Artificial Neural Network (ANN) based models were developed for predicting viscosity and wax deposition potentials of petroleum reservoir fluids as a preliminary measure to address the problem of loss of production associated with wax deposition. Several ANN architectures were trained using supervised paradigms for viscosity modeling and unsupervised paradigms for wax deposition potentials. Input to the models is temperature, pressure and viscosity data of the reservoirs. Five Nigerian crude oil and gas condensate reservoir data were used to validate the models. ANN competitive layer wax deposition model developed in this work excellently identified crude oil and gas condensate potential to deposit wax in upstream and downstream facilities compared to classical regression technique (CRT) based mathematical model. The inherent problems of tubing and pipeline blockage by wax deposits would be minimized by the application of the predicting models during well development stage prior to production Introduction Paraffin crude oil problems have been identified practically in every oil producing country around the world in a trend similar to global oil occurrences. Paraffin deposition causes a loss of billions of dollars per year worldwide due to the enormous cost of prevention and remediation, reduced or deferred production, well shut-in, pipeline replacements and/or abandonment, equipment failures, extra horse power requirements, and increased manpower needs. In Nigeria, pipelines have been known to wax up beyond recovery. Production tubing has also been known to wax up necessitating frequent wax cutting, using scrapers conveyed by wireline, which is an expensive practice. The problem is becoming more severe because production is predominantly offshore, where it is more difficult to pressurize the system at intermediate points thus repeatedly leading to loss of flow-lines and abandonment of wells.
The many purposes and benefits of tubing pickling include iron control, scale removal, sludge prevention, removal of damaging pipe dope, asphaltene or paraffin deposit, elimination of spent acid, prevention of sulphur species deposition, improvement in stimulation and reduction in overall treatment cost. Corrosive hydrochloric or acetic acid is the common pickling solution. Additionally they often contain hazardous organic solvent and surfactant to remove asphaltene or wax deposit and pipe damaging dope residue. The major problem of acid based system is safety concern as pickle acid systems are classified as hazardous materials before pickling and upon return to the surface after treatment. The near neutral pickling fluid is an environmentally favourable derusting fluid which has the capability of reacting with rust, mill scale and steel substrate producing a protective phosphate film that coats the metal surface to provide a corrosion protection through passivity mechanisms. Near neutral pickling fluid has been successfully applied in some workover risers in the Niger Delta at low seabed temperature. Results of the applications are very impressive and these shall be discussed in this paper. Also to be discussed is the application of the near neutral fluid in the fishing of a 2-3/8″PXN plug which got stuck at the XN-nipple in an old tubing making it impossible to set an A-5 dual completion parker. All previous attempts to retrieve the fish for over 72 hours had failed but the fish (23ft long) was recovered with slick line after soaking well with the near neutral fluid over night.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.