Predictive performance monitoring of material handling systems using the performance spectrum

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

Predictive performance analysis is crucial for supporting operational processes. Prediction is challenging when cases are not isolated but influence each other by competing for resources (spaces, machines, operators). The so-called performance spectrum maps a variety of performance-related measures within and across cases over time. We propose a novel prediction approach that uses the performance spectrum for feature selection and extraction to pose machine learning problems used for performance prediction in non-isolated cases. Although the approach is general, we focus on material handling systems as a primary example. We report on a feasibility study conducted for the material handling systems of a major European airport. The results show that the use of the performance spectrum enables much better predictions than baseline approaches.

Original languageEnglish
Title of host publicationProceedings - 2019 International Conference on Process Mining, ICPM 2019
Place of PublicationPiscataway
PublisherInstitute of Electrical and Electronics Engineers
Pages137-144
Number of pages8
ISBN (Electronic)978-1-7281-0919-0
DOIs
Publication statusPublished - 1 Jun 2019
Event1st International Conference on Process Mining, ICPM 2019 - Aachen, Germany
Duration: 24 Jun 201926 Jun 2019

Conference

Conference1st International Conference on Process Mining, ICPM 2019
CountryGermany
CityAachen
Period24/06/1926/06/19

Fingerprint

Materials handling
Monitoring
Feature extraction
Airports
Learning systems
Material handling system
Performance monitoring
Prediction

Keywords

  • Material handling systems
  • Performance spectrum
  • Predictive process monitoring

Cite this

Denisov, V., Fahland, D., & van der Aalst, W. M. P. (2019). Predictive performance monitoring of material handling systems using the performance spectrum. In Proceedings - 2019 International Conference on Process Mining, ICPM 2019 (pp. 137-144). [8786068] Piscataway: Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICPM.2019.00029
Denisov, Vadim ; Fahland, Dirk ; van der Aalst, Wil M.P. / Predictive performance monitoring of material handling systems using the performance spectrum. Proceedings - 2019 International Conference on Process Mining, ICPM 2019. Piscataway : Institute of Electrical and Electronics Engineers, 2019. pp. 137-144
@inproceedings{14a322a5cfa84245874bc8fad3ce7db3,
title = "Predictive performance monitoring of material handling systems using the performance spectrum",
abstract = "Predictive performance analysis is crucial for supporting operational processes. Prediction is challenging when cases are not isolated but influence each other by competing for resources (spaces, machines, operators). The so-called performance spectrum maps a variety of performance-related measures within and across cases over time. We propose a novel prediction approach that uses the performance spectrum for feature selection and extraction to pose machine learning problems used for performance prediction in non-isolated cases. Although the approach is general, we focus on material handling systems as a primary example. We report on a feasibility study conducted for the material handling systems of a major European airport. The results show that the use of the performance spectrum enables much better predictions than baseline approaches.",
keywords = "Material handling systems, Performance spectrum, Predictive process monitoring",
author = "Vadim Denisov and Dirk Fahland and {van der Aalst}, {Wil M.P.}",
year = "2019",
month = "6",
day = "1",
doi = "10.1109/ICPM.2019.00029",
language = "English",
pages = "137--144",
booktitle = "Proceedings - 2019 International Conference on Process Mining, ICPM 2019",
publisher = "Institute of Electrical and Electronics Engineers",
address = "United States",

}

Denisov, V, Fahland, D & van der Aalst, WMP 2019, Predictive performance monitoring of material handling systems using the performance spectrum. in Proceedings - 2019 International Conference on Process Mining, ICPM 2019., 8786068, Institute of Electrical and Electronics Engineers, Piscataway, pp. 137-144, 1st International Conference on Process Mining, ICPM 2019, Aachen, Germany, 24/06/19. https://doi.org/10.1109/ICPM.2019.00029

Predictive performance monitoring of material handling systems using the performance spectrum. / Denisov, Vadim; Fahland, Dirk; van der Aalst, Wil M.P.

Proceedings - 2019 International Conference on Process Mining, ICPM 2019. Piscataway : Institute of Electrical and Electronics Engineers, 2019. p. 137-144 8786068.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Predictive performance monitoring of material handling systems using the performance spectrum

AU - Denisov, Vadim

AU - Fahland, Dirk

AU - van der Aalst, Wil M.P.

PY - 2019/6/1

Y1 - 2019/6/1

N2 - Predictive performance analysis is crucial for supporting operational processes. Prediction is challenging when cases are not isolated but influence each other by competing for resources (spaces, machines, operators). The so-called performance spectrum maps a variety of performance-related measures within and across cases over time. We propose a novel prediction approach that uses the performance spectrum for feature selection and extraction to pose machine learning problems used for performance prediction in non-isolated cases. Although the approach is general, we focus on material handling systems as a primary example. We report on a feasibility study conducted for the material handling systems of a major European airport. The results show that the use of the performance spectrum enables much better predictions than baseline approaches.

AB - Predictive performance analysis is crucial for supporting operational processes. Prediction is challenging when cases are not isolated but influence each other by competing for resources (spaces, machines, operators). The so-called performance spectrum maps a variety of performance-related measures within and across cases over time. We propose a novel prediction approach that uses the performance spectrum for feature selection and extraction to pose machine learning problems used for performance prediction in non-isolated cases. Although the approach is general, we focus on material handling systems as a primary example. We report on a feasibility study conducted for the material handling systems of a major European airport. The results show that the use of the performance spectrum enables much better predictions than baseline approaches.

KW - Material handling systems

KW - Performance spectrum

KW - Predictive process monitoring

UR - http://www.scopus.com/inward/record.url?scp=85071197116&partnerID=8YFLogxK

UR - https://github.com/processmining-in-logistics/psm/tree/ppm

U2 - 10.1109/ICPM.2019.00029

DO - 10.1109/ICPM.2019.00029

M3 - Conference contribution

AN - SCOPUS:85071197116

SP - 137

EP - 144

BT - Proceedings - 2019 International Conference on Process Mining, ICPM 2019

PB - Institute of Electrical and Electronics Engineers

CY - Piscataway

ER -

Denisov V, Fahland D, van der Aalst WMP. Predictive performance monitoring of material handling systems using the performance spectrum. In Proceedings - 2019 International Conference on Process Mining, ICPM 2019. Piscataway: Institute of Electrical and Electronics Engineers. 2019. p. 137-144. 8786068 https://doi.org/10.1109/ICPM.2019.00029