Optimizing Well Perforation with Machine Learning: A Breakthrough in Predictive Modeling

Abstract The accurate measurement of perforation length is important for better fluid flow and cost management. For the past eight decades, research has focused on well perforators within both ballistics science and energy domains. Past years saw numerous standardized testing and empirical model development to estimate perforation penetration depth under downhole conditions. The existing models possess restricted functionality while needing regular calibration and ignore numerous components that influence the penetration depth of perforations. This research aims to create an adaptable machine learning system based on API-19B standard perforator data obtained from different operational environments for perforation penetration length prediction. The holistic machine learning methodology allowed us to create ten machine learning models from normal perforation operational data that includes shot phasing, shot density, casing grade, casing nominal weight, casing outer diameter, explosive type, temperature rating and explosive weight, cement compressive strength, and gun diameter. The created models utilize penetration lengths directly measured through API-19B Section-01 testing, which serve as their output data. The paper implements Gradient Boosting, AdaBoost, Random Forest, Support Vector Machines, Decision Trees, K-Nearest Neighbor, Linear Regression, Neural Network, and Stochastic Gradient Descent algorithms, which received data from 1,648 actual API-19B Section-01 tests. The dataset consists of 16,480 points, which are divided into two sections where 80% (13,184 points) serve training algorithms and 20% (3,296 points) evaluate their predictive capacity. Moreover, the machine learning model's efficiency is evaluated through both K-fold and random sampling validation techniques. The computation of mean absolute percent error (MAPE) revealed the most effective machine learning models, which included AdaBoost, Random Forest, Gradient Boosting, Neural Network (L-BFGS), and K-Nearest Neighbors at 3.3%, 4.5%, 5.3%, and 8.1%, respectively, compared to actual measurements of perforation penetration length. In addition, the models demonstrate high correlation rates (R²) with 0.92, 0.88, 0.86, 0.84, and 0.69, respectively. This paper presents the operational improvements achieved through using machine learning models for estimating perforation penetration length. A machine learning modeling system provides precise, rapid, and economic estimation of perforation penetration length through an easier approach than either API-19B Section-01 tests or empirical models. These machine learning models have the capability to process multiple gun parameters along with different well completion types, which solved a universal problem that empirical models could not manage.