Yuhe Liao
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuhe Liao has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Peng Sun
Shaanxi Key Laboratory of Mechanical Product Quality Assurance and Diagnostics, Xi’an Jiaotong University, Xi’an 710049, China
5 shared publications - Rongkai Duan
Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xian Jiaotong University, Xian, China
5 shared publications Lei Yang
Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi’an Jiaotong University, 710049 Xi’an, People’s Republic of China
4 shared publications- Jing Lin
School of Reliability and Systems Engineering, Beihang University, Beijing, China
3 shared publications Jiutao Xue
3 shared publications- Lei Yang
Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System and Shaanxi Key Laboratory of Mechanical Product Quality Assurance and Diagnostics, Xian Jiaotong University, Xian, China
3 shared publications
Latest Publications
- 28 July 2025
- Published by Elsevier in Digital Signal Processing
- Vol. 168
Short-time weighted ridge separation: A novel ridge detector with separation of overlapped non-stationary signals
- 28 July 2025
- Published by Elsevier in Digital Signal Processing
- Vol. 168
Short-time weighted ridge separation: A novel ridge detector with separation of overlapped non-stationary signals
- 28 March 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 150
Two-stream structure-oriented neighbor enhancement network for dental model segmentation
- 28 March 2025
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 150
Two-stream structure-oriented neighbor enhancement network for dental model segmentation
- 9 January 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (2) , 026117
An optimal frequency band selection approach via periodic shock indicator for bearing fault feature extraction
There are two challenges in the bearing fault feature extraction approach based on optimal frequency band (OFB) selection. The first is to design a high-precision signal decomposition algorithm to ensure that no fault information is lost; The second is to construct an indicator that is sensitive to the statistical characteristics of fault information. This paper proposed a novel OFB selection approach to solve the above challenges. Firstly, a parameter selection strategy is introduced for fixed bandwidth overlap-and-slip filter banks (FBOSFB). Adopting this strategy, the FBOSFB can decompose the signal into several narrowband signals while ensuring that no fault information is lost. Secondly, a novel indicator, namely periodic shock indicator (PSI), is constructed. The PSI has the capability to simultaneously assess both the periodic and shock characteristics of the bearing fault feature signal. Thirdly, the narrowband signals obtained from the first step are used as input to the OFB search algorithm, and then the OFB is determined by maximizing the PSI. Finally, three real bearing fault data are employed to verify the fault feature extraction performance of the proposed approach, the results show that the proposed approach can effectively extract the bearing fault feature.
- 9 January 2025
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (2) , 026117
An optimal frequency band selection approach via periodic shock indicator for bearing fault feature extraction
There are two challenges in the bearing fault feature extraction approach based on optimal frequency band (OFB) selection. The first is to design a high-precision signal decomposition algorithm to ensure that no fault information is lost; The second is to construct an indicator that is sensitive to the statistical characteristics of fault information. This paper proposed a novel OFB selection approach to solve the above challenges. Firstly, a parameter selection strategy is introduced for fixed bandwidth overlap-and-slip filter banks (FBOSFB). Adopting this strategy, the FBOSFB can decompose the signal into several narrowband signals while ensuring that no fault information is lost. Secondly, a novel indicator, namely periodic shock indicator (PSI), is constructed. The PSI has the capability to simultaneously assess both the periodic and shock characteristics of the bearing fault feature signal. Thirdly, the narrowband signals obtained from the first step are used as input to the OFB search algorithm, and then the OFB is determined by maximizing the PSI. Finally, three real bearing fault data are employed to verify the fault feature extraction performance of the proposed approach, the results show that the proposed approach can effectively extract the bearing fault feature.
- 11 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (3) , 4943-4957
An Optimal Dual Data-Driven Framework for RUL Prediction With Uncertainty Quantification
The prognosis of Remaining Useful Life (RUL) plays a crucial role in the domain of predictive maintenance, particularly for high-end equipment. Data-driven methods are commonly employed for RUL prediction. However, deep learning approaches provide only point estimates and lack reliability. Statistical models, used for uncertainty quantification, suffer from inaccurate parameter estimation due to incomplete degradation data. To address these issues, we introduce an Optimal Dual Data-driven Framework for RUL prediction with uncertainty quantification. This framework incorporates a Deep Bidirectional Recursive Gated Dual Attention Unit (DBR-GDAU) as its foundational network, providing robust multi-step point estimation. A meta-heuristic optimization algorithm is employed to adaptively select optimal hyperparameters for the optimal DBR-GDAU. Utilizing the multi-step predictions from the optimal DBR-GDAU, we establish a nonlinear adaptive Wiener process model, with model parameters estimated through maximum likelihood estimation. The probability density function of RUL is derived through the first passage time, and the 95% confidence interval is defined as the interval estimation for RUL. We demonstrate the efficacy and superiority of the proposed method by applying it to real bearing datasets and comparing its performance with state-of-the-art prediction methods.
