Home » Curated Content » Case Study: Predicting Rare Failures in Hydro Turbines

× Share this Presentation

Facebook
Twitter
Email
LinkedIn

Download the Case Study: Predicting Rare Failures in Hydro Turbines

First Name

Last Name

Company Name

Phone Number

Job Title

Opt-in To Future Emails

Thank you!

Error - something went wrong!

Case Study: Predicting Rare Failures in Hydro Turbines

May 23, 2018

Share this Flipbook
Facebook
Twitter
Email
LinkedIn

Hydropower is a unique resource in that it is both sustainable and highly efficient at converting natural, kinetic energy into electricity.

Modern hydro turbines are massive assets, producing hundreds of megawatts of power, and a catastrophic failure can case a turbine to be out of service for months, with expensive repair costs and potential disruption to the energy grid.

Previous Flipbook

Use Case: Improving Grid Reliability and Resiliency

The utility sector has already benefited from the use of machine learning by implementing predictive mainte...

You've reached the end!

Curated AI News Straight to Your Inbox Every Month. Subscribe to our Newsletter.

First Name

Last Name

Company Name

Phone Number

Job Title

Opt-in To Future Emails

Thank you!

Error - something went wrong!

Other content in this Stream

From Data to Application: Darwin's Unique Approach to AutoML

Darwin automates time-consuming tasks ranging from model creation and optimization to model deployment and continuous maintenance.

Garbage In, Garbage Out: Automated ML Begins with Quality Data

Machine learning methods are highly dependent on the quality of the data they receive as input, but data preparation and cleaning can be an unwieldy task, taking up 60% of data scientists' time.

Breaking Away from Cookie-Cutter Algorithms: True Generalization with Evolutionary Methods

Most autoML solutions in the market focus on searching for the best algorithm to fit a given data set. However, these methods lack the ability to produce novel, elegant model architectures.

How to Put Machine Learning Models to Work: Bridging the Gap Between Model Production and Operationalization

Automated machine learning has the potential to reduce the burden on overwhelmed teams by automating the bottlenecks in the data science process. But just having an algorithm isn't enough.

eBook: Your Guide to Small Business Cybersecurity

Roughly two-thirds of Americans dream of opening a small business. However, an increasing number of small businesses face an unfortunate reality—becoming victims of a cyber attack.

eBook: AI Implementation in the Oil & Gas Industry

Companies that emerge the strongest from inevitable slowdowns are the ones who adopt innovative technologies. This booklet highlights how AI implementation can help O&G companies in three key areas.

AV-Comparatives Malware Protection Test Fact Sheet

SparkCognition’s DeepArmor® Endpoint Protection Platform scored a 99.9% protection rate with zero false positives on common business applications.

Case Study: Improving Offshore Production with AI-Based Predictive Analytics

One major oil platform operator was facing recurring failures in production subcomponents that resulted in >10% downtime and millions of dollars of lost production. They employed SparkCognition’s turn

49:07

Webinar: Are You Data-Ready for Predictive Maintenance in O&G?

O&G companies' projects with machine learning-based predictive analytics will ultimately be driven by data quality, availability, and management. This webinar will expose you to the key data requireme

Watch Video

Case Study: Predicting Maintenance and Production in Oil Wells

Customer Success Story: Identifying Non-Productive Time and Invisible Lost Time on Oil Rigs

Non-productive time is a great enemy for oil and gas operators. E&P operators need to better categorize and analyze rig activities to track and eliminate non-productive time and invisible lost time.

DeepArmor Endpoint Protection Testing

Reimagine Offshore Maintenance with AI

The oil and gas industry is a dynamic, ever changing arena. SparkCognition has developed AI-based predictive and prescriptive maintenance solutions to help companies adapt to the age of digitization.

Automating Model Building on the Google Cloud Platform

SparkCognition and Google Cloud Technology have partnered to weave artificial intelligence into the fabric of organizations by expanding the range of applications and tools optimized to run on GCP.

Case Study: Improving Operational Efficiency and Returns in Oil and Gas

To remain competitive and maximize returns, oil and gas companies must utilize the massive amounts of data generated in the fields. The rise of the Internet of Things and smart sensors have created...

The Practical Guide to Industrial AI: Benefits and Implementation

Artificial intelligence is certainly not a new topic. The field has seen starts and stalls, as many of AI's successes have been promising for research progress. With new developments and impactful

Use Case: Alternative Data for Investment Management

From hedge fund managers to mutual funds and even private equity managers, alternative data has the power to improve valuation of securities and boost the clarity of the investment process.

Darwin Efficacy Report

Darwin's automated model building capabilities offer unparalleled performance to generate highly accurate models. Thus, we sought to compare how Darwin performs against other platforms on the market.

Whitepaper: Neuroevolution Under the Hood

Neuroevolution amplifies a data scientist's work by enabling more effective model building, providing the ability to rapidly iterate through thousands of different models and architectures.

2:59

Predicting Customer Insurance Costs with Artificial Intelligence

Predict customer insurance costs using machine learning. Darwin builds neuroevolution tailored models that reduce the amount of tie spent building and maintaining models. Darwin. Automated Model

Watch Video

Return to Home