Motor Magnetizer Machine Learning Control for Winding Resistance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional magnetization units for motors face challenges in maintaining a high magnetization rate and torque due to increasing winding resistance as the number of magnetized rotors grows, leading to reduced magnetic flux density and motor performance.
Innovation Solution
A machine learning system that includes a state observer, reward calculator, and learning unit to monitor and adjust the magnetization unit's parameters, such as winding temperature and resistance, to optimize the magnetization rate by updating an action value table and determining a voltage command for maintaining a desired magnetic flux density.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a current flows at a constant voltage in the magnetization unit, then the magnetization process is simple, but the winding resistance increases with continuous operation causing reduced magnetization rate
Solution Approach 1:
The patent transitions from a static constant voltage control system to a dynamic control system that continuously monitors winding temperature and resistance, and adjusts the voltage command in real-time to maintain stable magnetization rate despite changing operating conditions
Solution Approach 2:
The patent implements a feedback control mechanism where the state observer monitors winding temperature and resistance, feeds this information back to the learning unit, which then adjusts the voltage command to compensate for resistance changes and maintain consistent magnetization performance
2Productivity
If continuous magnetization of multiple rotors is performed, then productivity increases, but winding temperature rises causing resistance increase and magnetization rate reduction
Solution Approach 1:
The patent uses the state observer to detect winding temperature and resistance changes in advance, allowing the learning unit to proactively adjust the voltage command before significant magnetization rate degradation occurs, thereby maintaining consistent quality during continuous high-volume production
Solution Approach 2:
The patent dynamically changes the voltage command parameter based on detected winding temperature and resistance variations, allowing the system to adapt to thermal effects during continuous operation and maintain stable magnetization rate across multiple rotors
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system stabilizes the magnetization rate and improves motor torque by automatically adjusting parameters in real-time, preventing the reduction in magnetization rate caused by increasing winding resistance.
Implementation Method 1
a magnetizing current is supplied to the magnetizing winding L1. As a result of a back electromotive force generated in the magnetizing winding L1
Implementation Method 2
a capacitor discharge magnetization unit in which a capacitor is charged and energy accumulated in the capacitor is discharged into the magnetizing yoke to generate a strong magnetic field
Implementation Method 3
The circulating current of the flywheel diode prevents heat generation in the winding, and regenerates the back electromotive energy
Data Source
AI summary
A machine learning system according to an embodiment of the present invention includes a state observer for observing the winding temperature, winding resistance, current value, and rotor magnetic flux density of a magnetization unit having a magnetizing yoke and windings; a reward calculator for calculating a reward from the rotor magnetic flux density obtained by the state observer; and a learning unit for updating an action value table based on a magnetization rate calculated from the rotor magnetic flux density and a target magnetic flux density, the winding temperature, and the winding resistance.