Research and Application of Element Logging Intelligent Identification Model Based on Data Mining

Haibo Liang,Chen Yun,Muhammad Junaid Kan,Jianchong Gao

doi:10.1109/access.2019.2928001

Abstract

Underground strata are reflected in various information sources in petroleum exploration, including good logging and drilling data. Real-time measurement parameters obtained from mud logging can provide data support for the early discovery of oil and gas resources and the prevention of safety accidents. It plays a forward-looking role in the drilling process. In this paper, we aim at the defection of fuzzy and random characteristics of the big data of drilling element parameters in the current drilling process. A new method named grey wolf optimization-support vector machine (GWO-SVM) is proposed by analyzing the relationship between logging data and formation to solve the serious problem of formation misjudgment. Using element content and Gamma-ray value, data mining is performed by a large number of real-time data obtained from the drilling site. The obtained information is used for comprehensive estimation and prediction of strata. First, the data is normalized, and then, the best $\zeta $ and $\sigma $ values are found through the optimization of gray wolf algorithm, next the SVM training is carried out, finally, the formation prediction model is established, and the error analysis of the results was conducted. In the paper, the algorithm model is subsequently applied to three actual wells. The GWO-SVM model based on drilling data is used to predict the formation, and the error analysis showed that the error range of the GWO-SVM algorithm is within 10%. Compared with the GWO-SVM, the model accuracy of SVM, Particle Swarm Optimization-Support Vector Machine (PSO-SVM) algorithm is lower 53% and 23%, respectively. The GWO-SVM has higher robustness, reliability, and achieves faster convergence speed, stronger generalization effect, and improves the identification accuracy of elements for the formation. The average accuracy of the GWO-SVM in stratum dynamic identification is 93.5%. This model is implemented to support the logging system to improve application strength.

Highlights

Data mining includes 8 processes, such as data cleaning, data transformation, data mining process, pattern evaluation, and knowledge representation [1]
We explore a more effective element logging method grey wolf optimization-support vector machine (GWO-support vector machine (SVM)) algorithm model based on multi-information fusion
The results demonstrate that the accuracy of SVM and Particle Swarm OptimizationSupport Vector Machine (PSO-SVM) models is less than that of Grey Wolf Optimization (GWO)-SVM

Summary

INTRODUCTION

Data mining includes 8 processes, such as data cleaning, data transformation, data mining process, pattern evaluation, and knowledge representation [1]. We explore a more effective element logging method GWO-SVM algorithm model based on multi-information fusion. It can reflect the underground element data in real time and provide an effective and accurate method to evaluate the formation. GWO-SVM model process steps are as follows (FIGURE 4.): Step: We collect original element logging data. Step: Taking the normalized data as the learning sample of SVM, we match the GWO model to the σ and ζ parameter to optimize the operation. The SVM is trained according to the sample data, and the optimal kernel function parameters and penalty parameters are obtained. Increasing and updating the training sample set makes the GWO-SVM model to obtain more accurate results

ENGINEERING APPLICATION

Findings

CONCLUSION