Optimizing a Digital Twin for Fault Diagnosis in Grid Connected Inverters -- A Bayesian Approach

TL;DR

This paper presents a Bayesian hyperparameter tuning method for digital twins to improve fault diagnosis in grid-connected inverters, enabling high precision detection with limited data and integrating deep learning for enhanced tuning.

Contribution

It introduces an online Bayesian optimization framework for digital twin hyperparameter tuning, improving fault diagnosis accuracy with limited data and incorporating deep learning tools.

Findings

Enhanced fault detection accuracy in grid inverters

Effective digital twin deployment with limited data

Integration of deep learning improves hyperparameter tuning

Abstract

In this paper, a hyperparameter tuning based Bayesian optimization of digital twins is carried out to diagnose various faults in grid connected inverters. As fault detection and diagnosis require very high precision, we channelize our efforts towards an online optimization of the digital twins, which, in turn, allows a flexible implementation with limited amount of data. As a result, the proposed framework not only becomes a practical solution for model versioning and deployment of digital twins design with limited data, but also allows integration of deep learning tools to improve the hyperparameter tuning capabilities. For classification performance assessment, we consider different fault cases in virtual synchronous generator (VSG) controlled grid-forming converters and demonstrate the efficacy of our approach. Our research outcomes reveal the increased accuracy and fidelity levels achieved by our digital twin design, overcoming the shortcomings of traditional hyperparameter tuning methods.