Please wait a minute...
浙江大学学报(工学版)
J4  2011, Vol. 45 Issue (12): 2181-2187    DOI: 10.3785/j.issn.1008-973X.2011.12.017
    
Prediction of ash fusion temperature
based on grid search and support vector machine
LI Qing-yi, ZHOU Hao, LIN A-ping, QIU Kun-zan, CEN Ke-fa
State Key Laboratory of Cleanenergy Utilization, Zhejiang University, Hangzhou 310027, China
Download:   PDF(0KB) HTML
Export: BibTeX | EndNote (RIS)      

Abstract  

Support vector machine (SVM) was used to model the mixed coals’ ash softening temperature. The coal ash compositions were employed as the inputs of SVM, and the measured ash softening temperatures were used as the outputs. Parameters of the SVM model were optimized by grid search and the best parameters were obtained for different setting precisions. Single and mixed coals’ ash fusion temperatures were predicted by the optimized SVM and the predicted values were compared with the actual measurement results. The relative error of testing single coal was the smallest when the setting precision was 0.01. The results showed that the maximum predicting error was 3.00%, and the average predicting error was 0.48%. Using the 0.01 precision for the mixed coals, the maximum relative error was 1.74%, and the average relative error was 0.62%. So the SVM model optimized by grid search has good predicting performance of ash fusion temperature.

Published: 01 December 2011
CLC:  TK 223  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Cite this article:

LI Qing-yi, ZHOU Hao, LIN A-ping, QIU Kun-zan, CEN Ke-fa. Prediction of ash fusion temperature
based on grid search and support vector machine. J4, 2011, 45(12): 2181-2187.

URL:

https://www.zjujournals.com/eng/10.3785/j.issn.1008-973X.2011.12.017     OR     https://www.zjujournals.com/eng/Y2011/V45/I12/2181


基于网格搜索和支持向量机的灰熔点预测

为了预测混煤的灰熔点,采用支持向量机建立煤灰软化温度模型,模型将煤的灰成分作为输入量,煤的软化温度作为输出量,利用网格搜索寻优方法对支持向量机(SVM)模型的参数进行了优化,在设定的不同精度下分别获得模型的最优参数,利用优化后的模型对单煤和混煤的灰熔点进行了预测,并将不同精度下的预测结果与实验结果进行对比.煤灰软化温度模型设定精度为0.01时,单煤样本预测相对误差最小,其最大相对误差和平均相对误差分别为3.00%和0.48%；运用此模型对混煤预测的最大相对误差和平均相对误差分别为1.74%和0.62%.预测结果表明,经网格搜索优化后的支持向量机模型对煤灰熔点预测较精确.

［1］ 岑可法,周昊,池作和.大型电站锅炉安全及优化运行技术［M］.北京：中国电力出版社,2002.
［2］ LOLJA S A,HAXHI H,MARTTIN D J.Correlations in the properties of Albanian coals［J］.Fuel,2002,81(9)： 1095-1100.
［3］ LOLJA SAIMIR A,HAJRI H,DHIMITRI R,et al.Correlation Albanian coal ashes［J］.Fuel,2002,81(17)： 2257-2261.
［4］ OZBYOGLU G,EVREN O M.A new approach for the prediction of ash fusion temperatures:A case study using Turkish lignites［J］.Fuel,2006,85(4)： 545-552.
［5］ 陈文敏,姜宁.煤灰成分和煤灰熔性的关系［J］.洁净煤技术,1996,2(2)： 34-37.
CHEN Wenmin, JIANG Ning. Relation between the coal ash composition and fusibility［J］.Technology of Clean Coal,1996,2(2)： 34-37.
［6］ YIN Chungen,LUO Zhongyang,NI Mingjiang,et al.Predicting coal ash fusion temperature with a backpropagation neural network model［J］.Fuel,1998,77(15)： 1777-1782.
［7］ 王春林,周昊,李国能,等.基于支持向量机与遗传算法的灰熔点预测［J］.中国电机工程学报,2007,27(8)： 11-15.
WANG Chunlin,ZHOU hao,LI Guoneng,et al. Combining support vector machine and genetic algorithm to predict ash fusion temperature［J］. Proceedings of the CSEE,2007,27(8)： 11-15.
［8］ 《电力用燃料标准汇编》委员会.电力用燃料标准汇编［M］.北京：中国标准出版社,1990.
［9］ VAPNIK V N.The nature of statiscal learning theory ［M］.New York:SpringerVerlag,1999： 138-167.
［10］ 申宇皓,孟晨,傅振华,等.基于改进支持向量机的仿真电路故障诊断研究［J］.计算机仿真,2010, 27(1): 346-350.
SHEN Yuhao, MENG Chen, FU Zhenhua,et al. Research on simulation circuit fault diagnosis based on improved SVM ［J］.Computer Simulation,2010,27(1)： 346-350.
［11］ 徐玉兵.支持向量机在道路交通事故预测中的应用［J］.交通标准化, 2010(1): 160-162.
XU Yubing. Application of support vector machine in prediction of road traffic accidents［J］.Transport Standardization,2010（1）： 160-162.
［12］ 曹志坤,谷波,黄彬彬,等.基于冷损双流体模型及主元分析支持向量机算法的制冷陈列柜冷风幕优化分析［J］.上海交通大学学报,2009,43(5)： 772-778.
CAO Zhikun,GU Bo, HUANG Binbin,et al. Optimization of cold air curtain of refrigeration display case based on RLTF model and PCASVM algorithm［J］.Journal of Shanghai Jiaotong University,2009,43(5)： 772-778.
［13］ 张孟奇,郭青.网格搜索法在送电线路铁塔基础计算机优化设计中的应用［J］.电力建设,1998（7）: 23-26.
ZHANG Mengqi,GUO Qing. Application of network search ing method in optimized design in tower foundation in transmission lines［J］.Electric Power Construction,1998（7）: 23-26.
［14］ 王兴玲,李占斌. 基于网格搜索的支持向量机核函数参数的确定［J］. 中国海洋大学学报：自然科学版,2005,35(5)： 859-862.
WANG Xingling,LI Zhanbin. Identifying the parameters of the kernel function in support vector machines based on the gridsearch method［J］. Journal of Ocean University of Qingdao: Natural Science,2005,35(5)： 859-862.
［15］ 王春林,周昊,李国能,等.大型电厂锅炉NOx排放特性的支持向量机模型［J］.浙江大学学报：工学版,2006,40(10): 1787-1791.
WANG Chunlin, ZHOU Hao, LI Guoneng,et al. Support vector machine modeling on NOx emission property of high capacity power station boiler［J］.Journal of Zhejiang University: Engineering Science, 2006, 40(10): 1787-1791.
\
[16\] 朱树先，张仁杰.支持向量机该函数选择的研究\
[J\].科学技术与工程，2008，8（16）：4513-4517.
ZHU Shuxian, ZHANG Renjie. Research for selection of kernel functions used in support vector machine\
[J\]. Science Technology and Engineering, 2008, 8(16): 4513-4517.
［17］ PANG Jiufeng,LI Xianfeng,XIE Jinsong,et al. Microarchitectural design space exploration via support vector machine ［J］.Acta Scientiarum Naturalium Universitatis Pekinensis,2010,46(1)： 55-63.
[1] TUN Feng, ZHOU Hao, ZHENG Li-Gang, CEN Ge-Fa. Application of scaleable chaotic ant colony algorithm in control of
unburned carbon in fly ash[J]. J4, 2010, 44(6): 1127-1132.