Advanced Engineering Informatics, Год журнала: 2025, Номер 65, С. 103189 - 103189
Опубликована: Фев. 15, 2025
Язык: Английский
Advanced Engineering Informatics, Год журнала: 2025, Номер 65, С. 103189 - 103189
Опубликована: Фев. 15, 2025
Язык: Английский
Information Fusion, Год журнала: 2024, Номер 106, С. 102290 - 102290
Опубликована: Фев. 10, 2024
Язык: Английский
Процитировано
10Mechanical Systems and Signal Processing, Год журнала: 2024, Номер 220, С. 111663 - 111663
Опубликована: Июнь 24, 2024
Язык: Английский
Процитировано
10Information Fusion, Год журнала: 2025, Номер unknown, С. 102875 - 102875
Опубликована: Янв. 1, 2025
Язык: Английский
Процитировано
2IEEE 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
1Knowledge-Based Systems, Год журнала: 2025, Номер unknown, С. 113075 - 113075
Опубликована: Фев. 1, 2025
Язык: Английский
Процитировано
1IEEE 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
5Information Fusion, Год журнала: 2024, Номер 110, С. 102453 - 102453
Опубликована: Май 1, 2024
Язык: Английский
Процитировано
5Advanced Engineering Informatics, Год журнала: 2024, Номер 61, С. 102511 - 102511
Опубликована: Апрель 1, 2024
Язык: Английский
Процитировано
4ISA Transactions, Год журнала: 2024, Номер 154, С. 352 - 370
Опубликована: Сен. 2, 2024
Язык: Английский
Процитировано
4International Journal of Mechanical Sciences, Год журнала: 2024, Номер 285, С. 109821 - 109821
Опубликована: Ноя. 15, 2024
Язык: Английский
Процитировано
3