Temperature Prediction Using Multivariate Time Series Deep Learning in the Lining of an Electric Arc Furnace for Ferronickel Production

Abstract

The analysis of data from sensors in structures subjected to extreme conditions such as the ones used in smelting processes is a great decision tool that allows knowing the behavior of the structure under different operational conditions. In this industry, the furnaces and the different elements are fully instrumented, including sensors to measure variables such as temperature, pressure, level, flow, power, electrode positions, among others. From the point of view of engineering and data analytics, this quantity of data presents an opportunity to understand the operation of the system under normal conditions or to explore new ways of operation by using information from models provided by using deep learning approaches. Although some approaches have been developed with application to this industry, it is still an open research area. As a contribution, this paper presents an applied deep learning temperature prediction model for a 75 MW electric arc furnace, which is used for ferronickel production. In general, the methodology proposed considers two steps: first, a data cleaning process to increase the quality of the data, eliminating both redundant information as well as atypical and unusual data, and second, a multivariate time series deep learning model to predict the temperatures in the furnace lining. The developed deep learning model is a sequential one based on GRU (gated recurrent unit) layer plus a dense layer. The GRU + Dense model achieved an average root mean square error (RMSE) of 1.19 °C in the test set of 16 different thermocouples radially distributed on the furnace.

Enhancing the accuracy of low-cost thermocouple devices through deep-wavelet neural network calibration

“…Discrete wavelet transform is more commonly used than continuous wavelet transforms for signal decomposition [29]. The Haar transformation is used in the noise reduction function because of its simplicity, versatility, and computational efficiency [30], as shown in (7) and (8).…”

“…In fact, the process of implementing the Kalman filter is strongly depend on the system dynamic model which is set at the beginning and ineffective with the high variation data [7]. Another approach by Leon-Medina et al [8] using a deep neural network has also been carried out to minimize the amount of noise contained in the thermocouple data and obtain the best of root mean squared error (RMSE) value of 1.19 °C. However, the presence of noise is still visible in the peak signal area.…”

Data‐Driven Approach Using Supervised Learning for Predicting Endpoint Temperature of Molten Steel in the Electric Arc Furnace

“…Through this approach, it was found that the carbon content had the largest effect on electrical energy consumption in the EAF. Leon–Medina et al [ 6 ] analyzed the voltage, power, and electrode positions of an EAF system and proposed an EAF temperature prediction model using a grated recurrent unit (GRU) deep learning model. Chen et al [ 7 ] applied a deep learning technique to energy consumption modeling to improve the energy efficiency of an EAF system.…”

Attention-Based Deep Recurrent Neural Network to Forecast the Temperature Behavior of an Electric Arc Furnace Side-Wall

“…The lining monitoring variables comprise temperature, heat fluxes, water quality, remaining thickness refractory, sidewall erosion and protective layer formation, among others [14]. However, the development of temperature lining prediction models in an EAF is still an open research field because of the reduced number of works in this area [15,16].…”