摘要
为解决传统实验方法测量二元混合液体自燃温度所面临的时间和安全问题,本文提出了一种运用神经网络优化定量结构-性质关系(QSPR)预测模型的方法。首先,分别使用BP神经网络(BPNN)和一维卷积神经网络(1DCNN)处理混合分子描述符数据。然后,采用卷积神经网络(CNN)处理分子结构图数据,以此建立BPNN+CNN和1DCNN+CNN两种预测模型。通过交叉验证、残差分析和应用域分析等多种方法对两种模型的预测能力、拟合能力和稳定性进行了验证。最后,讨论了4种优化器和不同维度的分子结构图对模型性能的影响。通过实验可知,两种模型的决定系数分别为0.989 8和0.987 1;10折交叉验证复相关系数分别为0.961 1和0.963 3;交互验证系数分别为0.982 6和0.992 5。结果表明,两种模型均可对大多数二元混合液体自燃温度进行预测,其中,BPNN+CNN模型有较好的拟合能力,1DCNN+CNN模型有较好的稳定性。
To solve the time and safety problems faced by the traditional experimental methods for measur‐ing the auto-ignition temperature of binary mixed liquids,a method optimizing the quantitative structure-property relationship(QSPR)prediction model by using neural networks is proposed.BP neural network(BPNN)and the one-dimensional convolutional neural network(1DCNN)are used to process the mixed molecular descriptor data,respectively.Then,the molecular structure map data is processed using the convolutional neural network(CNN),and in this way,two prediction models,BPNN+CNN and IDCNN+CNN,are established.After that,the prediction ability,fitting ability and stability of the experimentally designed BPNN+CNN and 1DCNN+CNN models are verified through cross-validation,residual analysis and application domain analysis.Finally,the effects of different optimizers on the model performance are discussed.And the results of two-dimensional and three-dimensional molecular structure diagrams on the model performance are analyzed.The experimental results show that the coefficients of determination of the two models are 0.9898 and 0.9871,respectively.The 10-fold cross-validated com‐plex correlation coefficients are 0.9611 and 0.9633,respectively.And the cross-validated coefficients are 0.9826 and 0.9925,respectively.The results indicate that both models can predict the self-ignition temperature of most binary mixed liquids.The BPNN+CNN model has better fitting ability,and the 1DCNN+CNN model has better stability.
作者
程泽会
杨剑
郭丙宇
张泽宇
CHENG Zehui;YANG Jian;GUO Bingyu;ZHANG Zeyu(School of Software,North University of China,Taiyuan 030051,China;School of Environment and Safety Engineering,North University of China,Taiyuan 030051,China)
出处
《中北大学学报（自然科学版）》
CAS
2024年第1期90-97,共8页
Journal of North University of China(Natural Science Edition)
关键词
二元混合液体
自燃温度
神经网络
QSPR
分子描述符
binary mixed liquids
auto-ignition temperature
neural networks
QSPR
molecular descriptor
