THE OBJECTIVE OF THIS STUDY WAS TO FIND AN EFFICIENT METHOD THAT ALLOWS TIME AND YIELD INCREASE VOLUME USE AND UTILITY OF THE SAWMILLS THAT PROCESS LOGS PRUNED PINUS RADIATA, LINKING EXTERNAL INFORMATION PROVIDED BY A SCANNER INDUSTRY AND SIMULATION OF CYLINDRICAL DEFECTIVE CORE (CDC) IN THE CONSTITUTION OF A THREE-DIMENSIONAL LOG, WHERE THE OPTIMAL CUTTING PATTERN WAS ESTABLISHED BY MEANS OF A DYNAMIC PROGRAMMING ALGORITHM. SAWING WAS SIMULATED ON A SAMPLE OF 30 LOGS OBTAINED RANDOMLY INDUSTRIAL PROCESS OF SCANNING. THE RESULTS WERE COMPARED WITH THOSE OBTAINED BY A HEURISTIC DEVELOPED BY A COMPANY. DYNAMIC PROGRAMMING ALGORITHM ACHIEVED A YIELD OF THE RAW MATERIAL OF 64% AND AN AVERAGE RELATIVE NET UTILITY OF 11 US$/LOG WAS OBTAINED.

BECAUSE 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.

THIS PAPER FOCUSES ON ADOPTING CYBERSECURITY PROCEDURES IN CHILEAN MANUFACTURING COMPANIES IN THE CONTEXT OF THE FOURTH INDUSTRIAL REVOLUTION?S DATA-DRIVEN DEMANDS, WHICH HAVE EXPOSED VULNERABILITIES IN CYBERSECURITY. THIS ANALYSIS IS BASED ON DATA FROM THE FIFTH LONGITUDINAL SURVEY OF COMPANIES - ELE 5 - CONDUCTED BY THE NATIONAL INSTITUTE OF STATISTICS. USING THE TOE ADOPTION MODEL, WE EMPLOY BINARY AND ORDERED LOGIT AND PROBIT MODELS WITH DATA FROM 574 COMPANIES AND 17 EXPLANATORY VARIABLES. THE OBJECTIVE IS TO GAIN INSIGHT INTO THE FACTORS INFLUENCING THE ADOPTION OF CYBERSECURITY PROCESSES, COMPLEMENTING THE EXISTING LITERATURE, WHICH OFTEN FOCUSES ON DEVELOPING SPECIFIC TECHNOLOGIES OR CONDUCTING COMPREHENSIVE ANALYSES OF DIGITAL TRANSFORMATION. THE STUDY HIGHLIGHTS THE SIGNIFICANCE OF COMPANY SIZE IN EXPLAINING THE ADOPTION OF CYBERSECURITY PROCEDURES AND REVEALS THE RELEVANCE OF EXPLANATORY VARIABLES AS THE DEPTH OF ADOPTION INCREASES. THE FINDINGS UNDERSCORE THE NEED FOR PUBLIC POLICIES THAT FACILITATE THE IMPLEMENTATION OF EXISTING REGULATIONS, SUCH AS ISO 27.001, PARTICULARLY FOR SMALL COMPANIES. ADDITIONALLY, THE STUDY EMPHASIZES THE IMPORTANCE OF FOSTERING A

THIS WORK DESCRIBES AN AUTOMATIC GRADING SYSTEM USING ARTIFICIAL VISION TO IMPROVE THE QUALITY OF WOOD PANELS SURFACES. THE OBJECTIVE IS TO CONTROL STAINS ON THE SURFACE. ARTIFICIAL VISION TECHNIQUES LIKE THRESHOLDING AND TRANSFORMED WATERSHED METHODS ARE APPLIED. DEFECTS QUANTITATIVE MEASURES FOUND ON THE SURFACE ARE ALSO PRESENTED, IN PARTICULAR QUANTITY, AREA, INTENSITY AND DISTRIBUTION.

