基于数据分析的水轮机石墨烯陶瓷涂层配方协同优化方法和系统
By using data analysis methods, deep neural networks and convolutional neural networks are used to generate abrasion distribution information, determine the coating adjustment area of the turbine flow components, realize global collaborative optimization of graphene ceramic coating formulation, solve the problem of uneven coating protection, and improve the operating efficiency and resource utilization efficiency of the turbine.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHENGDU ZHAORI ENVIRONMENTAL PROTECTION TECH
- Filing Date
- 2026-04-30
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies make it difficult to accurately determine the target formulation of graphene ceramic coatings suitable for different areas of turbine flow components, resulting in uneven coating protection, waste of material resources, and low maintenance efficiency, which cannot meet the precise and efficient management needs of modern hydropower stations.
By acquiring historical flow field data and images of the turbine's flow components, deep neural networks and convolutional neural networks are used to generate abrasion distribution information, determine the test and other areas to be adjusted in the formulation, perform simulation optimization of the graphene ceramic coating formulation, construct a coating formulation simulation map, and use the coating formulation optimization model to perform global formulation collaborative optimization.
The graphene ceramic coating formula of each region of the turbine flow components was precisely matched, which improved the coating protection performance, reduced material waste, improved maintenance efficiency, and met the high-efficiency management requirements of modern hydropower stations.
Smart Images
Figure CN122157909B_ABST