Lightweight Adaptive Feature Compression and Dynamic Network Fusion for Rotating Machinery Fault Diagnosis Under Extreme Conditions

Zhang, Kaiyi; Liu, Xuling; Yang, Guohua; Zhai, Kun; An, Gaofei; Zhang, Yusong; Peng, Chaofeng

doi:10.3390/act14090458

Open AccessArticle

Lightweight Adaptive Feature Compression and Dynamic Network Fusion for Rotating Machinery Fault Diagnosis Under Extreme Conditions

by

Kaiyi Zhang

,

Xuling Liu

^*,

Guohua Yang

,

Kun Zhai

,

Gaofei An

,

Yusong Zhang

and

Chaofeng Peng

School of Mechanical and Electronic Engineering, Zhengzhou University of Light Industry, Zhengzhou 450002, China

^*

Author to whom correspondence should be addressed.

Actuators 2025, 14(9), 458; https://doi.org/10.3390/act14090458

Submission received: 30 July 2025 / Revised: 10 September 2025 / Accepted: 12 September 2025 / Published: 19 September 2025

(This article belongs to the Section Actuators for Manufacturing Systems)

Download

Browse Figures

Versions Notes

Abstract

Reliable fault diagnosis of rotating machines under extreme conditions—strong speed, load variation, intense noise, and severe class imbalance—remains a critical industrial challenge. We develop an ultra-light yet robust framework to accurately detect weak bearing, and gear faults when less than 5% labels, 10 dB noise, 100:1 imbalance and plus or minus 20% operating-point drift coexist. Methods: The proposed Adaptive Feature Module–Conditional Dynamic GRU Auto-Encoder (AFM-CDGAE) first compresses 512 d spectra into 32/48 d “feature modules” via K-means while retaining 98.4% fault energy. A workload-adaptive multi-scale convolution with spatial attention and CPU-aware λ-scaling suppresses noise and adapts to edge–device load. A GRU-based auto-encoder, enhanced by self-attention, is trained with balanced-subset sampling and minority-F1-weighted voting to counter extreme imbalance. On Paderborn (5-class) and CWRU (7-class) benchmarks, the 0.87 M-parameter model achieves 99.12% and 98.83% Macro-F1, surpassing five recent baselines by 3.1% under normal and 5.4% under the above extreme conditions, with only 1.5 to 1.8% F1 drop versus 6.7% for baselines. AFM-CDGAE delivers state-of-the-art accuracy, minimal footprint and strong robustness, enabling real-time deployment at the edge.

Keywords: K-means feature module clustering; workload-adaptive multi-scale convolution; self-attention dynamic GRU auto-encoder; extreme class imbalance; rotating machinery fault diagnosis

Share and Cite

MDPI and ACS Style

Zhang, K.; Liu, X.; Yang, G.; Zhai, K.; An, G.; Zhang, Y.; Peng, C. Lightweight Adaptive Feature Compression and Dynamic Network Fusion for Rotating Machinery Fault Diagnosis Under Extreme Conditions. Actuators 2025, 14, 458. https://doi.org/10.3390/act14090458

AMA Style

Zhang K, Liu X, Yang G, Zhai K, An G, Zhang Y, Peng C. Lightweight Adaptive Feature Compression and Dynamic Network Fusion for Rotating Machinery Fault Diagnosis Under Extreme Conditions. Actuators. 2025; 14(9):458. https://doi.org/10.3390/act14090458

Chicago/Turabian Style

Zhang, Kaiyi, Xuling Liu, Guohua Yang, Kun Zhai, Gaofei An, Yusong Zhang, and Chaofeng Peng. 2025. "Lightweight Adaptive Feature Compression and Dynamic Network Fusion for Rotating Machinery Fault Diagnosis Under Extreme Conditions" Actuators 14, no. 9: 458. https://doi.org/10.3390/act14090458

APA Style

Zhang, K., Liu, X., Yang, G., Zhai, K., An, G., Zhang, Y., & Peng, C. (2025). Lightweight Adaptive Feature Compression and Dynamic Network Fusion for Rotating Machinery Fault Diagnosis Under Extreme Conditions. Actuators, 14(9), 458. https://doi.org/10.3390/act14090458

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Lightweight Adaptive Feature Compression and Dynamic Network Fusion for Rotating Machinery Fault Diagnosis Under Extreme Conditions

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI