Particle Swarm Optimization–Long Short-Term Memory-Based Dynamic Prediction Model of Single-Crystal Furnace Temperature and Heating Power
Open Access
Abstract
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.Keywords
Funding Information
- Qinghai Province Science and Technology Department Project (2023-GX-C03, 2023YG02, 2022-Z-03, 2021-Y-01)
- Science and Technology Department of Yibin Project (2023-GX-C03, 2023YG02, 2022-Z-03, 2021-Y-01)
- Major Science and Technology Projects of the Xining Science and Technology Bureau (2023-GX-C03, 2023YG02, 2022-Z-03, 2021-Y-01)
This publication has 31 references indexed in Scilit:
- PSO–LSTM–Markov Coupled Photovoltaic Power Prediction Based on Sunny, Cloudy and Rainy WeatherJournal of Electrical Engineering & Technology, 2024
- Crystal surface heat transfer during the growth of 300mm monocrystalline silicon by the Czochralski processInternational Journal of Heat and Mass Transfer, 2024
- Numerical study of continuous Czochralski (CCz) silicon single crystal growth in a double-side heaterJournal of Crystal Growth, 2023
- Development and validation of a thermal simulation for the Czochralski crystal growth process using model experimentsJournal of Crystal Growth, 2022
- Physically-based, lumped-parameter models for the prediction of oxygen concentration during Czochralski growth of silicon crystalsJournal of Crystal Growth, 2021
- A method for state-of-charge estimation of lithium-ion batteries based on PSO-LSTMEnergy, 2021
- PSO–LSTM for short term forecast of heterogeneous time series electricity price signalsJournal of Ambient Intelligence and Humanized Computing, 2020
- LSTM based long-term energy consumption prediction with periodicityEnergy, 2020
- Particle swarm optimization algorithm: an overviewSoft Computing, 2017
- Global simulation of the Czochralski silicon crystal growth in ANSYS FLUENTJournal of Crystal Growth, 2013