IN THIS ARTICLE, WE PRESENT THE DEVELOPMENT OF A SIMPLE MULTIAGENT-BASED SYSTEM FOR THE CONTROL OF A FLEXIBLE MANUFACTURING SYSTEM. WE FOLLOWED THE STAGES OF A METHODOLOGY SPECIALLY CONCEIVED FOR THE DEVELOPMENT OF AGENT-BASED SYSTEM, WHICH IS AN INTEGRATION OF THE CLASSICAL METHODOLOGY FOR AGENT-ORIENTED ANALYSIS AND DESIGN GAIA, AND AUML (AGENT-UNIFIED MODELING LANGUAGE). WE ADOPTED AS STUDY CASE THE CIMUBB LABORATORY AT THE UNIVERSITY OF BIO-BIO, WHICH HAS A FLEXIBLE MANUFACTURING SYSTEM INCLUDING THREE FLEXIBLE MANUFACTURING CELLS INTERCONNECTED BY A CONVEYOR BELT. IN THE ANALYSIS STAGE, WE IDENTIFIED ROLES INVOLVED, AND WE DESIGN MODELS REPRESENTING ROLES AND PROTOCOLS. IN THE DESIGN STAGE, WE APPLIED GAIA AGENT, SERVICES, AND ACQUAINTANCE MODELS FROM GAIA, AND WE COMPLEMENTED WITH AUML AS THE ADOPTED METHODOLOGY SUGGESTS. WITH THE DEVELOPED MODELS, WE CONSTRUCTED A FULLY FUNCTIONAL SYSTEM WHERE EACH AGENT WAS BUILT AS AN INDEPENDENT PROCESS TREE. AGENTS COMMUNICATE BY PASSING MESSAGES THROUGH THE ETHERNET NETWORK WITH SOCKET INTERFACES. VARIOUS TESTS EXECUTED IN OUR LABORATORY SCALE MANUFACTURING SYSTEM SHOW THE EFFECTIVENESS OF OUR IMPLEMENTATION. COPYRIGHT © 2015 JOHN WILEY & SONS, LTD.

THIS STUDY INVESTIGATES THE WORST-CASE PERFORMANCE GUARANTEE OF LOCALLY OPTIMAL SOLUTIONS TO MINIMIZE THE TOTAL WEIGHTED COMPLETION TIME ON UNIFORMLY RELATED PARALLEL MACHINES. THE INVESTIGATED NEIGHBORHOOD STRUCTURE IS JUMP, ALSO CALLED INSERTION OR MOVE. THIS RESEARCH FOCUSED ON ESTABLISHING THE LOCAL OPTIMALITY CONDITION EXPRESSED AS AN INEQUALITY AND MAPPING THAT MAPS A SCHEDULE INTO AN INNER PRODUCT SPACE SO THAT THE NORM OF THE MAPPING IS CLOSELY RELATED TO THE TOTAL WEIGHTED COMPLETION TIME OF THE SCHEDULE. WE DETERMINE TWO NEW UPPER BOUNDS FOR THE PERFORMANCE GUARANTEE, WHICH TAKE THE FORM OF AN EXPRESSION BASED ON PARAMETERS THAT DESCRIBE THE FAMILY OF INSTANCES: THE SPEED OF THE FASTEST MACHINE, THE SPEED OF THE SLOWEST MACHINE, AND THE NUMBER OF MACHINES. THESE NEW BOUNDS OUTPERFORM THE PARAMETRIC UPPER BOUND PREVIOUSLY ESTABLISHED IN THE EXISTING LITERATURE AND ENABLE A BETTER UNDERSTANDING OF THE PERFORMANCE OF THE SOLUTIONS OBTAINED FOR THE JUMP NEIGHBORHOOD IN THIS SCHEDULING PROBLEM, ACCORDING TO PARAMETERS THAT DESCRIBE THE FAMILY OF INSTANCES.

IN THIS RESEARCH WORK AN ALGORITHM THAT GATHERS THE BEST PROCEDURES APPLIED IN SAWMILLS WAS DEVELOPED, ALONG WITH A METHODOLOGY BASED ON CUTTING GEOMETRICAL LINE ANALYSIS. THIS APPLICATION WAS PROGRAMMED UNDER THE C++ LANGUAGE, SIZES OBJECTIVE BOARD AND ITS PRICES, AND THE 2-D SLAB GEOMETRY ARE THE INPUT DATA, OBTAINING LENGTH AND WIDTH SOLUTIONS FOR EVERY SLAB. ITS OUTCOMES HAVE BEEN COMPARED WITH A PATTERN THAT MATCHES THE SOLUTIONS PROVIDED BY AN

