首页|Investigators from China University of Petroleum Have Reported New Data on Machi ne Learning (Interpretable Lost Circulation Analysis : Labeled, Identified, and Analyzed Lost Circulation In Drilling Operations)
Investigators from China University of Petroleum Have Reported New Data on Machi ne Learning (Interpretable Lost Circulation Analysis : Labeled, Identified, and Analyzed Lost Circulation In Drilling Operations)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Fresh data on Machine Learning are pre sented in a new report. According to news reporting originating from Beijing, Pe ople’s Republic of China, by NewsRx correspondents, research stated, “Lost circu lation (LC) is a serious problem in drilling operations, as it increases nonprod uctive time and costs. It can occur due to various complex factors, such as geol ogical parameters, drilling fluid properties, and operational drilling parameter s, either individually or in combination.” Our news editors obtained a quote from the research from the China University of Petroleum, “Therefore, studying the types, influencing factors, and causes of L C is crucial for effectively improving prevention and plugging techniques. Curre ntly, the expert diagnosis of LC types relies heavily on the experience and judg ment of experts, which may lead to inconsistencies and biases. Additionally, dif ficulties in obtaining data or missing important data can affect the efficiency and timeliness of diagnosis. Traditional physical modeling methods struggle to a nalyze complex factor correlations, and conventional machine learning techniques have limited interpretability. In this paper, we propose an interpretable lost circulation analysis (ILCA) framework that provides a new method for analyzing L C. First, we use Gaussian mixture model (GMM) clustering to analyze the LC chara cteristics of regional case data, efficiently and accurately labeling 296 LC eve nts. Second, we establish the relationship between geological features, drilling fluid properties, operational drilling parameters, and LC types using the XGBoo st algorithm. This enables timely identification of LC types during drilling ope rations using real - time data, with a precision greater than 85 %. Finally, we use interpretable machine learning techniques to conduct a comprehen sive quantitative analysis of influencing factors based on the established XGBoo st model, providing a clear explanation for the identification model. This enabl es drilling engineers to gain deeper insights into the factors influencing LC ev ents. In summary, the proposed ILCA framework is capable of efficiently labeling LC types based on regional case data, identifying LC types in a timely manner u sing real - time data, and conducting quantitative analysis of the factors and c auses of LC.”
BeijingPeople’s Republic of ChinaAsi aCyborgsEmerging TechnologiesMachine LearningChina University of Petrole um
NETL
NSTL
