This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
The maintenance paradigm has evolved over the last few years and companies that want to remain co... more The maintenance paradigm has evolved over the last few years and companies that want to remain competitive in the market need to provide condition-based maintenance (CBM). The diagnosis and prognosis of the health status of equipment, predictive maintenance (PdM), are fundamental strategies to perform informed maintenance, increasing the company’s profit. This article aims to present a diagnosis and prognosis methodology using a hidden Markov model (HMM) classifier to recognise the equipment status in real time and a deep neural network (DNN), specifically a gated recurrent unit (GRU), to determine this same status in a future of one week. The data collected by the sensors go through several phases, starting by cleaning them. After that, temporal windows are created in order to generate statistical features of the time domain to better understand the equipment’s behaviour. These features go through a normalisation to produce inputs for a feature extraction process, via a principal c...
Forecasting algorithms have been used to support decision making in companies, and it is necessar... more Forecasting algorithms have been used to support decision making in companies, and it is necessary to apply approaches that facilitate a good forecasting result. The present paper describes assessments based on a combination of different neural network models, tested to forecast steel production in the world. The main goal is to find the best machine learning model that fits the steel production data in the world to make a forecast for a nine-year period. The study is important for understanding the behavior of the models and sensitivity to hyperparameters of convolutional LSTM and GRU recurrent neural networks. The results show that for long-term prediction, the GRU model is easier to train and provides better results. The article contributes to the validation of the use of other variables that are correlated with the steel production variable, thus increasing forecast accuracy.
Predictive maintenance strategies are becoming increasingly more important with the increased nee... more Predictive maintenance strategies are becoming increasingly more important with the increased needs for automation and digitalization within pulp and paper manufacturing sector.Hence, this study contributes to examine the most efficient pre-processing approaches for predicting sensory data trends based on Gated Recurrent Unit (GRU) neural networks. To validate the model, the data from two paper pulp presses with several pre-processing methods are utilized for predicting the units' conditions. The results of validation criteria show that pre-processing data using a LOWESS in combination with the Elimination of discrepant data filter achieves more stable results, the prediction error decreases, and the predicted values are easier to interpret. The model can anticipate future values with MAPE, RMSE and MAE of 1.2, 0.27 and 0.30 respectively. The errors are below the significance level. Moreover, it is identified that the best hyperparameters found for each paper pulp press must be different.
Forecasting Steel Production in the World—Assessments Based on Shallow and Deep Neural Networks, 2022
Forecasting algorithms have been used to support decision making in companies, and it is necessar... more Forecasting algorithms have been used to support decision making in companies, and it is necessary to apply approaches that facilitate a good forecasting result. The present paper describes assessments based on a combination of different neural network models, tested to forecast steel production in the world. The main goal is to find the best machine learning model that fits the steel production data in the world to make a forecast for a nine-year period. The study is important for understanding the behavior of the models and sensitivity to hyperparameters of convolutional LSTM and GRU recurrent neural networks. The results show that for long-term prediction, the GRU model is easier to train and provides better results. The article contributes to the validation of the use of other variables that are correlated with the steel production variable, thus increasing forecast accuracy.
Nowadays, companies want to give a quick answer in order to face their market competitors. Theseq... more Nowadays, companies want to give a quick answer in order to face their market competitors. Thesequick responses must be reflected in the quality of the products; to this be possible, it is necessary to manage anumber of factors that will bring benefits in its market positioning. As technology grows, there is the possibility, ata computational level, to create a combination of mathematical and technological tools that were not implementedin the past due to the lack of resources, since they have high robustness about their analytical resolution.This paper presents mathematical and computer tools that have potential great benefits when applied to industrialproblems solving, such as operation management.Along the paper it is made a temporal location of all tools with their main objectives about optimizing industrial processes, focusing on maintenance costs, contributing directly to the rationalization of global costs of theprocesses.Analytical and technological methods that have had gre...
