A BP Neural Network Predictor Model for Desulfurizing Molten Iron

Conference PaperinLecture Notes in Computer Science 3584:728-735 · July 2005with7 Reads
DOI: 10.1007/11527503_86 · Source: DBLP
Conference: Advanced Data Mining and Applications, First International Conference, ADMA 2005, Wuhan, China, July 22-24, 2005, Proceedings
Abstract
Desulfurization of molten iron is one of the stages of steel production process. A back-propagation (BP) artificial neural network (ANN) model is developed to predict the operation parameters for desulfurization process in this paper. The primary objective of the BP neural network predictor model is to assign the operation parameters on the basis of intelligent algorithm instead of the experience of operators. This paper presents a mathematical model and development methodology for predicting the three main operation parameters and optimizing the consumption of desulfurizer. Furthermore, a software package is developed based on this BP ANN predictor model. Finally, the feasibility of using neural networks to model the complex relationship between the parameters is been investigated.
    • "When modelling processes that have noise and complex characteristics such as the hot-rolling process, the goal is not only to generate models that approximate the given target output value, but also to give an insight on the dynamics of the underlying system. Many authors focused on the issue of quality monitoring in hot-rolling process using artificial neural networks (ANN) and fuzzy logic (FL) (Rong et al., 2005; Bouhouche et al., 2008; Tiensuu et al., 2011; Barrios et al., 2012; Faris et al., 2013). The rolling force model is a significant factor in technology-controlled rolling process. "
    [Show abstract] [Hide abstract] ABSTRACT: Satisfying the customers' need for manufacturing plants and the demand for high-quality products becomes more challenging nowadays. Manufacturers need to retain advanced attributes of their products by applying high-quality automation process. In this paper, a genetic programming (GP) approach is applied in order to develop three mathematical models for the force, torque and slab temperature in the hot-rolling industrial process. A frequency-based analysis using GP is performed to provide an insight into the process significant factors. The performance of the GP developed models is evaluated with respect to the known soft computing models explored in the literature. Experimental data were collected from the Ereğli Iron and Steel Factory in Turkey and used to test the performance of the GP models. Genetic programming shows better performance modelling capabilities compared with models-based artificial neural networks and fuzzy logic.
    Full-text · Article · Jan 2014
    • "Recently, many soft computing techniques were applied to quality monitoring in hot rolling process (Gorni 2002). Most of these techniques focused on using ANNs and FL approaches (Rong, Dan, and Yi 2005; Bouhouche et al. 2008; Barrios, Torres-Alvarado, and Cavazos 2012). In Zarate and Dias (2009), a neural network was used for modelling a cold rolling process. "
    [Show abstract] [Hide abstract] ABSTRACT: Steel making industry is becoming more competitive due to the high demand. In order to protect the market share, automation of the manufacturing industrial process is vital and represents a challenge. Empirical mathematical modelling of the process was used to design mill equipment, ensure productivity and service quality. This modelling approach shows many problems associated to complexity and time consumption. Evolutionary computing techniques show significant modelling capabilities on handling complex non-linear systems modelling. In this research, symbolic regression modelling via genetic programming is used to develop relatively simple mathematical models for the hot rolling industrial non-linear process. Three models are proposed for the rolling force, torque and slab temperature. A set of simple mathematical functions which represents the dynamical relationship between the input and output of these models shall be presented. Moreover, the performance of the symbolic regression models is compared to the known empirical models for the hot rolling system. A comparison with experimental data collected from the Ere[gtilde]li Iron and Steel Factory in Turkey is conducted for the verification of the promising model performance. Genetic programming shows better performance results compared to other soft computing approaches, such as neural networks and fuzzy logic.
    Article · Aug 2013
    • "It consists of an input layer, a hidden layer and an output layer. BP-ANN can be used to approximate any a nonlinear function: f: X→Y[13]. "
    [Show abstract] [Hide abstract] ABSTRACT: Nondestructive measurement of grape leaf chlorophyll content is essential for precision vineyard management. Multi-spectral imaging technology was adopted for image acquisition of grape leave. For each leaf, a color (R-G-B) image and a near-infrared (NIR) image were taken. These images were then transformed into three vegetation indices, e.g. RVI, NDVI and GNDVI. Calibration models were established, by single-variable linear regression, multi-variable linear regression and BP-ANN. Three color space systems, e.g. R-G-B, CIE XYZ and HIS, were examined with the purpose of model optimization. A total of 112 leave were divided into a calibration set(62) and an independent validation set(50). A SPAD-502 chlorophyll meter was used for reference measurement. The single-variable linear regression result shows that the NDVI index is most significant for the measurement of leaf chlorophyll content with coefficient of determination (r2) of 0.70 for calibration set and 0.69 for independent validation set. It is found that the model for R-index produces higher accuracy than those for G- and B-index, which confirms that chlorophyll content can be correlated with R-grayscale values. By comparison, the multi-variable linear regression models based on R-G-B-NIR achieves higher prediction accuracy with r2 of 0.8174. To further improve the prediction accuracy, several BP-ANN models were developed. The best result was achieved for R-G-B-NIR with r2 of 0.99 for independent validation set. It is concluded that multi-spectral imaging technology coupled with BP-ANN calibration model of R-G-B-NIR grayscales is promising for nondestructive measurement of grape leaf chlorophyll content. This method proposed in the study is worthy of being further examined for in situ determination of nutrition diagnose of grape plant.
    Article · Sep 2011
Show more

  • undefined · undefined
  • undefined · undefined
  • undefined · undefined