使用机器学习在LC-LC调无线电力传输系统中没有传感器的情况下预测接收器特性
Minhyuk Kim1, Wend Yam Ella Flore Niada2, Sangwook Park3
1EM Environment R&D Department, Korea Automotive Technology Institute, Cheonan 31214, Republic of Korea.
本研究使用机器学习 (ML) 来预测无线电力传输 (WPT) 系统特性,消除了对发射机接收器通信的需求. ML模型可以准确预测负载和合系数,提高WPT的效率并降低成本.
科学领域:
- 电气工程 电气工程
- 电力电子 电力电子 电力电子
- 机器学习应用 机器学习应用
背景情况:
- 无线电力传输 (WPT) 系统在效率,成本和维护方面面临着挑战.
- 现有的接收器 (Rx) 无传感器WPT同步方法缺乏一致的准确性和可用性.
- 机器学习 (ML) 提供了一种有希望的方法来提高WPT的性能.
研究的目的:
- 用基于机器学习的预测来取代传统的发射器 (Tx) -Rx通信.
- 使用Tx侧参数来预测LC-LC调节的WPT系统中的负载和合系数.
- 通过ML集成来提高WPT系统的效率和准确性.
主要方法:
- 开发了两个ML模型来预测负载和合系数.
- 利用Tx侧的电流和电压特征进行模型训练.
- 使用额外的树回归器来预测WPT系统特征.
主要成果:
- 额外树回归器在预测负载和合系数方面取得了很高的准确性.
- 负载的确定系数为0.967,合的确定系数为0.996.
- 负载时的平均绝对百分比误差低至0.11%,合时为0.017%.
结论:
- 在LC-LC调的WPT系统中,ML有效地取代了Tx-Rx通信.
- 拟议的ML方法显著提高了WPT参数的预测准确性.
- 这种方法为WPT系统优化提供了具有成本效益和效率的解决方案.
更多相关视频
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
15:25Design and Characterization Methodology for Efficient Wide Range Tunable MEMS Filters
Published on: February 4, 2018
相关概念视频
Characteristics of Series Resonant Circuit
Linear Approximation in Frequency Domain
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
The Maximum Power Transfer Theorem
The load connected draws the current, and the circuit delivers the power to the load. The alternating current flowing through the load is determined using the rectangular form of voltages, currents, network impedance, and load impedance. The average power delivered to the load is obtained from the product of the square of current and load resistance.
LC Circuits
Design Example: Underdamped Parallel RLC Circuit
Starting with a fixed...
Mesh Analysis for AC Circuits
The process of harmonizing these impedances begins with a clear understanding of the input and output signals. Once these signals are known, the...
