylidene fluoride (PVDF)/polyurethane (PU) nanofibers, optimizing their application in wearable NAEHs. We use a feed-forward neural network along with solving an optimization problem to find the optimal input values of the electrospinning (applied voltage, nozzle-collector distance, electrospinning time, and drum rotation speed) to generate maximum output performance (acoustic-to-electricity conversion efficiency). We first prepared a dataset to train the network to predict the output power given the input variables with high accuracy. Upon introducing the neural network, we fix the network and then solve an optimization problem using a genetic algorithm to search for the input values that lead to the maximum energy harvesting efficiency. Our ML-guided wearable PVDF/PU NAEH platform can deliver a maximal acoustoelectric power density output of 829 µW/cm3 within the surrounding noise levels. In addition, our system can function stably in a broad frequency (0.1–2 kHz) with a high energy conversion efficiency of 66%. Sound recognition analysis reveals a robust correlation exceeding 0.85 among lexically akin terms with varying sound intensities, contrasting with a diminished correlation below 0.27 for words with disparate semantic connotations. Overall, this work provides a previously unexplored route to utilize ML in advancing wearable NAEHs with excellent practicability.


menu
Abstract
Full text
Outline
Electronic supplementary material
About this article

A machine learning-guided design and manufacturing of wearable nanofibrous acoustic energy harvesters

Show Author's information Negar Hosseinzadeh Kouchehbaghi1,2, Maryam Yousefzadeh2( ), Aliakbar Gharehaghaji2( ), Safoora Khosravi1,3, Danial Khorsandi1, Reihaneh Haghniaz1, Ke Cao4, Mehmet R. Dokmeci1, Mohammad Rostami5, Ali Khademhosseini1( ), Yangzhi Zhu1( )
Terasaki Institute for Biomedical Innovation, Los Angeles, CA 91367, USA
Department of Textile Engineering, Amirkabir University of Technology (Tehran Polytechnic), Hafez Avenue, 1591634311 Tehran, Iran
Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC V6T1Z4, Canada
Chemical Sciences Division, Oak Ridge National Laboratory, Oak Ridge, Tennessee 37831, USA
Department of Computer Science, University of Southern California, Los Angeles, CA 90007, USA

Abstract

Nanofibrous acoustic energy harvesters (NAEHs) have emerged as promising wearable platforms for efficient noise-to-electricity conversion in distributed power energy systems and wearable sound amplifiers for assistive listening devices. However, their real-life efficacy is hampered by low power output, particularly in the low-frequency range (< 1 kHz). This study introduces a novel approach to enhance the performance of NAEHs by applying machine learning (ML) techniques to guide the synthesis of electrospun polyvinylidene fluoride (PVDF)/polyurethane (PU) nanofibers, optimizing their application in wearable NAEHs. We use a feed-forward neural network along with solving an optimization problem to find the optimal input values of the electrospinning (applied voltage, nozzle-collector distance, electrospinning time, and drum rotation speed) to generate maximum output performance (acoustic-to-electricity conversion efficiency). We first prepared a dataset to train the network to predict the output power given the input variables with high accuracy. Upon introducing the neural network, we fix the network and then solve an optimization problem using a genetic algorithm to search for the input values that lead to the maximum energy harvesting efficiency. Our ML-guided wearable PVDF/PU NAEH platform can deliver a maximal acoustoelectric power density output of 829 µW/cm3 within the surrounding noise levels. In addition, our system can function stably in a broad frequency (0.1–2 kHz) with a high energy conversion efficiency of 66%. Sound recognition analysis reveals a robust correlation exceeding 0.85 among lexically akin terms with varying sound intensities, contrasting with a diminished correlation below 0.27 for words with disparate semantic connotations. Overall, this work provides a previously unexplored route to utilize ML in advancing wearable NAEHs with excellent practicability.

