Energy optimization and prediction of complex petrochemical industries using an improved artificial neural network approach integrating data envelopment analysis

Abstract Since the complex petrochemical data have characteristics of multi-dimension, uncertainty and noise, it is difficult to accurately optimize and predict the energy usage of complex petrochemical systems. Therefore, this paper proposes a data envelopment analysis (DEA) integrated artificial neural network (ANN) approach (DEA-ANN). The proposed approach utilizes the DEA model with slack variables for sensitivity analysis to determine the effective decision making units (DMUs) and indicate the optimized direction of the ineffective DMUs. Compared with the traditional ANN approach, the DEA-ANN prediction model is effectively verified by executing a linear comparison between all DMUs and the effective DMUs through the standard data source from the UCI (University of California at Irvine) repository. Finally, the proposed model is validated through an application in a complex ethylene production system of China petrochemical industry. The optimization result and the prediction value are obtained to reduce energy consumption of the ethylene production system, guide ethylene production and improve energy efficiency.

[1]  R. Hecht-Nielsen,et al.  Theory of the Back Propagation Neural Network , 1989 .

[2]  Q. Wei.  Data envelopment analysis , 2001 .

[3]  Qunxiong Zhu,et al.  Energy Efficiency Estimation Based on Data Fusion Strategy: Case Study of Ethylene Product Industry , 2012 .

[4]  Yongming Han,et al.  Energy Efficiency Evaluation Based on Data Envelopment Analysis Integrated Analytic Hierarchy Process in Ethylene Production , 2014 .

[5]  Martin Kumar Patel,et al.  Olefins from conventional and heavy feedstocks: Energy use in steam cracking and alternative processes , 2006 .

[6]  S. A. MirHassani,et al.  An efficient approach for computing non-Archimedean epsilon in DEA based on integrated models , 2005, Appl. Math. Comput..

[7]  Adisa A. Jimoh,et al.  Review of energy models to the development of an efficient industrial energy model , 2014 .

[8]  Philipp Slusallek,et al.  Introduction to real-time ray tracing , 2005, SIGGRAPH Courses.

[9]  Richard P. Lippmann,et al.  An introduction to computing with neural nets , 1987 .

[10]  Abolfazl Vahedi,et al.  Optimal design of permanent magnet flux switching generator for wind applications via artificial neural network and multi-objective particle swarm optimization hybrid approach , 2016 .

[11]  William W. Cooper,et al.  Choosing weights from alternative optimal solutions of dual multiplier models in DEA , 2007, Eur. J. Oper. Res..

[12]  Toshiyuki Sueyoshi,et al.  DEA window analysis for environmental assessment in a dynamic time shift: Performance assessment of U.S. coal-fired power plants , 2013 .

[13]  Eva Gonzalez-Romera,et al.  Monthly electric energy demand forecasting with neural networks and Fourier series , 2008 .

[14]  Wei-Wen Wu,et al.  Beyond Travel & Tourism competitiveness ranking using DEA, GST, ANN and Borda count , 2011, Expert Syst. Appl..

[15]  Zhiqiang Geng,et al.  Energy Efficiency Hierarchy Evaluation Based on Data Envelopment Analysis and its Application in a Petrochemical Process , 2014 .

[16]  O. A. Olanrewaju,et al.  Integrated IDA–ANN–DEA for assessment and optimization of energy consumption in industrial sectors , 2012 .

[17]  John Ruggiero,et al.  Impact Assessment of Input Omission on Dea , 2005, Int. J. Inf. Technol. Decis. Mak..

[18]  Amparo Alonso-Betanzos,et al.  Linear-least-squares initialization of multilayer perceptrons through backpropagation of the desired response , 2005, IEEE Transactions on Neural Networks.

[19]  Sarawat Anam,et al.  Face Recognition Using Genetic Algorithm and Back Propagation Neural Network , 2009 .

[20]  Zhang Hao.  Consensus measurement in micro-inertial sensors , 2001 .

[21]  Qunxiong Zhu,et al.  Energy efficiency analysis method based on fuzzy DEA cross-model for ethylene production systems in chemical industry , 2015 .

[22]  William W. Cooper,et al.  Introduction to Data Envelopment Analysis and Its Uses: With Dea-Solver Software and References , 2005 .

[23]  Katarina M. Rajković,et al.  Optimization of sunflower oil ethanolysis catalyzed by calcium oxide: RSM versus ANN-GA , 2015 .

[24]  Jianye Sun.  Learning algorithm and hidden node selection scheme for local coupled feedforward neural network classifier , 2012, Neurocomputing.

[25]  Qunxiong Zhu,et al.  Energy efficiency analysis based on DEA integrated ISM: A case study for Chinese ethylene industries , 2015, Eng. Appl. Artif. Intell..

[26]  Zheng Tang,et al.  A modified error function for the backpropagation algorithm , 2004, Neurocomputing.

[27]  L. Liang,et al.  Does environmental regulation affect energy efficiency in China's thermal power generation? Empirical evidence from a slacks-based DEA model , 2014 .

[28]  B. Likozar,et al.  Modelling chemical kinetics of a complex reaction network of active pharmaceutical ingredient (API) synthesis with process optimization for benzazepine heterocyclic compound , 2016 .

[29]  Abraham Charnes,et al.  Measuring the efficiency of decision making units , 1978 .

[30]  Toshiyuki Sueyoshi,et al.  DEA radial measurement for environmental assessment: A comparative study between Japanese chemical and pharmaceutical firms , 2014 .

[31]  Ali Emrouznejad,et al.  DEA models for ratio data:convexity consideration , 2009 .

[32]  Lawrence M. Seiford,et al.  Data envelopment analysis (DEA) - Thirty years on , 2009, Eur. J. Oper. Res..

[33]  J. Davim,et al.  Prediction on tribological behaviour of composite PEEK-CF30 using artificial neural networks , 2007 .

[34]  M. R. Alirezaee,et al.  Recognizing the efficiency, weak efficiency and inefficiency of DMUs with an epsilon independent linear program , 2006, Appl. Math. Comput..

[35]  Hecht-Nielsen.  Theory of the backpropagation neural network , 1989 .

[36]  Toshiyuki Sueyoshi,et al.  Performance analysis of US coal-fired power plants by measuring three DEA efficiencies , 2010 .

[37]  He Jiang,et al.  Intelligent optimization models based on hard-ridge penalty and RBF for forecasting global solar radiation , 2015 .

[38]  WU Yu-hua.  Review on DEA models involving the non-Archimedean infinitesimal , 2010 .

[39]  Qun Dai,et al.  A two-phased and Ensemble scheme integrated Backpropagation algorithm , 2014, Appl. Soft Comput..

[40]  Elizabeth F. Wanner,et al.  A multiobjective optimization approach for combating Aedes aegypti using chemical and biological alternated step-size control. , 2015, Mathematical biosciences.

[41]  Emmanuel K. Yiridoe,et al.  Energy conservation on Nova Scotia farms: Baseline energy data , 2008 .