Xiying Fan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xiying Fan has a total of 44 co-authors. Here are the top co-authors by number of shared publications:
Yonghuan Guo
School of Mechanical Engineering, Jiangsu Normal University , Xuzhou , 221116 , P.R. China
13 shared publicationsLie Li
School of Mechanical Engineering, Jiangsu Normal University, Xuzhou, People’s Republic of China
6 shared publicationsLiuyu Zhu
School of Mechanical Engineering, Jiangsu Normal University, Xuzhou, People’s Republic of China
6 shared publicationsXin Liu
School of Mechanical and Electrical Engineering , Jiangsu Normal University , Xuzhou 221116 , P. R. China
6 shared publications- Yonghuan Guo
School of Mechatronic Engineering, Jiangsu Normal University, Xuzhou, China
6 shared publications Xiangning Lu
School of Mechanical and Electrical Engineering , Jiangsu Normal University , 221116 , Xuzhou , China
5 shared publications
Latest Publications
- 14 October 2026
- Published by Springer Nature in International Journal of Material Forming
- Vol. 19 (4) , 130
Interpretable machine learning and hybrid metaheuristic algorithms for multi-objective optimization in injection molding
- 14 October 2026
- Published by Springer Nature in International Journal of Material Forming
- Vol. 19 (4) , 130
Interpretable machine learning and hybrid metaheuristic algorithms for multi-objective optimization in injection molding
- Open Access
- 8 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Multi-objective optimization of injection molding process parameters for thin-walled shell parts based on a RIME-RF-MOGWO framework
- 8 August 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessMulti-objective optimization of injection molding process parameters for thin-walled shell parts based on a RIME-RF-MOGWO framework
- Open Access
- 23 June 2026
- Published by Walter de Gruyter GmbH in Chemical Product and Process Modeling
Multi-objective optimization of injection molding via interpretable ensemble learning and a multi-strategy improved MOCGO algorithm
To address the nonlinear coupling and performance conflicts among warpage deformation, volumetric shrinkage, and clamping force in injection molding, a collaborative framework integrating multi-model learning and multi-objective optimization is proposed. High-coverage simulation samples are first generated using Central Composite Design (CCD) and Latin Hypercube Sampling (LHS). On this basis, an ensemble prediction model is constructed by combining Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Multilayer Perceptron (MLP), and Long Short-Term Memory (LSTM), with hyperparameters optimized via the Improved Runge-Kutta (IRUN) algorithm. Model interpretability is enhanced using SHapley Additive exPlanations (SHAP). In the optimization phase, multiple strategies – including good point set (GPS) initialization, Cauchy local perturbation, Lévy flight mutation, and adaptive PBI-based sorting – are incorporated into the Multi-objective Chaotic Game Optimization (MOCGO) algorithm to improve performance. Finally, the proposed method is validated through coupled simulations using Moldflow and Ansys. Warpage, shrinkage, and clamping force are reduced by 24.0 %, 6.3 % and 7.4 %, respectively, with improved stress distribution, demonstrating both effectiveness and engineering applicability.
- 23 June 2026
- Published by Walter de Gruyter GmbH in Chemical Product and Process Modeling
Open AccessMulti-objective optimization of injection molding via interpretable ensemble learning and a multi-strategy improved MOCGO algorithm
To address the nonlinear coupling and performance conflicts among warpage deformation, volumetric shrinkage, and clamping force in injection molding, a collaborative framework integrating multi-model learning and multi-objective optimization is proposed. High-coverage simulation samples are first generated using Central Composite Design (CCD) and Latin Hypercube Sampling (LHS). On this basis, an ensemble prediction model is constructed by combining Random Forest (RF), eXtreme Gradient Boosting (XGBoost), Multilayer Perceptron (MLP), and Long Short-Term Memory (LSTM), with hyperparameters optimized via the Improved Runge-Kutta (IRUN) algorithm. Model interpretability is enhanced using SHapley Additive exPlanations (SHAP). In the optimization phase, multiple strategies – including good point set (GPS) initialization, Cauchy local perturbation, Lévy flight mutation, and adaptive PBI-based sorting – are incorporated into the Multi-objective Chaotic Game Optimization (MOCGO) algorithm to improve performance. Finally, the proposed method is validated through coupled simulations using Moldflow and Ansys. Warpage, shrinkage, and clamping force are reduced by 24.0 %, 6.3 % and 7.4 %, respectively, with improved stress distribution, demonstrating both effectiveness and engineering applicability.
