Within a model of scientific and technical cooperation between the company Cerro
Matoso S.A. (CMSA) and the National University of Colombia (UNAL), a project was developed to
take advantage of the data obtained from a sensor network of a ferronickel electric arc furnace at
CMSA to improve the structural health monitoring process. Through this sensor network, online
data is obtained on the measurement of temperatures in the refractory lining of the electric
furnace, along with heat fluxes, and the chemical characterization of the minerals in each stage of
the process. These data are stored in a local database, which has several years of historical data
with valuable information for control and analysis tasks. These data reflect the behavior of the
industrial process and can be used in the development of machine learning models to predict the
operation of the electric arc furnace, and thus improve the decision-making process. Currently,
most of the data is analyzed by the experts of the structural control department but, due to the
large amount of data, the development of analytical tools is necessary to support their work. This
paper proposes a data cleaning approach to improve data quality by creating a set of rules and
filters based on both expert judgment and best practices in data quality. A statistical analysis was
also carried out to detect variables with anomalies and outliers, which do not represent a real
operation and belong to anomalous data that should not be considered for modelling. With the
proposed process, the quality of the data was improved and the data that were not useful were
eliminated, in order to consolidate a clean data set for later use in the development of machine
learning models. This work contributes to understanding the data cleansing rules that must be
considered to reflect the real behavior of the electric furnace operation for further analysis and
modeling tasks.