近红外光谱和极限学习机分析反硝化除磷中胞内聚合物

发布时间：2018-07-03 09:32

本文选题：反硝化除磷 + 聚-β-羟基丁酸酯　；参考：《中国环境科学》2017年05期

【摘要】：为利用近红外光谱技术同时实现反硝化除磷工艺中胞内聚-β-羟基丁酸酯(PHB)、多聚磷酸盐(Poly-P)、糖原(Gly)含量的快速分析,采用多元散射校正预处理法和极限学习机算法建立PHB、Poly-P、Gly含量分析的校正模型(ELM模型).结果表明:多元散射校正预处理法可以有效消除散射对原始近红外光谱数据的影响.采用极限学习机算法对预处理后的光谱数据建立PHB、Poly-P、Gly的定量分析模型,优选出的PHB、Poly-P、Gly的ELM模型主成分数分别为6、6、7,隐含层节点数分别为18、12、17.模型对PHB、Poly-P、Gly含量的校正相关系数(rc)分别为0.9835、0.9499、0.9589,校正均方根误差(RMSECV)分别为0.0541、0.0579、0.0489.模型对PHB、Poly-P、Gly含量的预测相关系数(rp)分别为0.9683、0.9288、0.9488,预测均方根误差(RMSEP)分别为0.0668、0.0776、0.0501,模型对PHB、Poly-P、Gly含量有较好的预测效果.用近红外光谱技术结合极限学习机算法建立ELM模型为反硝化除磷工艺中PHB、Poly-P、Gly的同时快速定量分析提供了较为简便的方法.
[Abstract]:In order to realize the rapid analysis of the contents of poly- 尾 -hydroxybutyrate (PHB), polyphosphate (Poly-P) and glycogen (gly) in denitrifying phosphorus removal process by near infrared spectroscopy (NIR). A correction model (ELM model) for the analysis of Poly-Py gly content in PHBs is established by using multivariate scattering correction preprocessing method and extreme learning machine algorithm. The results show that the multivariate scattering correction preprocessing method can effectively eliminate the influence of scattering on the original near infrared spectral data. The quantitative analysis model of PHBP Poly-Py gly was established by using the extreme learning machine algorithm. The main scores of the ELM model of PHBP Poly-PU gly were 6 / 6 / 7, respectively, and the number of hidden layer nodes were 18 / 1212 / 17, respectively. The calibration correlation coefficient (rc) of the model for the content of Poly-Pu gly in the model is 0.9835 ~ 0.949 9 ~ 0.958 9, respectively, and the corrected root mean square error (RMSECV) is 0.0541 ~ 0.0579 ~ 0.0489. The predicted correlation coefficient (rp) and root mean square error (RMSEP) of the model for the content of Poly-Pu gly were 0.9683 / 0.92880.488and 0.0668 / 0.0776/ 0.0501, respectively. The ELM model established by Near-Infrared Spectroscopy (NIR) combined with extreme Learning Machine (LLM) algorithm provides a simple and convenient method for the simultaneous rapid quantitative analysis of PHBH Poly-Pu gly in denitrifying phosphorus removal process.
【作者单位】：安徽建筑大学环境与能源工程学院;水污染控制与废水资源化安徽省重点实验室;
【基金】：安徽省高校优秀青年骨干人才国内外访学研修项目(gxfx2017054) 安徽省高校优秀青年人才支持计划重点项目(gxyq ZD2017059) 安徽省高校自然科学研究重点项目(KJ2016A817) 国家“水体污染控制与治理”科技重大专项(2014ZX07405-003-03)
【分类号】：X703

【相似文献】