MOD-DBWORLD Archives

DBWorld @ ACM SIGMOD

MOD-DBWORLD@LISTSERV.ACM.ORG

Options: Use Forum View

Use Monospaced Font
Show Text Part by Default
Show All Mail Headers

Message: [<< First] [< Prev] [Next >] [Last >>]
Topic: [<< First] [< Prev] [Next >] [Last >>]
Author: [<< First] [< Prev] [Next >] [Last >>]

Print Reply
Subject:
From:
Carlos Ferreira <[log in to unmask]>
Reply To:
Date:
Wed, 20 Sep 2023 04:36:17 -0400
Content-Type:
text/plain
Parts/Attachments:
text/plain (88 lines)
Subject: [new deadline] Competition - Predictive Maintenance @ Xai for Predictive Maintenance Tutorial - ECAI 2023

Call for Participation

----------------------


We invite you to participate in our Predictive Maintenance Competition. This is the shared task of the XAI for Predictive Maintenance Tutorial at ECAI 2023 (https://slawomirnowaczyk.wixsite.com/ecai-xpm).

 

Competition website: https://slawomirnowaczyk.wixsite.com/ecai-xpm

Kaggle website: https://www.kaggle.com/datasets/pattinson9999/uci-metropt-3-dataset




Important dates

----------------------

 

· 25/09/2023: submission deadline.


----------------------

Description

The compressed air system is a crucial component of the train and delivers essential pressurized air to several clients like:

·       pneumatic suspension

·       oil injection on the rail to reduce the friction and noise on the curves

·       injection of sand to gain traction rails

·       connect other trains

Requirements

Predict a failure or detect an anomaly two hours in advance (minimum time required by the company to schedule the replacement of the faulty train).

Description

·       The dataset consists of more than 15 million examples

·       Collected from February to August 2020

·       15 features from 7 analogue (1-7) and 8 digital (8-15) sensors

Failures

·       Air leak: relevant sensors: tp2, tp3, h1, dv_pressure, comp, motor_current

·       Oil leak: relevant sensors: oil_temp, oil_level

Possible Tasks:

·       Anomaly Detection

·       Anomaly Explanation

·       Failure Prediction

·       Remaining Useful Life (RUL)

Solution:

·       Best Posters will be available on the XPM project website and presented online during the Tutorial

·       Open repository with solution

·       Send the Technical Poster to [log in to unmask]


Best,

Organizers


---------------


To unsubscribe from the DBWorld mailing list please visit https://dbworld.sigmod.org and follow the unsubscribe directions given there.

ATOM RSS1 RSS2