Integrated ANN-Based MTPA and LQR-HODO Current Control for IPMSM Drives
In the era of transportation electrification, interior permanent magnet synchronous motors (IPMSMs) are pivotal for high-performance drive systems. However, their inherent nonlinear characteristics, such as magnetic saturation and cross-coupling effects, challenge traditional analytical modeling. This study proposes an integrated control framework utilizing a high-fidelity finite element method (FEM) model to accurately capture intricate electromagnetic phenomena. The proposed architecture features a model-free maximum torque per ampere (MTPA) strategy implemented via artificial neural networks (ANNs) to optimize operational efficiency without prior parameter knowledge. Concurrently, an advanced current controller integrating a linear quadratic regulator (LQR) with a high-order disturbance observer (HODO) is developed to mitigate internal disturbances and parameter variations. Comprehensive evaluations through both simulation and hardware-in-the-loop (HIL) experiments validate the effectiveness of the proposed scheme over a PI current controller. The results demonstrate a significant reduction in steady-state torque ripple by over 70.9%, while accurate MTPA trajectory tracking contributes to a 12% reduction in stator copper losses. Ultimately, the quantitative results confirm that the proposed architecture delivers outstanding parameter robustness, torque quality, and energy efficiency for high-performance IPMSM applications.
Authors
- Van Nam Giap (ORCID: https://orcid.org/0000-0003-0670-874X)
- Phuong Vu (ORCID: https://orcid.org/0000-0003-4404-2504)
- Duc Quang Nguyen
- Doanh Le Dinh
- Phong Bui The (ORCID: https://orcid.org/0009-0006-2734-2643)
Institutions
- Trường Đại học Khoa học và Công nghệ Hà Nội (VN)
- Hanoi University of Science and Technology (VN)
Publication Details
- Journal
- Engineering Research Express
- Published
- 2026-11-20
- DOI
- https://doi.org/10.1088/2631-8695/aec53e
- Primary Topic
- Sensorless Control of Electric Motors
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Trường Đại học Bách Khoa Hà Nội