基于引力搜索算法的造纸过程模型辨识  

Model Identification of Papermaking Process Based on Gravitational Search Algorithm

作　　者：李政 李俊红[1] 顾菊平[1] 华亮[1] LI Zheng;LI Jun-hong;GU Ju-ping;HUA Liang(School of Electrical Engineering,Nantong University,Nantong 226019,China)

机构地区：[1]南通大学电气工程学院,江苏南通226019

出　　处：《控制工程》2022年第11期1974-1980,共7页Control Engineering of China

基　　金：国家自然科学基金资助项目(61973176,61973178);江苏省高校自然科学研究项目(19KJA350002);江苏省六大人才高峰项目(XYDXX-038);智能电网联合基金重点项目(U2066203);南通市社会民生科技重点项目(MS22021032)。

摘　　要：造纸过程是一个多输入多输出的过程,造纸过程的模型辨识具有重要的研究意义。建立了造纸过程的多输入多输出模型,采用引力搜索算法(GSA)对造纸过程的模型进行参数辨识,并将预测模型的预测输出与实际模型的输出作对比。同时,论文使用广义增广随机梯度算法(GESG)对该造纸过程的模型进行辨识,并将两种算法的辨识效果进行对比。结果表明,GSA在造纸过程的辨识方面具有较高的辨识精度,预测模型的输出与系统输出较为吻合。相比于GESG算法,GSA具有收敛速度快、辨识精度高等优点。在不同的噪声方差影响下,GSA也能取得较好的辨识效果。该算法对造纸过程的参数辨识具有一定的可行性。The papermaking process is a multiple-input and multiple-output process, and the model identification of the papermaking process is of great significance. In this paper, a multiple-input and multiple-output model of the papermaking process is established, and the parameters of the model are identified by gravitational search algorithm(GSA), and the predicted output of the prediction model is compared with the real output of the actual model. At the same time, generalized extended stochastic gradient(GESG) algorithm is used to identify the papermaking process model, and the identification effects of the two algorithms are compared in this paper. The results show that GSA has high identification accuracy in the identification of the papermaking process, and the output of the prediction model is consistent with the system output. Compared with GESG algorithm, GSA has the advantages of fast convergence speed and high identification accuracy.Under the influence of different noise variances, GSA can still achieve good identification results. The algorithm has certain feasibility for the parameter identification of the papermaking process.

关 键 词：造纸过程 多输入多输出 系统辨识 参数估计 引力搜索算法 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]