Hydrofoil Motion Control Using Wave Prediction and AoA Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion control systems for hydrofoil watercrafts are inadequate in providing a smooth ride in environments with irregular and fast-changing waves, as they assume a dominant wave frequency and shape, which is not applicable in scenarios with high variance in wave frequencies and amplitudes.
Innovation Solution
A controller unit that uses a neural network to predict wave acceleration based on the shape of the water surface in front of the hydrofoil, speed, angle of attack, and measured acceleration, determining a target route that minimizes total acceleration while constraining the hydrofoil's position and acceleration magnitude, thereby adjusting the angle of attack to optimize the watercraft's motion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional control systems use reactive measurements and known control procedures, then the system is simple to implement, but the ride comfort and smoothness are insufficient in irregular wave conditions
Solution Approach 1:
The system performs preliminary action by predicting future wave accelerations using a neural network before the watercraft actually encounters them. The neural network processes current water surface shape data to forecast upcoming wave conditions, allowing the control system to prepare appropriate hydrofoil adjustments in advance, thereby reducing the impact of wave-induced accelerations on ride comfort.
Solution Approach 2:
The patent replaces traditional mechanical control approaches with an intelligent system combining neural networks and optimization algorithms. Instead of relying on simple reactive measurements and predefined control procedures, the system uses machine learning to predict wave patterns and employs computational optimization to determine optimal hydrofoil angles, substituting mechanical intuition with adaptive intelligent control.
2Device complexity
If waveform predicting methods assume similar future wave shapes as past waves, then the prediction is simple to calculate, but the applicability is limited to orderly ocean waves with dominant frequencies
Solution Approach 1:
The system applies dynamics by using a neural network that continuously adapts to changing wave conditions rather than assuming static wave patterns. The neural network processes real-time water surface shape data and can adjust its predictions based on the actual state of the waves, allowing it to handle both orderly ocean waves with dominant frequencies and irregular waves with high variance in frequencies and amplitudes.
Solution Approach 2:
The patent implements parameter changes by using a neural network that can detect and respond to changes in wave parameters such as frequency, amplitude, and wave shape. Instead of assuming constant wave characteristics, the system continuously monitors water surface shape and adjusts its predictions based on observed parameter changes, enabling versatility across different sea states.
3Object-affected harmful factors
If the hydrofoil watercraft runs with submerged foils in irregular waves, then the ride smoothness is improved, but the control complexity increases to handle high variance in wave frequencies and amplitudes
Solution Approach 1:
The system introduces an intermediary layer between wave detection and hydrofoil control in the form of a neural network. This intermediary processes the complex relationship between water surface shape and upcoming wave accelerations, translating raw sensor data into predictive information that the optimization algorithm can use to determine appropriate control actions, thereby managing control complexity while maintaining ride smoothness.
Solution Approach 2:
The patent implements feedback by continuously monitoring the water surface shape in front of the hydrofoil and using this information to update neural network predictions and adjust hydrofoil control commands. The system creates a closed-loop control mechanism where past and present wave conditions inform future control actions, enabling the watercraft to adapt to irregular wave conditions while maintaining manageable control complexity.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
A method and a controller unit (110) for controlling motion of a watercraft (120) with a hydrofoil (130) are disclosed. The controller unit (110) obtains (A010) information indicating shape of water surface in front of the hydrofoil (130). The controller unit (110) further predicts (A040) wave acceleration of the watercraft (120) using a neural network. Furthermore, the controller unit (110) determines a target route and corresponding total acceleration of the watercraft (120) under a set of constraints. The total acceleration is minimized when the watercraft (120) travels according to the target route. The set of constraints includes: a first constraint that the hydrofoil (130) stays within an interval relative to the water surface, and a second constraint relating to magnitude of acceleration derived from maximum AoA and the predicted wave acceleration. The controller unit (110) calculates an AoA for the target route. Next, the controller unit (110) sends a signal for adjusting the hydrofoil (130) according to the AoA. A corresponding computer program (403) and a computer program carrier (405) are also disclosed.