Prediction of Energy Consumption in Steel Enterprises based on BP Adaboost Algorithm
Low-carbon production is the aim of every heavy industry enterprises. Iron and steel companies are no exceptions. This thesis complished the prediction goal by applying the framework of BP neural network and Adaboost algorithm based on Matlab platform. Data used as training set were the energy consumption from 2005–2009 and the data of 2010–2015 were set as target. The result indicated that the main trend of the energy consumption in this industry was declining and the gaps between companies were decreasing eventually.
KeywordsBP neural network Energy consumption Prediction Iron and steel enterprise
Unable to display preview. Download preview PDF.
- 1.Zhang JY, Zhang DJ, Zhang L (2009) Summary of the metheds of energy consumption forecast in iron and steel enterprises. Energy for Metallurgical industry 28:11–14Google Scholar
- 2.Zeng ZL, Zheng Y (2009) The grey model and its application to forecast of inbound visitors from Mainland China to Macau. In: Proceedings of Third International Conference on Management Science and Engineering Management 48–54Google Scholar
- 3.Huan HY, Huan HJ (2008) Application of improved BP neural network in economic forecasts. Statistics and Information Forum 23:58–62Google Scholar
- 4.Ma ZQ, Meng QB (2009) The research on customer satisfaction evaluation of energy-saving buildings based on RBF neural network. In: Proceedings of Third International Conference on Management Science and Engineering Management 190–194Google Scholar
- 5.Zhu K, Wang ZL (2010) Mastering the neural network in MATLAB toolbox. Publishing House of Electronics Industry, Beijing (In Chinese)Google Scholar
- 6.WangW, Zhang YT (2007) Analysis and improving way of BP ANN in predicting time series data. Computer Engineering and Design 28:5292–5294Google Scholar
- 7.Hong T, Ma ZQ, Fan Q et al (2009) The research of ability evaluation on green manufacturing of Chinese manufacturing enterprises based on fuzzy neural network. In: Proceedings of Third International Conference on Management Science and Engineering Management 117–123Google Scholar
- 8.Schapire ER, Freund Y, Bartlet TP et al (1998) Boosting the margin: A new explanation for the effectiveness of voting methods. The Annals of Statistics 26:1651–1686Google Scholar
- 9.Shi F,Wang XC, Yu L et al (2010) 30 case-studies about neural network in Matlab. Publishing house of Beihang University, Beihang (In Chinese)Google Scholar
- 10.Huang L (2009) With improved BP algorithm to realize the evaluation of forecast system. Sun Yat-sen University, Nanjing (In Chinese)Google Scholar
- 11.Li CH, Li TQ (2005) Application of an improved feature selection method in text classifying system. Journal of Xiamen University 44:94–98Google Scholar