Artificial Neural Networks (ANN) have traditionally enjoyed considerable attention in process control applications. Thus, the paper is focused on real system control design using neural networks. The point is to show whether neural networks bring better performances to nonlinear process control or not. Artificial Neural Network is nowadays a popular methodology with lots of practical and indust...

This paper describes the development of a hybrid model based on artificial neural network and its industrial application to the ironmaking at Companhia Siderúrgica Nacional (CSN -Volta Redonda/Brazil). The Iron Blast Furnace is highly complex process subject to oscillations in raw material characteristics. A precise model is essential to adjust © 2002 charging and blow conditions to match produ...

Non-fragile fault-tolerant controller is designed for a class of linear uncertain time-delayed systems. Two cases of controller perturbation are investigated in view of different application conditions. One case is the controller gain attenuation, the other is random uncertainty caused by noise possibly existing in an industrial field. The controller to be designed can guarantee systems to have...

Three-dimensional information of the burden surface in high temperature and excessive dust industrial conditions has been previously hard to obtain. This paper presents a novel microstrip-fed dielectric-filled waveguide antenna element which is resistant to dust and high temperatures. A novel microstrip-to-dielectric-loaded waveguide transition was developed. A cylinder and cuboid composite str...

Inorganic arsenic removal from water using low-cost adsorbents is presented in this paper. Selective removal of As(III) and As(V) from water was performed with natural materials (zeolite, bentonite, sepiolite, pyrolusite and limonite) and industrial by-products (waste filter sand as a water treatment residual and blast furnace slag from steel production); all inexpensive and locally available. ...

The aim of this paper is to present and compare four different neuro-fuzzy approaches to the construction of fuzzy rule-based models for dynamic processes. These approaches have been applied to modelling of an industrial gas furnace system (Box-Jenkins benchmark). The following neuro-fuzzy systems have been considered: nfMod – the system proposed in this paper, the well-known ANFIS and NFIDENT ...

Amathematical model of the reheating process of steel slabs in industrial fuel-fired furnaces is developed. The transient temperature field inside the slabs is computed by means of the Galerkin method. Radiative heat transfer inside the furnace constitutes boundary conditions that couple the dynamic subsystems of the slabs. Constraining the heat fluxes to piecewise linear, discontinuous signals...

A mathematical heat transfer model for the prediction of transient heating of the slab in a direct-fired walking beam type reheating furnace has been developed by considering the nongray thermal radiation with given furnace environments. The furnace is modeled as radiating nongray medium with carbon dioxide and water with five-zoned gas temperature and the furnace wall is considered as a consta...