Optimizing wind energy harvesting performance remains a significant challenge.Machine learning(ML)offers a promising approach for addressing this challenge.This study proposes an ML-based approach using the radial bas...Optimizing wind energy harvesting performance remains a significant challenge.Machine learning(ML)offers a promising approach for addressing this challenge.This study proposes an ML-based approach using the radial basis function neural network(RBFNN)and differential evolution(DE)to predict and optimize the structural parameters(the diameter of the spherical bluff body D,the total spring stiffness k,and the length of the piezoelectric cantilever beam L)of the wind energy harvester(WEH).The RBFNN model is trained with theoretical data and validated with wind tunnel experimental results,achieving the coefficient-of-determination scores R2of 97.8%and 90.3%for predicting the average output power Pavgand aero-electro-mechanical efficiencyηaem,respectively.The DE algorithm is used to identify the optimal parameter combinations for wind speeds U ranging from 2.5 m/s to 6.5 m/s.The maximum Pavgis achieved when D=57.5 mm,k=28.8 N/m,L=112.1 mm,and U=4.6 m/s,while the maximumηaemis achieved when D=52.7 mm,k=29.2 N/m,L=89.2 mm,and U=4.7 m/s.Compared with that of the non-optimized structure,the WEH performance is improved by 28.6%in P_(avg)and 19.1%inη_(aem).展开更多
A new piezoelectric energy harvester is proposed which employs the coupling effect between a piezoelectric beam and an elastic-supported sphere to capture wind energy from multiple directions.As wind flows across the ...A new piezoelectric energy harvester is proposed which employs the coupling effect between a piezoelectric beam and an elastic-supported sphere to capture wind energy from multiple directions.As wind flows across the sphere,it induces vortical vibrations that transfer to the piezoelectric beam,converting wind energy into electricity.A nonlinear coupled dynamic theoretical model based on the Euler-Lagrange equation is developed to study the interactions between the sphere and beam vibrations.The vortex-induced force acting on the sphere is determined,and the dynamic model of the coupled system is validated through experiments.The results show that in order to reach convergence,at least four modes are required in the Galerkin discretization.Moreover,the output performance of the energy harvester strongly depends on the frequency ratio between the sphere and the piezoelectric beam.We find that at a frequency ratio of approximately 1.34,the harvester achieves a maximum average power of 190μW at a wind speed of 3.90 m/s,with the lock-in region between 2.63 and 5.30 m/s.Subsequently,the impact of wind flow direction on the electrical performance of the energy harvester is investigated in a wind tunnel,by adjusting the angle between the harvester and incoming flows ranging from 0°to 360°.The findings indicate that the harvester maintains strong and consistent performance across variable wind flow directions and speeds.Particularly within the lock-in region,the output voltage fluctuations are below 5.5%,showcasing the robustness of the design.This result points to the potential utility of this novel harvester in complex environments.Our study also provides a theoretical basis for the development of small-scale offshore wind energy harvesting technologies.展开更多
基金Project supported by the National Key R&D Program of China(No.2021YFF0501001)the National Natural Science Foundation of China(Nos.52308315,51922046,and 52192661)+3 种基金the Research Funds of Huazhong University of Science and Technology(No.2023JCYJ014)the China Postdoctoral Science Foundation(No.2023M731206)the Research Funds of China Railway Siyuan Survey and Design Group Co.Ltd.(Nos.KY2023014S,KY2023126S,2021K085,2020K006,and 2020K172)the Autonomous Innovation Fund of Hubei Province of China(No.5003242027)。
文摘Optimizing wind energy harvesting performance remains a significant challenge.Machine learning(ML)offers a promising approach for addressing this challenge.This study proposes an ML-based approach using the radial basis function neural network(RBFNN)and differential evolution(DE)to predict and optimize the structural parameters(the diameter of the spherical bluff body D,the total spring stiffness k,and the length of the piezoelectric cantilever beam L)of the wind energy harvester(WEH).The RBFNN model is trained with theoretical data and validated with wind tunnel experimental results,achieving the coefficient-of-determination scores R2of 97.8%and 90.3%for predicting the average output power Pavgand aero-electro-mechanical efficiencyηaem,respectively.The DE algorithm is used to identify the optimal parameter combinations for wind speeds U ranging from 2.5 m/s to 6.5 m/s.The maximum Pavgis achieved when D=57.5 mm,k=28.8 N/m,L=112.1 mm,and U=4.6 m/s,while the maximumηaemis achieved when D=52.7 mm,k=29.2 N/m,L=89.2 mm,and U=4.7 m/s.Compared with that of the non-optimized structure,the WEH performance is improved by 28.6%in P_(avg)and 19.1%inη_(aem).
基金supported by the National Key R&D Program of China(No.2021YFF0501001)the National Natural Science Foundation of China(Nos.52308315,51922046,and 52192661)+4 种基金the Research Funds of Huazhong University of Science and Technology(No.2023JCYJ014)the China Postdoctoral Science Foundation(No.2023M731206)the Research Funds of China Railway Siyuan Survey and Design Group Co.,Ltd.(Nos.KY2023014S,KY2023126S,2021K085,2020K006,and 2020K172)the Research Fund of China Construction Science and Industry(No.CSCEC-PT-004-2022-KT-3.3)the Autonomous Innovation Fund of Hubei Province(No.5003242027),China.
文摘A new piezoelectric energy harvester is proposed which employs the coupling effect between a piezoelectric beam and an elastic-supported sphere to capture wind energy from multiple directions.As wind flows across the sphere,it induces vortical vibrations that transfer to the piezoelectric beam,converting wind energy into electricity.A nonlinear coupled dynamic theoretical model based on the Euler-Lagrange equation is developed to study the interactions between the sphere and beam vibrations.The vortex-induced force acting on the sphere is determined,and the dynamic model of the coupled system is validated through experiments.The results show that in order to reach convergence,at least four modes are required in the Galerkin discretization.Moreover,the output performance of the energy harvester strongly depends on the frequency ratio between the sphere and the piezoelectric beam.We find that at a frequency ratio of approximately 1.34,the harvester achieves a maximum average power of 190μW at a wind speed of 3.90 m/s,with the lock-in region between 2.63 and 5.30 m/s.Subsequently,the impact of wind flow direction on the electrical performance of the energy harvester is investigated in a wind tunnel,by adjusting the angle between the harvester and incoming flows ranging from 0°to 360°.The findings indicate that the harvester maintains strong and consistent performance across variable wind flow directions and speeds.Particularly within the lock-in region,the output voltage fluctuations are below 5.5%,showcasing the robustness of the design.This result points to the potential utility of this novel harvester in complex environments.Our study also provides a theoretical basis for the development of small-scale offshore wind energy harvesting technologies.
