Understanding the mechanical stability of wellbores using machine learning
ثبت نشده
چکیده
We try to understand the various components affecting the stability of tunneling and wellbore operations. We use a series of advanced finite element (FE) simulations to obtain a dataset which contains the stress response of the soil during drilling operations as a function of 12 input parameters. Using Multivariate Adaptive Regression Splines (MARS), we create a simplified model of the simulations (meta-model) and test its accuracy. Using the created meta-model, we perform Sobol sensitivity analysis and study the most important variables and interactions. Additionally, we explain how this approach is helpful for inverting the model to optimize the input variables.
منابع مشابه
Fault Detection of Anti-friction Bearing using Ensemble Machine Learning Methods
Anti-Friction Bearing (AFB) is a very important machine component and its unscheduled failure leads to cause of malfunction in wide range of rotating machinery which results in unexpected downtime and economic loss. In this paper, ensemble machine learning techniques are demonstrated for the detection of different AFB faults. Initially, statistical features were extracted from temporal vibratio...
متن کاملOnline Voltage Stability Monitoring and Prediction by Using Support Vector Machine Considering Overcurrent Protection for Transmission Lines
In this paper, a novel method is proposed to monitor the power system voltage stability using Support Vector Machine (SVM) by implementing real-time data received from the Wide Area Measurement System (WAMS). In this study, the effects of the protection schemes on the voltage magnitude of the buses are considered while they have not been investigated in previous researches. Considering overcurr...
متن کاملMachine Learning Models for Housing Prices Forecasting using Registration Data
This article has been compiled to identify the best model of housing price forecasting using machine learning methods with maximum accuracy and minimum error. Five important machine learning algorithms are used to predict housing prices, including Nearest Neighbor Regression Algorithm (KNNR), Support Vector Regression Algorithm (SVR), Random Forest Regression Algorithm (RFR), Extreme Gradient B...
متن کاملApplication of the Extreme Learning Machine for Modeling the Bead Geometry in Gas Metal Arc Welding Process
Rapid prototyping (RP) methods are used for production easily and quickly of a scale model of a physical part or assembly. Gas metal arc welding (GMAW) is a widespread process used for rapid prototyping of metallic parts. In this process, in order to obtain a desired welding geometry, it is very important to predict the weld bead geometry based on the input process parameters, which are voltage...
متن کاملPREDICTION OF SLOPE STABILITY STATE FOR CIRCULAR FAILURE: A HYBRID SUPPORT VECTOR MACHINE WITH HARMONY SEARCH ALGORITHM
The slope stability analysis is routinely performed by engineers to estimate the stability of river training works, road embankments, embankment dams, excavations and retaining walls. This paper presents a new approach to build a model for the prediction of slope stability state. The support vector machine (SVM) is a new machine learning method based on statistical learning theory, which can so...
متن کامل