An Intelligent Optimization Strategy Based on Prediction Model for Carbon Efficiency in Sintering Process

I0610. In the paper, first, comprehensive coke ratio (CCR) is taken to be a metric of the carbon efficiency. By analyzing the sintering mechanism, sintering parameters affecting the CCR are determined. Next, the fuzzy C-means clustering algorithm is used to identify different operating conditions. Then, least-squares support vector machine (LS-SVM) sub-models are established for the different operating conditions, and a CCR prediction model is established by incorporating the sub-models using the T-S fuzzy intelligent fusion method. Finally, based on the CCR prediction model, a differential evolution algorithm is used to optimize the CCR by adjusting the operating parameters. Simulations using actual run data show that the prediction accuracy of the CCR prediction model is higher than that of a back-propagation neural network model and a single LS-SVM model, and the carbon efficiency optimization strategy reduced the CCR by 1.97 kg/t on average. Thus, the method provides us a guidance for an actual sintering process.

[1]  Rainer Storn,et al.  Differential Evolution – A Simple and Efficient Heuristic for global Optimization over Continuous Spaces , 1997, J. Glob. Optim..

[2]  Chang-Ha Lee,et al.  Evaluation of the energy efficiency of the shell coal gasification process by coal type , 2017 .

[3]  Jinhua She,et al.  A hybrid just-in-time soft sensor for carbon efficiency of iron ore sintering process based on feature extraction of cross-sectional frames at discharge end , 2017 .

[4]  Sangmin Choi,et al.  Combustion characteristics in an iron ore sintering bed—evaluation of fuel substitution , 2006 .

[5]  Jinhua She,et al.  Modeling and optimization method featuring multiple operating modes for improving carbon efficiency of iron ore sintering process , 2016 .

[6]  Shaojiang Dong,et al.  Bearing degradation process prediction based on the PCA and optimized LS-SVM model , 2013 .

[7]  Min Wu,et al.  Intelligent integrated optimization and control system for lead–zinc sintering process☆ , 2009 .

[8]  Jinhua She,et al.  Hybrid Prediction Model of Carbon Efficiency for Sintering Process , 2017 .

[9]  Weihua Cao,et al.  Neural-network-based integrated model for predicting burn-through point in lead–zinc sintering process , 2012 .

[10]  Jizhen Liu,et al.  A novel least squares support vector machine ensemble model for NOx emission prediction of a coal-fired boiler , 2013 .

[11]  Ming-Jia Li,et al.  Review of methodologies and polices for evaluation of energy efficiency in high energy-consuming industry , 2017 .

[12]  Guangdong Tian,et al.  A carbon efficiency evaluation method for manufacturing process chain decision-making , 2017 .

[13]  Yaonan Wang,et al.  Operating Point Optimization of Auxiliary Power Unit Using Adaptive Multi-Objective Differential Evolution Algorithm , 2017, IEEE Transactions on Industrial Electronics.

[14]  Dingli Yu,et al.  PID controller tuning for a multivariable glass furnace process by genetic algorithm , 2016, International Journal of Automation and Computing.

[15]  Dipti Srinivasan,et al.  A hybrid intelligent model based on recurrent neural networks and excitable dynamics for price prediction in deregulated electricity market , 2013, Eng. Appl. Artif. Intell..

[16]  G. Roy,et al.  Mathematical modelling of iron ore sintering process using genetic algorithm , 2012 .

[17]  Chee Peng Lim,et al.  Power Quality Analysis Using a Hybrid Model of the Fuzzy Min–Max Neural Network and Clustering Tree , 2016, IEEE Transactions on Neural Networks and Learning Systems.

[18]  Jing Zhang,et al.  Hybrid particle swarm optimization with differential evolution for numerical and engineering optimization , 2018, Int. J. Autom. Comput..