Cada vez mais a globalização tem a noção da importância de efetuar previsões frente a alguns fenó... more Cada vez mais a globalização tem a noção da importância de efetuar previsões frente a alguns fenómenos que podem ocorrer, como por exemplo catástrofes naturais ou conflitos armados, uma vez que estes são um dos factores que apresentam grande influência na estabilidade económica e política de um país. Por consequência as empresas têm desenvolvido a procura de respostas sólidas de forma a reunir condições bastante suficientes para que se faça frente aos problemas. O presente estudo utiliza as séries temporais (ARMA e SARIMA) de forma a ser possível a construção de um modelo de previsão que melhor se ajusta aos dados de produção do aço, no caso, o país da comunidade europeia com valor de produção e consumo significativo de aço (Alemanha). Com a utilização das séries temporais, foi possível apresentar previsões que melhor se ajustam num espaço de tempo de 5 anos. Neste trabalho é apresentado um estudo exploratório relativamente à produção do aço, tendo como base de estudo a produção de ...
The accuracy of a predictive system is critical for predictive maintenance and to support the rig... more The accuracy of a predictive system is critical for predictive maintenance and to support the right decisions at the right times. Statistical models, such as ARIMA and SARIMA, are unable to describe the stochastic nature of the data. Neural networks, such as long short-term memory (LSTM) and the gated recurrent unit (GRU), are good predictors for univariate and multivariate data. The present paper describes a case study where the performances of long short-term memory and gated recurrent units are compared, based on different hyperparameters. In general, gated recurrent units exhibit better performance, based on a case study on pulp paper presses. The final result demonstrates that, to maximize the equipment availability, gated recurrent units, as demonstrated in the paper, are the best options.
Predictive maintenance is very important in industrial plants to support decisions aiming to maxi... more Predictive maintenance is very important in industrial plants to support decisions aiming to maximize maintenance investments and equipment’s availability. This paper presents predictive models based on long short-term memory neural networks, applied to a dataset of sensor readings. The aim is to forecast future equipment statuses based on data from an industrial paper press. The datasets contain data from a three-year period. Data are pre-processed and the neural networks are optimized to minimize prediction errors. The results show that it is possible to predict future behavior up to one month in advance with reasonable confidence. Based on these results, it is possible to anticipate and optimize maintenance decisions, as well as continue research to improve the reliability of the model.
Nowadays, companies want to give a quick answer in order to face their market competitors. Theseq... more Nowadays, companies want to give a quick answer in order to face their market competitors. Thesequick responses must be reflected in the quality of the products; to this be possible, it is necessary to manage anumber of factors that will bring benefits in its market positioning. As technology grows, there is the possibility, ata computational level, to create a combination of mathematical and technological tools that were not implementedin the past due to the lack of resources, since they have high robustness about their analytical resolution.This paper presents mathematical and computer tools that have potential great benefits when applied to industrialproblems solving, such as operation management.Along the paper it is made a temporal location of all tools with their main objectives about optimizing industrial processes, focusing on maintenance costs, contributing directly to the rationalization of global costs of theprocesses.Analytical and technological methods that have had gre...
Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press, 2021
The accuracy of a predictive system is critical for predictive maintenance and to support the rig... more The accuracy of a predictive system is critical for predictive maintenance and to support the right decisions at the right times. Statistical models, such as ARIMA and SARIMA, are unable to describe the stochastic nature of the data. Neural networks, such as long short-term memory (LSTM) and the gated recurrent unit (GRU), are good predictors for univariate and multivariate data. The present paper describes a case study where the performances of long short-term memory and gated recurrent units are compared, based on different hyperparameters. In general, gated recurrent units exhibit better performance, based on a case study on pulp paper presses. The final result demonstrates that, to maximize the equipment availability, gated recurrent units, as demonstrated in the paper, are the best options.
