2011 PHM Society Conference Data Challenge

The PHM Data Challenge is a competition open to all potential conference attendees. This year the challenge is focused on anemometer fault detection, a critical problem for the wind power industry, strongly affecting among other things the financing of a potential site.

Both Student and Professional teams are encouraged to enter! Winners of the Student and the Professional categories who attend the conference and submit an invited paper to ijPHM on their technique will be awarded a cash prize. Top scoring participants will be invited to present at a special session of the conference.

Participants will be scored based on their ability to identify faulty anemometers in two data sets. Winners of the Student and the Professional categories who attend the conference and submit an invited paper to ijPHM on their technique will be awarded a cash prize. Top scoring participants will be invited to present at a special session of the conference.

Questions can be asked and additional information can be found on the competition forum.

Teams
Teams may be comprised of one or more researchers. One winner from each of two categories will be determined on the basis of score. The categories are:

  • Professional: open to anyone (including mixed teams)
  • Student: open to any team with all members enrolled as full time students during the spring or fall 2011 semesters.

Teams must declare what category they belong to when signing up. There is a cash prize of $1000 for the top entrant from each category, contingent upon:

  • attending the conference
  • giving an invited presentation on the winning technique
  • submitting a journal-quality paper to the International Journal of Prognostics and Health Management (ijPHM) which discloses the full algorithm used.

Additionally, top scoring teams will be invited to give presentations at a special session, and submit papers to ijPHM. Submission of the challenge special session papers is outside the regular paper submission process and follows its own schedule.

The organizers of the competition reserve the right to both modify these rules and disqualify any team at their discretion.

Registration
Teams may register by contacting the Competition organizers with their name(s), a team alias under which the scores would be posted, affiliation(s) with address(es), contact phone number (for verification) and competition category (professional or student). Student teams should also send the name of the university and the semesters where they are enrolled full-time. You will be emailed your username and password after verification.

PLEASE NOTE: In the spirit of fair competition, we allow only one account per team. Please do not register multiple times under different user names, under fictitious names, or using anonymous accounts. Competition organizers reserve the right to delete multiple entries from the same person (or team) and/or to disqualify those who are trying to "game" the system or using fictitious identities.

Data
There are two data sets, one for "paired" data, and one for "shear" data:
paired
shear

The data files are ~7 MB each.

Paired Data
The paired data consist of 12 training sets of nominal, paired anemometer data from the same height. Each training set consists of 25 days of data. The test data consists of 420 test files, of 5 days of data. There are 16 columns of comma separated data, with columns corresponding to:
Anemometer 1: mean, standard deviation, maximum, minimum wind speed
Anemometer 2: mean, standard deviation, maximum, minimum wind speed
Wind Direction (degrees North): mean, standard deviation, maximum, minimum
Temperature: mean, standard deviation, maximum, minimum

Shear Data
The shear data consist of 7 training sets of nominal, anemometer data in an array from different heights. Each training set consists of 25 days of data. The test data consists of 255 test files, of 5 days of data. There are 20 or 16 columns of comma separated data, with columns corresponding to:
Height Data: 3 or 4 integer values representing the height of the anemometers,
1st (highest) Anemometer: mean, standard deviation, maximum, minimum wind speed
2nd (next highest) Anemometer: mean, standard deviation, maximum, minimum wind speed
3rd (next highest) Anemometer: mean, standard deviation, maximum, minimum wind speed
4th (lowest) Anemometer: mean, standard deviation, maximum, minimum wind speed. Some sites only have 3 anemometers in an array.
Wind Direction (degrees North): mean, standard deviation, maximum, minimum
Temperature: mean, standard deviation, maximum, minimum
Date: Month/Day/Year hours:minutes:seconds

Domain Fundamentals
Background on the data are here.

Performance Evaluation and Submitting Results
Details on how the competition is scored and how to submit results are here.

Leaderboard
The leaderboard is here.

Schedule for PHM Data Challenge
03-May-11 Data released
11-May-11 Leaderboard open
11-Jul-11 Final submissions due
13-Jul-11 Provisional winners announced, invitation to submit paper
15-Jul-11 Confirmation of willingness to present and publish FULL algorithm in ijPHM
15-Jul-11 Winners announced
01-Sep-11 Papers due to ijPHM
25-Sep-11 PHM11 Starts

PHM Competition Start: 
May 2, 2011 - 10:00pm
PHM Competition End: 
July 11, 2011 - 8:59pm
PHM Competition Status: 
Completed
 Login or register to post comments
 
 
 

follow us

PHM Society on Facebook Follow PHM Society on Twitter PHM Society on LinkedIn PHM Society RSS News Feed