基于IFWA-MLSSVR的海洋溶菌酶发酵过程软测量  

Soft Measurement of Marine Lysozyme Fermentation Process Based on IFWA-MLSSVR

作　　者：朱湘临[1] 王维杰 王博[1] ZHU Xiang-lin;WANG Wei-jie;WANG Bo(School of Electrical and Information Engineering,Jiangsu University,Zhenjiang 212013,China)

机构地区：[1]江苏大学电气信息工程学院,江苏镇江212013

出　　处：《软件导刊》2022年第9期63-68,共6页Software Guide

基　　金：江苏省自然科学基金项目(BK20140568,BK20151345);吉林省重大科技攻关专项(20140203005SF);江苏高校优势学科建设工程项目(PAPD);镇江市重点研发计划项目(SH2017002)。

摘　　要：为改善传统软测量模型易于陷入局部最优且精度不高等缺点,采用一种混合核函数的最小二乘支持向量机(MLSSVR)进行软测量建模,并以改进的烟花算法IFWA对其参数进行寻优,提高预测精度。以海洋溶菌酶作为研究对象,仿真结果表明,该模型相比FWA-MLSSVR和IFWA-LSSVR在均方根误差上分别减小了0.343 9和0.746 2,其中混合核函数策略可避免局部最优,IFWA参数优化策略可有效提高模型预测精度。该预测模型很好地满足了设计要求,具有较高应用价值。In order to improve the shortcomings of traditional soft-sensing models that are easy to fall into local optimality and low accuracy,a kind of MLSSVR with mixed kernel parameters is used for soft measurement modeling,and the improved Fireworks Competition Fireworks Algorithm Optimization is used to optimize its parameters.Taking Marine lysozyme as the research object,the simulation results show that compared with FWA-MLSSVR and IFWA-LSSVR,the RMS error calculation of this model is reduced by 0.3439 and 0.7462,respectively. The mixed core parameter method effectively avoids local optimization,IFWA improves the prediction accuracy of the model. The prediction model satisfies the design requirements well and has high application value.

关 键 词：海洋溶菌酶 最小二乘支持向量机 烟花算法 软测量 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]