Keywords: machine learning, wearable electronics, electrospun nanofiber, piezoelectric nanogenerator, acoustic energy harvester

References(49)

[1]

Zhu, Y. Z.; Li, J. H.; Kim, J.; Li, S. P.; Zhao, Y. C.; Bahari, J.; Eliahoo, P.; Li, G. H.; Kawakita, S.; Haghniaz, R. et al. Skin-interfaced electronics: A promising and intelligent paradigm for personalized healthcare. Biomaterials 2023, 296, 122075.
DOI Google Scholar
[2]

Luo, Y. F.; Abidian, M. R.; Ahn, J. H.; Akinwande, D.; Andrews, A. M.; Antonietti, M.; Bao, Z. N.; Berggren, M.; Berkey, C. A.; Bettinger, C. J. et al. Technology roadmap for flexible sensors. ACS Nano 2023, 17, 5211–5295.
DOI Google Scholar
[3]

Mo, X. W.; Zhou, H.; Li, W. B.; Xu, Z. S.; Duan, J. J.; Huang, L.; Hu, B.; Zhou, J. Piezoelectrets for wearable energy harvesters and sensors. Nano Energy 2019, 65, 104033.
DOI Google Scholar
[4]

Zhu, Y. Z.; Haghniaz, R.; Hartel, M. C.; Guan, S. H.; Bahari, J.; Li, Z. J.; Baidya, A.; Cao, K.; Gao, X. X.; Li, J. H. et al. A breathable, passive-cooling, non-inflammatory, and biodegradable aerogel electronic skin for wearable physical-electrophysiological-chemical analysis. Adv. Mater. 2023, 35, 2209300.
DOI Google Scholar
[5]

Fan, X.; Chen, J.; Yang, J.; Bai, P.; Li, Z. L.; Wang, Z. L. Ultrathin, rollable, paper-based triboelectric nanogenerator for acoustic energy harvesting and self-powered sound recording. ACS Nano 2015, 9, 4236–4243.
DOI Google Scholar
[6]

Choi, J.; Jung, I.; Kang, C. Y. A brief review of sound energy harvesting. Nano Energy 2019, 56, 169–183.
DOI Google Scholar
[7]

Kim, S.; Choi, J.; Seung, H. M.; Jung, I.; Ryu, K. H.; Song, H. C.; Kang, C. Y.; Kim, M. Gradient-index phononic crystal and Helmholtz resonator coupled structure for high-performance acoustic energy harvesting. Nano Energy 2022, 101, 107544.
DOI Google Scholar
[8]
Biswas, S.; Lee, S. W.; Lee, Y.; Choi, H. J.; Chen, J. J.; Yang, X.; Du, Y. X.; Falcone, N.; de Barros, N. R.; Lee, S. M. et al. Emerging energy harvesters in flexible bioelectronics: From wearable devices to biomedical innovations. Small Sci., in press, DOI: 10.1002/smsc.202300148.
DOI
[9]

Chen, F. Q.; Wu, Y. H.; Ding, Z. Y.; Xia, X.; Li, S. H.; Zheng, H. W.; Diao, C. L.; Yue, G. T.; Zi, Y. L. A novel triboelectric nanogenerator based on electrospun polyvinylidene fluoride nanofibers for effective acoustic energy harvesting and self-powered multifunctional sensing. Nano Energy 2019, 56, 241–251.
DOI Google Scholar
[10]

Yuan, M.; Cao, Z. P.; Luo, J.; Chou, X. J. Recent developments of acoustic energy harvesting: A review. Micromachines (Basel) 2019, 10, 48.
DOI Google Scholar
[11]

Sezer, N.; Koç, M. A comprehensive review on the state-of-the-art of piezoelectric energy harvesting. Nano Energy 2021, 80, 105567.
DOI Google Scholar
[12]

Xu, W. K.; Guo, J. T.; Wen, H. Y.; Meng, X. H.; Hong, H. X.; Yuan, J. B.; Gao, J. A.; Liu, D. Y.; Ran, Q.; Wang, Y. D. et al. Laminated triboelectric acoustic energy harvester based on electrospun nanofiber towards real-time noise decibel monitoring. Nano Energy 2022, 99, 107348.
DOI Google Scholar
[13]

