Influence of Variation/Response Space Complexity and Variable Completeness on BP-ANN Model Establishment: Case Study of Steel Ladle Lining

Artificial neural network (ANN) is widely applied as a predictive tool to solve complex problems. The performance of an ANN model is significantly affected by the applied architectural parameters such as the node number in a hidden layer, which is largely determined by the complexity of cases, the quality of the dataset, and the sufficiency of variables. In the present study, the impact of variation/response space complexity and variable completeness on backpropagation (BP) ANN model establishment was investigated, with a steel ladle lining from secondary steel metallurgy as the case study. The variation dataset for analysis comprised 160 lining configurations of ten variables. Thermal and thermomechanical responses were obtained via finite element (FE) modeling with elastic material behavior. Guidelines were proposed to define node numbers in the hidden layer for each response as a function of the node number in the input layer weighted with the percent value of the significant variables contributing above 90% to the response, as well as the node number in the output layer. The minimum numbers of input variables required to achieve acceptable prediction performance were three, five, and six for the maximum compressive stress, the end temperature, and the maximum tensile stress.

[1]  Y. Villacampa,et al.  Artificial neural network modeling of cross-shore profile on sand beaches: The coast of the province of Valencia (Spain) , 2017 .

[2]  Xueqing Zhang,et al.  A comprehensive review on the application of artificial neural networks in building energy analysis , 2019, Neurocomputing.

[3]  Azni Idris,et al.  Phytoremediation of palm oil mill secondary effluent (POMSE) by Chrysopogon zizanioides (L.) using artificial neural networks , 2017, International journal of phytoremediation.

[4]  Akhil Garg,et al.  A coupled and interactive influence of operational parameters for optimizing power output of cleaner energy production systems under uncertain conditions , 2019, International Journal of Energy Research.

[5]  Simon Haykin,et al.  Neural Networks and Learning Machines , 2010 .

[6]  C. H. Antunes,et al.  Estimation of renewable energy and built environment-related variables using neural networks – A review , 2018, Renewable and Sustainable Energy Reviews.

[7]  Fei He,et al.  Prediction model of end-point phosphorus content in BOF steelmaking process based on PCA and BP neural network , 2018, Journal of Process Control.

[8]  L. A. Dobrzański,et al.  Use of Neural Networks and Artificial Intelligence Tools for Modeling, Characterization, and Forecasting in Material Engineering , 2014 .

[9]  B. D. Ikotun,et al.  Prediction of compressive and flexural strengths of a modified zeolite additive mortar using artificial neural network , 2018, Construction and Building Materials.

[10]  S. Karsoliya,et al.  Approximating Number of Hidden layer neurons in Multiple Hidden Layer BPNN Architecture , 2012 .

[11]  Ching-Tai Ng,et al.  The selection of pattern features for structural damage detection using an extended Bayesian ANN algorithm , 2008 .

[12]  H. Harmuth,et al.  A Method for Steel Ladle Lining Optimization Applying Thermomechanical Modeling and Taguchi Approaches , 2018, JOM.

[13]  Wei Li,et al.  Combining discriminant analysis and neural networks for corn variety identification , 2010 .

[14]  S. Chokphoemphun,et al.  Moisture content prediction of paddy drying in a fluidized-bed drier with a vortex flow generator using an artificial neural network , 2018, Applied Thermal Engineering.

[15]  Ian Flood,et al.  Towards the next generation of artificial neural networks for civil engineering , 2008, Adv. Eng. Informatics.

[16]  Boguslaw Wiecek,et al.  Estimation of FeO content in the steel slag using infrared imaging and artificial neural network , 2018 .

[17]  Yasin Tunckaya,et al.  Comparative performance evaluation of blast furnace flame temperature prediction using artificial intelligence and statistical methods , 2016 .

[18]  David Bienvenido-Huertas,et al.  Applying an artificial neural network to assess thermal transmittance in walls by means of the thermometric method , 2019, Applied Energy.

[19]  Kaiqiang Gao,et al.  Back propagation neutral network based signal acquisition for Brillouin distributed optical fiber sensors. , 2019, Optics express.

[20]  Sohichi Hirose,et al.  Investigation on the Sensitivity of Ultrasonic Test Applied to Reinforced Concrete Beams Using Neural Network , 2018 .

[21]  Katayoon Kalantari,et al.  Optimization of process parameters for rapid adsorption of Pb(II), Ni(II), and Cu(II) by magnetic/talc nanocomposite using wavelet neural network , 2016, Research on Chemical Intermediates.

[22]  H. Harmuth,et al.  Thermal and Thermomechanical Responses Prediction of a Steel Ladle Using a Back‐Propagation Artificial Neural Network Combining Multiple Orthogonal Arrays , 2019, steel research international.

[23]  Lai Fuqiang,et al.  A lithology identification method for continental shale oil reservoir based on BP neural network , 2018 .

[24]  Danial Jahed Armaghani,et al.  Random Forests and Cubist Algorithms for Predicting Shear Strengths of Rockfill Materials , 2019, Applied Sciences.

[25]  Rajesh Ransing,et al.  Application of neural computing in basic oxygen steelmaking , 2002 .