基于VMD与改进麻雀算法优化LSSVM的多晶硅生产能耗预测

赵铁成; 谢丽蓉; 范协诚; 王智勇; 邓佑刚; 李朋; 叶金鑫

doi:10.13568/j.cnki.651094.651316.2021.08.05.0001

您当前的位置：

首页 >

文章列表页 >

基于VMD与改进麻雀算法优化LSSVM的多晶硅生产能耗预测

工程技术 | 更新时间：2026-01-21

- 基于VMD与改进麻雀算法优化LSSVM的多晶硅生产能耗预测
- 基于VMD与改进麻雀算法优化LSSVM的多晶硅生产能耗预测
- 新疆大学学报（自然科学版中英文） 2022年39卷第4期页码：498-507
- 作者机构：
  
  1. 新疆大学电气工程学院
  2. 新特能源股份有限公司
  3. 新疆燚加华工业科技有限公司
- 作者简介：
- 基金信息：
  
  国家自然科学基金（62163034）
- DOI：10.13568/j.cnki.651094.651316.2021.08.05.0001
  中图分类号： TQ127.2;TP18
- 纸质出版：2022
- 稿件说明：
移动端阅览
[1]赵铁成,谢丽蓉,范协诚,等.基于VMD与改进麻雀算法优化LSSVM的多晶硅生产能耗预测[J].新疆大学学报(自然科学版)(中英文),2022,39(04):498-507.
[1]赵铁成,谢丽蓉,范协诚,等.基于VMD与改进麻雀算法优化LSSVM的多晶硅生产能耗预测[J].新疆大学学报(自然科学版)(中英文),2022,39(04):498-507. DOI： 10.13568/j.cnki.651094.651316.2021.08.05.0001.

DOI：10.13568/j.cnki.651094.651316.2021.08.05.0001.

摘要

针对多晶硅还原生产能耗预测精度较低问题，提出了基于VMD-ASSA-LSSVM模型的多晶硅生产能耗预测方法．首先，采用主成分分析方法对能耗影响因素的数据降维处理，提高模型执行效率．利用变分模态分解（Variational Mode Decomposition

VMD）将能耗序列分解为不同特征尺度能耗分量，降低能耗序列的非平稳性、复杂度．其次，为解决麻雀搜索算法（Sparrow Search Algorithm

SSA）的收敛慢与收敛精度低问题，引入适应性学习因子进行改进．结合改进的自适应麻雀搜索算法寻优最小二乘支持向量机的可调参数，建立了VMD-ASSA-LSSVM的能耗预测组合模型；然后对分解的能耗分量单独预测，叠加子序列预测结果即为最终能耗预测．最后，以某多晶硅企业实际生产数据验证该方法的有效性，证实提高了预测精度．

Abstract

Aiming at the low prediction accuracy of polysilicon reduction production energy consumption

a polysilicon production energy consumption prediction method based on VMD-ASSA-LSSVM model is proposed.Firstly

principal component analysis is used to reduce the dimension of the data of energy consumption influencing factors to improve the execution efficiency of the model. The energy consumption series is decomposed into energy consumption components with different characteristic scales by using variational mode decomposition(VMD)

which reduces the complexity of energy consumption series. Secondly

to solve the problems of slow convergence and low convergence accuracy of sparrow search algorithm(SSA)

adaptive learning factor is introduced to improve it. Combined with the improved adaptive sparrow search algorithm to optimize the adjustable parameters of least squares support vector machine

a combined energy consumption prediction model of VMD-ASSA-LSSVM is established; Then

each energy consumption component is predicted separately

and the final energy consumption prediction is obtained by superimposing the prediction results of subsequence. Finally

the actual production data of a polysilicon enterprise are used to verify the effectiveness of the method and improve the prediction accuracy.

关键词

Keywords

references

江华,金艳梅,叶幸.等.中国光伏产业2019年回顾与2020年展望[J].太阳能,2020,3:14-23.

