A method and system for predicting the nitrogen content of nitrocellulose based on machine learning
By constructing a machine learning-based nitrogen content prediction system for nitrocellulose, the problems of low accuracy and poor scenario adaptability in existing technologies have been solved, achieving high-precision and convenient prediction of nitrogen content in nitrocellulose, which meets the production requirements of the military and aerospace fields.
CN122415004APending Publication Date: 2026-07-17HARBIN INST OF TECH
View PDF 0 Cites 0 Cited by
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- HARBIN INST OF TECH
- Filing Date
- 2026-04-02
- Publication Date
- 2026-07-17
Smart Images
Figure CN122415004A_ABST
Abstract
本发明公开了一种基于机器学习的硝化棉含氮量预测方法及系统。本发明采集硝化棉合成过程中的硝酸量、硫酸量、反应温度、反应时间和水量五项工艺参数及对应的含氮量数据，构建原始数据集；对原始数据集进行数据清洗、缺失值处理及标准化处理，采用数据迁移技术构建工业‑实验室双模式数据集，并按比例划分为训练集与测试集。基于双模式数据集，采用XGBoost、GBDT、LR、SVM、BPNN、RF、BP七种机器学习算法进行模型训练，通过网格搜索与贝叶斯优化进行超参数调优，以MAE、MSE、RMSE、R²为评估指标筛选得到最优预测模型。将最优预测模型封装为桌面端应用程序及微信小程序，用于向用户提供硝化棉含氮量预测服务。
Need to check novelty before this filing date? Find Prior Art