Synthesis of Ultra High Molecular Weight HPAM and Viscosity Forecast by BP Neural Network
Keywords:ultra high molecular weight HPAM, BP neural network, viscosity, oil-displacing agent
AbstractHydrolyzed polyacrylamide (HPAM) is widely used to increase the sweep efficiency of water phase in oil reservoirs. It is very important to select proper polymer for the reservoirs. In this study, a series of ultra high molecular weight HPAMs were synthesized and characterized by FT-IR analysis. Their physical properties were tested under reservoir condition. BP neural network (BPNN) was employed to forecast the viscosity of high molecular weight HPAM in produced water. The input indices including molecular weight, solid content, degree of hydrolysis, water-insoluble residue, polymer concentration, temperature of reservoir and salinity of produced water. The results show that all physical properties fulfill the requirements of Q/SY DQ1059-2005. This BPNN can predict the viscosity of ultra high molecular weight HPAM accurately. It is proposed that this BPNN can be used to screen proper polymers for enhance oil recovery.
The copyrights for articles in this journal are retained by the author(s), with first publication rights granted to the journal. By virtue of their appearance in this open-access journal, articles are free to use with proper attribution in educational and other non-commercial settings.