朱晨曦.基于NICA的多晶硅还原炉能耗与质量优化[D].广州:广东工业大学,2018.

NIE Z F,RAMACHANDRAN P A,HOU Y Q.Optimization of effective parameters on Siemens reactor to achieve potential maximum deposition radius:an energy consumption analysis and numerical simulation[J].International Journal of Heat and Mass Transfer,2018,117:1083-1098.

沈琛.多晶硅尾气吸附塔再生气回收工艺的节能优化及流程模拟[J].现代化工,2019,39(S1):192-194.

刘继三,姚又省.冷氢化工艺的节能优化及流程模拟[J].化学工程,2016,44(1):11-13.

韩金豆,梁世民.三氯氢硅节能精馏工艺模拟研究[J].现代化工,2019,39(7):207-210.

杨金祥,石爽,姜大川,等.多晶硅定向凝固过程中温度对凝固速率的影响[J].材料导报,2019,33(S1):28-32.

方文宝,周扬民,聂陟枫,等.多晶硅还原炉中硅棒的直流电加热模型[J].太阳能学报,2018,39(8):2287-2292.

夏小霞,周乃君.多晶硅还原炉内三氯氢硅氢还原过程的数值模拟[J].硅酸盐学报,2014,42(7):932-938.

郭久俊.基于LSTM-Adaboost的多晶硅生产的能耗预测[J].计算机应用与软件,2018,35(12):71-75+117.

王依宁,解大,王西田,等.基于PCA-LSTM模型的风电机网相互作用预测[J].中国电机工程学报,2019,39(14):4070-4081.

WU Q L,LIN H X.Short-term wind speed forecasting based on hybrid variational mode decomposition and least squares support vector machine optimized by bat algorithm model[J].Sustainability,2019,11(3):652-668.

梁智,孙国强,李虎成,等.基于VMD与PSO优化深度信念网络的短期负荷预测[J].电网技术,2018,42(2):598-606.

牛安敏,张宏立,王聪.基于VMD-Leaky-ESN的电力系统短期负荷多步预测方法[J].新疆大学学报(自然科学版)(中英文),2020,37(4):562-569.

XUE J,SHEN B.A novel swarm intelligence optimization approach:sparrow search algorithm[J].Systems Science&Control Engineering,2020,8(1):22-34.

LIU C,NIU P F,LI G Q,et al.A hybrid heat rate forecasting model using optimized LSSVM based on improved GSA[J].Neural Processing Letters,2017,45(1):299-318.

ZHANG J H,LIU Y.Application of complete ensemble intrinsic time-scale decomposition and least-square SVM optimized using hybrid DE and PSO to fault diagnosis of diesel engines[J].Frontiers of Information Technology&Electronic Engineering,2017,18(2):272-287.

GU X D,DENG F,GAO X,et al.An improved sensor fault diagnosis scheme based on TA-LSSVM and ECOC-SVM[J].Journal of Systems Science&Complexity,2018,31(2):372-384.

梁甜,高丙朋.生物氧化预处理过程中氧化槽温度的预测控制[J].新疆大学学报(自然科学版),2018,35(1):108-114.

张妍,韩璞,王东风,等.基于变分模态分解和LSSVM的风电场短期风速预测[J].太阳能学报,2018,39(1):194-202.

肖怀硕,李清泉,施亚林,等.灰色理论-变分模态分解和NSGA-II优化的支持向量机在变压器油中气体预测中的应用[J].中国电机工程学报,2017,37(12):3643-3653.

张英杰,许伟,汤龙波,等.基于滚动时间窗的PSO-LSSVM的通信基站能耗建模[J].湖南大学学报(自然科学版),2017,44(2):122-128.

陶凯,吴定会.基于VMD-JAYA-LSSVM的短期风电功率预测[J].控制工程,2021,28(6):1143-1149.

刘长良,武英杰,甄成刚.基于变分模态分解和模糊C均值聚类的滚动轴承故障诊断[J].中国电机工程学报,2015,35(13):3358-3365.

浏览量

450

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

暂无数据