Scholarlink

<p>The use of environmentally friendly, renewable sources in the energy sector plays a crucial role and greatly contributes to sustainable, advanced technological solutions that meet diverse energy needs. Recent developments with green energy harvesting modules like Eco-Piezoelectric Energy Harvesters (E-PEHs) integrated with piezoelectric materials made from various bio-wastes are emerging in recent times, as evident from the literature. Traditional modules struggle with inconsistent energy output and low efficiency, and the absence of integrated energy storage systems hinders the reliability under different environmental conditions are major gaps of research in the current stage. To address this, the research focuses on effectively harnessing ambient energy sources like mechanical vibrations from wind turbine using bio-piezoelectric materials and integrating these systems with effective energy storage solutions, which features an intelligent power management unit that optimizes both energy harvesting and storage process by utilizing novel machine learning controller of Residual Self-Attention Long Short-Term Memory with Transfer Learning Network (ReSALeT-Net), which is optimized with hybrid algorithm of Dynamic Step Opposition-Based Learning Superb Fairy-Wren Optimization Algorithm (DSOBL-SFO) that ensures continuous and efficient energy supply. Using comprehensive simulations and experimental testing, the performance of the system is validated and compared with piezoelectric materials in recent literature. With a cut-in speed of wind 2&#xa0;m/s, the proposed harvester produces a peak power output of about 0.55&#xa0;mW/cm<sup>3</sup>, exceeding power outputs reported in recent research, and this module is designed to support a wide range of real-world applications, including Internet of Things devices, remote sensors, and wearable electronics. Ultimately, it contributes to reduce the dependence on non-renewable energy sources and supports the development of self-sustaining energy systems for modern applications.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Bio-piezoelectric energy harvesting with integrated storage and deep learning-based optimization for sustainable energy systems

  • 期刊论文

  • 发表日期：

    2026年5月20日

查看全文
  • M. Mary Linda

摘要

The use of environmentally friendly, renewable sources in the energy sector plays a crucial role and greatly contributes to sustainable, advanced technological solutions that meet diverse energy needs. Recent developments with green energy harvesting modules like Eco-Piezoelectric Energy Harvesters (E-PEHs) integrated with piezoelectric materials made from various bio-wastes are emerging in recent times, as evident from the literature. Traditional modules struggle with inconsistent energy output and low efficiency, and the absence of integrated energy storage systems hinders the reliability under different environmental conditions are major gaps of research in the current stage. To address this, the research focuses on effectively harnessing ambient energy sources like mechanical vibrations from wind turbine using bio-piezoelectric materials and integrating these systems with effective energy storage solutions, which features an intelligent power management unit that optimizes both energy harvesting and storage process by utilizing novel machine learning controller of Residual Self-Attention Long Short-Term Memory with Transfer Learning Network (ReSALeT-Net), which is optimized with hybrid algorithm of Dynamic Step Opposition-Based Learning Superb Fairy-Wren Optimization Algorithm (DSOBL-SFO) that ensures continuous and efficient energy supply. Using comprehensive simulations and experimental testing, the performance of the system is validated and compared with piezoelectric materials in recent literature. With a cut-in speed of wind 2 m/s, the proposed harvester produces a peak power output of about 0.55 mW/cm3, exceeding power outputs reported in recent research, and this module is designed to support a wide range of real-world applications, including Internet of Things devices, remote sensors, and wearable electronics. Ultimately, it contributes to reduce the dependence on non-renewable energy sources and supports the development of self-sustaining energy systems for modern applications.