Open Collections will undergo scheduled maintenance on the following dates: On Monday, April 27th, 2026, the site will not be available from 7:00 AM – 9:00 AM PST and on Tuesday, April 28th, 2026, the site will remain accessible from 7:00 AM – 9:00 AM PST, however item images and media will not be available during this time.

Open Collections

UBC Research Data

The Arc Loss Dataset Ibrahim Yousef; Lee D. Rippon; Carole Prévost; Sirish L. Shah; R. Bhushan Gopaluni

Description

The Arc Loss Dataset is a benchmark dataset designed for time series classification in industrial applications, particularly for fault detection and diagnosis (FDD). It was collected from a large-scale pyrometallurgical plant and captures the real-world complexities of industrial processes, including high dimensionality, sensor noise, and variable system dynamics. The dataset consists of 3,226 multivariate time series samples, each containing 1,101 time steps (equivalent to 55 minutes) with 96 process variables. The dataset is split into three subsets: I) train.pt (70% of the samples, 2,258 samples), II) val.pt (10%, 323 samples), and III) test.pt (20%, 645 samples). More information can be found in the README.txt

Item Metadata

Title
The Arc Loss Dataset
Creator
Ibrahim Yousef; Lee D. Rippon; Carole Prévost; Sirish L. Shah; R. Bhushan Gopaluni
Contributor
Ibrahim
Date Issued
2025-02-03
Description
The Arc Loss Dataset is a benchmark dataset designed for time series classification in industrial applications, particularly for fault detection and diagnosis (FDD). It was collected from a large-scale pyrometallurgical plant and captures the real-world complexities of industrial processes, including high dimensionality, sensor noise, and variable system dynamics. The dataset consists of 3,226 multivariate time series samples, each containing 1,101 time steps (equivalent to 55 minutes) with 96 process variables. The dataset is split into three subsets: I) train.pt (70% of the samples, 2,258 samples), II) val.pt (10%, 323 samples), and III) test.pt (20%, 645 samples). More information can be found in the README.txt
Subject
Computer and Information Science; Engineering; Time Series Classification; Fault Detection and Diagnosis; Industrial Benchmark; Process Monitoring
Type
Dataset
Date Available
2025-02-02
Provider
University of British Columbia Library
License
CC BY-NC 4.0
DOI
10.14288/1.0447904
URI
https://doi.org/10.5683/SP3/NREPZM
Publisher DOI
https://doi.org/10.5683/SP3/NREPZM
Rights URI
http://creativecommons.org/licenses/by-nc/4.0
Aggregated Source Repository
Dataverse

Item Media

Item Citations and Data

License

CC BY-NC 4.0