- 21 November 2025
- Published by Walter de Gruyter GmbH in International Polymer Processing
- Vol. 41 (1) , 27-37
Multi-objective optimization of process parameters in (PC/TPU) dual-material injection molding
Focusing on a dual-material translucent window (PC/TPU), this study aims to reduce warping deformation and volume shrinkage, thereby improving its surface molding quality. Six key process parameters in dual-material injection molding were selected as influencing factors. Warping deformation and volume shrinkage were taken as quality indicators. A Taguchi experimental design with 50 groups was used for Moldflow simulation. Additionally, the Gorilla Troops Optimization (GTO) algorithm was applied to optimize the parameters of the Generalized Additive Model (GAM). A mathematical model was established to link injection molding process parameters with quality objectives. Subsequently, the established mathematical model was globally optimized using the Multi-objective Dragonfly Algorithm (MODA). This yielded the optimal combination of process parameters. Compared to pre-optimization results, the warping deformation of the first PC injection was reduced by 9.77 %. Volume shrinkage was reduced by 21.63 %. For the second TPU injection, warping deformation was reduced by 13.29 %. Volume shrinkage was reduced by 4.48 %. These results demonstrate the effectiveness and reliability of the optimization method.
- 21 November 2025
- Published by Walter de Gruyter GmbH in International Polymer Processing
- Vol. 41 (1) , 27-37
Multi-objective optimization of process parameters in (PC/TPU) dual-material injection molding
Focusing on a dual-material translucent window (PC/TPU), this study aims to reduce warping deformation and volume shrinkage, thereby improving its surface molding quality. Six key process parameters in dual-material injection molding were selected as influencing factors. Warping deformation and volume shrinkage were taken as quality indicators. A Taguchi experimental design with 50 groups was used for Moldflow simulation. Additionally, the Gorilla Troops Optimization (GTO) algorithm was applied to optimize the parameters of the Generalized Additive Model (GAM). A mathematical model was established to link injection molding process parameters with quality objectives. Subsequently, the established mathematical model was globally optimized using the Multi-objective Dragonfly Algorithm (MODA). This yielded the optimal combination of process parameters. Compared to pre-optimization results, the warping deformation of the first PC injection was reduced by 9.77 %. Volume shrinkage was reduced by 21.63 %. For the second TPU injection, warping deformation was reduced by 13.29 %. Volume shrinkage was reduced by 4.48 %. These results demonstrate the effectiveness and reliability of the optimization method.
- 8 July 2025
- Published by Walter de Gruyter GmbH in Journal of Polymer Engineering
- Vol. 45 (8) , 710-721
Based on WCA-KELM and MOSOA: optimization of injection molding quality for plastic alloy products
For PC/ABS plastic alloy injection-molded products, warping and volumetric shrinkage are two prevalent quality defects attributed to the injection molding process. To mitigate these defects to the greatest extent, this study introduces an optimized injection molding process parameter scheme based on the water cycle algorithm enhanced kernel extreme learning machine (WCA-KELM), the multi-objective seagull optimization algorithm (MOSOA), and grey relational evaluation. Firstly, all experimental data were derived from orthogonal experimental designs conducted via Moldflow software, focusing on seven factors, such as melt temperature, mold temperature, packing pressure, and packing time. Warpage and volume shrinkage results were obtained in each set of experiments. Secondly, the predictive accuracy of the unoptimized kernel extreme learning machine (KELM) model was compared against that of the WCA-KELM model within this optimization framework, demonstrating that the WCA-KELM model predicts defect values with enhanced precision. Finally, the MOSOA was utilized to identify the pareto optimal frontier, from which the optimal solution was pinpointed through grey relational evaluation. According to the results, the warpage and volume shrinkage are 0.9388 mm and 8.538 %, respectively, which are effectively reduced by 41.73 % and 18.37 % compared with before optimization, indicating the efficacy and reliability of the proposed optimization methodology.
- 8 July 2025
- Published by Walter de Gruyter GmbH in Journal of Polymer Engineering
- Vol. 45 (8) , 710-721
Based on WCA-KELM and MOSOA: optimization of injection molding quality for plastic alloy products
For PC/ABS plastic alloy injection-molded products, warping and volumetric shrinkage are two prevalent quality defects attributed to the injection molding process. To mitigate these defects to the greatest extent, this study introduces an optimized injection molding process parameter scheme based on the water cycle algorithm enhanced kernel extreme learning machine (WCA-KELM), the multi-objective seagull optimization algorithm (MOSOA), and grey relational evaluation. Firstly, all experimental data were derived from orthogonal experimental designs conducted via Moldflow software, focusing on seven factors, such as melt temperature, mold temperature, packing pressure, and packing time. Warpage and volume shrinkage results were obtained in each set of experiments. Secondly, the predictive accuracy of the unoptimized kernel extreme learning machine (KELM) model was compared against that of the WCA-KELM model within this optimization framework, demonstrating that the WCA-KELM model predicts defect values with enhanced precision. Finally, the MOSOA was utilized to identify the pareto optimal frontier, from which the optimal solution was pinpointed through grey relational evaluation. According to the results, the warpage and volume shrinkage are 0.9388 mm and 8.538 %, respectively, which are effectively reduced by 41.73 % and 18.37 % compared with before optimization, indicating the efficacy and reliability of the proposed optimization methodology.
