摘要
This study addresses the challenge of real-time resistivity gradient measurement in the Czochralski(CZ)silicon production process.Due to the inability to directly measure this parameter,we propose a Long Short-Term Memory soft-sensing model based on Convolutional Neural Network(CNN)and attention mechanism(CNN-ALSTM)that enhances traditional LSTM by integrating CNN and attention mechanism to overcome time lag variations during silicon pulling.The CNN module extracts spatial features from multi-source sensor data,while the attention-enhanced LSTM(ALSTM)dynamically adjusts historical parameter weights,enabling accurate resistivity gradient prediction.Experiments with real production data show that CNN-ALSTM outperforms SVR,FNN,RNN,XGBoost,and GRU,improving prediction accuracy by 11.76%,16.67%,21.05%,30.23%,and 9.09%,respectively.This soft-sensing approach enhances real-time monitoring and optimization of monocrystalline silicon growth.
