EUVIMEDEUVIMED entdecken
Crossref

A Hierarchical Localization and Dual-Stream Heterogeneous Learning Framework for Sensor Fault Diagnosis in BESSs

Qiangsheng Chen, Guogang Zhang, Chuanqi Lin, Yongkang Zhang, Hengyu Li

IEEE Sensors Journal · 2026-11 · 26 (21) · 33239-33248

DOI: 10.1109/jsen.2026.3729117 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Sensors Journal, 2026-11. Verfasst von Qiangsheng Chen und 4 weiteren Autor:innen. Die Arbeit nennt 25 Literaturangaben. Gefördert von: National Key Research and Development Program.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large-scale battery energy storage systems (BESSs) employ dense sensor arrays that generate high-dimensional data and exhibit heterogeneous multiscale fault characteristics, creating substantial computational burdens for real-time diagnosis. This article proposes a hierarchical collaborative framework that coordinates fault localization and fine-grained diagnosis through a localization-before-classification strategy. First, the hierarchical fault localization and checking (HFLC) algorithm exploits intersensor spatial correlations to identify suspicious channels and reduce redundant high-dimensional inputs before classification. The localized fault segments are then processed by a dual-stream heterogeneous neural network, in which a continuous wavelet transform–convolutional neural network (CNN) branch characterizes transient time–frequency disturbances, while a discrete wavelet transform (DWT)–bidirectional long short-term memory (LSTM) branch captures slowly evolving trend features. Simulation-based experiments show that the proposed framework achieves 99.52% classification accuracy across seven operating states with attention-based fusion and maintains stable performance at a signal-to-noise ratio (SNR) of 40 dB. HFLC retains approximately 97% localization accuracy when 21 of 52 adjacent sensors are simultaneously faulty. At a scale of 832 sensor channels, the framework reduces peak memory usage and processing time by approximately 88% and 93%, respectively, compared with a conventional end-to-end CNN, demonstrating a favorable balance between diagnostic accuracy and computational efficiency.

Förderung

  • National Key Research and Development Program

Zitieren

APA

Chen, Q., Zhang, G., Lin, C., Zhang, Y., & Li, H. (2026). A Hierarchical Localization and Dual-Stream Heterogeneous Learning Framework for Sensor Fault Diagnosis in BESSs. IEEE Sensors Journal, 26(21), 33239-33248. https://doi.org/10.1109/jsen.2026.3729117

Vancouver

Chen Q, Zhang G, Lin C, Zhang Y, Li H. A Hierarchical Localization and Dual-Stream Heterogeneous Learning Framework for Sensor Fault Diagnosis in BESSs. IEEE Sensors Journal. 2026;26(21):33239-33248. doi:10.1109/jsen.2026.3729117

BibTeX
@article{Chen2026,
  author = {Chen, Qiangsheng and Zhang, Guogang and Lin, Chuanqi and Zhang, Yongkang and Li, Hengyu},
  title = {A Hierarchical Localization and Dual-Stream Heterogeneous Learning Framework for Sensor Fault Diagnosis in BESSs},
  journal = {IEEE Sensors Journal},
  year = {2026},
  volume = {26},
  number = {21},
  pages = {33239--33248},
  doi = {10.1109/jsen.2026.3729117}
}
Kostenlos starten →