- 5 March 2025
- Published by Springer Nature in International Journal of Precision Engineering and Manufacturing
- Vol. 26 (6) , 1469-1479
Optimization of Glass Fiber Reinforced Injection Molded Product Quality Based on the ILSO-RF Model and MSINSWOA
- 5 March 2025
- Published by Springer Nature in International Journal of Precision Engineering and Manufacturing
- Vol. 26 (6) , 1469-1479
Optimization of Glass Fiber Reinforced Injection Molded Product Quality Based on the ILSO-RF Model and MSINSWOA
- 5 October 2024
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 38 (10) , 5639-5647
Control of quality defects of the glass fiber injection molded product based on LSO-RF and NSWOA
- 5 October 2024
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 38 (10) , 5639-5647
Control of quality defects of the glass fiber injection molded product based on LSO-RF and NSWOA
- 3 April 2024
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering
- Vol. 239 (5) , 2590-2600
Multiobjective optimization of laser welding parameters for P92 steel based on MFO/MOEAD-Kriging
P92 steel is used in steam equipment of thermal power plants and nuclear power plants. It needs to withstand high temperature and high pressure during service, so high-quality welds are required. Laser welding can easily obtain good weld quality and reduce the probability of coarse grains and welding defects in the heat-affected zone. Post-weld deformation, residual stress, and weld hardness are important indexes for evaluating weld quality, which largely depends on the combination of laser welding process parameters. The multiobjective optimization methods of moth-flame optimization (MFO) and multiobjective evolutionary algorithm based on decomposition under the Kriging model were compared in this research. It was found that the MFO algorithm has a faster optimization speed and better overall effect. The Optimal Latin hypercube sampling method was used to design the simulation test. The welding seam-forming process was simulated by the SYSWELD software. The Kriging model was used to make the nonlinear relationship between the process parameters and the weld quality indexes significant. A new data set was designed to evaluate the accuracy of the model. On this basis, the efficiency of the combination of process parameters optimized by the two algorithms was compared. The simulation and experimental results were in good agreement with the multiobjective optimization results of the MFO. In the experimental verification, the optimized weld quality was analyzed from the aspects of microstructure and mechanical properties. The results showed that the multiobjective optimization method quickly and effectively reduces the probability of weld quality defects in actual welding, thereby improving weld quality. This multiobjective optimization method provides valuable research ideas for engineering research and development to effectively shorten its development cycle.
- 3 April 2024
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part E: Journal of Process Mechanical Engineering
- Vol. 239 (5) , 2590-2600
Multiobjective optimization of laser welding parameters for P92 steel based on MFO/MOEAD-Kriging
P92 steel is used in steam equipment of thermal power plants and nuclear power plants. It needs to withstand high temperature and high pressure during service, so high-quality welds are required. Laser welding can easily obtain good weld quality and reduce the probability of coarse grains and welding defects in the heat-affected zone. Post-weld deformation, residual stress, and weld hardness are important indexes for evaluating weld quality, which largely depends on the combination of laser welding process parameters. The multiobjective optimization methods of moth-flame optimization (MFO) and multiobjective evolutionary algorithm based on decomposition under the Kriging model were compared in this research. It was found that the MFO algorithm has a faster optimization speed and better overall effect. The Optimal Latin hypercube sampling method was used to design the simulation test. The welding seam-forming process was simulated by the SYSWELD software. The Kriging model was used to make the nonlinear relationship between the process parameters and the weld quality indexes significant. A new data set was designed to evaluate the accuracy of the model. On this basis, the efficiency of the combination of process parameters optimized by the two algorithms was compared. The simulation and experimental results were in good agreement with the multiobjective optimization results of the MFO. In the experimental verification, the optimized weld quality was analyzed from the aspects of microstructure and mechanical properties. The results showed that the multiobjective optimization method quickly and effectively reduces the probability of weld quality defects in actual welding, thereby improving weld quality. This multiobjective optimization method provides valuable research ideas for engineering research and development to effectively shorten its development cycle.
- 6 February 2024
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 38 (2) , 861-871
Multi-objective optimization of laser welding process parameters of steel/Al based on BO-RF and MOJS
- 6 February 2024
- Published by Springer Nature in Journal of Mechanical Science and Technology
- Vol. 38 (2) , 861-871
Multi-objective optimization of laser welding process parameters of steel/Al based on BO-RF and MOJS