Anticipating Future Behavior of an Industrial Press Using LSTM Networks, 2021
Predictive maintenance is very important in industrial plants to support decisions aiming to maxi... more Predictive maintenance is very important in industrial plants to support decisions aiming to maximize maintenance investments and equipment’s availability. This paper presents predictive models based on long short-term memory neural networks, applied to a dataset of sensor readings. The aim is to forecast future equipment statuses based on data from an industrial paper press. The datasets contain data from a three-year period. Data are pre-processed and the neural networks are optimized to minimize prediction errors. The results show that it is possible to predict future behavior up to one month in advance with reasonable confidence. Based on these results, it is possible to anticipate and optimize maintenance decisions, as well as continue research to improve the reliability of the model.
Production Optimization versus Asset Availability – a Review, 2020
Nowadays, companies want to give a quick answer in order to face their market competitors. These ... more Nowadays, companies want to give a quick answer in order to face their market competitors. These quick responses must be reflected in the quality of the products; to this be possible, it is necessary to manage a number of factors that will bring benefits in its market positioning. As technology grows, there is the possibility, at a computational level, to create a combination of mathematical and technological tools that were not implemented in the past due to the lack of resources, since they have high robustness about their analytical resolution. This paper presents mathematical and computer tools that have potential great benefits when applied to industrial problems solving, such as operation management. Along the paper it is made a temporal location of all tools with their main objectives about optimizing industrial processes, focusing on maintenance costs, contributing directly to the rationalization of global costs of the processes. Analytical and technological methods that have had great success regarding to the reduction costs of production in industries are presented. The approaches of this paper bring a literary review of process optimization, namely about Neural Networks and multivariate analysis for prediction
This article is an open access article distributed under the terms and conditions of the Creative... more This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY
The maintenance paradigm has evolved over the last few years and companies that want to remain co... more The maintenance paradigm has evolved over the last few years and companies that want to remain competitive in the market need to provide condition-based maintenance (CBM). The diagnosis and prognosis of the health status of equipment, predictive maintenance (PdM), are fundamental strategies to perform informed maintenance, increasing the company’s profit. This article aims to present a diagnosis and prognosis methodology using a hidden Markov model (HMM) classifier to recognise the equipment status in real time and a deep neural network (DNN), specifically a gated recurrent unit (GRU), to determine this same status in a future of one week. The data collected by the sensors go through several phases, starting by cleaning them. After that, temporal windows are created in order to generate statistical features of the time domain to better understand the equipment’s behaviour. These features go through a normalisation to produce inputs for a feature extraction process, via a principal c...
Forecasting algorithms have been used to support decision making in companies, and it is necessar... more Forecasting algorithms have been used to support decision making in companies, and it is necessary to apply approaches that facilitate a good forecasting result. The present paper describes assessments based on a combination of different neural network models, tested to forecast steel production in the world. The main goal is to find the best machine learning model that fits the steel production data in the world to make a forecast for a nine-year period. The study is important for understanding the behavior of the models and sensitivity to hyperparameters of convolutional LSTM and GRU recurrent neural networks. The results show that for long-term prediction, the GRU model is easier to train and provides better results. The article contributes to the validation of the use of other variables that are correlated with the steel production variable, thus increasing forecast accuracy.
Predictive maintenance strategies are becoming increasingly more important with the increased nee... more Predictive maintenance strategies are becoming increasingly more important with the increased needs for automation and digitalization within pulp and paper manufacturing sector.Hence, this study contributes to examine the most efficient pre-processing approaches for predicting sensory data trends based on Gated Recurrent Unit (GRU) neural networks. To validate the model, the data from two paper pulp presses with several pre-processing methods are utilized for predicting the units' conditions. The results of validation criteria show that pre-processing data using a LOWESS in combination with the Elimination of discrepant data filter achieves more stable results, the prediction error decreases, and the predicted values are easier to interpret. The model can anticipate future values with MAPE, RMSE and MAE of 1.2, 0.27 and 0.30 respectively. The errors are below the significance level. Moreover, it is identified that the best hyperparameters found for each paper pulp press must be different.
