Ladle Furnace Steel Temperature Prediction Model Based on Partial Linear Regularization Networks with Sparse Representation

Abstract

Partial linear regularization networks (PLRN) combined with sparse representation technique is developed to establish the steel temperature prediction model for LF. Parametric linear part is introduced into the classical regularization networks in order to fit the partial linear structured temperature model, which is obtained by analyzing the mechanism of LF thermal system in detail. Improvement in prediction accuracy is achieved due to the well learning performance of regularization networks and the modification according to the special structure. Furthermore, sparse representation technique is adopted on original PLRN for the sake of reducing computational cost and further improving the generalization performance. Learning scheme of recursive version is designed to train the sparsely represented PLRN, in which support vectors is selected one-by-one and recursive algorithm is adopted for computational efficiency. The proposed method is examined by practical data. The experiment results demonstrate that the proposed method can both improve the prediction accuracy and lead to sparse solution, so that it reduce the storage need and the prediction time for practical application.

Online monitoring method for multiple operating batch processes based on local collection standardization and multi‐model dynamic PCA

“…After the melting and refining processes, the molten scrap is unloaded into a ladle and subjected to secondary steelmaking operations in the ladle furnace (LF). The LF steelmaking process is often used for the secondary refining of alloy steel . A LF furnace offers strong heating fluxes and enables precise temperature control, thereby allowing the addition of desired amounts of various alloying elements.…”

“…The LF steelmaking process is based on the simulation of a practical industrial process, which has been applied to predictive control composition and temperature of molten steel . The simulation model of the decentralized control strategy is capable of simulating a power supply system, a cooling water system, hydraulic system, electrode, and an argon gas system under various operating conditions.…”

“…The LF steelmaking process is often used for the secondary refining of alloy steel. [37,20] A LF furnace offers strong heating fluxes and enables precise temperature control, thereby allowing the addition of desired amounts of various alloying elements. It also provides outstanding desulphurization at high-temperature treatment by reducing molten steel fluxes and removing deoxidation products.…”

“…The feasibility and performance of the proposed method are illustrated by a 120 t LF steelmaking process. The studies on LF steelmaking process are mainly the bottom blowing argon technology, temperature control, and quality forecast . In the monitoring studies on LF steelmaking process, Dong proposed the fault diagnosis of a bottom blowing argon system based on a neural network in the steelmaking process.…”

“…The studies on LF steelmaking process are mainly the bottom blowing argon technology, temperature control, and quality forecast. [19][20][21] In the monitoring studies on LF steelmaking process, Dong [22] proposed the fault diagnosis of a bottom blowing argon system based on a neural network in the steelmaking process. Wang et al [23] proposed a fast monitoring method for the LF steelmaking process with incomplete modelling data types, in which the updown monitoring method is exploited to monitor a new batch type.…”