Chunyang Sheng

Dr. Chunyang Sheng

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
28 July 2022 in Journal of Ambient Intelligence and Humanized Computing
Verified
Journal Article
Closed access
PDF file
MTMuhammad Taimoor
Muhammad Taimoor
Xiao LuXiao Lu
Xiao Lu
HMHamid Maqsood
Hamid Maqsood
CSChunyang Sheng
Chunyang Sheng

6 November 2023 in Applied Sciences
Verified
Journal Article
Open access
PDF file
XQXin Qi
Xin Qi
CSChunyang Sheng
Chunyang Sheng
YGYongbao Guo
Yongbao Guo
TSTao Su
Tao Su
HWHaixia Wang
Haixia Wang
Aiming at the problem that online parameter identification, based on the Model Reference Adaptive System (MRAS), is easily affected by the high-frequency noise of the sensor, an improved MRAS, based on variable bandwidth linear Active Disturbance Rejection Control (ADRC) adaptive law, is proposed. The proposed ADRC adaptive law, including an extended state observer, exhibits good anti-disturbance ability while effectively tracking the error signal through adjusting the bandwidth of the controller according to the observation error. When the observation error is large, the bandwidth of the controller is increased to enhance the tracking accuracy; in the opposite situation, the bandwidth is reduced to improve the anti-disturbance performance. To illustrate feasibility, a stability analysis of the proposed ADRC adaptive law is carried out and some comparison and validation experiments are designed to identify the inductance and flux linkage of the permanent magnet synchronous motor (PMSM). The experimental results show that the proposed method has better anti-disturbance performance than the MRAS based on traditional Proportional Integral (PI) adaptive law or switched PI adaptive law.

10 October 2024 in Control Engineering Practice
Verified
Journal Article
Closed access
JNJun Nie
Jun Nie
GZGuihua Zhang
Guihua Zhang
XLXiao Lu
Xiao Lu
HWHaixia Wang
Haixia Wang
CSChunyang Sheng
Chunyang Sheng
LSLijie Sun
Lijie Sun

21 November 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
CSChunyang Sheng
Chunyang Sheng
AHAn Hao
An Hao
NJNie Jun
Nie Jun
WHWang Haixia
Wang Haixia
Xiao LuXiao Lu
Xiao Lu
Both DQN and M-DQN is commonly used for mobile robot path planning, with the problem of relatively low efficiencies of the action selection policy and the reward function when coping with complex environments. To solve the problem, an improved $\epsilon$ -UCB action selection method based on neural network is proposed to fit the uncertainty of state-action pairs, which effectively improves the exploration efficiency. Meanwhile, aiming at the effectiveness of the reward function, a multi-goal fusion reward function is proposed to improve the guidance ability. Further, the proposed $\epsilon$ -UCB action selection policy and the multi-goal fusion reward function are introduced into the M-DQN framework to complete the path planning task of the mobile robot. Finally, some comparative experiments are carried out to verify the effectiveness of the proposed method. The experimental results show that the proposed method exhibits faster convergence speed and higher learning efficiency for the path planning of mobile robots in complex environments than other existing methods.

6 August 2018 in Assembly Automation
Verified
Journal Article
Closed access
HWHaixia Wang
Haixia Wang
Xiao LuXiao Lu
Xiao Lu
WCWei Cui
Wei Cui
ZZZhiguo Zhang
Zhiguo Zhang
YLYuxia Li
Yuxia Li
CSChunyang Sheng
Chunyang Sheng
Purpose: Developing general closed-form solutions for six-degrees-of-freedom (DOF) serial robots is a significant challenge. This paper thus aims to present a general solution for six-DOF robots based on the product of exponentials model, which adapts to a class of robots satisfying the Pieper criterion with two parallel or intersecting axes among its first three axes. Design/methodology/approach: The proposed solution can be represented as uniform expressions by using geometrical properties and a modified Paden–Kahan sub-problem, which mainly adopts the screw theory. Findings: A simulation and experiments validated the correctness and effectiveness of the proposed method (general resolution for six-DOF robots based on the product of exponentials model). Originality/value: The Rodrigues rotation formula is additionally used to turn the complex problem into a solvable trigonometric function and uniformly express six solutions using two formulas.

10 February 2025 in Computer Applications in Engineering Education
Verified
Journal Article
Closed access
CSChunyang Sheng
Chunyang Sheng
ZMZhong Maiying
Zhong Maiying