1. Comparing LSTM and GRU Models to Predict the Condition of a Pulp Paper Press
- Author
-
Antonio J. Marques Cardoso, Rui Assis, Balduíno César Mateus, Mateus Mendes, and José Torres Farinha
- Subjects
Technology ,Multivariate statistics ,Control and Optimization ,Computer science ,GRU ,Energy Engineering and Power Technology ,Machine learning ,computer.software_genre ,Predictive maintenance ,predictive maintenance ,LSTM ,recurrent neural network ,paper press ,Autoregressive integrated moving average ,Electrical and Electronic Engineering ,Engineering (miscellaneous) ,Hyperparameter ,Artificial neural network ,Renewable Energy, Sustainability and the Environment ,business.industry ,Univariate ,Statistical model ,Recurrent neural network ,Artificial intelligence ,business ,computer ,Energy (miscellaneous) - Abstract
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.
- Published
- 2021
- Full Text
- View/download PDF