## THERMAL SCIENCE

International Scientific Journal

### SHORT-TERM AND LONG-TERM THERMAL PREDICTION OF A WALKING BEAM FURNACE USING NEURO-FUZZY TECHNIQUES

**ABSTRACT**

The walking beam furnace (WBF) is one of the most prominent process plants often met in an alloy steel production factory and characterized by high non-linearity, strong coupling, time delay, large time-constant and time variation in its parameter set and structure. From another viewpoint, the WBF is a distributed-parameter process in which the distribution of temperature is not uniform. Hence, this process plant has complicated non-linear dynamic equations that have not worked out yet. In this paper, we propose one-step non-linear predictive model for a real WBF using non-linear black-box sub-system identification based on locally linear neuro-fuzzy (LLNF) model. Furthermore, a multi-step predictive model with a precise long prediction horizon (i.e., ninety seconds ahead), developed with application of the sequential one-step predictive models, is also presented for the first time. The locally linear model tree (LOLIMOT) which is a progressive tree-based algorithm trains these models. Comparing the performance of the one-step LLNF predictive models with their associated models obtained through least squares error (LSE) solution proves that all operating zones of the WBF are of non-linear sub-systems. The recorded data from Iran Alloy Steel factory is utilized for identification and evaluation of the proposed neuro-fuzzy predictive models of the WBF process.

**KEYWORDS**

PAPER SUBMITTED: 2012-04-10

PAPER REVISED: 2012-05-10

PAPER ACCEPTED: 2012-10-14

**THERMAL SCIENCE** YEAR

**2015**, VOLUME

**19**, ISSUE

**2**, PAGES [703 - 721]

- Shaoyuan, Li., Chen, Q., Huang, G., Dynamic temperature modeling of continuous annealing furnace using GGAP-RBF neural network, neurocomputing, vol.69, (2006), pp.524-536
- Zhang, B., Chen, Z., Xu, L., Wang, J., Zhang, J., Shao, H., The Modeling and Control of A Reheating Furnace, Proceedings of the American Control Conference, (2002), pp.3823-3828
- Laurinen, P., Roning, J., An adaptive neural network model for predicting the post roughing mill temperature of steel slabs in the reheating furnace, Materials Processing Technology, (2005), pp.423-430
- Chen, Q., Li, S., Xi, Y., Huang, G., Furnace Temperature Modeling for Continuous Annealing Process Based on Generalized Growing and Pruning RBF Neural Network, Advances in Neural Networks, vol.3174, (2004), pp.755-760
- Banadaki, H. D., Nozari, H. A., Kakahaji, H., Non-linear Simulator model Identification of a Walking Beam Furnace Using Recurrent Local Linear Neuro-Fuzzy Network, International Journal of Control and Automation, vol.4, no.4 , (2011), pp.123-134
- Kusters, A.,van Ditzhuijzen, G.A.J.M., MIMO system identification of a slab reheating furnace, Proceedings of the Third IEEE Conference on Control Applications, (1994), pp.3097-1563
- Gobbak, K.A., Raghavendran, H., Internal Feedback Neuron Networks for Modeling of an Industrial Furnace, Neural Networks, International Conference, (1997),pp.1948-1953
- Liao, Y., Wu, M., She, J., Modeling of reheating-furnace dynamics using neural network based on improved sequential-learning algorithm, Computer Aided Control System Design, (2006), pp.3175-318
- Xuegang, S., Chao, Y., Yihui, C., Dynamic Modeling of Reheat-Furnace Using Neural Network based on PSO Algorithm, International Conference on Mechatronics and Automation, (2009), pp.3097-3101
- Pongam, T., Srisertpol, J., Khomphis, V., Open-loop Identification of the Mathematical Model of the Reheating Furnace Walking Hearth Type in Manufacturing Process, International Conference on System Modeling and Optimization, (2012), vol.23, pp.24-30
- Ogawa, M., Yichun, Y., Kawanari, S., Ogai, H., Long-term prediction of industrial furnace by Extended Sequential Prediction method of LOM, SICE Annual Conference, (2010), pp.1490-1493
- Leea, D., Leeb, Y., Application of neural-network for improving accuracy of roll-force model in hot-rolling mill, Control Engineering Practice, (2002), vol.10, pp.473-478
- Kaiju, Z., Di, J., Cheng, S., Fuzzy neural network's application in furnace temperature compensation based on rolling information, IFAC World Congress, (2005),vol.16, part 1
- Schlanga, M., Langb, B., Poppeb, T., Runklerb, T., Weinzierlc, K., Current and future development in neural computation in steel processing, Control Engineering Practice, (2001), vol.9, pp.975-986
- Roger Jang, J., Sun, C., Mizutani, E., Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, Prentice Hal Inc.l, 1997
- Razavi-Far, R., Davilu, H., Palade, V., Lucas, C., Model-based fault detection and isolation of a steam generator using neuro-fuzzy networks, neurocomputing, vol.72, (2009), pp.2939-2951
- Sadeghian, M., Fatehi, A., Identification of Non-linear Predictor and Predictor Models of a Cement Rotary Kiln by Locally Linear Neuro-Fuzzy Technique, World Academy of Science, Engineering and Technology, (2009), pp.1121-1127
- Nozari, H. A., Banadaki, H. D., Mokhtare, M., Vahed, S. H., Intelligent non-linear modelling of an industrial winding process using recurrent local linear neuro-fuzzy networks, Journal of Zhejiang University - Science C, vol.13, no.6, (2012), pp.403-412
- Mohammadzaheri, M., Lei, C., Intelligent Modeling of MIMO Non-linear Dynamic Process Plants for Predictive Control Purposes, Proceedings of the 17th World Congress the International Federation of Automatic Control Seoul, (2008), pp.12401-12406
- Nelles, O., Local linear model tree for on-line identification of time variant non-linear dynamic systems, International Conference on Artificial Neural Networks, vol.1112,(1996), pp.115-120
- Nelles, O., Non-linear system identification, Springer Inc., 2001
- Ljung, L., System Identification Theory for the user, Prentice Hall Inc
- Nozari, H. A., Shoorehdeli, M. A., Simani, S., Banadaki, H. D, Model-based robust fault detection and isolation of an industrial gas turbine prototype using soft computing techniques, neurocomputing, vol.91, (2012), pp.29-47
- Nelles, O., Isermann, R., Basis function networks for interpolation of locally linear models, Proc. of IEEE Conference on Decision and Control, (1996), pp.470-475
- Judd, K., Small, M.,Towards long-term prediction, Journal of Physica, vol.136, (2000), pp.31-44