IN THE CONTEXT OF THE FOURTH INDUSTRIAL REVOLUTION THIS PAPER ANALYZES THE FACTORS THAT EXPLAIN THE DEGREE OF DIFFUSION OF SOME INFORMATION TECHNOLOGIES (ICTS) ENABLING INDUSTRIES 4.0 IN CHILEAN COMPANIES. IN THIS GROUP WE FIND TECHNOLOGIES SUCH AS: BIG DATA, RIFD (RADIO FREQUENCY IDENTIFICATION), CLOUD COMPUTING, ERP (ENTERPRISE REQUIREMENTS PLANNING), CRM (CUSTOMER RELATIONSHIP MANAGEMENT), SCM (SUPPLY CHAIN MANAGEMENT) AND COMPUTER SECURITY. THROUGH THE ANALYSIS OF CLUSTERS, ORDERLY LOGISTIC REGRESSION AND DECISION TREE, BASED ON 2,081 COMPANIES REPORTED IN THE SURVEY OF ACCESS AND USE OF INFORMATION COMMUNICATION TECHNOLOGY (ICT) IN COMPANIES 2018 (MINECON, 2020). IT IS CONCLUDED THAT THERE IS AN IMPORTANT DIFFERENCE IN TECHNOLOGICAL ADOPTION BASED ON SIZE FROM THE VOLUME OF SALES AND THE AMOUNT OF DIRECT LABOR. IT IS ALSO NOTED THAT COMPANIES THAT SUBCONTRACT AND AT THE SAME TIME HAVE ICT PROFESSIONALS ARE MORE LIKELY TO INVEST IN THIS TYPE OF TECHNOLOGY. WE DETECTED A ?TECHNOLOGICAL STAGGERING? WHERE COMPANIES BEGIN BY INCORPORATING CLOUD COMPUTING AND ERP AND THEN INCREASE IN THE NUMBER AND COMPLEXITY OF THE TECHNOLOGIES USED, ACHIEVING GREATER SYNERGIES AND BENEFITS IN DIGITAL TRANSFORMATION. IT IS NECESSARY TO IMPLEMENT MECHANISMS FOR MONITORING TECHNICAL CHANGE TO GENERATE PUBLIC POLICIES AIMED AT LEVELING TECHNOLOGICAL ADOPTION IN SMALL AND MEDIUM-SIZED ENTERPRISES. THIS WORK PROVIDES A GLOBAL AND INTERSECTORAL VIEW OF THE PROCESS OF DIFFUSION OF ENABLING TECHNOLOGIES FOR INDUSTRY 4.0 THROUGH MULTIVARIATE ANALYSIS TECHNIQUES AND DATA SCIENCE, BEING A CONTRIBUTION TO WHAT IS CURRENTLY WORKED ON FOCUSED ON THE STUDY OF BUSINESS CASES, ON THE MONITORING OF A SPECIFIC TECHNOLOGY OR ON AN ANALYSIS OF A SPECIFIC PRODUCTIVE SECTOR.

THE FOURTH INDUSTRIAL REVOLUTION HAS BUILT UPON THE LESSONS LEARNED FROM COVID-19 AND HAS EMPHASIZED THE URGENT NEED FOR DIGITAL TRANSFORMATION IN SMALL AND MEDIUM ENTERPRISES (SMES) IN LATIN AMERICA. THIS STUDY AIMS TO IDENTIFY THE FACTORS THAT CAN EXPLAIN THE VARYING DEGREES OF ADOPTION OF DIGITAL TECHNOLOGIES 4.0 (DT 4.0). THE RESEARCH ANALYZES THE RESULTS OF SURVEYS CONDUCTED AMONG 35 COMPANIES LOCATED IN THE CENTRAL REGION OF ARGENTINA AND THE BIOBIO REGION OF CHILE. BY UTILIZING THE TECHNOLOGY, ORGANIZATION, AND ENVIRONMENT (TOE) MODEL OF ADOPTION AND EMPLOYING DATA SCIENCE TOOLS, SUCH AS CLUSTER ANALYSIS (K-MEANS) AND DECISION TREES (J48), THE STUDY PARAMETERIZES THE DIFFERENT RESPONSES AND GENERATES VALUABLE INSIGHTS. OUR WORK PROVIDES A COMPLEMENTARY VIEW TO EXISTING STUDIES, ANALYZING THE KEY FACTORS IN THE ADOPTION OF DT 4.0 IN A GROUP OF SMES LOCATED IN REGIONS, NOT NATIONAL CAPITALS, OF TWO LATIN AMERICAN COUNTRIES WITH DIFFERENT GROWTH MODELS. THE RESULTS HIGHLIGHT THE SIGNIFICANCE OF BUSINESS LEADERS POSSESSING KNOWLEDGE OF DT 4.0, THE IMPORTANCE OF HAVING SPECIALIZED HUMAN CAPITAL, AND THE NEED FOR AN ORGANIZATIONAL CULTURE THAT EMBRACES INNOVATION. PUBLIC POLICY SHOULD FOCUS ON TRANSFORMING BUSINESS LEADERSHIP AND ORGANIZATIONAL DYNAMICS TO STIMULATE DIGITAL TRANSFORMATION.

