Azimuth Thruster Distribution Using Neural Networks to Cut Thrust Loss
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Dynamic positioning systems for offshore structures face thrust loss due to water power interference between azimuth thrusters, leading to energy waste and suboptimal power distribution, as existing solutions require prohibited angles that restrict thruster movement and prevent full power minimization.
Innovation Solution
A dynamic positioning and thrust distribution method based on an artificial neural network is implemented, which trains a neural network to optimize thrust coefficients in real-time, allowing for continuous thrust distribution iteration and avoiding prohibited angles, thereby minimizing total thruster power and reducing energy waste.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If a prohibited area is provided for the rotation angle of the front thruster to avoid thrust loss, then thrust loss is prevented, but the thruster cannot penetrate through the prohibited angle during rotation, causing the corner of the thruster to be clamped at the edge of the prohibited angle and preventing optimization of power distribution
Solution Approach 1:
The invention changes the parameter of thrust coefficient from a fixed theoretical value to a dynamic value that varies with the rotation angle of the front thruster. By establishing the relationship between rotation angle and thrust coefficient, and using neural network to fit this relationship, the system dynamically adjusts the thrust coefficient parameter to reflect actual thrust conditions, enabling continuous optimization of power distribution without prohibited angles
Solution Approach 2:
The invention implements a feedback mechanism where the actual thrust produced by the rear thruster (affected by front thruster's rotation angle) is measured and fed back to adjust the thrust coefficient. The neural network continuously learns from the relationship between rotation angles and actual thrust performance, providing real-time feedback to optimize power distribution and eliminate the need for prohibited angle areas
2Loss of energy
If the corner of the front thruster is kept in the prohibited angle area to prevent tail flow from affecting the rear thruster, then thrust loss is avoided, but the total power of the thrusters cannot be minimized, causing energy waste
Solution Approach 1:
The invention transforms the static thrust coefficient into a dynamic parameter that changes with the front thruster's rotation angle. By using neural network to fit the relationship between rotation angle and thrust coefficient, the system can accurately determine the actual thrust at any angle, enabling continuous optimization of power distribution to minimize total power consumption without restricting the thruster to prohibited angle areas
Solution Approach 2:
The invention makes the power distribution system dynamic by continuously adjusting the thrust coefficient based on the real-time rotation angle of the front thruster. This dynamic adjustment allows the system to optimize power distribution at every moment, minimizing total power consumption while avoiding thrust loss, rather than relying on static prohibited angle restrictions
Data Source
AI summary
The invention provides a dynamic positioning and thrust distribution method based on an artificial neural network, is a quadratic programming problem in the optimization problem, and can compute the thrust coefficient of a rear thruster in a constraint condition of a thrust distribution problem by taking into account of the corner of a front thruster and through the artificial neural network. Then the optimization problem enabling the power of the thruster to be minimized is solved according to a sequential quadratic programming algorithm, so that a thrust distribution scheme on the azimuth thrusters is obtained. Meanwhile the invention further provides a dynamic positioning and thrust distribution device based on an artificial neural network. The invention, through the introduction of the concept of thrust coefficients, on the one hand, can accurately quantize thrust loss, and on the other hand can enlarge the feasible area of the rotation angle of the thruster, thereby ensuring that the more optimized and reasonable result can be obtained for the quadratic programming problem, reducing the power of the thruster and saving energy.