[1] Ding Weiming, Wu Xiaoli, Wei Haikun,. Prediction of coal ash fusion temperatureusing constructive-pruning hybrid method for RBF networks [J]. Journal of Southeast University (English Edition), 2011, 27 (2): 159-163. [doi:10.3969/j.issn.1003-7985.2011.02.009]
Copy
Prediction of coal ash fusion temperatureusing constructive-pruning hybrid method for RBF networks(
)
基于构造-剪枝混合优化RBF网络的煤灰熔点预测方法
)Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]
- Volumn:
- 27
- Issue:
- 2011 2
- Page:
- 159-163
- Research Field:
- Chemistry and Chemical Engineering
- Publishing date:
- 2011-06-30
Info
- Title:
- Prediction of coal ash fusion temperatureusing constructive-pruning hybrid method for RBF networks
- 基于构造-剪枝混合优化RBF网络的煤灰熔点预测方法
- Author(s):
- Ding Weiming1; Wu Xiaoli1; Wei Haikun2
-
1 School of Energy and Environment, Southeast University, Nanjing 210096, China
2 School of Automation, Southeast University, Nanjing 210096, China
- PACS:
- TQ520.62
- DOI:
- 10.3969/j.issn.1003-7985.2011.02.009
- Abstract:
- A constructive-pruning hybrid method(CPHM)for radial basis function(RBF)networks is proposed to improve the prediction accuracy of ash fusion temperatures(AFT). The CPHM incorporates the advantages of the construction algorithm and the pruning algorithm of neural networks, and the training process of the CPHM is divided into two stages: rough tuning and fine tuning. In rough tuning, new hidden units are added to the current network until some performance index is satisfied. In fine tuning, the network structure and the model parameters are further adjusted. And, based on components of coal ash, a model using the CPHM is established to predict the AFT. The results show that the CPHM prediction model is characterized by its high precision, compact network structure, as well as strong generalization ability and robustness.
- 为提高煤灰熔点的预测精度, 提出了一种基于构造-剪枝混合优化RBF网络的煤灰熔点预测方法.该方法融合了神经网络构造算法和剪枝算法的优点, 分为“粗调”和“精调”2个阶段.粗调阶段动态增加隐节点数目直至满足相应的停止准则;精调阶段对粗调得到的RBF网络的结构和参数作进一步调整.基于煤灰的化学组成成分建立相应的构造-剪枝混合优化RBF网络预测煤灰熔点.预测结果表明:所建模型在具有较高精度的同时, 具有较小的结构、较好的泛化能力和较强的鲁棒性.
References:
[1] van Dyk J C, Keyser M J, van Zyl J W. Suitability of feedstocks for the Sasol-Lurgi fixed bed dry bottom gasification process[C]//Gasification Technologies Conference. San Francisco, USA, 2001:1-11.
[2] Romero C E, Saro R D, Craparo J, et al. Laser-induced breakdown spectroscopy for coal characterization and assessing slagging propensity[J]. Energy Fuels, 2010, 24(1): 510-517.
[3] Song W J, Tang L H, Zhu X D, et al. Effect of coal ash composition on ash fusion temperatures [J]. Energy Fuels, 2010, 24(1):182-189.
[4] Dunnu G, Maier J, Scheffknecht G. Ash fusibility and compositional data of solid recovered fuels[J]. Fuel, 2010, 89(7):1534-1540.
[5] Kalogirou S A. Artificial intelligence for the modeling and control of combustion processes[J]. Progress in Energy and Combustion Seience, 2003, 29(6): 515-566.
[6] Amoudi A, Zhang L. Application of radial basis function networks for solar array modeling and maximum power-point prediction[J]. IEE Proceedings: Generation, Transmission and Distribution, 2000, 147(5): 310-316.
[7] Chandok J S, Kar I N, Tuli Suneet. Estimation of furnace exit gas temperature(FEGT)using optimized radial basis and back-propagation neural networks[J]. Energy Conversion and Management, 2008, 49(8):1989-1998.
[8] Orr M. Regularization in the selection of radial basis function centers[J]. Neural Computation, 1995, 7(3):606-623.
[9] Plat J. A resource-allocating network for function interpolation[J]. Neural Computation, 1991, 3(2):213-225.
[10] Chen S. Local regularization assisted orthogonal least squares regression[J]. Neurocomputing, 2006, 69(4/5/6):559-585.
[11] Weigend A, Rumelhart D, Huberman B. Generalization by weight-elimination with application to forecasting[C]//Advances in Neural Information Processing Systems. Cambridge, MA, USA: The MIT Press, 1991, 3: 875-882.
Memo
- Memo:
-
Biography: Ding Weiming(1959—), male, associate professor, wmding@seu.edu.cn.
Foundation items: The National Natural Science Foundation of China(No. 60875035), the Natural Science Foundation of Jiangsu Province(No.BK2008294), the National High Technology Research and Development Program of China(863 Program)(No.2006AA05A107).
Citation: Ding Weiming, Wu Xiaoli, Wei Haikun. Prediction of coal ash fusion temperature using constructive-pruning hybrid method for RBF networks[J].Journal of Southeast University(English Edition), 2011, 27(2):159-163.[doi:10.3969/j.issn.1003-7985.2011.02.009]