A smart device learns to drill

A smart device learns to drill

Guiding a drill through the earth with the same advanced automation used to steer planes and cars is currently impossible because the dense materials underground slow the speed of any instruction transmitted to a crawl.

Two recent engineering grads from Texas A&M University circumvent this slowdown with an advanced smart tool that processes sensor data, renders subsurface models, maps a route and directs drilling, all while sitting behind the drill bit.

Drs. Enrique Losoya ’22 and Narendra Vishnumolakala ’22 came up with the idea for the device when they were graduate students. Along with fellow student Connor Ust, they founded their own company, Teale Engineering LLC, in 2020 to take on the challenge of creating their product. In 2021, Teale received a Phase I grant of $256,000 in non-dilutive seed capital from the National Science Foundation (NSF) Small Business Technology Program.

“The goal of Phase I was to perform research, prove technical feasibility, and build the necessary proof-of-concept hardware and software,” Losoya said.

Former students enlisted Dr. Eduardo Gildin, LF Peterson Professor ’36 in the Harold Vance Department of Petroleum Engineering; Sheelabhadra Dey, PhD student in the Department of Computer Science and Engineering; and Paul Deere ’92 alumnus, an accomplished innovator and expert in downhole and measurement-while-drilling technology, as the research team for the project.

Currently, drillers steer bits using a downhole assembly that contains a bias or curvature. The drill string – the pipe attached to the assembly – is pushed down from above and constantly rotated to lower the drill bit. If the drill string is not rotated, the bit will drill in the direction of the bias. Drillers know which direction a drill bit is heading by following a tracker through the assembly. They direct the bit by reading reservoir models or maps generated by computers using data from underground sensors. Unfortunately, sensor data is transmitted through thousands of feet of rock and other materials to reach these computers. While modern commercial cellular transmissions can travel up to 10,000,000,000 bits, or 10 Gigabits, per second through air or space, Earth’s subsurface slows those speeds down to 2-6 bits. per second.

“Drilling with models is like driving a car blindly in the dark with only the instructions on the dashboard screen to guide you,” said Gildin, who is the team technical advisor. “Slow transmission speeds mean that these instructions take a long time to produce.”

The team puts the tool down the hole to get as close to the sensors as possible. This way, it can process the data and model a map in near real time. Placing the device right behind the drill also means it can steer with faster reaction times.

Several obstacles stood in the way of their product. First, the team had to build a physical device that was small enough to fit in the space behind a drill bit, but big enough to hold all the hardware. Second, they had to produce the software needed to process and render the sensor data. Third, they had to create animated simulations to train their tool’s machine-learning algorithms to understand its unique view of the tank and model – much like a car driver would if looking through a 360 windshield. degrees – and how to manipulate the drill string behind this. Additionally, the tool had to examine the reservoir model as a driller would, with production needs and safety issues as primary destinations and priorities.

For the first prototype, the former students borrowed what they could from off-the-shelf hardware while creating lots of software. Gildin and Dey helped develop the reinforcement learning algorithms needed for the tool to understand how to correctly judge the best drill path and drill speeds from the models. Losoya and Vishnumolakala created the virtual environment and real-time linearized model simulations needed to test the capabilities of the learning algorithms. The work was done on Teale servers and Texas A&M supercomputers under the direction of Gildin.

Dey said the custom drilling simulators were developed using popular simulation engines such as Unity Physics Engine, a “mature 3D development platform typically used for video games.”

Several months of trial and error finally resulted in successful lab tests, but the job is far from done. Now that the simulations and algorithms are working, the team needs to replace all the off-the-shelf technology with more robust equipment that can handle the harsh downhole conditions.

“We are seeking a Phase II grant from the NSF,” Losoya said. “This is where we evolve, refine, and focus on developing a smart, field-ready prototype and product.”

“Costs are higher as we experiment with new configurations and new materials,” said Deere, team manager and marketing consultant. “We will work with the major downhole tool vendors we know to scale our production so that we can deliver a smart and affordable product to operators. I am excited to help bring this research to market and expect that have a significant impact on the directional drilling market.

If the team can produce a cost-effective product smart enough to follow the best drilling routes every time, the tool could make drilling oil and geothermal wells more precise, more profitable and much safer.

Losoya and Vishnumolakala both earned master’s degrees in petroleum engineering and doctorates in multidisciplinary engineering from Texas A&M. Gildin, who mentored them during their time in petroleum engineering, emphasized how rare this opportunity is.

“It’s a tangible project where a product is developed,” Gildin said. “It’s an aspect of research that few students get to see because most research is scholarly.”

Since this project has strong research components, Losoya, Vishnumolakala, Dey and Gildin are producing a paper on the Phase I work which is scheduled for publication in 2023.

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of press releases posted on EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.

#smart #device #learns #drill

Leave a Comment

Your email address will not be published. Required fields are marked *