EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

TWIN-ADAPT: Continuous Learning for Digital Twin-Enabled Online Anomaly Classification in IoT-Driven Smart Labs

Ragini Gupta, Beitong Tian, Yaohui Wang, Klara Nahrstedt

Future Internet · 04.07.2024 · 16 (7) · 239

DOI: 10.3390/fi16070239 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Future Internet, online erschienen am 04.07.2024. Verfasst von Ragini Gupta und 3 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In the rapidly evolving landscape of scientific semiconductor laboratories (commonly known as, cleanrooms), integrated with Internet of Things (IoT) technology and Cyber-Physical Systems (CPSs), several factors including operational changes, sensor aging, software updates and the introduction of new processes or equipment can lead to dynamic and non-stationary data distributions in evolving data streams. This phenomenon, known as concept drift, poses a substantial challenge for traditional data-driven digital twin static machine learning (ML) models for anomaly detection and classification. Subsequently, the drift in normal and anomalous data distributions over time causes the model performance to decay, resulting in high false alarm rates and missed anomalies. To address this issue, we present TWIN-ADAPT, a continuous learning model within a digital twin framework designed to dynamically update and optimize its anomaly classification algorithm in response to changing data conditions. This model is evaluated against state-of-the-art concept drift adaptation models and tested under simulated drift scenarios using diverse noise distributions to mimic real-world distribution shift in anomalies. TWIN-ADAPT is applied to three critical CPS datasets of Smart Manufacturing Labs (also known as “Cleanrooms”): Fumehood, Lithography Unit and Vacuum Pump. The evaluation results demonstrate that TWIN-ADAPT’s continual learning model for optimized and adaptive anomaly classification achieves a high accuracy and F1 score of 96.97% and 0.97, respectively, on the Fumehood CPS dataset, showing an average performance improvement of 0.57% over the offline model. For the Lithography and Vacuum Pump datasets, TWIN-ADAPT achieves an average accuracy of 69.26% and 71.92%, respectively, with performance improvements of 75.60% and 10.42% over the offline model. These significant improvements highlight the efficacy of TWIN-ADAPT’s adaptive capabilities. Additionally, TWIN-ADAPT shows a very competitive performance when compared with other benchmark drift adaptation algorithms. This performance demonstrates TWIN-ADAPT’s robustness across different modalities and datasets, confirming its suitability for any IoT-driven CPS framework managing diverse data distributions in real time streams. Its adaptability and effectiveness make it a versatile tool for dynamic industrial settings.

Förderung

  • National Science Foundation

Zitieren

APA

Gupta, R., Tian, B., Wang, Y., & Nahrstedt, K. (2024). TWIN-ADAPT: Continuous Learning for Digital Twin-Enabled Online Anomaly Classification in IoT-Driven Smart Labs. Future Internet, 16(7), 239. https://doi.org/10.3390/fi16070239

Vancouver

Gupta R, Tian B, Wang Y, Nahrstedt K. TWIN-ADAPT: Continuous Learning for Digital Twin-Enabled Online Anomaly Classification in IoT-Driven Smart Labs. Future Internet. 2024;16(7):239. doi:10.3390/fi16070239

BibTeX
@article{Gupta2024,
  author = {Gupta, Ragini and Tian, Beitong and Wang, Yaohui and Nahrstedt, Klara},
  title = {TWIN-ADAPT: Continuous Learning for Digital Twin-Enabled Online Anomaly Classification in IoT-Driven Smart Labs},
  journal = {Future Internet},
  year = {2024},
  volume = {16},
  number = {7},
  pages = {239},
  doi = {10.3390/fi16070239}
}
Kostenlos starten →