A Learning Probabilistic Boolean Network Model of a Manufacturing Process with Applications in System Asset Maintenance

Probabilistic Boolean Networks (PBN) can model the dynamics of complex biological systems, as well as other non-biological systems like manufacturing systems and smart grids. In this proof-of-concept paper, we propose a PBN architecture with a learning process that significantly enhances fault and f...

Full description

Saved in:
Bibliographic Details
Main Authors: Pedro Juan Rivera Torres, Chen Chen, Sara Rodríguez González, Orestes Llanes Santiago
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Entropy
Subjects:
Online Access:https://www.mdpi.com/1099-4300/27/5/463
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327647277973504
author Pedro Juan Rivera Torres
Chen Chen
Sara Rodríguez González
Orestes Llanes Santiago
author_facet Pedro Juan Rivera Torres
Chen Chen
Sara Rodríguez González
Orestes Llanes Santiago
author_sort Pedro Juan Rivera Torres
collection DOAJ
description Probabilistic Boolean Networks (PBN) can model the dynamics of complex biological systems, as well as other non-biological systems like manufacturing systems and smart grids. In this proof-of-concept paper, we propose a PBN architecture with a learning process that significantly enhances fault and failure prediction in manufacturing systems. This concept was tested using a PBN model of an ultrasound welding process and its machines. Through various experiments, the model successfully learned to maintain a normal operating state. Leveraging the complex properties of PBNs, we utilize them as an adaptive learning tool with positive feedback, demonstrating that these networks may have broader applications than previously recognized. This multi-layered PBN architecture offers substantial improvements in fault detection performance within a positive feedback network structure that shows greater noise tolerance than other methods.
format Article
id doaj-art-5beb048b59f5490eb64d31ecaccf002b
institution Kabale University
issn 1099-4300
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Entropy
spelling doaj-art-5beb048b59f5490eb64d31ecaccf002b2025-08-20T03:47:49ZengMDPI AGEntropy1099-43002025-04-0127546310.3390/e27050463A Learning Probabilistic Boolean Network Model of a Manufacturing Process with Applications in System Asset MaintenancePedro Juan Rivera Torres0Chen Chen1Sara Rodríguez González2Orestes Llanes Santiago3Departmento de Informática y Automática, Universidad de Salamanca, Patio de las Escuelas 1, 37006 Salamanca, SpainSt. Edmund’s College, University of Cambridge, Mount Pleasant, Cambridge CB3 0BN, UKDepartmento de Informática y Automática, Universidad de Salamanca, Patio de las Escuelas 1, 37006 Salamanca, SpainDepartamento de Automática y Computación, Universidad Tecnológica de La Habana José Antonio Echeverría (CUJAE), Marianao, La Habana 11500, CubaProbabilistic Boolean Networks (PBN) can model the dynamics of complex biological systems, as well as other non-biological systems like manufacturing systems and smart grids. In this proof-of-concept paper, we propose a PBN architecture with a learning process that significantly enhances fault and failure prediction in manufacturing systems. This concept was tested using a PBN model of an ultrasound welding process and its machines. Through various experiments, the model successfully learned to maintain a normal operating state. Leveraging the complex properties of PBNs, we utilize them as an adaptive learning tool with positive feedback, demonstrating that these networks may have broader applications than previously recognized. This multi-layered PBN architecture offers substantial improvements in fault detection performance within a positive feedback network structure that shows greater noise tolerance than other methods.https://www.mdpi.com/1099-4300/27/5/463fault detection and isolationmachine learning algorithmsprobabilistic Boolean networksprobabilistic Boolean network modeling
spellingShingle Pedro Juan Rivera Torres
Chen Chen
Sara Rodríguez González
Orestes Llanes Santiago
A Learning Probabilistic Boolean Network Model of a Manufacturing Process with Applications in System Asset Maintenance
Entropy
fault detection and isolation
machine learning algorithms
probabilistic Boolean networks
probabilistic Boolean network modeling
title A Learning Probabilistic Boolean Network Model of a Manufacturing Process with Applications in System Asset Maintenance
title_full A Learning Probabilistic Boolean Network Model of a Manufacturing Process with Applications in System Asset Maintenance
title_fullStr A Learning Probabilistic Boolean Network Model of a Manufacturing Process with Applications in System Asset Maintenance
title_full_unstemmed A Learning Probabilistic Boolean Network Model of a Manufacturing Process with Applications in System Asset Maintenance
title_short A Learning Probabilistic Boolean Network Model of a Manufacturing Process with Applications in System Asset Maintenance
title_sort learning probabilistic boolean network model of a manufacturing process with applications in system asset maintenance
topic fault detection and isolation
machine learning algorithms
probabilistic Boolean networks
probabilistic Boolean network modeling
url https://www.mdpi.com/1099-4300/27/5/463
work_keys_str_mv AT pedrojuanriveratorres alearningprobabilisticbooleannetworkmodelofamanufacturingprocesswithapplicationsinsystemassetmaintenance
AT chenchen alearningprobabilisticbooleannetworkmodelofamanufacturingprocesswithapplicationsinsystemassetmaintenance
AT sararodriguezgonzalez alearningprobabilisticbooleannetworkmodelofamanufacturingprocesswithapplicationsinsystemassetmaintenance
AT orestesllanessantiago alearningprobabilisticbooleannetworkmodelofamanufacturingprocesswithapplicationsinsystemassetmaintenance
AT pedrojuanriveratorres learningprobabilisticbooleannetworkmodelofamanufacturingprocesswithapplicationsinsystemassetmaintenance
AT chenchen learningprobabilisticbooleannetworkmodelofamanufacturingprocesswithapplicationsinsystemassetmaintenance
AT sararodriguezgonzalez learningprobabilisticbooleannetworkmodelofamanufacturingprocesswithapplicationsinsystemassetmaintenance
AT orestesllanessantiago learningprobabilisticbooleannetworkmodelofamanufacturingprocesswithapplicationsinsystemassetmaintenance