Sen Hu

Sen Hu

Auto-generated profile, based on publicly available information

Sen Hu

School of Reliability and Systems Engineering, Beihang University, Beijing, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
15 January 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
MYMiao Yonghao
Miao Yonghao
SHSen Hu
Sen Hu
YLYantong Liu
Yantong Liu
HDHuajia Dong
Huajia Dong
It is significant for the machinery fault diagnosis to extract the fault information from the multi-component vibration signal. Feature mode decomposition (FMD) which can accurately separate the fault feature has been widely verified and accepted in this field. However, it greatly limited its application that FMD cannot be directly applied under the speed-varying condition (SVC) since its decomposition objective, correlated kurtosis, is only defined in the stationary condition. Motivated by this, a new angle-domain feature mode decomposition (AFMD) is tailored under the speed-varying condition. In this paper, average kurtosis (AK) which inherently highlights the periodic impulses from the angle domain is firstly used as the decomposition objective. Subsequently, a finite impulse response filter bank initialized by the Hanning window is designed to provide a direction for the decomposition. Then, the adaptive filtering decomposition is iteratively performed constrained by the objective AK. Finally, the redundant and mixing modes are removed by the mode dropout strategy with correlation coefficient as its criterion. The simulations and experiments validate the effectiveness of the proposed method AFMD under SVC and its success in extending FMD to the speed-varying condition.

26 May 2026 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
MYMiao Yonghao
Miao Yonghao
SHSen Hu
Sen Hu
XWXun Wang
Xun Wang
Yun KongYun Kong
Yun Kong
Qiuyang ZhouQiuyang Zhou
Qiuyang Zhou
The extraction of fault features under strong noise condition (SNC) has been successfully addressed by the deep network-based maximum correlated kurtosis deconvolution (MCKD-DeNet) method. However, under speed-varying condition (SVC), this MCKD-DeNet method exhibits significant performance limitations due to inherent deficiencies in its objective function. To overcome the diagnostic challenge under SNC and SVC, this paper presents a novel angle-domain deep deconvolution (ADD) method. Initially, the method establishes a multi-layer neural network architecture, wherein feature learning is seamlessly integrated into the deconvolution framework to enhance the deep extraction capability of fault characteristics. Subsequently, the angle-domain index average kurtosis, which can effectively measure the fault characteristics under SVC, acts as the guiding criterion for optimizing the network. Furthermore, through the implementation of adaptive weight updating and feature learning strategies, fault features are progressively extracted and strengthened. Ultimately, the effectiveness of ADD is rigorously verified via simulations and experimental analysis, which consistently demonstrate its enhanced ability to accurately extract fault features under both SNC and SVC conditions, outperforming conventional techniques in terms of robustness and diagnostic accuracy.

25 August 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
MYMiao Yonghao
Miao Yonghao
SHSen Hu
Sen Hu
Jiantao ChangJiantao Chang
Jiantao Chang
The feature mode decomposition method has been proven to possess outstanding performance in bearing compound fault diagnosis. Nevertheless, the method exhibits limitations in terms of feature characterization, especially for the cyclostationary characteristic of bearing faults, due to the restrictions of its time-domain indicator, while its suboptimal equal frequency band division strategy may distort signal components during the filter initialization process, degrading the subsequent decomposition performance. To mitigate these constraints, a novel spectral sparse adaptive decomposition (SSAD) method is developed in this paper. The method begins by implementing the trend spectrum-guided strategy for filter initialization, which maintains the intact decomposition of the signal components through intelligent frequency band division. Building upon this foundation, SSAD incorporates square envelope spectral kurtosis as its decomposition objective, specifically designed to capture the cyclostationary characteristic of bearing faults. The decomposition process is further enhanced through the application of the eigenvalue algorithm, enabling precise identification of multiple fault signatures. In the final stage, the envelope spectrum-domain correlation coefficient-based screening strategy effectively discards redundant modes, ensuring the acquisition of the optimal decomposition results. Simulation and experimental validations confirm that SSAD significantly outperforms conventional methods, demonstrating superior capability in fault feature extraction.

13 May 2026 in IEEE Sensors Journal
Verified
Journal Article
Closed access
CZChuntao Zhang
Chuntao Zhang
SHSen Hu
Sen Hu
Qiuyang ZhouQiuyang Zhou
Qiuyang Zhou
MYMiao Yonghao
Miao Yonghao
Rolling bearing fault diagnosis under speed-varying condition (SVC) presents a significant challenge due to the non-stationary nature of vibration signals. The narrowband filtering demodulation (NFD) methods, while effective under constant speeds, faces severe limitations under such non-stationary operations. Specifically, their traditional feature indicators fail to characterize the non-stationary fault impulses, leading to significant performance degradation. Furthermore, the inherent fixed frequency band segmentation strategy of these methods can also impair their diagnostic accuracy. To address these limitations, this paper proposes AKgram, a novel adaptive diagnostic method designed specifically for the SVC. First, the fluctuation trend spectrum (FTS) is derived from the signal spectrum to realize adaptive frequency band segmentation, constructing a multi-level tower-shaped boundary distribution map while preserving full spectral component integrity and overcoming fixed segmentation limitations. Then, average kurtosis (AK) is introduced as a robust indicator to quantify fault-induced impulses and extract non-stationary fault features under SVC. Finally, AK values of segmented sub-bands are visualized in the tower-shaped map to form the AKgram, with the sub-band of maximum AK identified as the optimal demodulation band for direct fault feature extraction. The effectiveness and superiority of AKgram are validated via simulation and experimental data from a variable-speed bearing test bench, outperforming the classical Kurtogram method in optimal band identification and fault feature extraction.