一种水电工程岩质边坡推荐坡比的确定方法及系统
By combining the rock fracture angle theory with machine learning, and utilizing standardized parameter reduction and multi-condition verification, the problems of insufficient parameter dimensions in traditional methods and lack of constraints in machine learning are solved, thus achieving accuracy and safety in rock slope design. This method is applicable to the excavation design of steep and complex geological slopes in hydropower projects.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- POWERCHINA ZHONGNAN ENG
- Filing Date
- 2026-05-15
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional methods for determining the slope ratio of rock slopes fail to fully consider multi-dimensional geological and engineering conditions, resulting in large discrepancies between the calculated results and the actual situation. Furthermore, existing machine learning methods lack standardized constraints and safety verification, making it difficult to meet the safety requirements of engineering design.
Using the rock mass strength parameters and basic geological parameters after standard reduction as input, and combined with a machine learning model, the initial slope ratio and the predicted slope ratio are weighted and fused to perform limit equilibrium verification under multiple working conditions, ensuring that the safety factor meets the preset threshold, and outputting the recommended slope ratio.
It achieves the interpretability and data accuracy of rock slope design specifications, adapts to the balance between safety and economy under different geological conditions, meets the safety control requirements under complex geology and diverse working conditions, and optimizes the economic efficiency of the project.
Smart Images
Figure CN122197172B_ABST