Deep Learning for the Prediction of Temperature Time Series in the Lining of an Electric Arc Furnace for Structural Health Monitoring at Cerro Matoso (CMSA)

Abstract

Cerro Matoso SA (CMSA) is located in Montelibano, Colombia. It is one of the biggest producers of ferronickel in the world. The structural health monitoring process performed in the electric arc furnaces at CMSA is of great importance in the maintenance and control of ferronickel production. The control of thermal and dimensional conditions of the electric furnace aims to detect and prevent failures that may affect its physical integrity. A network of thermocouples distributed radially and at different heights from the furnace wall, are responsible for monitoring the temperatures in the electric furnace lining. In order to optimize the operation of the electric furnace, it is important to predict the temperature at some points. However, this can be difficult due the number of variables which it depends on. To predict the temperature behavior in the electric furnace lining, a deep learning model for time series prediction has been developed. Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and other combinations were tested. GRU characterized by its multivariate and multi output type had the lowest square error. A study of the best input variables for the model that influence the temperature behavior is also carried out. Some of the input variables are the power, current, impedance, calcine chemistry, temperature history, among others. The methodology to tune the parameters of the GRU deep learning model is described. Results show an excellent behavior for predicting the temperatures 6 h into the future with root mean square errors of 3%. This model will be integrated to a software that obtains data for a time window from the Distributed Control System (DCS) to feed the model. In addition, this software will have a graphical user interface used by the operators furnace in the control room. Results of this work will improve the process of structural control and health monitoring at CMSA.

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

“…Recently, deep learning advances have emerged as a satisfactory method to perform time series forecasting. The recurrent neural networks and their variants, such as Gated Recurrent Unit (GRU) and Long Short-Term Memory (LSTM), have addressed the problem of vanishing gradient and long-term dependencies, achieving remarkable behaviors [19].…”

“…This kind of model can use recurrent neural networks (RNN) to handle the temporal dynamic behavior of the data. The long-term dependency of the temperature predictions in the EAF was compared using, first, a Long Short-Term Memory (LSTM) unit and, second, a Gated Recurrent Unit (GRU) approach [19]. These kinds of cells are used in contrast with traditional RNN due to the capacity to handle the vanishing and exploding long-term gradient problems [20].…”

Monitoring of the refractory lining in a shielded electric arc furnace: An online multitarget regression trees approach

“…A work related to data preprocessing to handle a large amount of operation data in the CMSA furnaces presents a set of rules and filters in order to detect variables with anomalies and outliers 26 . Another work related to the development of a predictive temperature model based on deep learning time series reached low mean square error errors, predicting accurately temperatures in different sectors of the furnace 27 . In the process of shut down and initialize again the furnace, a contraction and expansion process of the hearth lining occurs; to measure the possible gap formation, an ultrasound‐based method was deploy in the work of Tibaduiza et al in 2020.…”

“…26 Another work related to the development of a predictive temperature model based on deep learning time series reached low mean square error errors, predicting accurately temperatures in different sectors of the furnace. 27 In the process of shut down and initialize again the furnace, a contraction and expansion process of the hearth lining occurs; to measure the possible gap formation, an ultrasound-based method was deploy in the work of Tibaduiza et al in 2020. This work found two important measures related with the gap monitoring in the furnace hearth, the signal to noise ratio, and the DC component of the signals.…”