Declarative Programming Approaches for Robust Anomaly Detection in HPDC Process Data

Tomasz Michno; Roxana Holom; Sebastian Schmalzer; Pauline Meyer-Heye; Giulia Scampone; Elias Riegler; Matthias Hartmann; Urban Repanšek; Nejc Košir; Peter Šifrer

doi:10.1007/978-3-032-05745-7_4

Declarative Programming Approaches for Robust Anomaly Detection in HPDC Process Data

Tomasz Michno
, Roxana Holom
, Sebastian Schmalzer
, Pauline Meyer-Heye
, Giulia Scampone
, Elias Riegler
, Matthias Hartmann
, Urban Repanšek
, Nejc Košir
, Peter Šifrer

Publikation: Beitrag in Buch oder Tagungsband › Vortrag mit Beitrag in Tagungsband › Begutachtung

Abstract

The increasing demand for lightweight components with complex geometries and high performance has significantly driven the use of High Pressure Diecasting technologies in the transportation sector. However, the production of high-quality HPDC components necessitates precise control of process parameters. Within this scope, the Data and Metadata for Advanced Digitalization of Manufacturing Industrial Lines (metaFacturing) project, funded by the EU Horizon program, is trying to solve some of the challenges. The focus is on a digitalized toolchain that will optimize the use of raw materials, incorporating recycled ones, reduce operator costs and effort, as well as waste caused by out-of-specification production results. In this paper, a solution for the challenge of the structured data characteristics is presented using two differently trained classifiers for anomalous and non-anomalous data in order to improve classification performance. To additionally increase efficiency and utilize process data characteristics, different declarative programming methods are investigated, such as ILP, ASP, CLP, and CP.

Originalsprache	Englisch
Titel	Lecture Notes in Networks and Systems
Untertitel	Distributed Computing and Artificial Intelligence, Special Sessions I, 22nd International Conference. DCAI 2025.
Herausgeber (Verlag)	Springer
Seiten	39-50
Seitenumfang	11
Band	1631
ISBN (elektronisch)	978-3-032-05745-7
ISBN (Print)	978-3-032-05744-0
DOIs	https://doi.org/10.1007/978-3-032-05745-7_4
Publikationsstatus	Veröffentlicht - 2 Jan. 2026
Veranstaltung	22nd International Conference on Distributed Computing and Artificial Intelligence - University of Lille, Lille, Frankreich Dauer: 25 Juni 2025 → 27 Juni 2025 Konferenznummer: 22 https://www.dcai-conference.net/

Publikationsreihe

Name	Lecture Notes in Networks and Systems
Herausgeber (Verlag)	Springer Nature Switzerland AG
ISSN (Print)	2367-3370
ISSN (elektronisch)	2367-3389

Konferenz

Konferenz	22nd International Conference on Distributed Computing and Artificial Intelligence
Kurztitel	DCAI 2025
Land/Gebiet	Frankreich
Stadt	Lille
Zeitraum	25/06/25 → 27/06/25
Internetadresse	https://www.dcai-conference.net/

Research Field

High-Performance Vision Systems
Innovation Systems and Digitalisation
Außerhalb der AIT Research Fields

Zugriff auf Dokument

10.1007/978-3-032-05745-7_4Lizenz: Sonstige

1 Vortrag mit Beitrag in Tagungsband

Porosity Classification in High Pressure Die Casting using Thermal Images and Sensor Data Fusion via Fuzzy Cognitive Maps
Michno, T., Holom, R., Schmalzer, S., Scampone, G., Riegler, E., Hartmann, M., Repanšek, U., Košir, N., Šifrer, P. & Poczęta, K., 19 Dez. 2025, (Angenommen/Im Druck) Proceedings of the 21th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.
Publikation: Beitrag in Buch oder Tagungsband › Vortrag mit Beitrag in Tagungsband › Begutachtung

1 Teilnahme an Konferenzkomitees

22nd International Conference on Distributed Computing and Artificial Intelligence (Veranstaltung)
Michno, T. (Gutachter:in)
2025
Aktivität: Begutachtungstätigkeit › Teilnahme an Konferenzkomitees

