In response to several requests, scoring of the test set has been reactivated.  This capability is offered in a non-competitive setting since the data challenge has ended.  Your score is for your information only and will not be counted in the data challenge.

Scores of final test set

Introduction
The PHM Data Challenge is a competition open to all potential conference attendees. The goal is to estimate remaining life of an unspecified component using data-driven techniques. Teams may be comprised of one or more researchers. One winner from each of three 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 2008 semester.
• IEEE GOLD (Graduates of the Last Decade): open to any team comprised solely of IEEE members who received their first professional degree after March 1998. See http://www.ieee.org/web/membership/gold/index.html for more information on the IEEE GOLD program.

Teams must declare what category they belong to when submitting results. There is a cash prize of $2500 for the top entrant from each category that both attends the conference and presents an invited paper on their winning technique. These papers will be presented in a dedicated session. Submission of the challenge special session papers is outside the regular paper submission process and follows its own schedule. The organizers of the contest reserve the right to both modify these rules and disqualify any team at their discretion.

Please click here to upload the result.

Data
A data set consisting of multiple multivariate time series is provided. This data set is further divided in to training and testing subset. Each time series is from a different instance of the same complex engineered system (referred to as a "unit") - e.g., the data might be from a fleet of ships of the same type. Each unit starts with different degrees of initial wear and manufacturing variation which is unknown to the user. This wear and variation is considered normal, i.e., it is not considered a fault condition. There are three operational settings that have a substantial effect on unit performance. These settings are also included in the data. The data is contaminated with sensor noise.

The unit is operating normally at the start of each time series, and develops a fault at some point during the series. In the training set, the fault grows in magnitude until system failure. In the test set, the time series ends some time prior to system failure. The objective of the competition is to predict the number of remaining operational cycles before failure in the test set, i.e., the number of operational cycles after the last cycle that the unit will continue to operate.

The data are provided as a zip-compressed text file with 26 columns of numbers, separated by spaces. Each row is a snapshot of data taken during a single operational cycle, each column is a different variable. The columns correspond to:
   1) unit number
   2) time, in cycles
   3) operational setting 1
   4) operational setting 2
   5) operational setting 3
   6) sensor measurement 1
   7) sensor measurement 2
   ...
   26) sensor measurement 21

The data can be downloaded here

The test set RULs can be downloaded here

The final test set can be downloaded here

Performance Evaluation
Results must be uploaded to the conference web site as text files with each file consisting only of numerical estimates of remaining operating cycles, with one estimate per line in the order of the units in the test set. Results presented in a different format will not be accepted and will be excluded from the competition. The results will be automatically scored and results of the top 20 scores will be posted to a leader board using the team registered names. To upload results to the web site, click here.

There will be a "final test set" (FTS) released on 19 May 2008. The FTS will be drawn from the same distribution as the training and test sets. Algorithms will be scored on the basis of performance on the FTS only. To prevent people from using feedback from the FTS to tune their algorithm, scores will not be released for the final test set until after the competition has closed. Results for the FTS may be uploaded until 11:59 pm PDT on 2 June 2008.

Algorithms will be scored based on the error of the predictions for the FTS set. Predictions far from the target are penalized exponentially. The penalty function is asymmetric, with late predictions penalized more heavily than early predictions (i.e., it is better to predict failure too soon than too late). Lower scores are better; a perfect algorithm would score zero.

Teams may upload results from the test set as often as they like but only the final set of results will be scored from each team each day (defined as 12:00 am to 11:59 pm PDT). Each newly submitted file overrides the previous file. Scores from submitted test set results will be posted to the leaderboard. You can use the leaderboard to see where you are in comparison to the other competitors. Our hope is that the leaderboard will inspire some friendly competition!

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. PHM08 reserves 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.

Top 20 list - test data

No.	Team Name	Score	Team Type
1.	sunbea	436.841	Professional
2.	FOH	512.426	Professional
3.	MyTeam	671.161
4.	heracles	737.769	Student
5.	Sentient	809.757	Professional
6.	last	908.588	Professional
7.	A	975.586	Professional
8.	beck1903	1,049.566	Professional
9.	L6	1,051.884	Student
10.	GoNavy	1,075.162	Student
11.	emi	1,083.905	Professional
12.	k_try	1,127.947	Professional
13.	SuperSiegel	1,139.832	Student
14.	percia	1,219.607	Professional
15.	bobosir	1,263.021	Student
16.	YY	1,557.608	Student
17.	IMS Center UC	1,808.751	Student
18.	RelRes	1,966.378	Student
19.	T_Test	2,065.474	Professional
20.	phmnrc	2,399.878	Professional

Questions
Questions may be submitted here. Answers will be posted to the FAQ at http://phmchallenge.blogspot.com.

Schedule for PHM Data Challenge

17 March 2008	Data released
2 June 2008	Results due
13 June 2008	Winners announced. Invitation to submit paper
21 July 2008	Papers due
28 July 2008	Reviewers' comments back to authors
15 August 2008	Final Paper Due