open access publication

Article, 2024

A Self-Commissioning Edge Computing Method for Data-Driven Anomaly Detection in Power Electronic Systems

IEEE Transactions on Industrial Electronics, ISSN 1557-9948, 0278-0046, Volume 71, 10, Pages 13319-13330, 10.1109/tie.2023.3347839

Contributors

Gmez, Pere Izquierdo (Corresponding author) [1] Gajardo, Miguel E Lopez 0000-0002-5485-3506 [1] Mijatovic, Nenad 0000-0002-9803-7973 [1] Dragicevic, Tomislav 0000-0003-4755-2024 [1]

Affiliations

  1. [1] Technical University of Denmark
    2. [NORA names: DTU Technical University of Denmark; University; Denmark; Europe, EU; Nordic; OECD]

Abstract

Ensuring the reliability of power electronic converters is a matter of great importance, and data-driven condition monitoring techniques are cementing themselves as an important tool for this purpose. However, translating methods that work well in controlled lab environments to field applications presents significant challenges, notably because of the limited diversity and accuracy of the lab training data. By enabling the use of field data, online machine learning can be a powerful tool to overcome this problem, but it introduces additional challenges in ensuring the stability and predictability of the training processes. This work presents an edge computing method that mitigates these shortcomings with minimal additional memory usage, by employing an autonomous algorithm that prioritizes the storage of training samples with larger prediction errors. The method is demonstrated on the use case of a self-commissioning condition monitoring system, in the form of a thermal anomaly detection scheme for a variable frequency motor drive, where the algorithm self-learned to distinguish normal and anomalous operation with minimal prior knowledge. The obtained results, based on experimental data, show a significant improvement in prediction accuracy and training speed, when compared with equivalent models trained online without the proposed data selection process.

Keywords

accuracy, algorithm, anomalous operations, anomaly detection, anomaly detection scheme, applications, autonomous algorithm, computational methods, condition monitoring system, condition monitoring techniques, converter, data, data selection process, data-driven, data-driven anomaly detection, detection, detection scheme, diversity, driving, electronic converters, electronic systems, equivalent model, error, experimental data, field, field application, field data, improvement, knowledge, lab, learning, machine learning, memory, memory usage, method, minimal prior knowledge, model, monitoring system, monitoring techniques, motor drive, online machine learning, operation, power, power electronic converters, power electronic systems, prediction, prediction accuracy, prediction error, prior knowledge, problem, process, reliability, reliability of power electronic converters, results, samples, scheme, selection process, self-commissioning, self-learning, speed, stability, storage, system, technique, training, training data, training process, training samples, training speed, usage, variable frequency motor drives

Funders

  • Agencia Nacional de Investigación y Desarrollo

Data Provider: Digital Science

LINKS
-

Matching Records in NORA

SUBJECTS
+

METRICS
+