Zhiyuan Chai

Mr. Zhiyuan Chai

Ningbo University, College of Science and Technology, Ningbo University, Ningbo, Zhejiang, China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
10 January 2025 in Sensors
Verified
Journal Article
Open access
PDF file
WXWenping Xiang
Wenping Xiang
JCJunhua Chen
Junhua Chen
HLHao Li
Hao Li
ZCZhiyuan Chai
Zhiyuan Chai
YLYinghou Lou
Yinghou Lou
Industrial robotic arms are often subject to significant end-effector pose deviations from the target position due to the combined effects of nonlinear deformations such as link flexibility, joint compliance, and end-effector load. To address this issue, a study was conducted on the analysis and compensation of end-position errors in a six-degree-of-freedom robotic arm. The kinematic model of the robotic arm was established using the Denavit–Hartenberg (DH) parameter method, and a rigid–flexible coupled virtual prototype model was developed using ANSYS and ADAMS. Kinematic simulations were performed on the virtual prototype to analyze the variation in end-effector position errors under rigid–flexible coupling conditions. To achieve error compensation, an approach based on an Enhanced Crayfish Optimization Algorithm (ECOA) optimizing a BP neural network was proposed to compensate for position errors. An experimental platform was constructed for error measurement and validation. The experimental results demonstrated that the positioning accuracy after compensation improves by 75.77%, fully validating the effectiveness and reliability of the proposed method for compensating flexible errors.

13 February 2025 in Sensors
Verified
Journal Article
Open access
PDF file
ZCZhiyuan Chai
Zhiyuan Chai
JCJunhua Chen
Junhua Chen
HLHao Li
Hao Li
WXWenping Xiang
Wenping Xiang
DCDongdong Chang
Dongdong Chang
ZLZewen Liu
Zewen Liu
In circular production lines, issues such as positional errors, manufacturing errors at different square groove workstations, and the accumulation of errors during continuous assembly reduce the assembly success rate and limit efficiency. To address these challenges in assembling square groove parts, this study focuses on the jamming and wedging problems encountered during the assembly of square grooves and square parts. It analyzes typical assembly hole searching contact situations and proposes corresponding strategies. Based on the relative geometric relationships between the assembly workpieces, the entire assembly process is divided into three stages: pre-assembly, hole search contact adjustment, and insertion. Due to the complexity of predicting assembly forces and the uncertainty of workstation assembly in circular production lines, this study emphasizes the hole search contact adjustment stage. An innovative vertical hole search strategy is proposed and compared with the Archimedes spiral search method. This strategy models the contact between the end effector and the environment as a mass–damping–spring second-order system, achieving compliant assembly of square holes through admittance control. By analyzing the admittance parameters using control variables, the optimal admittance parameters are determined, and the admittance parameter pattern is applied in the experiments. Experimental results on the square hole assembly platform show that, under the optimal admittance parameters, the vertical hole search strategy significantly reduces search time and improves efficiency. Compared to the traditional Archimedes spiral hole search strategy, the average search adjustment time was increased by 5.8 s, improving efficiency by 46.4%, and the desired assembly outcomes were achieved.
1

29 November 2024 in IEEE Access
Verified
Journal Article
Open access
ZLZewen Liu
Zewen Liu
SZShaoyi Zhou
Shaoyi Zhou
JCJianqiao Chu
Jianqiao Chu
ZCZhiyuan Chai
Zhiyuan Chai
DCDongdong Chang
Dongdong Chang
XWXiancheng Wang
Xiancheng Wang
Arthroscopic surgery is a major technique for the treatment of joint-related diseases, however, intraoperative bleeding often produces a blood mist that severely affects the surgeon’s field of vision and requires prompt high-flow drainage to remove the mist. Therefore, accurate bleeding detection is a prerequisite for effective blood mist removal. This paper proposes an arthroscopic image bleeding detection method based on the ViT-ResNet50 integrated model and transfer learning to solve the problem of relying on naked eye to identify bleeding in existing arthroscopic surgery. Firstly, Vision Transformer model and ResNet50 model are used to learn features by transfer learning on ImageNet dataset respectively. Then, a difference-enhanced proportional sampling method is proposed to enhance the unbalanced data. Finally, the two sub-network models are integrated through weighted soft voting method to realize bleeding detection in arthroscopic images. In order to evaluate the performance of the model proposed in this paper, experimental results on real data show that the integrated model is superior to a single deep learning model in various performance indicators and has good effects in detecting bleeding in arthroscopic images.