Feng, Z. B.; Zhao, Z. Q.; Liu, Y. N.; Liu, Y. K.; Cao, X. Y.; Yu, D. G.; Wang, K. Piezoelectric effect polyvinylidene fluoride (PVDF): From energy harvester to smart skin and electronic textiles. Adv. Mater. Technol. 2023, 8, 2300021.
DOI Google Scholar
[14]

Abdolmaleki, H.; Haugen, A. B.; Buhl, K. B.; Daasbjerg, K.; Agarwala, S. Interfacial engineering of PVDF-TrFE toward higher piezoelectric, ferroelectric, and dielectric performance for sensing and energy harvesting applications. Adv. Sci. 2023, 10, 2205942.
DOI Google Scholar
[15]

Sun, W. H.; Ji, G. S.; Chen, J. L.; Sui, D.; Zhou, J.; Huber, J. Enhancing the acoustic-to-electrical conversion efficiency of nanofibrous membrane-based triboelectric nanogenerators by nanocomposite composition. Nano Energy 2023, 108, 108248.
DOI Google Scholar
[16]

Ge, X. H.; Hu, N.; Yan, F. J.; Wang, Y. Development and applications of electrospun nanofiber-based triboelectric nanogenerators. Nano Energy 2023, 112, 108444.
DOI Google Scholar
[17]

Zhang, M. D.; Liu, C. K.; Li, B. Y.; Shen, Y. T.; Wang, H.; Ji, K. Y.; Mao, X.; Wei, L.; Sun, R. J.; Zhou, F. L. Electrospun PVDF-based piezoelectric nanofibers: Materials, structures, and applications. Nanoscale Adv. 2023, 5, 1043–1059.
DOI Google Scholar
[18]

Su, Y. J.; Li, W. X.; Cheng, X. X.; Zhou, Y. H.; Yang, S.; Zhang, X.; Chen, C. X.; Yang, T. N.; Pan, H.; Xie, G. Z. et al. High-performance piezoelectric composites via β phase programming. Nat. Commun. 2022, 13, 4867.
DOI Google Scholar
[19]

Nezadi, M.; Keshvari, H.; Yousefzadeh, M. Using Taguchi design of experiments for the optimization of electrospun thermoplastic polyurethane scaffolds. Adv. Nano Res. 2021, 10, 59–69.
DOI Google Scholar
[20]

Gupta, V.; Kumar, A.; Mondal, B.; Babu, A.; Ranpariya, S.; Sinha, D. K.; Mandal, D. Machine learning-aided all-organic air-permeable piezoelectric nanogenerator. ACS Sustain. Chem. Eng. 2023, 11, 6173–6182.
DOI Google Scholar
[21]

Ieracitano, C.; Paviglianiti, A.; Campolo, M.; Hussain, A.; Pasero, E.; Morabito, F. C. A novel automatic classification system based on hybrid unsupervised and supervised machine learning for electrospun nanofibers. IEEE/CAA J. Autom. Sin. 2021, 8, 64–76.
DOI Google Scholar
[22]

Hwang, S. H.; Song, J. Y.; Ryu, H. I.; Oh, J. H.; Lee, S.; Lee, D.; Park, D. Y.; Park, S. M. Adaptive electrospinning system based on reinforcement learning for uniform-thickness nanofiber air filters. Adv. Fiber Mater. 2023, 5, 617–631.
DOI Google Scholar
[23]

Zhan, Y. H.; Zhu, J. Response surface methodology and artificial neural network-genetic algorithm for modeling and optimization of bioenergy production from biochar-improved anaerobic digestion. Appl. Energy 2024, 355, 122336.
DOI Google Scholar
[24]

