1. Sie sind hier:
  2. FrostByte Dataset
...

    Datenpaket: FrostByte Dataset

    Alternativer Identifier:
    -
    Verwandter Identifier:
    (Is Identical To) 10.15771/1894 - DOI
    (Is Supplement To) https://hdl.handle.net/2108/323763 - HANDLE
    (Is Documented By) 10.1016/j.conengprac.2021.104815 - DOI
    (Is Referenced By) 10.1016/j.buildenv.2026.115033 - DOI
    Ersteller/in:
    Reiff-Stephan, Jörg https://orcid.org/0000-0003-4176-6371 [Technische Hochschule Wildau]

    van de Sand, Ron https://orcid.org/0000-0002-8975-4030 [van de Sand, Ron]
    Beitragende:
    (Other)
    Potsdamer Anlagenbau und Kältetechnik GmbH
    Titel:
    FrostByte Dataset
    Weitere Titel:
    -
    Beschreibung:
    (Abstract) It is with great pleasure that we announce the release of the “Frost Byte” dataset. The dataset was collected during research on fault detection and diagnosis (FDD) approaches and their transferability to heterogeneous systems of industrial refrigeration systems at the Technical University of Applie...
    Mehr anzeigen
    Schlagworte:
    FDD
    Maschinelles Lernen
    Instandhaltung
    machine learning
    predictive maintenance
    Zugehörige Informationen:
    (Hinweis zu verwandtem Identifier / verwandten Publikationen) This dataset was used in: Bezyan, Y., Nasiri, F. & Nik-Bakht, M. (2026). A comprehensive framework for automatic labeling and fault detection in chillers under steady and transient states. Building And Environment, 305, 115033. https://doi.org/10.1016/j.buildenv.2026.115033. The use of this dataset was confirmed by the creators of the dataset. In Beyzan et al, the dataset was acknowledged as having been shared by Dr. Ron van de Sand, rather than formally cited in the reference list. The same dataset has also been used in the following publications by the research group associated with the dataset: van de Sand et al. (2021), Positive-Unlabelled Learning based Novelty Detection for Industrial Chillers: A Data-Driven Approach to Avoid Energy Wastage. DOI: 10.52825/thwildauensp.v1i.32. and: Falk et al. (2021), A Comparison Study of Data-Driven Anomaly Detection Approaches for Industrial Chillers. DOI: 10.52825/thwildauensp.v1i.33 The dataset creators confirmed that the same measurement data were used in these publications. However, the dataset was not formally cited in either publication.
    Sprache:
    Englisch
    Version:
    -
    Herausgeber/in:
    Technical University of Applied Sciences Wildau
    Erstellungsjahr:
    Fachgebiet:
    Engineering
    Objekttyp:
    Dataset
    Datenquelle:
    (Instrument) Ammonia refrigeration system with a refrigeration capacity of 100 kW. Measurement data are acquired via a programmable logic controller (PLC) using analog and digital sensors. Some measurement variables are recorded redundantly.
    Verwendete Software:
    Software für Datenbearbeitung
    Software:
    Python (including the libraries: NumPy, pandas, scikit-learn) - -
    Alternative Software:
    -
    Datenverarbeitung:
    The measurement data were processed using steady-state detection, filtering, smoothing, and outlier removal. Only steady-state operating conditions were included in the published dataset. These comprise normal operation and several fault scenarios: reduced water flow rates at the evaporator and condenser, the presence of non-condensable gases, and refrigerant loss.
    Erscheinungsjahr:
    Rechteinhaber/in:
    Förderung:
    Bundesministerium für Wirtschaft und Energie - (SmCoCo - Smart Cooling Control Entwicklung einer smarten Steuerung für industrielle und gewerbliche Kälteanlagen im Hinblick auf Industrie 4.0 und agile Zustandsüberwachung)(ZF4012225RE7)
    Land Brandenburg - (PrAndyPiK - Applikation der Präskriptiven Analytik für die dynamische Prozessführung von intelligenten Kälteanlagen)(80237615)
    Ministerium für Wirtschaft, Energie, Klimaschutz und Europa - (PrAndyPiK - Applikation der Präskriptiven Analytik für die dynamische Prozessführung von intelligenten Kälteanlagen)(80237615)
    Name Speichervolumen Metadaten Upload Aktion
    Status:
    Publiziert
    Eingestellt von:
    THW_Admin
    Erstellt am:
    Archivierungsdatum:
    2026-10-21
    Archivgröße:
    3,2 MB
    Archiversteller:
    THW_Admin
    Archiv-Prüfsumme:
    6a874cb7326642456f5a06f19bf56965 (MD5)
    Embargo-Zeitraum:
    -