数据驱动的离子盐差发电结构生成系统及性能优化方法
By using a data-driven approach, the ion salinity gradient power generation structure is optimized using migration graph convolutional neural networks and generative adversarial networks, solving the problem of structural optimization difficulties in existing technologies and achieving efficient performance optimization and cost savings.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- XI AN JIAOTONG UNIV
- Filing Date
- 2023-10-31
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies lack effective systems and methods for optimizing ion salt gradient power generation structures, resulting in heavy experimental and simulation burdens and making it difficult to find materials and structures with optimized performance.
A data-driven approach is adopted, utilizing the transfer graph convolutional neural network TL-GCNN and the generative adversarial network GAN to generate new structures and predict performance by learning data from the ion salinity gradient power generation system, thereby reducing the burden of experiments and simulations and optimizing the ion salinity gradient power generation system.
Generating ion salt gradient power generation structures using a data-driven approach saves on the cost and time of experiments and simulations, improves system efficiency, and has significant social and economic benefits.
Smart Images
Figure CN117612640B_ABST