Salari, M.; Alahabadi, A.; Rahmani-Sani, A.; Miri, M.; Yazdani-Aval, M.; Lotfi, H.; Saghi, M. H.; Rastegar, A.; Sepehr, M. N.; Darvishmotevalli, M. A comparative study of response surface methodology and artificial neural network based algorithm genetic for modeling and optimization of EP/US/GAC oxidation process in dexamethasone degradation: Application for real wastewater, electrical energy consumption. Chemosphere 2024, 349, 140832.
DOI Google Scholar
[25]

Balraj, S.; Prakash, D. G.; Iyyappan, J.; Bharathiraja, B. Modelling and optimization of biodiesel production from waste fish oil using nano immobilized r Pichiapastoris whole cell biocatalyst with response surface methodology and hybrid artificial neural network based approach. Bioresour. Technol. 2024, 393, 130012.
DOI Google Scholar
[26]

Komori, T.; Makishima, K. Numbers of fiber-to-fiber contacts in general fiber assemblies. Text. Res. J. 1977, 47, 13–17.
DOI Google Scholar
[27]

Soin, N.; Boyer, D.; Prashanthi, K.; Sharma, S.; Narasimulu, A. A.; Luo, J.; Shah, T. H.; Siores, E.; Thundat, T. Exclusive self-aligned β-phase PVDF films with abnormal piezoelectric coefficient prepared via phase inversion. Chem. Commun. 2015, 51, 8257–8260.
DOI Google Scholar
[28]

Martins, P.; Lopes, A. C.; Lanceros-Mendez, S. Electroactive phases of poly(vinylidene fluoride): Determination, processing and applications. Prog. Polym. Sci. 2014, 39, 683–706.
DOI Google Scholar
[29]

Shao, H.; Wang, H. X.; Cao, Y. Y.; Ding, X.; Bai, R. X.; Chang, H. B.; Fang, J.; Jin, X.; Wang, W. Y.; Lin, T. Single-layer piezoelectric nanofiber membrane with substantially enhanced noise-to-electricity conversion from endogenous triboelectricity. Nano Energy 2021, 89, 106427.
DOI Google Scholar
[30]

Haghdoost, F.; Razbin, M.; Bahrami, H.; Barzin, J.; Ghaee, A. Modeling and optimization of the core–shell nanofibrous composite mat as a scaffold via hybrid models. J. Ind. Text 2022, 52, 15280837221112406.
DOI Google Scholar
[31]

Kara, F.; Karabatak, M.; Ayyıldız, M.; Nas, E. Effect of machinability, microstructure and hardness of deep cryogenic treatment in hard turning of AISI D2 steel with ceramic cutting. J. Mater. Res. Technol. 2020, 9, 969–983.
DOI Google Scholar
[32]
Davim, J. P. Statistical and Computational Techniques in Manufacturing; Springer: Berlin, Heidelberg, 2012.
DOI
[33]
Majumdar, A. Soft Computing in Textile Engineering; Elsevier: Amsterdam, 2010.
DOI
[34]

Xie, L. P.; Zhang, Z. L.; Wu, Q. S.; Gao, Z. X.; Mi, G. T.; Wang, R. Q.; Sun, H. B.; Zhao, Y.; Du, Y. N. Intelligent wearable devices based on nanomaterials and nanostructures for healthcare. Nanoscale 2023, 15, 405–433.
DOI Google Scholar
[35]

Wu, X. S.; Wang, S. C.; Huang, W.; Dong, Y.; Wang, Z. R.; Huang, W. G. Wearable in-sensor reservoir computing using optoelectronic polymers with through-space charge-transport characteristics for multi-task learning. Nat. Commun. 2023, 14, 468.
DOI Google Scholar
[36]

Cao, Z. L.; Sun, B.; Zhou, G. D.; Mao, S. S.; Zhu, S. H.; Zhang, J.; Ke, C.; Zhao, Y.; Shao, J. Y. Memristor-based neural networks: A bridge from device to artificial intelligence. Nanoscale Horiz. 2023, 8, 716–745.
DOI Google Scholar
[37]

