An Adaptable and Unsupervised TinyML Anomaly Detection System for Extreme Industrial Environments
Sensors · 20.02.2023 · 23 (4) · 2344
DOI: 10.3390/s23042344 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 20.02.2023. Verfasst von Mattia Antonini und 3 weiteren Autor:innen. Beteiligte Einrichtung: Fondazione Bruno Kessler, Via Sommarive 18, 38123 Trento, Italy. Die Arbeit wurde bisher 97-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: “Legge provinciale 6/99 sugli incentivi alle imprese” (L.P. 6/99) della Provincia Autonoma di Trento, European Union Next-GenerationEU.
Abstract (Originalsprache)
Industrial assets often feature multiple sensing devices to keep track of their status by monitoring certain physical parameters. These readings can be analyzed with machine learning (ML) tools to identify potential failures through anomaly detection, allowing operators to take appropriate corrective actions. Typically, these analyses are conducted on servers located in data centers or the cloud. However, this approach increases system complexity and is susceptible to failure in cases where connectivity is unavailable. Furthermore, this communication restriction limits the approach’s applicability in extreme industrial environments where operating conditions affect communication and access to the system. This paper proposes and evaluates an end-to-end adaptable and configurable anomaly detection system that uses the Internet of Things (IoT), edge computing, and Tiny-MLOps methodologies in an extreme industrial environment such as submersible pumps. The system runs on an IoT sensing Kit, based on an ESP32 microcontroller and MicroPython firmware, located near the data source. The processing pipeline on the sensing device collects data, trains an anomaly detection model, and alerts an external gateway in the event of an anomaly. The anomaly detection model uses the isolation forest algorithm, which can be trained on the microcontroller in just 1.2 to 6.4 s and detect an anomaly in less than 16 milliseconds with an ensemble of 50 trees and 80 KB of RAM. Additionally, the system employs blockchain technology to provide a transparent and irrefutable repository of anomalies.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Fondazione Bruno Kessler, Via Sommarive 18, 38123 Trento, Italy.
ORCID-Profile: Mattia Antonini, Miguel Pincheira, Massimo Vecchio, Fabio Antonelli
Förderung
- “Legge provinciale 6/99 sugli incentivi alle imprese” (L.P. 6/99) della Provincia Autonoma di Trento
- European Union Next-GenerationEU
Zitieren
APA
Antonini, M., Pincheira, M., Vecchio, M., & Antonelli, F. (2023). An Adaptable and Unsupervised TinyML Anomaly Detection System for Extreme Industrial Environments. Sensors, 23(4), 2344. https://doi.org/10.3390/s23042344
Vancouver
Antonini M, Pincheira M, Vecchio M, Antonelli F. An Adaptable and Unsupervised TinyML Anomaly Detection System for Extreme Industrial Environments. Sensors. 2023;23(4):2344. doi:10.3390/s23042344
BibTeX
@article{Antonini2023,
author = {Antonini, Mattia and Pincheira, Miguel and Vecchio, Massimo and Antonelli, Fabio},
title = {An Adaptable and Unsupervised TinyML Anomaly Detection System for Extreme Industrial Environments},
journal = {Sensors},
year = {2023},
volume = {23},
number = {4},
pages = {2344},
doi = {10.3390/s23042344}
}
EUVIMED