最优加权融合SO<sub>2</sub>转化率预测模型

王宁宁

doi:10.3969/j.issn.2095-476X.2015.3/4.030

September 2015

Article Contents

WANG Ning-ning. Optimal weighted fusion SO2 conversion ratio predication model[J]. Journal of Light Industry, 2015, 30(3-4): 138-141. doi: 10.3969/j.issn.2095-476X.2015.3/4.030

Citation: WANG Ning-ning. Optimal weighted fusion SO2 conversion ratio predication model[J]. Journal of Light Industry, 2015, 30(3-4): 138-141. doi: 10.3969/j.issn.2095-476X.2015.3/4.030 shu

Optimal weighted fusion SO₂ conversion ratio predication model

WANG Ning-ning

Party Committee Office, Aba Teachers University, Wenchuan 623002, China

Received Date: 2014-12-03
Available Online: 2015-09-15

Abstract

Selecting SO₂ conversion ratio of metallurgical off-gases making acid as the research object, in order to solve the problem of over learning or slow network convergence speed existed in using single BP or RBF neural network to predict SO₂ conversion ratio,the optimal mean square error weighted fusion algorithm was used to achieve fusion of two kinds of neural network and construct the better SO₂ conversion ratio predication model. The simulation results showed that the optimal mean square error weighted fusion model avoided the lack of information of the single model,realized the complementation of information and effectively improved the SO₂ conversion ratio predication precision.
- neural network,
- metallurgical off-gases making acid SO₂ conversion ratio,
- information fusion,
- optimal weighted fusion,
References
1. [1]
  孙治忠,谢成,柴瑾瑜.金川公司冶炼烟气制酸技术创新回顾[J].硫酸工业,2014(2):10.
2. [2]
  潘立登,李大字.软测量技术原理与应用[M].北京:中国电力出版社,2009:1-4.
3. [3]
  周品.MATLAB神经网络设计与应用[M].北京:清华大学出版社,2013:153-184.
4. [4]
  王芹,王晓东,吴建德,等.神经网络和SVM多传感器融合的隧道CO体积分数研究[J].传感器与微系统,2012(7):6.
5. [5]
  黄清容.云铜冶炼烟气制酸系统DCS控制系统的升级改造[D].昆明:昆明理工大学,2010:4-12.
6. [6]
  李东玉,王睿.基于BP神经网络的阀控铅酸盐蓄电池劣化程度预测[J].郑州轻工业学院学报:自然科学版,2012,27(4):12.
7. [7]
  潘泉,王增福,梁彦,等.信息融合理论的基本方法与进展(Ⅱ)[J].控制理论与应用,2012(10):1233.
8. [8]
  李伟,何鹏举,高社生.多传感器加权信息融合算法研究[J].西北工业大学学报:自然科学版,2010(5):674.
Proportional views