EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Genetic Algorithm-Optimized CNN-BiLSTM Framework for Predicting the Remaining Useful Life of IGBT Modules

Yukai Hao, Jiao Wu, Zhiheng Zhang, Yuanhao Wang, Tao Wang, Yujie Liang iD

Sensors · 21.03.2026 · 26 (6) · 1964

DOI: 10.3390/s26061964 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.03.2026. Verfasst von Yukai Hao und 5 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Xidian University, Xi'an 710126, China. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 26 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the aging and failure issues that arise during the long-term operation of insulated gate bipolar transistors (IGBTs), this paper proposes a method for predicting their remaining useful life (RUL). The proposed method utilizes a genetic algorithm to optimize a hybrid model that combines a convolutional neural network (CNN) with a bidirectional long short-term memory (BiLSTM) network. First, based on the failure mechanism of IGBTs, various commonly used RUL prediction methods are analyzed and compared. Considering that CNNs are particularly effective at extracting spatial features, while LSTMs excel at capturing long-term dependencies in time-series data, a hybrid CNN-BiLSTM model is developed for RUL prediction, with hyperparameters, including the initial learning rate, optimized using a genetic algorithm. Experimental results demonstrate that the proposed CNN-BiLSTM model achieves superior performance across all metrics compared with benchmark algorithms, and the genetic algorithm significantly accelerates the parameter optimization process and enhances the overall training efficiency.

Schlagwörter

Stichwörter der Autor:innen

IGBTconvolutional neural networkgenetic algorithmlong short-term memory networkremaining useful life

Autor:innen und Institutionen

  • School of Computer Science and Technology, Xidian University, Xi'an 710126, China.
  • Aeronautics Computing Technology Research Institute, Aviation Industry Corporation of China, Ltd., Xi'an 710068, China.
  • Guangzhou Institute of Technology, Xidian University, Guangzhou 510555, China.

ORCID-Profile: Yujie Liang

Zitieren

APA

Hao, Y., Wu, J., Zhang, Z., Wang, Y., Wang, T., & Liang, Y. (2026). Genetic Algorithm-Optimized CNN-BiLSTM Framework for Predicting the Remaining Useful Life of IGBT Modules. Sensors, 26(6), 1964. https://doi.org/10.3390/s26061964

Vancouver

Hao Y, Wu J, Zhang Z, Wang Y, Wang T, Liang Y. Genetic Algorithm-Optimized CNN-BiLSTM Framework for Predicting the Remaining Useful Life of IGBT Modules. Sensors. 2026;26(6):1964. doi:10.3390/s26061964

BibTeX
@article{Hao2026,
  author = {Hao, Yukai and Wu, Jiao and Zhang, Zhiheng and Wang, Yuanhao and Wang, Tao and Liang, Yujie},
  title = {Genetic Algorithm-Optimized CNN-BiLSTM Framework for Predicting the Remaining Useful Life of IGBT Modules},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {6},
  pages = {1964},
  doi = {10.3390/s26061964}
}
Kostenlos starten →