Shan Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Shan Wang has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Dedong Gao
Qinghai university
6 shared publications Dedong Gao
Qinghai university
3 shared publicationsZuxing Qi
Qinghai university
3 shared publicationsGuoying Bao
Qinghai university
2 shared publications- Haixing Lin
Department of Mechanical Engineering, Qinghai University, Xining 810016, China
2 shared publications Haohao Wu
Qinghai Univ, Sch Mech Engn, Xining 810016, Qinghai, Peoples R China
2 shared publications
Latest Publications
- Open Access
Particle Swarm Optimization–Long Short-Term Memory-Based Dynamic Prediction Model of Single-Crystal Furnace Temperature and Heating Power
Precise temperature and heating power control are crucial for crystal quality and production efficiency in the Czochralski single-crystal growth process. Existing sensor technologies can only monitor these parameters in real time, lacking the ability to predict future trends, which limits the ability to implement preventive control before issues arise. To address this, a temperature and heating power prediction model based on Long Short-Term Memory (LSTM) is proposed and developed using extensive production data. Spearman’s rank correlation coefficient is applied to identify the key parameters related to temperature and heating power. Hyperparameter optimization uses Particle Swarm Optimization (PSO) to improve prediction accuracy. The performance of the PSO-LSTM model is compared with two other widely used prediction models, demonstrating its superior predictive capability. The results show that the PSO-LSTM model achieves highly accurate temperature and heating power predictions in the crystal growth process, with a Mean Absolute Error (MAE) of 0.0295 for temperature and 0.0392 for heating power, further validating its effectiveness for real-time predictive control.
Open AccessParticle Swarm Optimization–Long Short-Term Memory-Based Dynamic Prediction Model of Single-Crystal Furnace Temperature and Heating Power
Precise temperature and heating power control are crucial for crystal quality and production efficiency in the Czochralski single-crystal growth process. Existing sensor technologies can only monitor these parameters in real time, lacking the ability to predict future trends, which limits the ability to implement preventive control before issues arise. To address this, a temperature and heating power prediction model based on Long Short-Term Memory (LSTM) is proposed and developed using extensive production data. Spearman’s rank correlation coefficient is applied to identify the key parameters related to temperature and heating power. Hyperparameter optimization uses Particle Swarm Optimization (PSO) to improve prediction accuracy. The performance of the PSO-LSTM model is compared with two other widely used prediction models, demonstrating its superior predictive capability. The results show that the PSO-LSTM model achieves highly accurate temperature and heating power predictions in the crystal growth process, with a Mean Absolute Error (MAE) of 0.0295 for temperature and 0.0392 for heating power, further validating its effectiveness for real-time predictive control.
- Open Access
- 1 January 2025
- Published by AIP Publishing in AIP Advances
- Vol. 15 (1)
Simulation of oxygen and carbon impurity transport during magnetically controlled Czochralski silicon growth
This study establishes a multi-field coupling model that includes a thermal field, flow field, oxygen and carbon impurity concentration field, and magnetic field, focusing on controlling the transport of oxygen impurities at the free surface of the melt. The effects of cusp magnetic field introduction, argon inlet flow velocity, and furnace pressure on the transport of oxygen and carbon impurities are analyzed, and the concentration field distribution of oxygen and carbon impurities within the furnace at the equal-diameter stage (300 mm) under different parameters is obtained. The results show that the method combining the cusp magnetic field with adjustments in furnace pressure and argon flow velocity can significantly reduce the oxygen concentration in the melt below the crystal and effectively expel oxygen and carbon impurities, providing optimization references for applying cusp magnetic fields and reducing oxygen and carbon impurities in the melt for large-sized Czochralski single-crystal silicon.
