Oil & Gas


Driving reliability and improving maintenance outcomes with machine learning

#artificialintelligence

To remain competitive, complex industries need to deploy industrial automation more than ever, as intense global competition drives process industries to increase efficiency through reduced operating costs, increased production, higher quality and lower inventories. Applying the failure signature to the rest of the pumps provided an early warning, allowing early action to avoid a repeat incident, thus preventing a major problem. In another case, a leading railway freight firm operating across 23 states in the US used machine learning to address perennial locomotive engine failures costing millions in repairs, fines and lost revenue. With the right software solutions, predictive technologies will detect the conditions that limit asset effectiveness, while providing prescriptive guidance that assures firms remain profitable and improve margins.


How AI will help knowledge workers

#artificialintelligence

There are two basic ways to understand the world of AI: artificial general intelligence (general AI, or AGI) and narrow artificial intelligence (narrow AI). Narrow AI is the use of machines to intelligently solve specific problems, while general AI is a machine or group of machines that have the complete cognitive capabilities of a human. Contrary to what the science fiction movies might suggest, general AI is still a long way off. The main challenge to general AI is that, well, we don't fully understand what consciousness is.


Our Earth Formation Theories Could Be All Wrong, New Experiment Suggests

International Business Times

The researchers put their results about the distribution of Zn and S into computer models based on current theories of Earth's formation, but none of them models came close to showing the same sulfur-to-zinc ratio of the present-day mantle. The main subclass of these non-metallic stony meteorites (called chondrites as a category) that is thought to have made up Earth is called enstatite chondrites. "However, this new work indicates that the Earth needs to have formed from a more S-poor source; in terms of the geochemistry, the best candidate for this material is the metal rich CH chondrites," Mahan said in the statement. Referring to the amount of sulfur in the Earth's crust, as capped at 2 percent by "most leading estimates," Mahan said using known meteorites as a source for Earth's formation doesn't concur with currently accepted values, thereby precluding "any of the solar system materials that have previously been proposed" as the source material for Earth.


Why Cybersecurity Needs a Human in the Loop

#artificialintelligence

Cognitive security, or artificial intelligence, can "understand" natural language, and is a logical and necessary next step to take advantage of this increasingly massive corpus of intelligence that exists. Pairing humans and cognitive security solutions will help make sense of all this data with speed and precision, accomplishing response in a fraction of the time. Deep Blue as it is Kasparov consulting with Deep Blue before deciding on his next move against an unknown opponent. Defense works best when people and machine work together.


?utm_content=buffer6a126&utm_medium=social&utm_source=twitter.com&utm_campaign=buffer

#artificialintelligence

In this special guest feature, Mike Brooks, Senior Business Consultant at AspenTech, discusses how companies can no longer rely solely on traditional equipment maintenance practices but must also incorporate operational behaviors in deploying data-driven solutions using machine learning. For example, a North American energy company was losing up to a million dollars in repairs and lost revenue from repeat breakdowns of electric submersible pumps. In another case, a leading railway freight firm operating across 23 states in the US used Machine Learning to address perennial locomotive engine failures costing millions in repairs, fines, and lost revenue. Companies can no longer rely solely on traditional maintenance practices but must also incorporate operational behaviors in deploying data-driven solutions.


AI can provide huge benefits to energy companies -- so why aren't they using it? ZDNet

#artificialintelligence

Artificial intelligence (AI) is already proving its value to oil and gas companies, and yet widespread adoption of AI technologies within the industry still faces lots of hurdles. "The barriers for oil companies to adopting new AI technologies are many, ranging from resistance to change, a belief that what they already have is sufficient, and skepticism about whether new technologies will deliver," said Ray Hall, energy sector director at Tessella, a provider of engineering and consulting services that has helped global energy companies identify ways to improve drilling and operational efficiency with data. It's important, from a competitive standpoint, that oil and gas companies overcome the challenges in adopting AI and other emerging technologies, because the industry is facing challenges on many levels. For example, it worked with one oil customer to help the company improve its understanding of durability and levels of corrosion of existing wells, as part of the company's plan to get greater returns from wells.


How cognitive tech can help energy companies ZDNet

#artificialintelligence

"Cognitive computing helps solve the problem by capturing vast amounts of data from varied sources, including the knowledge from experienced engineers and technical staff, to help oil and gas companies understand trends and previous results, match similar patterns, and connect disparate information to support decisions," Mataya said. "Cognitive is typically considered a subset of AI that deals with cognitive behaviors associated with thinking," Mataya says "Since many of the application areas in oil and gas require intuition combined with information to make incredibly risky decisions, applying AI and cognitive concepts increases the quality and accuracy of decision making." Among the key challenges of adopting cognitive technologies are data quality and availability, disparate data types and formats, lack of skilled resources, and cultural factors. "The oil and gas industry has historically relied on a blend of thinking, intuition, and ever-increasing amounts of complex data to make decisions."


Machine Learning Mondays: Vertica 8.1.1 Cheat Sheet - myVertica

#artificialintelligence

Cheat Sheet Posted on Monday, July 31st, 2017 at 12:16 pm. Vertica 8.1.1 provides SQL functions that support the complete machine learning workflow--from cleaning your data to training a model to evaluating model performance. Vertica machine learning is fast and scalable along the sizes of data samples, features, and computing cluster. If you're new to Vertica machine learning or you want a quick reference of the functions in the 8.1.1 offering, check out this cheat sheet.


Hybrid drones carry heavier payloads for greater distances

MIT News

It uses gasoline to generate the power that drives the lift motors, keeps backup batteries charged, and powers onboard electronics including computing, sensors, and communications equipment. Over the past several years, Top Flight has continued to develop major innovations for the microscale hybrid engine concept, called a "digital gearbox." Gasoline runs to a small generator, creating electric power, which the digital gearbox controls and sends in pulses to the electric motors and electronics. Immediate applications for Top Flight's drone capabilities may include inspecting infrastructure in remote areas.


China's Sunway TaihuLight supercomputer simulates cosmos

Daily Mail

Sunway TaihuLight, the world's fastest computer, has modelled the birth and early expansion of the universe using 10 trillion digital particles, a new report claims. Sunway TaihuLight (pictured), the world's fastest computer, has modelled the birth and early expansion of the universe using 10 trillion digital particles, a new report claims In astronomy, researchers simulate the universe by breaking down its mass into particles. The supercomputer may be used to conduct earth system modelling, ocean surface wave modelling, atomistic simulation, and phase-field simulation. The supercomputer may be used to conduct earth system modelling, ocean surface wave modelling, atomistic simulation, and phase-field simulation.