Artificial Neural Network and Data Dimensionality Reduction Based on Machine Learning Methods for PMSM Model Order Reduction

Maria Raluca Raia,Claudia Martis,Mircea Ruba,Raul Octavian Nemes

doi:10.1109/access.2021.3095668

Maria Raluca Raia, Claudia Martis + Show 2 more

Open Access

https://doi.org/10.1109/access.2021.3095668

Copy DOI

Journal: IEEE Access	Publication Date: Jan 1, 2021
Citations: 16	License type: CC BY 4.0

Affiliation: Technical University of Cluj-Napoca

Abstract

The present paper targets a solution for permanent motor synchronous machine (PMSM) model order reduction (MOR) using artificial neural networks and machine learning techniques for data dimensionality reduction. The neural networks are trained using data obtained from a series of electromagnetic Finite Element Analysis (FEA), conducted in conditions imposed by the data dimensionality reduction method. The workflow proposed to build the PMSM MOR, starts with data generation, goes further to its post-processing, and finishes with the model training and experimental validation. In the study, data dimensionality reduction procedure (adaptive data generation) is performed to increase the computational efficiency, also maintaining the model accuracy. Different data reduction approaches are compared from the computational cost’s point of view and their ease of use. The obtained results are compared to those obtained from FEA seeking the best solution for building the dynamic model. The resulting ROM is included in a real-time control prototyping platform to characterize machine’s performances. The model accuracy and its usability are proved in a comparative analysis with simulated versus experimental measurements.

Highlights

I N the automotive domain, the permanent magnet synchronous motor (PMSM) is preferred for both auxiliary and traction applications due to its well-known performances such as high power density and increased efficiency
The reduced order model (ROM) is built using the data obtained from electromagnetic simulations, where only the relationship between the input and the output is taken into account and included in the dynamic model, usually in the form of multi-dimensional lookup tables (LUTs)
This paper presented a PMSM modelling approach characterised by combining artificial neural networks and machine learning techniques for data dimensionality reduction

Summary

INTRODUCTION

I N the automotive domain, the permanent magnet synchronous motor (PMSM) is preferred for both auxiliary and traction applications due to its well-known performances such as high power density and increased efficiency. In [3] and [4], torque estimation methods and machine control techniques based on neural network are detailed, reaching highly accurate results To reduce both computational and neural network training times, the data dimension used to train the network is minimized by applying machine learning dimensionality reduction techniques. Different methods for data reduction based on machine learning allow obtaining quickly high-accuracy models Such an example is presented in [5], where a comparison of various data sampling and their effect on the accuracy of an ANN for torque estimation is discussed. The novelty of this study rises from involving data dimensionality reduction methods coming from the machine learning domain in the process of surrogate modelling The reason behind this approach is that the PMSM’s reduced order models developed using neuronal networks trained with reduced data sets are capable to reach high-accuracy results. The quadrature model currents (d- and q- axis) are ranged from -200 [A] to 200 [A], with a step of 20 [A], while the rotor position is varied from 0 to 60 mechanical degrees

MACHINE MODELING

MODEL IMPLEMENTATION

LEVENBERG-MARQUARDT BACKPROPAGATION ALGORITHM

EXPERIMENTAL VALIDATION

Findings

CONCLUSION