Automate Short Cyclic Well Job Candidacy Using Artificial Neural Networks–Enabled Lean Six Sigma Approach: A Case Study in Oil and Gas Company

Abstract

Artificial Neural Networks (ANNs) are a part of Artificial Intelligence (AI) that is commonly used for pattern recognition, regression and classification. This technology allows us to learn historical data and generate patterns from the precedent data. In oil and gas companies, large amounts of data are produced every day. Many accurate decisions in this type of company are made from the data. Cilon Indonesia (CI) Co. Ltd. is one of the oil and gas companies currently operating the largest oil field in Indonesia. This type of company's operation and financial profit depends on oil price, which is affected by global oil supply and demand. If oil prices fall suddenly, all oil and gas companies need to run their businesses more efficiently and effectively. There are many ways to make this kind of company run their business effectively and efficiently by implementing several strategies such as capital cost efficiency, operational cost efficiency and even laying off some employees. One of the major costs in operation in oil and gas companies is the cost for well workover. This well workover does not always produce oil gain. In fact, even it is resulting in oil gain, but not all well workover programs are economical whenever the oil price is low. This condition makes Petroleum Engineer (PE) need to select the best well workover for certain wells. Well candidates for workover are usually selected manually using data from many resources, reports and information. Well candidates are reviewed one by one, and with several criteria, the well is proposed to a certain type of well workover. This research explains how this company improves their selection of well candidates for the most economic workover called Short Cyclic Steam Stimulation (SCSS). The process improvement is done using the hybrid method: lean six sigma method and big data analytics method, which utilize ANNs to predict the oil after workover executed. The result demonstrates how this hybrid method can improve the process with a sustainable solution. Its successful improvement in PE time selects SCSS well candidates from 2 hours to 10 minutes to generate 20 wells per day. Its also improve the success rate of SCSS workover from 61% to 73%.