Enhancing Field-Oriented Control of Electric Drives with Tiny Neural Network Optimized for Micro-controllers

2025-02-01

AI Summary

Conventional PI controllers in field-oriented control (FOC) of permanent magnet synchronous motors (PMSMs) struggle with inherent nonlinear dynamics, while state-of-the-art neural controllers are computationally prohibitive for resource-constrained microcontrollers. Method: This paper proposes TinyFC—a highly compact feedforward neural network with only 1,400 parameters—optimized via structural pruning, 8-bit integer quantization, and joint hyperparameter tuning, enabling its first real-time deployment within a closed-loop FOC system on an embedded microcontroller. Contribution/Results: Experimental evaluation demonstrates that TinyFC reduces maximum overshoot by up to 87.5% compared to PI control; the pruned model achieves zero overshoot and significantly improved steady-state accuracy. This work establishes the feasibility and effectiveness of ultra-lightweight neural networks as viable replacements for classical controllers under extreme resource constraints (<2 KB RAM, <16 KB Flash), paving the way for a new paradigm of intelligent, edge-deployable motor control.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Intelligent Robots: Behavior Learning & Control
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

The deployment of neural networks on resource-constrained micro-controllers has gained momentum, driving many advancements in Tiny Neural Networks. This paper introduces a tiny feed-forward neural network, TinyFC, integrated into the Field-Oriented Control (FOC) of Permanent Magnet Synchronous Motors (PMSMs). Proportional-Integral (PI) controllers are widely used in FOC for their simplicity, although their limitations in handling nonlinear dynamics hinder precision. To address this issue, a lightweight 1,400 parameters TinyFC was devised to enhance the FOC performance while fitting into the computational and memory constraints of a micro-controller. Advanced optimization techniques, including pruning, hyperparameter tuning, and quantization to 8-bit integers, were applied to reduce the model's footprint while preserving the network effectiveness. Simulation results show the proposed approach significantly reduced overshoot by up to 87.5%, with the pruned model achieving complete overshoot elimination, highlighting the potential of tiny neural networks in real-time motor control applications.

Problem

• Permanent Magnet Synchronous Motor
• Magnetic Field Control
• Neural Network Control

Innovation

• TinyFC Neural Network
• Parameter Pruning
• Quantization