Diese Publikation zitieren

Michno, T., Holom, R., Schmalzer, S., Meyer-Heye, P., Scampone, G., Riegler, E., Hartmann, M., Repanšek, U., Košir, N., & Šifrer, P. (2026). Declarative Programming Approaches for Robust Anomaly Detection in HPDC Process Data. in Lecture Notes in Networks and Systems: Distributed Computing and Artificial Intelligence, Special Sessions I, 22nd International Conference. DCAI 2025. (Band 1631, S. 39-50). (Lecture Notes in Networks and Systems). Springer. https://doi.org/10.1007/978-3-032-05745-7_4

Michno, Tomasz ; Holom, Roxana ; Schmalzer, Sebastian et al. / Declarative Programming Approaches for Robust Anomaly Detection in HPDC Process Data. Lecture Notes in Networks and Systems: Distributed Computing and Artificial Intelligence, Special Sessions I, 22nd International Conference. DCAI 2025.. Band 1631 Springer, 2026. S. 39-50 (Lecture Notes in Networks and Systems).

@inproceedings{06194d7f1a6847118c9fd1d5c0d2b7c7,

title = "Declarative Programming Approaches for Robust Anomaly Detection in HPDC Process Data",

abstract = "The increasing demand for lightweight components with complex geometries and high performance has significantly driven the use of High Pressure Diecasting technologies in the transportation sector. However, the production of high-quality HPDC components necessitates precise control of process parameters. Within this scope, the Data and Metadata for Advanced Digitalization of Manufacturing Industrial Lines (metaFacturing) project, funded by the EU Horizon program, is trying to solve some of the challenges. The focus is on a digitalized toolchain that will optimize the use of raw materials, incorporating recycled ones, reduce operator costs and effort, as well as waste caused by out-of-specification production results. In this paper, a solution for the challenge of the structured data characteristics is presented using two differently trained classifiers for anomalous and non-anomalous data in order to improve classification performance. To additionally increase efficiency and utilize process data characteristics, different declarative programming methods are investigated, such as ILP, ASP, CLP, and CP.",

author = "Tomasz Michno and Roxana Holom and Sebastian Schmalzer and Pauline Meyer-Heye and Giulia Scampone and Elias Riegler and Matthias Hartmann and Urban Repan{\v s}ek and Nejc Ko{\v s}ir and Peter {\v S}ifrer",

year = "2026",

month = jan,

day = "2",

doi = "10.1007/978-3-032-05745-7\_4",

language = "English",

isbn = "978-3-032-05744-0",

volume = "1631",

series = "Lecture Notes in Networks and Systems",

publisher = "Springer",

pages = "39--50",

booktitle = "Lecture Notes in Networks and Systems",

address = "Germany",

note = "22nd International Conference on Distributed Computing and Artificial Intelligence, DCAI 2025 ; Conference date: 25-06-2025 Through 27-06-2025",

url = "https://www.dcai-conference.net/",

}

Michno, T, Holom, R, Schmalzer, S, Meyer-Heye, P , Scampone, G , Riegler, E , Hartmann, M, Repanšek, U, Košir, N & Šifrer, P 2026, Declarative Programming Approaches for Robust Anomaly Detection in HPDC Process Data. in Lecture Notes in Networks and Systems: Distributed Computing and Artificial Intelligence, Special Sessions I, 22nd International Conference. DCAI 2025.. Bd. 1631, Lecture Notes in Networks and Systems, Springer, S. 39-50, 22nd International Conference on Distributed Computing and Artificial Intelligence, Lille, Frankreich, 25/06/25. https://doi.org/10.1007/978-3-032-05745-7_4

Declarative Programming Approaches for Robust Anomaly Detection in HPDC Process Data. / Michno, Tomasz; Holom, Roxana; Schmalzer, Sebastian et al.
Lecture Notes in Networks and Systems: Distributed Computing and Artificial Intelligence, Special Sessions I, 22nd International Conference. DCAI 2025.. Band 1631 Springer, 2026. S. 39-50 (Lecture Notes in Networks and Systems).

