A Study on the Prediction of Pressure in Gas Governor System  
Author Eun-Wook Choi


Co-Author(s) Dayeon Lee; Shihyun Kim; Seohoon Jin


Abstract Urban gas companies need to efficiently manage static pressure devices to supply gas to consumers safely. This paper aims to improve the performance of the existing pressure management system through the prediction of the pressure. This study proposed an urban gas pressure prediction system based on time series model and the machine learning models such as LSTM and MLP. The data for analysis were collected using the SCADA system. External factors affecting the pressure were also gathered. After preprocessing the data, the data was composed of training data and validation data. The model was optimized through the normalization process. Through this, among the models examined, the MLP model showed good predictive performance in all predictive evaluation indicators. It is thought that the pressure prediction system proposed in this paper can increase the management efficiency of the static pressure machine and help experts make the better decisions based on visualized data.


Keywords Static pressure facility, time series, machine learning, prediction
    Article #:  DSBFI23-39
Proceedings of 2nd ISSAT International Conference on Data Science in Business, Finance and Industry
January 8-10, 2023 - Da Nang, Vietnam