IPM Motor Torque Control Using Neural-Network MTPA and Flux-Weakening
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Achieving optimal and efficient control of interior permanent magnet (IPM) synchronous machines over their full speed range is challenging due to nonlinear optimization problems, voltage and current constraints, and variations in motor parameters caused by saturation and cross-magnetization effects.
Innovation Solution
A neural network-based method is developed to determine maximum-torque-per-ampere (MTPA), flux-weakening, and maximum-torque-per-volt (MTPV) operating points, using cloud-based training data that accounts for variable motor parameters, allowing for fast and accurate current reference generation for optimal torque control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional nonlinear optimization methods are used for MTPA, flux-weakening, and MTPV control, then control accuracy is improved, but computational complexity and processing time increase significantly
Solution Approach 1:
The patent pre-calculates and stores optimal current references for MTPA, flux-weakening, and MTPV operations in lookup tables before actual motor operation. During runtime, the controller simply queries these pre-computed tables based on operating conditions, avoiding real-time nonlinear optimization calculations while maintaining control accuracy
Solution Approach 2:
The patent creates simplified computational models (lookup tables) that replicate the complex nonlinear optimization results. These tables contain pre-computed optimal current references that copy the essential characteristics of the full optimization solution, enabling fast retrieval without repeated complex calculations
2Adaptability or versatility
If cloud-based neural network training is used to handle variable motor parameters, then adaptability to parameter variations is improved, but system complexity and data processing requirements increase
Solution Approach 1:
The system performs self-characterization by automatically collecting motor parameter data during manufacturing testing and using this data to train cloud-based neural networks. The trained models then adapt to specific motor instances without requiring manual parameter input or complex system configuration, enabling the controller to handle parameter variations autonomously
Solution Approach 2:
The patent uses neural networks to learn and adapt to changes in motor parameters (such as resistance, inductance, and flux linkage) caused by saturation and cross-magnetization effects. The cloud-based training process adjusts network parameters based on measured motor characteristics, enabling the system to compensate for parameter variations without increasing operational complexity
Data Source
AI summary
A method for determining MTPA, flux-weakening, and MTPV operating points over the full speed range of an IPM motor for the most efficient torque control of the motor using a neural network is provided. The neural network is trained using a cloud-based neural network training algorithm. A special technique is developed to generate neural network training data, that is particularly suitable and favorable, to develop a high-performance neural network-based IPM torque control system, and the impact of variable motor parameters is embedded into the neural network system development and training. The provided method can achieve a fast and accurate current reference generation with a simple neural network structure, for optimal torque control of an IPM motor. The method can handle the MTPA, MTPV, and flux-weakening operation considering physical motor constraints.