Search

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. [ABSTRACT FROM AUTHOR]

In periodic condition monitoring, the main problem lies in determining the inspection time intervals. This paper presents a new method for setting an optimum calendar to inspect a critical component that fails due to wear and tear as described by a Weibull probability function. By considering a set of inspection intervals, such that reliability between every two inspections is kept equal or below a pre-set threshold while keeping the total costs of inspection, degraded production, consequences of failure, and repair to a minimum. The resulting calendar may be adjusted dynamically over time as inspections take place and test results are found to be negative, by considering the inspector's confidence in the test and the likelihood of the method's yielding false negatives. Consequently, the method becomes self-adjustable as it returns a new calendar after the observations of each test are known and properly interpreted. There are several studies that deal with this issue, but none addresses the concept of safe and unsafe time windows which results from merging two other concepts: descendant inspection time intervals and the time delay between a potential failure and a functional failure (the P-F period). [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]