摘要
金青醇沉是热毒宁注射液关键工艺单元之一,具有工艺参数多样、过程机制复杂的特点。为辨识影响金青醇沉过程的关键工艺参数,该文以热毒宁注射液数字化工厂为基础,采集热毒宁注射液金青醇沉工段2017—2018年的历史生产数据259批,共计829318数据点,呈现出数据量大、价值密度低、来源多样等大数据部分特征。以金青醇沉浓缩制得浸膏质量为响应变量,通过数据清洗和特征提取,数据点减少为9936个。采用Pearson相关分析和灰色关联度分析进行综合决策,从48个特征变量中筛选出15个潜在关键工艺参数(pCPPs)。进一步通过偏最小二乘(PLS)回归进行定量预测建模,证明基于15个pCPPs建立的预测模型与基于48个特征变量的建立的预测模型性能相当。通过变量重要性排序,辨识出影响金青醇沉浓缩浸膏质量的9个关键工艺参数(CPPs),包括4个初始输入浸膏质量参数、3个加醇量参数和2个醇沉上清液体积参数,至此数据点为1863个,占原始数据的0.28%。从全局数据出发,采用大数据分析的方法可有效提高数据的价值密度,筛选得到的关键工艺参数有助于解析金青醇沉生产过程质量传递规律。
Lonicerae Japonicae Flos and Artemisiae Annuae Herba(LA or Jinqing)alcohol precipitation has various process parameters and complex process mechanism,and is one of the key units for manufacturing Reduning Injection.In order to identify the critical process parameters(CPPs)affecting the weight of the extract produced from the alcohol precipitation process,259 batches of historical production data from 2017 to 2018 were collected,with a total of 829318 data points.These data showed characteristics of large data,such as a large data volume,a low value density,and diverse sources.The data cleaning and feature extraction were first performed,and 48 feature variables were selected.The original data points were reduced to 9936.Then,a combination of Pearson correlation analysis and grey correlation analysis were used to screen out 15 potential critical process parameters(pCPPs).After that,the partial least squares(PLS)was used in prediction of the weight of the extract,proving that the performance of predictive model based on 15 pCMAs is equivalent to that of predictive model based on 48 feature variables.The variable importance in projection(VIP)index was used to identify 9 CPPs,including 2 alcohol precipitation supernatant volume parameters,4 initial extract weight parameters and 3 added alcohol volume parameters.As a result,the number of data points was 1863,accounting for 0.28%of the original data.The big data analysis approach from a holistic point of view can effectively increase the value density of the original data.The critical process parameters obtained can help to accurately describe the quality transfer mechanism of the Jinqing alcohol precipitation process.
作者
杜慧
徐冰
徐芳芳
张欣
王晴
夏春燕
包乐伟
王振中
乔延江
肖伟
DU Hui;XU Bing;XU Fang-fang;ZHANG Xin;WANG Qing;XIA Chun-yan;BAO Le-wei;WANG Zhen-zhong;QIAO Yan-jiang;XIAO Wei(Nanjing University of Chinese Medicine,Nanjing 210023,China;Department of Chinese Medicine Information Science,Beijing University of Chinese Medicine,Beijing 102400,China;Jangsu Kanion Pharmaceutical Co.,Ltd.,Lianyungang 222001,China;State Key Laboratory of New-tech for Chinese Medicine Pharmaceutical Process,Lianyungang 222001,China;National&Local Joint Engineering Research Center on Intelligent Manufacturing of Traditional Chinese Medicine,Lianyungang 222001,China;Key Laboratory of New Technology for Extraction and Refining of Traditional Chinese Medicine,Lianyungang 222001,China)
出处
《中国中药杂志》
CAS
CSCD
北大核心
2020年第2期233-241,共9页
China Journal of Chinese Materia Medica
基金
国家“重大新药创新”科技重大专项(2018ZX09201010)
国家工信部智能制造综合标准化与新模式应用项目(KYYY20170820).
关键词
金青醇沉
热毒宁注射液
大数据
关键工艺参数
质量传递规律
Jinqing alcohol precipitation
Reduning Injection
big data
critical process parameter
quality transfer mechanism
作者简介
杜慧,硕士研究生,E-mail:2943586584@qq.com;通信作者:肖伟,博士,研究员级高级工程师,博士生导师,研究方向为中药新药的研究与开发,Tel:(0518)81152367,E-mail:kanionlunwen@163.com;通信作者:徐冰,副教授,硕士生导师,研究方向为中药质量和先进工艺控制,E-mail:xubing@bucm.edu.cn
