一种基于CNN洋流预测的长航程AUV节能控制方法、程序、设备及存储介质
By using a CNN-based ocean current prediction method and combining AUV kinematics and dynamics models, a CNN predictor and MPC controller were designed to achieve optimal energy control of AUVs in dynamic ocean current environments. This solves the problem of high energy consumption of long-range AUVs in dynamic ocean currents and improves endurance and environmental adaptability.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HARBIN ENG UNIV
- Filing Date
- 2025-11-17
- Publication Date
- 2026-07-17
AI Technical Summary
Long-range AUVs struggle to achieve optimal global energy control in dynamic ocean current environments. Existing technologies lack an integrated solution that deeply integrates dynamic environmental perception, online energy consumption prediction, and robust tracking control, resulting in high energy consumption and insufficient endurance.
A CNN-based ocean current prediction method is used to construct the kinematics and dynamics model of an AUV. By combining a CNN predictor and an MPC controller, optimal energy control in a dynamic ocean current field is achieved. By optimizing the dynamic desired velocity and heading of the AUV online, an MPC controller that meets the dynamic and boundary constraints is designed to reduce energy consumption.
Significantly reduces energy consumption of AUVs during long-endurance missions, improves endurance, enhances environmental adaptability and robustness, and achieves intelligent control for global energy optimization.
Smart Images
Figure CN121613728B_ABST