Abiodun, O. I.; Jantan, A.; Omolara, A. E.; Dada, K. V.; Mohamed, N. A.; Arshad, H. State-of-the-art in artificial neural network applications: A survey. Heliyon 2018, 4, e00938.
DOI Google Scholar
[38]

Beasley, D.; Bull, D. R.; Martin, R. R. An overview of genetic algorithms: Part 1, fundamentals. Univ. Comput. 1993, 15, 58–69.
Google Scholar
[39]

Beasley, D.; Bull, D. R.; Martin, R. R. An overview of genetic algorithms: Part 2, research topics. Univ. Comput. 1993, 15, 170–181.
Google Scholar
[40]
Mirjalili, S.; Dong, J. S. Multi-Objective Optimization Using Artificial Intelligence Techniques; Springer: Cham, 2020.
DOI
[41]

Manzoni, L.; Mariot, L.; Tuba, E. Balanced crossover operators in Genetic Algorithms. Swarm Evol. Comput. 2020, 54, 100646.
DOI Google Scholar
[42]

Hameed, W. M. The role of crossover on optimization of a function problem using genetic algorithms. Int. J. Comput. Sci. Mob. Comput. 2016, 5, 425–429.
Google Scholar
[43]

Garson, G. D. Interpreting neural-network connection weights. AI Expert 1991, 6, 46–51.
Google Scholar
[44]

Goh, A. T. C. Seismic liquefaction potential assessed by neural networks. J. Geotech. Eng. 1994, 120, 1467–1480.
DOI Google Scholar
[45]

Lang, C. H.; Fang, J.; Shao, H.; Ding, X.; Lin, T. High-sensitivity acoustic sensors from nanofibre webs. Nat. Commun. 2016, 7, 11108.
DOI Google Scholar
[46]

Mohammadi, A.; Barikani, M.; Barmar, M. Synthesis and investigation of thermal and mechanical properties of in situ prepared biocompatible Fe3O4/polyurethane elastomer nanocomposites. Polym. Bull. 2015, 72, 219–234.
DOI Google Scholar
[47]

Adeli, B.; Gharehaghaji, A. A.; Jeddi, A. A. A. A feasibility study on production and optimization of PVDF/PU polyblend nanofiber layers using expert design analysis. Iran. Polym. J. 2021, 30, 535–545.
DOI Google Scholar
[48]

Kaur, G.; Meena, J. S.; Jassal, M.; Agrawal, A. K. Synergistic effect of polyurethane in polyurethane-poly (vinylidene fluoride) nanofiber-based stretchable piezoelectric nanogenerators (S-PENGs). ACS Appl. Polym. Mater. 2022, 4, 4751–4764.
DOI Google Scholar
[49]

Li, Y.; Xu, M. H.; Xia, Y. S.; Wu, J. M.; Sun, X. K.; Wang, S.; Hu, G. H.; Xiong, C. X. Multilayer assembly of electrospun/electrosprayed PVDF-based nanofibers and beads with enhanced piezoelectricity and high sensitivity. Chem. Eng. J. 2020, 388, 124205.
DOI Google Scholar
File
6613_ESM.pdf (2.4 MB)
Publication history
Copyright
Acknowledgements

Publication history

Received: 24 November 2023
Revised: 06 March 2024
Accepted: 08 March 2024
Published: 20 April 2024

Copyright

© Tsinghua University Press 2024

Acknowledgements

Acknowledgements

This work was supported by Amirkabir University of Technology and the Terasaki Institute for Biomedical Innovation. The mechanical analysis, manufacturing, and healing kinetic study were supported by the U.S. DOE, Office of Science, Basic Energy Sciences, Materials Sciences and Engineering Division. We extend our deepest gratitude to Dr. Jamal Bahari for his expert guidance and significant contributions throughout the research process. We would also like to thank Milad Razbin for useful discussions in shaping this work.

Return