An interpretable deep feature aggregation framework for machinery incremental fault diagnosis DOI
Kui Hu, Qian Chen, Jintao Yao

и другие.

Advanced Engineering Informatics, Год журнала: 2025, Номер 65, С. 103189 - 103189

Опубликована: Фев. 15, 2025

Язык: Английский

Fusing consensus knowledge: A federated learning method for fault diagnosis via privacy-preserving reference under domain shift DOI
Baoxue Li, Pengyu Song, Chunhui Zhao

и другие.

Information Fusion, Год журнала: 2024, Номер 106, С. 102290 - 102290

Опубликована: Фев. 10, 2024

Язык: Английский

Процитировано

10

GRU-AE-wiener: A generative adversarial network assisted hybrid gated recurrent unit with Wiener model for bearing remaining useful life estimation DOI
Long Wen, Shaoquan Su, Xinyu Li

и другие.

Mechanical Systems and Signal Processing, Год журнала: 2024, Номер 220, С. 111663 - 111663

Опубликована: Июнь 24, 2024

Язык: Английский

Процитировано

10

Time- and frequency-domain fusion for source-free adaptation fault diagnosis DOI
Yu Gao,

Z. Zhang,

Bingquan Chen

и другие.

Information Fusion, Год журнала: 2025, Номер unknown, С. 102875 - 102875

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

2

Complex Symplectic Geometry Mode Decomposition and A Novel Time-Frequency Fault Feature Extraction Method DOI
Ge Xin, Yifei Chen,

Lingfeng Li

и другие.

IEEE Transactions on Instrumentation and Measurement, Год журнала: 2025, Номер 74, С. 1 - 10

Опубликована: Янв. 1, 2025

Although the condition monitoring of sophisticated equipment plays a crucial role in practical applications, fault symptom is often overwhelmed by harsh working conditions with compound and unknown interfering noise. To address this challenge, paper introduces novel signal decomposition scheme, termed Complex Symplectic Geometry Mode Decomposition (CSGMD), that leverages instantaneous complex envelope to ensure statistical structure hidden signal. First, applicable symplectic similar transform theory extended into domain facilitate exploitation phase information. Relying on phase-corrected Short-Time Fourier Transform, CSGMD achieves time-frequency while enhancing interpretation physical significance feature extraction. Target component reconstruction then executed using indicators, resulting reconstructed components are enriched original characteristic The effectiveness proposed method finally demonstrated both simulated measured signals. Through comparative experiments state-of-the-art methods, its superiority extraction further verified non trivial cases strong noise interference.

Язык: Английский

Процитировано

1

Cross-sensor contrastive learning-based pre-training for machinery fault diagnosis under sample-limited conditions DOI
Hao Hu, Yue Ma, Ruoxue Li

и другие.

Knowledge-Based Systems, Год журнала: 2025, Номер unknown, С. 113075 - 113075

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

1

Fourier Feature Refiner Network With Soft Thresholding for Machinery Fault Diagnosis Under Highly Noisy Conditions DOI
Huan Wang, Wenjun Luo, Zhiliang Liu

и другие.

IEEE Internet of Things Journal, Год журнала: 2024, Номер 11(13), С. 22880 - 22891

Опубликована: Фев. 7, 2024

Machinery fault diagnosis plays an important role in machine Prognostic and Health Management (PHM). Leveraging the abundant data obtained from Industrial Internet of Things (IIoT), health states machines can be effectively recognized, thereby ensuring safety mechanical system. However, lack noise robustness insufficient frequency domain perception make traditional methods to extract weak fault-related signals difficult under highly noisy conditions practical industrial scenarios. Therefore, a method with learning ability is urgently needed. To this end, paper proposes PHM framework, soft thresholding Fourier feature refiner network (Soft-FFRNet), for bearing vibration signal diagnosis. Specifically, framework includes which selectively extracts refines perspectives amplitude phase. It achieves extension time domain. In addition, proposed utilizes several residual blocks improve robustness. Their thresholds adaptively change during training process. The high-speed aeronautical (HSA) motor datasets different levels are used evaluate framework. results show that diagnose faults conditions.

Язык: Английский

Процитировано

5

Cross-modal zero-sample diagnosis framework utilizing non-contact sensing data fusion DOI
Sheng Li, Ke Feng, Yadong Xu

и другие.

Information Fusion, Год журнала: 2024, Номер 110, С. 102453 - 102453

Опубликована: Май 1, 2024

Язык: Английский

Процитировано

5

A federated cross-machine diagnostic framework for machine-level motors with extreme label shortage DOI
Yiming He, Weiming Shen

Advanced Engineering Informatics, Год журнала: 2024, Номер 61, С. 102511 - 102511

Опубликована: Апрель 1, 2024

Язык: Английский

Процитировано

4

Multiscale Conditional Adversarial Networks Based Domain-Adaptive Method for Rotating Machinery Fault Diagnosis Under Variable Working Conditions DOI
Z. K. Hei, Haiyang Yang, Weifang Sun

и другие.

ISA Transactions, Год журнала: 2024, Номер 154, С. 352 - 370

Опубликована: Сен. 2, 2024

Язык: Английский

Процитировано

4

Milling surface roughness monitoring using real-time tool wear data DOI
Runqiong Wang, Qinghua Song,

Yezhen Peng

и другие.

International Journal of Mechanical Sciences, Год журнала: 2024, Номер 285, С. 109821 - 109821

Опубликована: Ноя. 15, 2024

Язык: Английский

Процитировано

3