- 1 January 2025
- Published by AIP Publishing in AIP Advances
- Vol. 15 (1)
Open AccessSimulation of oxygen and carbon impurity transport during magnetically controlled Czochralski silicon growth
This study establishes a multi-field coupling model that includes a thermal field, flow field, oxygen and carbon impurity concentration field, and magnetic field, focusing on controlling the transport of oxygen impurities at the free surface of the melt. The effects of cusp magnetic field introduction, argon inlet flow velocity, and furnace pressure on the transport of oxygen and carbon impurities are analyzed, and the concentration field distribution of oxygen and carbon impurities within the furnace at the equal-diameter stage (300 mm) under different parameters is obtained. The results show that the method combining the cusp magnetic field with adjustments in furnace pressure and argon flow velocity can significantly reduce the oxygen concentration in the melt below the crystal and effectively expel oxygen and carbon impurities, providing optimization references for applying cusp magnetic fields and reducing oxygen and carbon impurities in the melt for large-sized Czochralski single-crystal silicon.
- 6 December 2024
- Published by Elsevier in Solar Energy
- Vol. 286
A novel ion exchange method for recover silver and aluminum from waste crystalline silicon photovoltaic modules
- 6 December 2024
- Published by Elsevier in Solar Energy
- Vol. 286
A novel ion exchange method for recover silver and aluminum from waste crystalline silicon photovoltaic modules
- Open Access
Antioxidant Behavior of Carbon/Carbon Composites with Hot Dip Plating and Electroplating for Single-Crystal Furnaces
In the Czochralski single-crystal silicon manufacturing industry, single-crystal furnaces often experience corrosion from silicon vapor, which reduces their operational lifespan. However, the preparation of metal coatings on the surface of C/C composites is challenging due to their low coefficient of thermal expansion and the intricate structure of carbon fibers. To address this issue and achieve high-quality alloy coatings, Ni-Al and Ni-Al/Si composite coatings are successfully prepared on the surface of C/C composites through a combination of electroplating and hot-dip plating, and their oxidation behavior at elevated temperatures is thoroughly investigated. The experimental results indicate that the Ni-Al composite coatings exhibit superior antioxidant properties compared to Ni coatings following thermal shock experiments, thereby significantly enhancing the antioxidant performance of C/C composites. This improvement is attributed to the preferential oxidation of surface aluminum, which forms a dense Al2O3 layer in aerobic and high-temperature environments, effectively preventing oxygen from reaching the underlying matrix. During the oxidation process, coating elements migrate outward along the concentration gradient, while oxygen molecules diffuse inward. Simultaneously, aluminum atoms diffuse inward, and Ni atoms diffuse outward, where they partially dissolve with oxygen. The inner coating’s Ni enhances the bonding of the coating by connecting the substrate to the outer layer. Meanwhile, the added Si in the Ni-Al/Si composite coating further improves the antioxidant properties of the coating.
Open AccessAntioxidant Behavior of Carbon/Carbon Composites with Hot Dip Plating and Electroplating for Single-Crystal Furnaces
In the Czochralski single-crystal silicon manufacturing industry, single-crystal furnaces often experience corrosion from silicon vapor, which reduces their operational lifespan. However, the preparation of metal coatings on the surface of C/C composites is challenging due to their low coefficient of thermal expansion and the intricate structure of carbon fibers. To address this issue and achieve high-quality alloy coatings, Ni-Al and Ni-Al/Si composite coatings are successfully prepared on the surface of C/C composites through a combination of electroplating and hot-dip plating, and their oxidation behavior at elevated temperatures is thoroughly investigated. The experimental results indicate that the Ni-Al composite coatings exhibit superior antioxidant properties compared to Ni coatings following thermal shock experiments, thereby significantly enhancing the antioxidant performance of C/C composites. This improvement is attributed to the preferential oxidation of surface aluminum, which forms a dense Al2O3 layer in aerobic and high-temperature environments, effectively preventing oxygen from reaching the underlying matrix. During the oxidation process, coating elements migrate outward along the concentration gradient, while oxygen molecules diffuse inward. Simultaneously, aluminum atoms diffuse inward, and Ni atoms diffuse outward, where they partially dissolve with oxygen. The inner coating’s Ni enhances the bonding of the coating by connecting the substrate to the outer layer. Meanwhile, the added Si in the Ni-Al/Si composite coating further improves the antioxidant properties of the coating.
