System and method for design of rapid excavating and wear-resistant drill bits
A method for designing lithology-specific drill bits. The method creates an experimentally verified multiphysics model to predict drilling into site-specific rock formations. A physics-based, Eulerian-Lagrangian computational modeling framework to predict particle flow and tribological phenomena. The method uses this multiphysics model to generate virtual drilling data and then generates a machine learning enabled surrogate model of the physics-based model using the data from virtual drilling to provide design charts for drill bits.
1. A method for designing rock-specific drill bits for a drilling site, comprising:
characterizing lithology of rock encountered at said drill site;
using a point load strength test and usage of the data from the point load strength test to calibrate a multiphysics virtual rock, having similar lithological behavior to the rock encountered at the drill site;
performing experimental benchtop rock drilling, said benchtop drilling simulating high pressure and high temperature conditions encountered at said drilling site;
performing virtual drilling on said multi-physics virtual rock;
comparing results of said virtual drilling with results of said experimental benchtop rock drilling;
training and testing machine learning regression algorithms to generate lithology-specific drill bit design charts, wherein the training and testing utilize the comparative results from the virtual drilling and experimental benchtop rock drilling.
2. The method for designing rock-specific drill bits according to claim 1 , further comprising:
3-D printing a drill bit in accordance with said drill bit design chart.
3. The method for designing rock-specific drill bits according to claim 2 , further comprising:
using said drill bit chart as a lookup chart for drill scheduling software.
4. The method for designing rock-specific drill bits according to claim 1 , further comprising:
using said drill bit chart as a lookup chart for drill scheduling software.
5. The method for designing rock-specific drill bits according to claim 1 , further wherein said performing virtual drilling on said multi-physics virtual rock comprises course sampling by varying the number, angle, orientation and placement of the cutters.
6. A method for designing lithology-specific drill bits comprising:
generating an experimentally verified multiphysics model of a drill site to predict drilling into site-specific rock formations, the multiphysics model using a physics-based, Eulerian-Lagrangian computational modeling framework to predict particle flow and tribological phenomena at the drill site;
generating virtual drilling data associated with the drill site using the multiphysics model;
generating a machine learning enabled surrogate model of the multiphysics model of the drill site using the generated virtual drilling data;
generating a drill bit design chart using said machine learning enabled surrogate model;
using said drill bit chart as a lookup chart for drill scheduling software; and manufacturing a drill bit in accordance with said drill bit design chart.
7. The method for designing lithology-specific drill bits according to claim 6 , further comprising:
3-D printing a drill bit in accordance with said drill bit design chart.
8. The method for designing lithology-specific drill bits according to claim 6 , wherein the machine learning enabled surrogate model comprises a multi-layer neural network.