Publikation: Beitrag in Buch oder Tagungsband › Vortrag mit Beitrag in Tagungsband › Begutachtung

TY - GEN

T1 - Declarative Programming Approaches for Robust Anomaly Detection in HPDC Process Data

AU - Michno, Tomasz

AU - Holom, Roxana

AU - Schmalzer, Sebastian

AU - Meyer-Heye, Pauline

AU - Scampone, Giulia

AU - Riegler, Elias

AU - Hartmann, Matthias

AU - Repanšek, Urban

AU - Košir, Nejc

AU - Šifrer, Peter

N1 - Conference code: 22

PY - 2026/1/2

Y1 - 2026/1/2

N2 - The increasing demand for lightweight components with complex geometries and high performance has significantly driven the use of High Pressure Diecasting technologies in the transportation sector. However, the production of high-quality HPDC components necessitates precise control of process parameters. Within this scope, the Data and Metadata for Advanced Digitalization of Manufacturing Industrial Lines (metaFacturing) project, funded by the EU Horizon program, is trying to solve some of the challenges. The focus is on a digitalized toolchain that will optimize the use of raw materials, incorporating recycled ones, reduce operator costs and effort, as well as waste caused by out-of-specification production results. In this paper, a solution for the challenge of the structured data characteristics is presented using two differently trained classifiers for anomalous and non-anomalous data in order to improve classification performance. To additionally increase efficiency and utilize process data characteristics, different declarative programming methods are investigated, such as ILP, ASP, CLP, and CP.

AB - The increasing demand for lightweight components with complex geometries and high performance has significantly driven the use of High Pressure Diecasting technologies in the transportation sector. However, the production of high-quality HPDC components necessitates precise control of process parameters. Within this scope, the Data and Metadata for Advanced Digitalization of Manufacturing Industrial Lines (metaFacturing) project, funded by the EU Horizon program, is trying to solve some of the challenges. The focus is on a digitalized toolchain that will optimize the use of raw materials, incorporating recycled ones, reduce operator costs and effort, as well as waste caused by out-of-specification production results. In this paper, a solution for the challenge of the structured data characteristics is presented using two differently trained classifiers for anomalous and non-anomalous data in order to improve classification performance. To additionally increase efficiency and utilize process data characteristics, different declarative programming methods are investigated, such as ILP, ASP, CLP, and CP.

U2 - 10.1007/978-3-032-05745-7_4

DO - 10.1007/978-3-032-05745-7_4

M3 - Conference Proceedings with Oral Presentation

SN - 978-3-032-05744-0

VL - 1631

T3 - Lecture Notes in Networks and Systems

SP - 39

EP - 50

BT - Lecture Notes in Networks and Systems

PB - Springer

T2 - 22nd International Conference on Distributed Computing and Artificial Intelligence

Y2 - 25 June 2025 through 27 June 2025

ER -

Michno T, Holom R, Schmalzer S, Meyer-Heye P , Scampone G , Riegler E et al. Declarative Programming Approaches for Robust Anomaly Detection in HPDC Process Data. in Lecture Notes in Networks and Systems: Distributed Computing and Artificial Intelligence, Special Sessions I, 22nd International Conference. DCAI 2025.. Band 1631. Springer. 2026. S. 39-50. (Lecture Notes in Networks and Systems). doi: 10.1007/978-3-032-05745-7_4

Declarative Programming Approaches for Robust Anomaly Detection in HPDC Process Data

Abstract

Publikationsreihe

Konferenz

Research Field

Zugriff auf Dokument

Fingerprint

Publikationen

Porosity Classification in High Pressure Die Casting using Thermal Images and Sensor Data Fusion via Fuzzy Cognitive Maps

Aktivitäten

22nd International Conference on Distributed Computing and Artificial Intelligence (Veranstaltung)

Diese Publikation zitieren