Title: Study on low flocculation and sterilisation technology of oilfield produced water based on GA-RBF optimisation algorithm
Authors: Fengbin Yang; Yujiang Wang
Addresses: Gudong Oil Production Company, Shengli Oilfield Company, SINOPEC, Dongying 257237, Shandong, China ' Shengli Oilfield Engineering Technology Management Centre, SINOPEC, Dongying 257000, Shandong, China
Abstract: There are a lot of sulphate reducing bacteria in produced water. A variety of cationic bactericides can be added to solve the problems of corrosion and blocking. The anionic polyacrylamide in the produced water of chemical flooding reacts with bactericide to produce flocculation sedimentation, which leads to the increase of sediment. Considering the bactericidal performance and compatibility, a kind of non-ionic low flocculation bactericide was developed, and its process parameters were optimised, which was proved by experiments. A genetic algorithm radial basis function (GA-RBF) neural network optimisation processor is proposed. The linear and nonlinear analyses of the orthogonal test parameters are carried out. Based on genetic algorithm, the weights and thresholds of neural network are optimised to complete the prediction of test samples and training samples.
Keywords: produced water; bactericide; experimental evaluation; RBF neural network; genetic algorithm.
DOI: 10.1504/IJMIC.2021.122495
International Journal of Modelling, Identification and Control, 2021 Vol.38 No.2, pp.165 - 174
Received: 04 Mar 2021
Accepted: 14 Apr 2021
Published online: 28 Apr 2022 *