Incorporating a Deep Neural Network into Moving Horizon Estimation for Embedded Thermal Torque Derating of an Electric Machine

2025/04/17 by Winkler, Alexander, Shah, Pranav, Baumgärtner, Katrin +3 · 1 citation
#FOS: Electrical engineering #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2504.12736

Abstract

This study presents a novel state estimation approach integrating Deep Neural Networks (DNNs) into Moving Horizon Estimation (MHE). This is a shift from using traditional physics-based models within MHE towards data-driven techniques. Specifically, a Long Short-Term Memory (LSTM)-based DNN is trained using synthetic data derived from a high-fidelity thermal model of a Permanent Magnet Synchronous Machine (PMSM), applied within a thermal derating torque control strategy for battery electric vehicles. The trained DNN is directly embedded within an MHE formulation, forming a discrete-time nonlinear optimal control problem (OCP) solved via the acados optimization framework. Model-in-the-Loop simulations demonstrate accurate temperature estimation even under noisy sensor conditions and simulated sensor failures. Real-time implementation on embedded hardware confirms practical feasibility, achieving computational performance exceeding real-time requirements threefold. By integrating the learned LSTM-based dynamics directly into MHE, this work achieves state estimation accuracy, robustness, and adaptability while reducing modeling efforts and complexity. Overall, the results highlight the effectiveness of combining model-based and data-driven methods in safety-critical automotive control systems.

Citations

• L4acados: Learning-based models for acados, applied to Gaussian process-based predictive control
• Neural Moving Horizon Estimation: A Systematic Literature Review
• Learning for CasADi: Data-driven Models in Numerical Optimization
• Nonlinear Moving Horizon Estimation and Model Predictive Control for Buildings with Unknown HVAC Dynamics
• Deep Learning based Model Predictive Control for Compression Ignition Engines
• Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions
• HPIPM: a high-performance quadratic programming framework for model predictive control
• acados: a modular open-source framework for fast embedded optimal control
• Long Short-Term Memory
• R.A. Fisher and the making of maximum likelihood 1912-1922
• Gradient-based learning applied to document recognition

Related

• Global Attention-based Encoder-Decoder LSTM Model for Temperature Prediction of Permanent Magnet Synchronous Motors
• Thermal management optimization of Battery Electric Vehicles via hierarchical NMPC with CMO-trained Neural Models
• Scenario-based Thermal Management Parametrization Through Deep Reinforcement Learning
• Parallelizable Complex Neural Dynamics Models for PMSM Temperature Estimation with Hardware Acceleration
• Data-Driven Temperature Modelling of Machine Tools by Neural Networks: A Benchmark