Hongping Shu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Hongping Shu has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Chen Cong
College of Mathematics and Informatics, Fujian Normal University, Shangjie, Minhou, Fuzhou, Fujian, China
1 shared publication Haiqing Zhang
1 shared publicationHong Tang
1 shared publication- Hong Zhong
Anhui University
1 shared publication - Jian-Min Jiang
Chengdu University of Information Technology
1 shared publication - Jianhong Gan
School of Software Engineering, Chengdu University of Information Technology, Chengdu, China
1 shared publication
Latest Publications
- 30 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-10
Hybrid Mapping Polynomial Neural Network Based on PSO Optimization for Robot Calibration
The absolute positioning accuracy of industrial robotic arms is crucial for advancing manufacturing applications such as automated assembly. This study presents a Hybrid Mapping Polynomial Neural Network based on Particle Swarm Optimization (PSO-HMPNN) for industrial robot calibration. The proposed approach integrates independent mapping neural networks with polynomial residual interaction neural modules to enhance error compensation capabilities, while employing the PSO algorithm to optimize neural network weights and avoid local optima. Experimental validation was performed on two distinct datasets (Dataset ABB and Dataset HSR) using ABB IRB120 and HSR JR680 robot, with performance compared against eight state-of-the-art calibration algorithms (M2-M9). Results demonstrate that PSO-HMPNN consistently achieved the lowest error metrics across both datasets. On the primary dataset (Dataset ABB), it reached a Mean Absolute Error (MAE) of 0.36mm, a Root Mean Square Error (RMSE) of 0.42mm, and a Maximum Error (MAX) of 0.92mm. This represents improvements of 14.3%, 19.2%, and 25.2% in MAE, RMSE, and MAX, respectively, over the best-performing baseline algorithm (M9). Similar high performance was also achieved on Dataset HSR, confirming the method’s robustness. Furthermore, the method shows excellent scalability, with an estimated computation time of 25.0s for a larger 500-sample dataset, achieving an optimal balance between accuracy and computational efficiency. The optimized Denavit-Hartenberg (D-H) parameters obtained after calibration meet industrial requirements, confirming the method’s superiority and applicability in robot calibration tasks.
- 30 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-10
Hybrid Mapping Polynomial Neural Network Based on PSO Optimization for Robot Calibration
The absolute positioning accuracy of industrial robotic arms is crucial for advancing manufacturing applications such as automated assembly. This study presents a Hybrid Mapping Polynomial Neural Network based on Particle Swarm Optimization (PSO-HMPNN) for industrial robot calibration. The proposed approach integrates independent mapping neural networks with polynomial residual interaction neural modules to enhance error compensation capabilities, while employing the PSO algorithm to optimize neural network weights and avoid local optima. Experimental validation was performed on two distinct datasets (Dataset ABB and Dataset HSR) using ABB IRB120 and HSR JR680 robot, with performance compared against eight state-of-the-art calibration algorithms (M2-M9). Results demonstrate that PSO-HMPNN consistently achieved the lowest error metrics across both datasets. On the primary dataset (Dataset ABB), it reached a Mean Absolute Error (MAE) of 0.36mm, a Root Mean Square Error (RMSE) of 0.42mm, and a Maximum Error (MAX) of 0.92mm. This represents improvements of 14.3%, 19.2%, and 25.2% in MAE, RMSE, and MAX, respectively, over the best-performing baseline algorithm (M9). Similar high performance was also achieved on Dataset HSR, confirming the method’s robustness. Furthermore, the method shows excellent scalability, with an estimated computation time of 25.0s for a larger 500-sample dataset, achieving an optimal balance between accuracy and computational efficiency. The optimized Denavit-Hartenberg (D-H) parameters obtained after calibration meet industrial requirements, confirming the method’s superiority and applicability in robot calibration tasks.
- 1 September 2019
- Published by Elsevier in Chemometrics and Intelligent Laboratory Systems
- Vol. 192
Spectra data classification with kernel extreme learning machine
- 1 September 2019
- Published by Elsevier in Chemometrics and Intelligent Laboratory Systems
- Vol. 192
Spectra data classification with kernel extreme learning machine
- Open Access
- 10 July 2019
- Published by KSI Research Inc.
Schedulability analysis for real-time mobile systems (S)
- 10 July 2019
- Published by KSI Research Inc.
Open AccessSchedulability analysis for real-time mobile systems (S)
- 1 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1841-1845
Design of Manufacturing Big Data Access Platform Based on SOA
In view of the lack of big data access platform in current manufacturing industry, the big data access platform was studied based on SOA. With the analysis of big data characteristics and the big data access business in manufacturing industry, the overall architecture of the service oriented manufacturing big data access platform was built. The whole technical scheme of the platform was introduced and the platform functional design was the elaborated. The platform has functions of the data access management, data processing management, log management, database management and the distributed storage management. These provide good foundation for manufacturing big data service.
- 1 December 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1841-1845
Design of Manufacturing Big Data Access Platform Based on SOA
In view of the lack of big data access platform in current manufacturing industry, the big data access platform was studied based on SOA. With the analysis of big data characteristics and the big data access business in manufacturing industry, the overall architecture of the service oriented manufacturing big data access platform was built. The whole technical scheme of the platform was introduced and the platform functional design was the elaborated. The platform has functions of the data access management, data processing management, log management, database management and the distributed storage management. These provide good foundation for manufacturing big data service.
- 1 December 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Automatic Drawing of Scleronomic Activity-On-Arrow Network
To meet some special needs, this article primarily introduced an automatic node arranging algorithm of Scleronomic activity-on-arrow network. By introducing the concept of main-path, the thoughts and steps of the algorithm realization, which means to arrange the nodes around the main-path from inside to outside, it helps the readers to understand the algorithm easily. The algorithm provides the necessary technical support to realize the auto drawing of PERT network chart. Its correctness has been proved in the auto drawings of various project network charts.
- 1 December 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Automatic Drawing of Scleronomic Activity-On-Arrow Network
To meet some special needs, this article primarily introduced an automatic node arranging algorithm of Scleronomic activity-on-arrow network. By introducing the concept of main-path, the thoughts and steps of the algorithm realization, which means to arrange the nodes around the main-path from inside to outside, it helps the readers to understand the algorithm easily. The algorithm provides the necessary technical support to realize the auto drawing of PERT network chart. Its correctness has been proved in the auto drawings of various project network charts.