TY  - CONF
UR  - https://www.scopus.com/inward/record.uri?eid=2-s2.0-85149141692&doi=10.1109%2fICFTSC57269.2022.10039824&partnerID=40&md5=8233009e139612f812397b9863da6d0c
AV  - none
PB  - Institute of Electrical and Electronics Engineers Inc.
N2  - Prediction of production flow rates of industrial flow meter will bring significance value in terms of production and maintenance optimization, and mass balancing in oil and gas industry. This paper proposes a long short-Term memory-based model to predict production flow of an industrial flow meter. Besides, this paper also discusses the significance of training sample size and hyperparameter of machine learning model upon the accuracy of the prediction. This paper found that with simpler model architecture (32 LSTM units and 8 Rectified Linear Units) has produced a prediction with 1.4 Root Mean Square Error, that has similar performance of a more complex model configuration (64 LSTM units). © 2022 IEEE.
N1  - cited By 1; Conference of 2022 International Conference on Future Trends in Smart Communities, ICFTSC 2022 ; Conference Date: 1 December 2022 Through 2 December 2022; Conference Code:186671
KW  - Balancing; Brain; Flow measurement; Flow of gases; Flowmeters; Gas industry; Long short-term memory; Mean square error
KW  -  Flow characteristic; Flow meter; Industrial flows; Maintenance optimization; Mass balancing; Memory units; Memory-based modeling; Oil and Gas Industry; Production flows; Production optimization
KW  -  Forecasting
SP  - 214
SN  - 9798350334548
TI  - Development of Gas Flow Characteristic Prediction for Industrial Flow Meter using Long Short-Term Memory (LSTM)
ID  - scholars17237
A1  - Mustafa, M.F.
A1  - Talib, A.M.
A1  - Rashid, R.Z.J.A.
A1  - Ismail, I.
A1  - Awang, A.
A1  - Saad, M.N.M.
A1  - Zahari, M.S.
EP  - 217
Y1  - 2022///
ER  -