【摘要】 萤石作为一种重要的工业矿物，其品质主要由其中氟化钙的含量决定。为了有效评估和预测萤石中的氟化钙含量，提出一种基于自适应噪声完全集合经验模态分解（CEEMDAN）和卷积神经网络（CNN）以及双向长短期记忆神经网络（BiLSTM）相结合的深度学习算法用于萤石中氟化钙含量的预测。实验结果表明，所提方法具有较高的预测精度和稳定性，为萤石的质量评估和工业应用提供重要参考。更多还原

【Abstract】 Fluorite is an important industrial mineral,its quality is primarily determined by the content of calcium fluoride within it. To effectively assess and predict the calcium fluoride content in fluorite,a deep learning algorithm that combines CEEMDAN,CNN and BiLSTM networks is proposed. Experimental results indicate that the proposed method achieves high prediction accuracy and stability, providing significant references for the quality assessment and industrial application of fluorite.更多还原