EUVIMEDEUVIMED entdecken
Crossref

An Efficient Fault Diagnosis Framework for Rotating Machinery Combining Progressive Knowledge Distillation and FPGA-Based Acceleration

Kehui Zhu, Xinming Li, Zhongheng Liu, Jinrui Zhang, Yanxue Wang

IEEE Transactions on Instrumentation and Measurement · 2026 · 75 · 1-16

DOI: 10.1109/tim.2026.3666004 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Instrumentation and Measurement, 2026. Verfasst von Kehui Zhu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 39 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Youth Beijing Scholars Program, Guangxi Science and Technology Major Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning (DL) has achieved significant progress in industrial equipment fault diagnosis. However, large-scale models are challenging to deploy in industrial settings that require low power consumption and high portability. Moreover, the high latency introduced by model inference reduces the efficiency of real-time fault detection. In this study, we propose a lightweight fault diagnosis network and develop a convolutional neural network (CNN) acceleration for field-programmable gate array (FPGA) deployment. First, a progressive knowledge distillation (KD) strategy is proposed to reduce the discrepancy between the teacher and student networks, thereby enhancing the overall distillation effectiveness. Experimental results demonstrate that the distilled student network, with only 1.32 K parameters, achieves remarkable diagnostic performance and robustness against noise. Second, we designed an FPGA-based CNN accelerator. This design integrates the Winograd algorithm with a systolic array architecture to substantially accelerate convolution operations while reducing resource consumption. Moreover, parallel computation and module reuse are employed to further enhance inference throughput. Experimental results demonstrate that, compared to CPU and GPU implementations, the proposed accelerator achieves speedups of $142.8\times $ and $1.40\times $ , respectively, while reducing power consumption by $14.5\times $ and $30.2\times $ . Compared to state-of-the-art FPGA accelerators, the proposed design provides an approximate 16% improvement in inference speed. The deployed models achieve $F1$ -scores exceeding 98% on two bearing datasets, validating the proposed method’s capability for real-time fault diagnosis in low-power industrial environments.

Förderung

  • National Natural Science Foundation of China
  • Youth Beijing Scholars Program
  • Guangxi Science and Technology Major Project
  • Beijing University of Civil Engineering and Architecture (BUCEA) Doctor Graduate Scientific Research Ability Improvement Project.

Zitieren

APA

Zhu, K., Li, X., Liu, Z., Zhang, J., & Wang, Y. (2026). An Efficient Fault Diagnosis Framework for Rotating Machinery Combining Progressive Knowledge Distillation and FPGA-Based Acceleration. IEEE Transactions on Instrumentation and Measurement, 75, 1-16. https://doi.org/10.1109/tim.2026.3666004

Vancouver

Zhu K, Li X, Liu Z, Zhang J, Wang Y. An Efficient Fault Diagnosis Framework for Rotating Machinery Combining Progressive Knowledge Distillation and FPGA-Based Acceleration. IEEE Transactions on Instrumentation and Measurement. 2026;75:1-16. doi:10.1109/tim.2026.3666004

BibTeX
@article{Zhu2026,
  author = {Zhu, Kehui and Li, Xinming and Liu, Zhongheng and Zhang, Jinrui and Wang, Yanxue},
  title = {An Efficient Fault Diagnosis Framework for Rotating Machinery Combining Progressive Knowledge Distillation and FPGA-Based Acceleration},
  journal = {IEEE Transactions on Instrumentation and Measurement},
  year = {2026},
  volume = {75},
  pages = {1--16},
  doi = {10.1109/tim.2026.3666004}
}
Kostenlos starten →