- 5 November 2023
- Published by Elsevier in Waste Management
- Vol. 172, 299-307
A novel method for layer separation in waste crystalline silicon PV modules via combined low-temperature and thermal treatment
- 5 November 2023
- Published by Elsevier in Waste Management
- Vol. 172, 299-307
A novel method for layer separation in waste crystalline silicon PV modules via combined low-temperature and thermal treatment
- Open Access
- 9 September 2023
- Published by Elsevier in Results in Physics
- Vol. 53
Design of follow-up superconducting Cusp magnetic field and system performance analysis of Czochralski single crystal furnace
- 9 September 2023
- Published by Elsevier in Results in Physics
- Vol. 53
Open AccessDesign of follow-up superconducting Cusp magnetic field and system performance analysis of Czochralski single crystal furnace
- Open Access
- 7 July 2023
- Published by Elsevier in Results in Physics
- Vol. 51
Design and optimization of superconducting CUSP electromagnetic field structure based on a COMSOL-GMDH-MOSO hybrid strategy
- 7 July 2023
- Published by Elsevier in Results in Physics
- Vol. 51
Open AccessDesign and optimization of superconducting CUSP electromagnetic field structure based on a COMSOL-GMDH-MOSO hybrid strategy
- 29 September 2019
- Published by Taylor & Francis in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects
- Vol. 45 (2) , 5380-5395
Fault diagnosis method of photovoltaic array based on support vector machine
Photovoltaic (PV) arrays are prone to various faults due to the hostile working environment. This paper presents the fault diagnosis algorithm based on support vector machine (SVM) to detect short circuit, open circuit, and lack of irradiation faults that occurred in PV arrays. By analyzing these faults and I–V characteristic curves of PV arrays, the short-circuit current, open-circuit voltage, maximum-power current, and maximum-power voltage are chosen as input parameters of SVM-based fault diagnosis algorithm. The data preprocessing methods are used to improve the quality of fault data set considering the effects of the quality on the performance of SVM-based fault diagnosis algorithm. The grid search and k-fold cross-validation methods are proposed to optimize the parameters of the SVM-based fault diagnosis algorithm. It gets test accuracy of 97% by testing the trained SVM-based fault diagnosis algorithm with 400 data. The experimental results indicate that the SVM-based fault diagnosis algorithm has higher accuracy and generalization ability than other algorithm for fault diagnosis of PV arrays.
- 29 September 2019
- Published by Taylor & Francis in Energy Sources, Part A: Recovery, Utilization, and Environmental Effects
- Vol. 45 (2) , 5380-5395
Fault diagnosis method of photovoltaic array based on support vector machine
Photovoltaic (PV) arrays are prone to various faults due to the hostile working environment. This paper presents the fault diagnosis algorithm based on support vector machine (SVM) to detect short circuit, open circuit, and lack of irradiation faults that occurred in PV arrays. By analyzing these faults and I–V characteristic curves of PV arrays, the short-circuit current, open-circuit voltage, maximum-power current, and maximum-power voltage are chosen as input parameters of SVM-based fault diagnosis algorithm. The data preprocessing methods are used to improve the quality of fault data set considering the effects of the quality on the performance of SVM-based fault diagnosis algorithm. The grid search and k-fold cross-validation methods are proposed to optimize the parameters of the SVM-based fault diagnosis algorithm. It gets test accuracy of 97% by testing the trained SVM-based fault diagnosis algorithm with 400 data. The experimental results indicate that the SVM-based fault diagnosis algorithm has higher accuracy and generalization ability than other algorithm for fault diagnosis of PV arrays.