Forecasting Steel Production in the World—Assessments Based on Shallow and Deep Neural Networks, 2022
Forecasting algorithms have been used to support decision making in companies, and it is necessar... more Forecasting algorithms have been used to support decision making in companies, and it is necessary to apply approaches that facilitate a good forecasting result. The present paper describes assessments based on a combination of different neural network models, tested to forecast steel production in the world. The main goal is to find the best machine learning model that fits the steel production data in the world to make a forecast for a nine-year period. The study is important for understanding the behavior of the models and sensitivity to hyperparameters of convolutional LSTM and GRU recurrent neural networks. The results show that for long-term prediction, the GRU model is easier to train and provides better results. The article contributes to the validation of the use of other variables that are correlated with the steel production variable, thus increasing forecast accuracy.
Nowadays, companies want to give a quick answer in order to face their market competitors. Theseq... more Nowadays, companies want to give a quick answer in order to face their market competitors. Thesequick responses must be reflected in the quality of the products; to this be possible, it is necessary to manage anumber of factors that will bring benefits in its market positioning. As technology grows, there is the possibility, ata computational level, to create a combination of mathematical and technological tools that were not implementedin the past due to the lack of resources, since they have high robustness about their analytical resolution.This paper presents mathematical and computer tools that have potential great benefits when applied to industrialproblems solving, such as operation management.Along the paper it is made a temporal location of all tools with their main objectives about optimizing industrial processes, focusing on maintenance costs, contributing directly to the rationalization of global costs of theprocesses.Analytical and technological methods that have had gre...
Cada vez mais a globalização tem a noção da importância de efetuar previsões frente a alguns fenó... more Cada vez mais a globalização tem a noção da importância de efetuar previsões frente a alguns fenómenos que podem ocorrer, como por exemplo catástrofes naturais ou conflitos armados, uma vez que estes são um dos factores que apresentam grande influência na estabilidade económica e política de um país. Por consequência as empresas têm desenvolvido a procura de respostas sólidas de forma a reunir condições bastante suficientes para que se faça frente aos problemas. O presente estudo utiliza as séries temporais (ARMA e SARIMA) de forma a ser possível a construção de um modelo de previsão que melhor se ajusta aos dados de produção do aço, no caso, o país da comunidade europeia com valor de produção e consumo significativo de aço (Alemanha). Com a utilização das séries temporais, foi possível apresentar previsões que melhor se ajustam num espaço de tempo de 5 anos. Neste trabalho é apresentado um estudo exploratório relativamente à produção do aço, tendo como base de estudo a produção de ...
The accuracy of a predictive system is critical for predictive maintenance and to support the rig... more The accuracy of a predictive system is critical for predictive maintenance and to support the right decisions at the right times. Statistical models, such as ARIMA and SARIMA, are unable to describe the stochastic nature of the data. Neural networks, such as long short-term memory (LSTM) and the gated recurrent unit (GRU), are good predictors for univariate and multivariate data. The present paper describes a case study where the performances of long short-term memory and gated recurrent units are compared, based on different hyperparameters. In general, gated recurrent units exhibit better performance, based on a case study on pulp paper presses. The final result demonstrates that, to maximize the equipment availability, gated recurrent units, as demonstrated in the paper, are the best options.
Predictive maintenance is very important in industrial plants to support decisions aiming to maxi... more Predictive maintenance is very important in industrial plants to support decisions aiming to maximize maintenance investments and equipment’s availability. This paper presents predictive models based on long short-term memory neural networks, applied to a dataset of sensor readings. The aim is to forecast future equipment statuses based on data from an industrial paper press. The datasets contain data from a three-year period. Data are pre-processed and the neural networks are optimized to minimize prediction errors. The results show that it is possible to predict future behavior up to one month in advance with reasonable confidence. Based on these results, it is possible to anticipate and optimize maintenance decisions, as well as continue research to improve the reliability of the model.
