# Predict and diagnose wind turbine faults & stand a chance to work with ReNew Power’s digital team

Unplanned downtime of wind turbines can result in a significant loss of revenue and energy. Predict and diagnose wind turbine faults and stand a chance of getting hired by ReNew Power .
 Listen to this story

In a bid to bring wind analytics to speed, ReNew Power, one of the leading renewable energy companies in India, in partnership with MachineHack, is launching a data science hiring hackathon scheduled from August 19, 2022, to September 9, 2022

The data science hiring hackathon provides data professionals with an exciting opportunity to prove their capabilities and get a chance to work with ReNew Power. The candidates would also stand a chance to win prizes like iPhone 13, iPad Air, Samsung Galaxy Watch 4–42mm, Alexa Echo Show 8 and more.

So register today!

Problem statement and description

Unplanned downtime of wind turbines can result in a significant loss of revenue and energy. Therefore, it is important to predict and flag the failure of components to prevent further loss and perform maintenance before the onset of complete failure, which in turn requires replacement of the components and incur higher costs.

Moreover, condition-based monitoring systems rely on supervisory control and data acquisition (SCADA) systems to predict faults and get valuable insights into turbine performance.

In this hackathon, ReNew Power shared minute-wise normalised data of wind speed, power and temperature data for multiple components of a wind turbine. The company is looking to create a model to get an ideally functioning turbine’s expected rotor bearing temperature. It will then use the model to check the deviation of the actual rotor bearing temperature of the faulty turbine from the expected temperature.

** It is to be note

### END DATE: 9th September

MachineHack and ReNew Power have created a training dataset of 909604 rows with 16 columns and a testing dataset of 303202 rows with 15 columns to solve the prediction problem.

Submission guidelines

Sklearn models support the predict() method to generate the predicted values

The participant should submit a .csv file with exactly 3,03,202 rows with 1 column [“Target”]. The submission will return an Invalid Score if you have extra rows or columns.

** The file should have exactly 1 column.

Evaluation criteria

The evaluation of the hackathon will be undertaken using the  Mean Absolute Percentage Error. One can use sklearn.metrics.mean_absolute_percentage_error to calculate the same.

The hackathon would also support private and public leaderboards, where the public leaderboard will be evaluated on 30% of test data. On the other hand, the private leaderboard will be available at the end of the hackathon and assessed on 100% of the test data.

Final score will be  70* [Leaderbaord (100% of test dataset)] + 30* [Solution Approach]

### END DATE: 9th September

Prizes

Top 25 candidates on the public leaderboard will get a chance to be interviewed/hired by ReNew Power. ReNew Power will select the top three (3) winners, alongside weekly winners, based on given criteria.

** Note: There will be two weekly winners for the first two weeks. This also makes it likely for the candidates to win two prizes (weekly prize + winner’s prize)

First prize: iPhone 13 (128GB)

Second price: iPad Air, WiFi (64GB)

Third prize: Samsung Galaxy Watch 4 – 42mm

Weekly winners (total 2): Alexa Echo Show 8

Dataset details

• Train: 909604 rows x 16 columns
• Test: 303202 rows x 15 columns
• Sample Submission.csv — Please check the ‘Evaluation’ section on the MachineHack web page for more details on generating a valid submission.

## Our Upcoming Events

### Telegram group

Discover special offers, top stories, upcoming events, and more.

### Discord Server

Stay Connected with a larger ecosystem of data science and ML Professionals

### How this Govt Initiative Found Moat in Oracle

Thanks to Oracle, CGTMSE has benefited approximately 12 million borrowers, guaranteeing loans totalling \$53 billion, of which \$21 billion are currently active

### GPU has an Energy Problem

If energy costs for running GPUs are climbing, what is the endgame?

### Oracle’s Billion-Dollar Baby

Cohere service will form the basis for generative AI capabilities embedded across Oracle’s suite of SaaS and industry applications

### It’s High Time Apple Bought Stability AI

Apple is the only big-tech that does not have its own research lab

### Why Microsoft is Using Nuclear to Fuel Its Data Centers?

Microsoft takes the helm in pioneering the development and execution of a worldwide strategy for small modular reactors (SMRs) and microreactor energy systems.

### Why Google will Not Rank Websites Just Based on SEOs

Google shifted SEO focus to quality over origin, embracing AI-generated content. This sparked concerns and debates among content creators

### AI Trust Grows When Hidden

While companies are heavily criticised for being secretive the approach is working in their favour

### When Sam Met Ollie

Silicon Valley has a new power couple

### Oracle Doesn’t Want You to Care About Data Anymore

“Nobody comes in to work in the morning and says, ‘today, I’m going to look at data’,” says TK Anand

### OpenAI is the New Apple

‘Joining OpenAI right now is probably like joining Apple pre iPod and iPhone’