A new multivariate extended homogeneously weighted moving average monitoring scheme incorporated with a support vector machine - LS2N - équipe CPS3 (Conception, Pilotage, Surveillance et Supervision des systèmes)
Article Dans Une Revue Quality and Reliability Engineering International Année : 2023

A new multivariate extended homogeneously weighted moving average monitoring scheme incorporated with a support vector machine

Résumé

Abstract Statistical process monitoring (SPM) provides a way, by means of monitoring schemes, to be alerted when a process significantly changes, and to initiate investigations for potential causes of variation. However, these schemes can only determine if the process is stable or unstable and they cannot provide any additional information. Several researchers have recommended the integration of machine learning (ML) approaches into SPM as a solution for the shortfalls of the techniques used to construct traditional monitoring schemes. This paper introduces a new multivariate extended homogeneously weighted moving average (MEHWMA) monitoring scheme and investigates its performance in terms of the run‐length distribution using simulation. In addition, the proposed MEHWMA scheme is integrated with a support vector machine to allow for the classification of the out‐of‐control events which facilitates the identification of the root causes of variation in the process. A numerical illustrative example is provided using real‐life data.
Fichier principal
Vignette du fichier
Project.pdf (723.84 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04198561 , version 1 (07-09-2023)

Identifiants

Citer

Luke Pieters, Jean‐claude Malela-Majika, Schalk Human, Philippe Castagliola. A new multivariate extended homogeneously weighted moving average monitoring scheme incorporated with a support vector machine. Quality and Reliability Engineering International, 2023, 39 (6), pp.2454-2475. ⟨10.1002/qre.3356⟩. ⟨hal-04198561⟩
58 Consultations
64 Téléchargements

Altmetric

Partager

More