Nowadays, companies want to give a quick answer in order to face their market competitors. Theseq... more Nowadays, companies want to give a quick answer in order to face their market competitors. Thesequick responses must be reflected in the quality of the products; to this be possible, it is necessary to manage anumber of factors that will bring benefits in its market positioning. As technology grows, there is the possibility, ata computational level, to create a combination of mathematical and technological tools that were not implementedin the past due to the lack of resources, since they have high robustness about their analytical resolution.This paper presents mathematical and computer tools that have potential great benefits when applied to industrialproblems solving, such as operation management.Along the paper it is made a temporal location of all tools with their main objectives about optimizing industrial processes, focusing on maintenance costs, contributing directly to the rationalization of global costs of theprocesses.Analytical and technological methods that have had gre...
Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press, 2021
The accuracy of a predictive system is critical for predictive maintenance and to support the rig... more The accuracy of a predictive system is critical for predictive maintenance and to support the right decisions at the right times. Statistical models, such as ARIMA and SARIMA, are unable to describe the stochastic nature of the data. Neural networks, such as long short-term memory (LSTM) and the gated recurrent unit (GRU), are good predictors for univariate and multivariate data. The present paper describes a case study where the performances of long short-term memory and gated recurrent units are compared, based on different hyperparameters. In general, gated recurrent units exhibit better performance, based on a case study on pulp paper presses. The final result demonstrates that, to maximize the equipment availability, gated recurrent units, as demonstrated in the paper, are the best options.
Anticipating Future Behavior of an Industrial Press Using LSTM Networks, 2021
Predictive maintenance is very important in industrial plants to support decisions aiming to maxi... more Predictive maintenance is very important in industrial plants to support decisions aiming to maximize maintenance investments and equipment’s availability. This paper presents predictive models based on long short-term memory neural networks, applied to a dataset of sensor readings. The aim is to forecast future equipment statuses based on data from an industrial paper press. The datasets contain data from a three-year period. Data are pre-processed and the neural networks are optimized to minimize prediction errors. The results show that it is possible to predict future behavior up to one month in advance with reasonable confidence. Based on these results, it is possible to anticipate and optimize maintenance decisions, as well as continue research to improve the reliability of the model.
Production Optimization versus Asset Availability – a Review, 2020
Nowadays, companies want to give a quick answer in order to face their market competitors. These ... more Nowadays, companies want to give a quick answer in order to face their market competitors. These quick responses must be reflected in the quality of the products; to this be possible, it is necessary to manage a number of factors that will bring benefits in its market positioning. As technology grows, there is the possibility, at a computational level, to create a combination of mathematical and technological tools that were not implemented in the past due to the lack of resources, since they have high robustness about their analytical resolution. This paper presents mathematical and computer tools that have potential great benefits when applied to industrial problems solving, such as operation management. Along the paper it is made a temporal location of all tools with their main objectives about optimizing industrial processes, focusing on maintenance costs, contributing directly to the rationalization of global costs of the processes. Analytical and technological methods that have had great success regarding to the reduction costs of production in industries are presented. The approaches of this paper bring a literary review of process optimization, namely about Neural Networks and multivariate analysis for prediction
Uploads
Papers by Balduíno Mateus
in the past due to the lack of resources, since they have high robustness about their analytical resolution.
This paper presents mathematical and computer tools that have potential great benefits when applied to industrial problems solving, such as operation management.
Along the paper it is made a temporal location of all tools with their main objectives about optimizing industrial processes, focusing on maintenance costs, contributing directly to the rationalization of global costs of the processes.
Analytical and technological methods that have had great success regarding to the reduction costs of production in industries are presented. The approaches of this paper bring a literary review of process optimization, namely about Neural Networks and multivariate analysis for prediction
in the past due to the lack of resources, since they have high robustness about their analytical resolution.
This paper presents mathematical and computer tools that have potential great benefits when applied to industrial problems solving, such as operation management.
Along the paper it is made a temporal location of all tools with their main objectives about optimizing industrial processes, focusing on maintenance costs, contributing directly to the rationalization of global costs of the processes.
Analytical and technological methods that have had great success regarding to the reduction costs of production in industries are presented. The approaches of this paper bring a literary review of process optimization, namely about Neural Networks and multivariate analysis for prediction