Developing a novel workflow for natural gas lift optimization using advanced support vector machine

• Long-term optimization of the NGL in a real field has been performed using PSO and GA.
• Eclipse software was replaced by the trained SVM to decrease the optimization time.
• The optimum SVM parameters were determined by the PSO algorithm (Advanced SVM).
• Taguchi design was used to determine optimum GA and PSO parameters.

Natural Gas Lift (NGL) is one of the most attractive methods to enhance oil recovery. In this method, oil is produced using gas from the gas region either adjacent or far from the oil layer. The reservoir simulation software should be run many times to optimize the NGL process. This is practically impossible due to time-consuming simulation of an actual reservoir. In this study, support vector machine (SVM) was used to overcome the problem. The reservoir simulation software was replaced by the trained SVM. Through this, each run only takes a few seconds. The process was optimized for a real field using particle swarm optimization (PSO) and genetic algorithm (GA). The optimum SVM parameters were determined by the PSO algorithm. Taguchi experiment design was used to determine optimum GA and PSO parameters.