- 11 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (3) , 4943-4957
An Optimal Dual Data-Driven Framework for RUL Prediction With Uncertainty Quantification
The prognosis of Remaining Useful Life (RUL) plays a crucial role in the domain of predictive maintenance, particularly for high-end equipment. Data-driven methods are commonly employed for RUL prediction. However, deep learning approaches provide only point estimates and lack reliability. Statistical models, used for uncertainty quantification, suffer from inaccurate parameter estimation due to incomplete degradation data. To address these issues, we introduce an Optimal Dual Data-driven Framework for RUL prediction with uncertainty quantification. This framework incorporates a Deep Bidirectional Recursive Gated Dual Attention Unit (DBR-GDAU) as its foundational network, providing robust multi-step point estimation. A meta-heuristic optimization algorithm is employed to adaptively select optimal hyperparameters for the optimal DBR-GDAU. Utilizing the multi-step predictions from the optimal DBR-GDAU, we establish a nonlinear adaptive Wiener process model, with model parameters estimated through maximum likelihood estimation. The probability density function of RUL is derived through the first passage time, and the 95% confidence interval is defined as the interval estimation for RUL. We demonstrate the efficacy and superiority of the proposed method by applying it to real bearing datasets and comparing its performance with state-of-the-art prediction methods.
- 6 July 2024
- Published by Elsevier in ISA Transactions
- Vol. 152, 331-357
A knowledge-data integration framework for rolling element bearing RUL prediction across its life cycle
- 6 July 2024
- Published by Elsevier in ISA Transactions
- Vol. 152, 331-357
A knowledge-data integration framework for rolling element bearing RUL prediction across its life cycle
- 4 May 2024
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 216, 111475
Weight extracting transform for instantaneous frequency estimation and signal reconstruction
- 4 May 2024
- Published by Elsevier in Mechanical Systems and Signal Processing
- Vol. 216, 111475
Weight extracting transform for instantaneous frequency estimation and signal reconstruction
- 22 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 71 (7) , 7864-7875
Morphological Analysis Based Adaptive Blind Deconvolution Approach for Bearing Fault Feature Extraction
How to accurately extract the fault related periodical impulses is the key to bearing fault diagnosis. The blind deconvolution (BD) method has been positively affirmed its ability in this field. However, the experience dependent parameter-setting and vulnerable to interference under complex working condition are two main problems that seriously limit its application. To address these issues, an improved BD method, named adaptive morphological BD, is proposed in this article. A new indicator, the morphological frequency negentropy, is first constructed through morphological analysis and adopted as the objective function for deconvolution. With its robustness to random impact and noise being verified, the optimal Morlet wavelet filter is selected with morphological frequency negentropy (MFN) and used as the initial filter. The sampling matrix is enhanced with varying morphological filtering and its size is adaptively determined by power spectral density. Through adaptive setting of the length of the filter, the dependence of prior knowledge for parameter setting is therefore reduced. Finally, the diagonal slice spectrum is applied on the filtered signal to remove in-band and residual noise. The effectiveness of the proposed method is validated by simulation signal and real datasets. Comparison analysis with other typical filter methods further shows its superiority.
- 22 August 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Electronics
- Vol. 71 (7) , 7864-7875
Morphological Analysis Based Adaptive Blind Deconvolution Approach for Bearing Fault Feature Extraction
How to accurately extract the fault related periodical impulses is the key to bearing fault diagnosis. The blind deconvolution (BD) method has been positively affirmed its ability in this field. However, the experience dependent parameter-setting and vulnerable to interference under complex working condition are two main problems that seriously limit its application. To address these issues, an improved BD method, named adaptive morphological BD, is proposed in this article. A new indicator, the morphological frequency negentropy, is first constructed through morphological analysis and adopted as the objective function for deconvolution. With its robustness to random impact and noise being verified, the optimal Morlet wavelet filter is selected with morphological frequency negentropy (MFN) and used as the initial filter. The sampling matrix is enhanced with varying morphological filtering and its size is adaptively determined by power spectral density. Through adaptive setting of the length of the filter, the dependence of prior knowledge for parameter setting is therefore reduced. Finally, the diagonal slice spectrum is applied on the filtered signal to remove in-band and residual noise. The effectiveness of the proposed method is validated by simulation signal and real datasets. Comparison analysis with other typical filter methods further shows its superiority.
- 27 January 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 120
A bidirectional recursive gated dual attention unit based RUL prediction approach
- 27 January 2023
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 120
A bidirectional recursive gated dual attention unit based RUL prediction approach
- 1 August 2022
- Published by Elsevier in ISA Transactions
- Vol. 127, 324-341
Adaptive tacholess order tracking method based on generalized linear chirplet transform and its application for bearing fault diagnosis
- 1 August 2022
- Published by Elsevier in ISA Transactions
- Vol. 127, 324-341
Adaptive tacholess order tracking method based on generalized linear chirplet transform and its application for bearing fault diagnosis