Predicting machine failure using recurrent neural network-gated recurrent unit (RNN-GRU) through time series data

Abstract

Time series data often involves big size environment that lead to high dimensionality problem. Many industries are generating time series data that continuously update each second. The arising of machine learning may help in managing the data. It can forecast future instance while handling large data issues. Forecasting is related to predicting task of an upcoming event to avoid any circumstances happen in current environment. It helps those sectors such as production to foresee the state of machine in line with saving the cost from sudden breakdown as unplanned machine failure can disrupt the operation and loss up to millions. Thus, this paper offers a deep learning algorithm named recurrent neural network-gated recurrent unit (RNN-GRU) to forecast the state of machines producing the time series data in an oil and gas sector. RNN-GRU is an affiliation of recurrent neural network (RNN) that can control consecutive data due to the existence of update and reset gates. The gates decided on the necessary information to be kept in the memory. RNN-GRU is a simpler structure of long short-term memory (RNN-LSTM) with 87% of accuracy on prediction.

Learning algorithm of artificial neural network factor forecasting power consumption of users

“…To develop an algorithm for training a neural network of factorial forecasting of electricity consumption by household consumers, it is proposed [23], [24]: − To identify and describe a mathematical model of additional variable factors (coefficient characterizing the terrain conditions) affecting the accuracy of the forecast in conditions of inaccessibility (elevation differences above sea level), the absence of other sources (gas supply and heat supply) and the welfare of consumers − Taking into account the coefficient characterizing the conditions of the area, propose a method for predicting electricity consumption by household consumers; − Build a computer model for predicting power consumption by household consumers in the MATLAB environment − Choice of a learning algorithm for artificial neural network factorial forecasting of electricity consumption by household consumers − Compare the results obtained by the method, computer and neural network model with the results of experiments.…”

Penerapan Deep Learning Menggunakan Gated Recurrent Unit Untuk Memprediksi Harga Minyak Mentah Dunia

“…GRU diciptakan untuk mengatasi permasalahan vanishing gradient yang terjadi pada RNN [20]. GRU dapat digunakan untuk memprediksi data timeseries seperti memprediksi harga saham [21]- [23], memprediksi bilangan sunspot [20], dan memprediksi kegagalan mesin [24]. Selain itu, terdapat penelitian yang dilakukan oleh Insyiraah Oxaichiko Arissinta, Indah Dwi Sulistiyawati, Dedy Kurnianto, dan Iqbal Kharisudin pada tahun 2022 melakukan perbandingan performansi LSTM, GRU dan ARIMA dalam memprediksi web traffic.…”