Open Access

ARTICLE

PREDICTING THE WAX DEPOSITION RATE BASED ON EXTREME LEARNING MACHINE

Qi Zhuang^a,* , Zhuo Chen^b, Dong Liu^c, Yangyang Tian^d

a The Second Gas Production Plant, PetroChina Changqing Oilfield Company, Xi’an China
b Sinopec Northwest Oil field Company, Urumqi, China
c Safety and Environmental Supervision Department, PetroChina Changqing Oilfield Company, Xi’an China
d Shaanxi Key Laboratory of Advanced Stimulation Technology for Oil & Gas Reservoirs, College of Petroleum Engineering, Xi’an Shiyou University, Xi’an China
* Corresponding Author. E-mail: 1900679914@qq.com.

Frontiers in Heat and Mass Transfer 2022, 19, 1-8. https://doi.org/10.5098/hmt.19.19

Abstract

In order to improve the accuracy and efficiency of wax deposition rate prediction of waxy crude oil in pipeline transportation, A GRA-IPSO-ELM model was established to predict wax deposition rate. Using Grey Relational Analysis (GRA) to calculate the correlation degree between various factors and wax deposition rate, determine the input variables of the prediction model, and establish the Extreme Learning Machine (ELM) prediction model, improved particle swarm optimization (IPSO) is used to optimize the parameters of ELM model. Taking the experimental data of wax deposition in Huachi operation area as an example, the prediction performance of the model is evaluated by modeling and simulation, and compared with other models. The results show that the Mean Relative Error (MRE) and the Root Mean Square Error (RMSE) of the GRA-IPSO-ELM model are 0.351% and 0.049 respectively. Compared with other models, the GRA-IPSO-ELM model has better prediction performance.

---

Keywords

---