Combustion optimization of a coal-fired boiler with double linear fast learning network

详细信息    查看全文

• 作者：Guoqiang Li ; Peifeng Niu
• 关键词：Fast learning network ; Extreme learning machine ; Least squared ; Coal ; fired boiler ; Combustion characteristics
• 刊名：Soft Computing - A Fusion of Foundations, Methodologies and Applications
• 出版年：2016
• 出版时间：January 2016
• 年：2016
• 卷：20
• 期：1
• 页码：149-156
• 全文大小：524 KB
• 参考文献：Anantachar M, Prasanna Kumar GV, Guruswamy T (2011) Development of artificial neural network models for the performance prediction of an inclined plate seed metering device. Appl Soft Comput 11:3753–3763CrossRef
  Castillo E, Guijarro-Berdinas B, Fontenla-Romero O, Alonso-Betanzos A (2006) A very fast learning method for neural networks based on sensitivity analysis. J Mach Learn Res 7:1159–1182MathSciNet MATH
  Chang J-R, Wei L-Y, Cheng C-H (2011) A hybrid ANFIS model based on AR and volatility for TAIEX forecasting. Appl Soft Comput 11:1388–1395
  Czibula G, Czibula IG, Gaceanu RD (2009) Intelligent data structures selection using neural networks. Knowl Inf Syst 34:171–192. doi:10.​1007/​s10115-011-0468-3 CrossRef
  Huang G-B, Zhu Q-Y, Siew C-K (2006) Extreme learning machine: theory and applications. Neurocomputing 70:489–501
  Huynh HT, Won Y (2009) Online training for single hidden-layer feedforward neural networks using RLS-ELM. IEEE International Symposium on Computational intelligence in robotics and automation (CIRA), pp:469–473
  Huynh HT, Won Y, Kim J-J (2008) An improvement of extreme learning machine for compact single-hidden-layer feedforward neural networks. Int J Neural Syst 18(5):433–441CrossRef
  Huynh HT, Yonggwan W (2008) Small number of hidden units for ELM with two-stage linear model. IEICE Trans Inf Syst 91(4):1042–1049CrossRef
  Huynh HT (2011) Regularized online sequential learning algorithm for single-hidden layer feedforward neural networks. Pattern Recogn Lett 32:1930–1935CrossRef
  Li G, Niu P (2011) An enhanced extreme learning machine based on ridge regression for regression. Neural Comput Appl 22:803–810. doi:10.​1007/​s00521-011-0771-7 CrossRef
  Li G, Niu P, Liu C, Zhang W (2012) Enhanced combination modeling method for combustion efficiency in coal-fired boilers. Appl Soft Comput 12:3132–3140. doi:10.​1016/​j.​asoc.​2012.​06.​016 CrossRef
  Li G, Niu P, Xiao X (2012) Development and investigation of efficient artificial bee colony algorithm for numerical function optimization. Appl Soft Comput 12:320–332CrossRef
  Li G, Niu P, Zhang W, Zhang Y (2012) Control of discrete chaotic systems based on echo state network modeling with an adaptive noise canceler. Knowl Based Syst 35:35–40. doi:10.​1016/​j.​knosys.​2012.​04.​019 CrossRef
  Li G, Niu P, Duan X, Zhang X (2013) Fast learning network: a novel artificial neural network with a fast learning speed. Neural Comput Appl 24:1683–1695. doi:10.​1007/​s00521-013-1398-7 CrossRef
  Li G, Niu P, Wang H, Liu Y (2014) Least square fast learning network for modeling the combustion efficiency of a 300WM coal-fired boiler. Neural Netw 51:57–66CrossRef MATH
  Liu F, Er MJ (2012) A novel efficient learning algorithm for self-generating fuzzy neural network with applications. Int J Neural Syst 22:21–35
  Park D-C (2009) Multiresolution-based bilinear recurrent neural network. Knowl Inf Syst 19:235–248CrossRef
  Suresh S, Saraswathi S, Sundararajan N (2010) Performance enhancement of extreme learning machine for multi-category sparse data classification problems. Eng Appl Artif Intell 23:1149–1157CrossRef
  Tang X, Han M (2009) Partial Lanczos extreme learning machine for single-output regression problems. Neurocomputing 72:3066–3076CrossRef
  Wang L, Yang B, Chen Y, Abraham A, Sun H, Chen Z, Wang H (2012) Improvement of neural network classifier using floating centroids. Knowl Inf Syst 31:433–454CrossRef
  Zhu Qin-Yu, Zhu Q-Y, Suganthan PN, Huang G-B (2005) Evolutionary extreme learning machine. Pattern Recogn 38:1759–1763CrossRef MATH
  
• 作者单位：Guoqiang Li (1) (2)
  Peifeng Niu (1) (2)
  
  1. Key Lab of Industrial Computer Control Engineering of Hebei Province, Yanshan University, Qinhuangdao, 066004, China
  2. National Engineering Research Center for Equipment and Technology of Cold Strip Rolling, Qinhuangdao, 066004, China
  
• 刊物类别：Engineering
• 刊物主题：Numerical and Computational Methods in Engineering
  Theory of Computation
  Computing Methodologies
  Mathematical Logic and Foundations
  Control Engineering
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1433-7479

文摘

Fast learning network (FLN) is a novel double parallel forward neural network, which proves to be a very good machine learning tool. However, some randomly initialed weights and biases may be non-optimal performance parameters. Therefore, for the problem, this paper proposes a double linear fast learning network (DLFLN), in which all weights and biases are divided into two parts and each part is determined by least squared method. DLFLN is employed to model the combustion characteristics of a 330 MW coal-fired boiler and is combined with an optimization algorithm to tune the operating parameters of the boiler to achieve the combustion optimization objective. Experimental results show that, compared with extreme learning machine and FLN, although the DLFLN is assigned much less hidden neural nodes, the DLFLN could achieve much better generalization performance and stability under various operational conditions; in addition, the effect of the combustion optimization is very satisfactory. Keywords Fast learning network Extreme learning machine Least squared Coal-fired boiler Combustion characteristics