Xingyu Chen

Dr. Xingyu Chen


Research Focus & Metrics

Academic Career Length

10Years (2017-Present)

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

Representative Publications

View All Publications
8 December 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
XCXingyu Chen
Xingyu Chen
LZLiye Zhao
Liye Zhao
JXJiawen Xu
Jiawen Xu
ZLZhikang Liu
Zhikang Liu
CZChengxin Zhang
Chengxin Zhang
NGNing Guo
Ning Guo
Noise suppression is of great significance in high-precision micro thrust calibration and measurement. Existing methods cannot simultaneously recover both the nonlinear transitions (generated by thrust) and smooth trends of the signals. Additionally, they exhibit poor robustness to noise model changes. To address the issues, in this research we propose a novel self-supervised contrastive denoising autoencoder (SCDAE) model. The SCDAE features end-to-end signal denoising based on a multi-task joint learning framework combining contrastive representation learning and denoising autoencoder (DAE) without the need for a clean signal reference. Specifically, SCDAE consists of a representation learner (RPL) and a denoising learner (DEL). In addition, considering the multi-staircase property of the measurement signal, a novel parallel hybrid data augmentation strategy is designed in the RPL to create positive sample pairs and greatly force the network to extract robust content-invariant and disentangled features. Besides, in order to solve the blindness of training target creation for the DEL, a new training target creation strategy is proposed based on the variational mode decomposition (VMD). An attention module is introduced to adaptively reinforce the content-invariant disentangled features from the RPL, guiding the DEL to generate the essential dynamic nature from the raw input signal, thus suppressing noise information. Extensive simulations and experimental case study were carried out to demonstrate the effectiveness and advancement of the proposed method in recovering signal details (nonlinear transitions and smooth trends) with comparison to existing classical methods.

21 August 2023 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
ZLZhikang Liu
Zhikang Liu
XCXingyu Chen
Xingyu Chen
JXJiawen Xu
Jiawen Xu
CZChengxin Zhang
Chengxin Zhang
LXLuxiang Xu
Luxiang Xu
RYRuqiang Yan
Ruqiang Yan
Micro-Newton thrusters are widely utilized in the field of astronautics. Typically, micro-newton thrust signal processing aims at the restoration of piecewise constant signals. Improving the amplitude accuracy of the denoised signal remains a major difficulty. In this research, we proposed a new nonlinear total variation denoising (TVD) algorithm with an adjustable majorization-minimization (MM) upper bound function for optimizing the iterative solution process of TVD. The influences of the upper bound function of the TVD on denoising are analyzed in detail. It is demonstrated that the proposed aTVD method shows extraordinary robustness for denoising signals with different noise levels. In addition, this algorithm can also adjust the sensitivity of the jumps in signals for optimized amplitude accuracy effectively. Numerical examples show that the proposed method has 40.4% and 18.2% accuracy improvement over conventional TVD using traditional quadratic upper bound and enhanced TVD using exponential upper bound function. Moreover, the advantages of the proposed method are validated in an experiment of measured thrust signal processing. The proposed method can be further adopted to improve the performance of signal denoising algorithms developed from the TVD method.

10 September 2025 in Thin-Walled Structures
Verified
Journal Article
Closed access
XCXingyu Chen
Xingyu Chen
LZLiye Zhao
Liye Zhao
JXJiawen Xu
Jiawen Xu
LXLuxiang Xu
Luxiang Xu
NGNing Guo
Ning Guo

9 April 2025 in Actuators
Verified
Journal Article
Open access
PDF file
YCYuhuan Cai
Yuhuan Cai
LZLiye Zhao
Liye Zhao
XCXingyu Chen
Xingyu Chen
ZLZhenjun Li
Zhenjun Li
The X-ray defect detection system for weld seams in deep-sea manned spherical shells is nonlinear and complex, posing challenges such as motor parameter variations, external disturbances, coupling effects, and high-precision dual-motor coordination requirements. To address these challenges, this study proposes a deep reinforcement learning-based control scheme, leveraging DRL’s capabilities to optimize system performance. Specifically, the TD3 algorithm, featuring a dual-critic structure, is employed to enhance control precision within predefined state and action spaces. A composite reward mechanism is introduced to mitigate potential motor instability, while CP-MPA is utilized to optimize the performance of the proposed m-TD3 composite controller. Additionally, a synchronous collaborative motion compensator is developed to improve coordination accuracy between the dual motors. For practical implementation and validation, a PMSM simulation model is constructed in MATLAB/Simulink, serving as an interactive training platform for the DRL agent and facilitating efficient, robust training. The simulation results validate the effectiveness and superiority of the proposed optimization strategy, demonstrating its applicability and potential for precise and robust control in complex nonlinear defect detection systems.

5 January 2024 in Actuators
Verified
Journal Article
Open access
PDF file
XCXingyu Chen
Xingyu Chen
LZLiye Zhao
Liye Zhao
JXJiawen Xu
Jiawen Xu
ZLZhikang Liu
Zhikang Liu
Micro-newton thrust stands are widely used in thruster ground calibration procedures for a variety of space missions. The conventional analytical model does not consider the gravity-induced extension effect and systematic error in displacement for thrust stands consisting of hanging pendulums based on flexure hinge structures. This paper proposes an improved analytical model of a hanging pendulum for thrust measurement, where an elliptical notched flexure hinge is the key component. A parametric model of the bending stiffness of the flexure hinge is developed. Equally, both the bending stiffness shift under the gravity-induced extension effect and the systematic error in displacement due to the assumed rotational center offset of the hinge are investigated. The presented stiffness equations for elliptical notched hinges can be degenerated into stiffness equations for circular notched as well as leaf-type hinges. The improved model aims to evaluate and highlight the influence of the two considered factors for use in thrust stand parameter design and thrust analysis. A finite element modeling solution is proposed to validate the proposed analytical model. The results show that the proposed model can quantify the hinge bending stiffness shift, which also demonstrates that even a small bending stiffness shift may introduce great uncertainty into the thrust analysis.

24 February 2025 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
XCXingyu Chen
Xingyu Chen
LZLiye Zhao
Liye Zhao
JXJiawen Xu
Jiawen Xu
ZLZhikang Liu
Zhikang Liu
ZDZhuoping Dai
Zhuoping Dai
HZHong Zhang
Hong Zhang
Removing noise and recovering the micronewton thrust signal are of great significance in high-precision static thrust measurements. Typically, the micronewton thrust signal is in the shape of a staircase signal. Existing methods have limitations in decoupling sharp step edges and flat regions from noisy signals while ensuring the accuracy of step amplitude reconstruction. In this study, we have developed a novel generative denoising method, named variational denoising autoencoder (VDAE), based on a unique deep learning-based Bayesian framework. Specifically, the encoder-parameterized approximate posterior maps the distribution of essential features (i.e., thrust step amplitudes) of limited training samples to a latent space with a Gaussian distribution. This distribution transformation gives the latent space the ability to describe complete continuous step amplitudes. VDAE inherits the excellent generalization ability of the generative model and greatly improves the amplitude accuracy of the denoised signals. In addition, considering the different scale features in the clean staircase signal, a trend feature disentangler (TFD) is introduced in the encoder. The TFD adaptively extracts ultra-high-frequency sharp step edge features and ultra-low-frequency flat region features. Furthermore, to address the issue of recovering sharp step edges, total variation (TV) sparse representation is introduced into the loss function, guiding the decoder to reconstruct the thrust step. Extensive simulations and experiments were carried out to demonstrate the effectiveness and superiority of the proposed method in micronewton thrust step reconstruction and measurement noise removal.