CNN-LSTM-Based Prognostics of Bidirectional Converters for Electric Vehicles' Machine.

Gabriel Rojas-Dueñas,Jordi-Roger Riba,Manuel Moreno-Eguilaz

doi:10.3390/s21217079

Gabriel Rojas-Dueñas, Jordi-Roger Riba + Show 1 more

Open Access

https://doi.org/10.3390/s21217079

Copy DOI

Abstract

This paper proposes an approach to estimate the state of health of DC-DC converters that feed the electrical system of an electric vehicle. They have an important role in providing a smooth and rectified DC voltage to the electric machine. Thus, it is important to diagnose the actual status and predict the future performance of the converter and specifically of the electrolytic capacitors, in order to avoid malfunctioning and failures, since it is known they have the highest failure rates among power converter components. To this end, accelerated aging tests of the electrolytic capacitors are performed by applying an electrical overstress. The gathered data are used to train a CNN-LSTM model that is capable of predicting the future values of the capacitance and the equivalent series resistance (ESR) of the electrolytic capacitor. This model can be used to estimate the remaining useful life of the device, thus, increasing the reliability of the system and ensuring an adequate operating condition of the electric motor.

Highlights

Electrical machines are being broadly applied in different fields, including electric automobiles, aviation, trains, ships, or industry among others, playing a key role in these applications
This paper proposes an approach to estimate the state of health of DC-DC converters that feed the electrical system of an electric vehicle
The gathered data are used to train a convolutional neural network (CNN)-long short-term memory neural network (LSTM) model that is capable of predicting the future values of the capacitance and the equivalent series resistance (ESR) of the electrolytic capacitor

Summary

Introduction

Electrical machines are being broadly applied in different fields, including electric automobiles, aviation, trains, ships, or industry among others, playing a key role in these applications. Mission-critical power electronics systems, including renewable energy integration, data center power delivery, and motor drives applications, require high reliability and availability of service [1,2] In many of these scenarios, techniques for fault prognosis are commonly employed, that is, methods for actively monitoring the system condition and predicting when failures will occur. It presents how the capacitor parameters are estimated during the degradation process and how these data are used to generate a CNN-LSTM model capable of predicting the future values of the capacitance and the ESR.

Powertrain of an Electric Vehicl Jmghj

Parameter Estimation Based on Nonlinear Least Squares Optimization

Results

Method