Publicación:
A MACHINE LEARNING APPROACH FOR PLYWOOD QUALITY PREDICTION

Vista sencilla de ítem
dc.creatorCYNTHIA BELÉN URRA GONZÁLEZ
dc.creatorMARIO ALEJANDRO RAMOS MALDONADO
dc.date2023
dc.date.accessioned2025-01-10T15:41:11Z
dc.date.available2025-01-10T15:41:11Z
dc.date.issued2023
dc.description.abstractBECAUSE OF THE IMPACT ON PRODUCTIVITY AND COST REDUCTION, DECISION MAKING IN INDUSTRIAL PROCESSES IS ONE OF THE MOST REQUIRED ASPECTS IN THE INDUSTRY. SPECIFICALLY IN THE PANEL INDUSTRIES, PRODUCT QUALITY DEPENDS ON MULTIPLE VARIABLES, ESPECIALLY WOOD VARIABILITY. AMONG OTHER FACTORS, QUALITY DEPENDS ON THE ADHESION OF VENEERS OR PERPENDICULAR TENSILE STRENGTH. THE MAIN OBJECTIVE OF THIS STUDY WAS TO EVALUATE A MACHINE LEARNING APPROACH TO PREDICT THE ADHESION UNDER INDUSTRIAL CONDITIONS IN THE GLUING AND PRE-PRESSING STAGE. THE CONTROL VARIABLES THAT DETERMINE THIS ADHESION ARE MAINLY: OPERATIONAL TIMES, AMOUNT OF ADHESIVE, ENVIRONMENTAL CONDITIONS, AND VENEER TEMPERATURE. USING KNOWLEDGE DISCOVERY IN DATABASES DATA ANALYTICS METHODOLOGY, ARTIFICIAL NEURAL NETWORKS AND SUPPORT VECTOR MACHINE WERE EVALUATED. THE SIGMOID ACTIVATION FUNCTION WAS USED WITH 3 HIDDEN LAYERS AND 245 NEURONS. IN ADDITION TO THE ADAM OPTIMIZER, MULTI-LAYERPERCEPTRON, ARTIFICIAL NEURAL NETWORKS DELIVERED THE BEST ACCURACY LEVELS OF OVER 66 %. SIGMOID SHOWED AN ACCURACY OF OVER 66 %, PRECISION FIT GOOD TO FIND POSITIVE RESULTS (70 %). RELU FUNCTION OBTAINED THE BEST RECALL (OVER 74 %) SHOWING A GOOD CAPACITY TO IDENTIFY REALITY. RESULTS SHOW THAT IT IS NOT SUFFICIENT TO GENERATE A DATA SET USING THE AVERAGES OF EACH PROCESS VARIABLE, SINCE IT IS DIFFICULT TO OBTAIN BETTER RESULTS WITH THE ALGORITHMS EVALUATED. THIS WORK CONTRIBUTES TO DEFINING A METHODOLOGY TO BE USED IN PLYWOOD PLANTS USING INDUSTRIAL DATA TO TRAIN AND VALIDATE MACHINE LEARNING MODELS.
dc.formatapplication/pdf
dc.identifier.doi10.4067/s0718-221x2023000100436.
dc.identifier.issn0717-3644
dc.identifier.issn0718-221X
dc.identifier.urihttps://repositorio.ubiobio.cl/handle/123456789/13184
dc.languagespa
dc.publisherMADERAS: CIENCIA Y TECNOLOGIA
dc.relation.uri10.4067/s0718-221x2023000100436.
dc.rightsPUBLICADA
dc.subjectwood industry
dc.subjectsupervised learning
dc.subjectpredictive models
dc.subjectplywood
dc.subjectMa- chine Learning
dc.subjectdata engineering
dc.subjectartificial neural networks.
dc.subjectAlgorithms
dc.subjecttableros contrachapados
dc.subjectRedes Neuronales Artificiales.
dc.subjectmode- los predictivos
dc.subjectMachine Learning
dc.subjectingeniería de datos
dc.subjectindustria de la madera
dc.subjectaprendizaje supervisado
dc.subjectAlgoritmos
dc.titleA MACHINE LEARNING APPROACH FOR PLYWOOD QUALITY PREDICTION
dc.title.alternativeUN ENFOQUE DE MACHINE LEARNING PARA LA PREDICCIÓN DE LA CALIDAD DE TABLEROS CONTRACHAPADOS
dc.typeARTÍCULO
dspace.entity.typePublication
ubb.EstadoPUBLICADA
ubb.Otra ReparticionDEPARTAMENTO DE INGENIERIA EN MADERAS
ubb.SedeCONCEPCIÓN
Archivos
Colecciones
Artículos científicos