LA FORMACIÓN ARQUITECTÓNICA DEBE DESARROLLAR HABILIDADES TÉCNICAS Y ESTÉTICAS PARA REALIZAR PROYECTOS DE CONSTRUCCIÓN. LAS NUEVAS MAQUINAS DE FABRICACIÓN DIGITAL PERMITEN ELABORAR MODELOS MATERIALES DE LOS DISEÑOS, ASÍ COMO ELEMENTOS CONSTRUCTIVOS INDUSTRIALIZADOS, GENERANDO NUEVAS CAPACIDADES QUE DEBEN SER ADECUADAMENTE INTEGRADAS EN LA ENSEÑANZA PROFESIONAL. EL ARTÍCULOANALIZA IMPLICANCIAS DE ESTAS TECNOLOGÍAS EN LA FORMACIÓN ARQUITECTÓNICA BASADO EN SIETE EXPERIENCIAS EDUCACIONALES

IN LATIN AMÉRICA THERE ARE LARGE EXPORTING COMPANIES INTENSIVE IN NATURAL RESOURCES WHICH DO NOT CONNECT WITH THE SMES IN THE TERRITORIES. THE AIM OF THIS STUDY IS TO PROVIDE ELEMENTS THAT EXPLAIN THE LIMITS TO THE PRODUCTIVITY OF SMALL AND MEDIUM ENTERPRISES LOCATED IN BIO-BASED TERRITORIES, PROVIDING INPUTS FOR A PUBLIC POLICY THAT ENHANCES LOCAL DEVELOPMENT. THE CASE OF SAWMILLS LOCATED IN THE PROVINCE OF ARAUCO, BÍO-BÍO REGION, CHILE, IS STUDIED. THE RESULTS OF A SURVEY APPLIED TO 42 COMPANIES ARE ANALYZED, IN THE CONTEXT OF AN INITIATIVE FINANCED BY THE REGIONAL GOVERNMENT OF BIOBÍO, WHICH REPRESENT 84% OF THE TOTAL SAWMILLS IN THE PROVINCE OF ARAUCO. DIFFERENT DATA SCIENCE ALGORITHMS ARE USED TO GENERATE CLUSTERS AND DECISION TREES. BASED ON THE RESULTS, A HETEROGENEITY WITHIN THE GROUP OF COMPANIES IS VERIFIED FROM THE PERCEPTION OF THE MAIN PROBLEMS, THE PROCESSES THAT ARE INTERNALIZED, THE NUMBER OF SECTORS IT SELLS TO AND THE COST OF RAW MATERIALS. PUBLIC POLICIES RECOMMENDATIONS ARE PRESENTED AIMED AT BUILDING SUPPORT NETWORKS, IMPROVING QUALITY STANDARDS THROUGH CERTIFICATIONS, ATTRACTING, AND RETAINING QUALIFIED HUMAN CAPITAL AND PROMOTING COLLABORATIVE DESIGN AMONG COMPANIES.

MACHINE LEARNING IS A TOOL THAT IS BEING USED TO OPTIMIZE HIGHLY COMPLEX INDUSTRIAL PROCESSES. IN THE PLYWOOD PANEL PRODUCTION INDUSTRY, VENEER DRYING IS ONE OF THE MOST IMPORTANT PROCESSES AS IT ALLOWS TO OBTAIN HIGH QUALITY PRODUCTS. THE BIOLOGICAL NATURE AND HIGH STRUCTURAL VARIABILITY OF WOOD TURNS ITS INDUSTRIAL PROCESSING MULTIVARIATE AND DIFFICULT TO CONTROL. THE LARGE NUMBER OF VARIABLES PRESENT AND THE INCREASING POSSIBILITY TO MEASURE THEM IN REAL TIME ARE ENABLING THE AVAILABILITY OF A LARGE AMOUNT OF DATA. NOWADAYS, DATA-DRIVEN APPROACH AND INTELLIGENCE ARTIFICIAL TECHNIQUES, SPECIFICALLY MACHINE LEARNING CAN ENABLE ROBUST PREDICTION AND CONTROL APPROACHES. IN THE PROCESS INDUSTRY, WITH HIGH LEVELS OF AUTOMATION, IT IS POSSIBLE TO ENABLE DECISION MAKING TO PREDICT PRODUCT QUALITY BY MONITORING EXPLANATORY CONTROL VARIABLES. THE OBJECTIVE OF THIS WORK WAS TO EVALUATE A MACHINE LEARNING ALGORITHM CAPABLE OF PREDICTING THE QUALITY OF THE VENEER DRYING PROCESS FROM A CONSIDERABLE NUMBER OF INPUT VARIABLES CAPTURED FROM A REAL INDUSTRIAL PROCESS. THE WEKA PLATFORM AND PYTHON CODE WERE USED. THREE ALGORITHMS WERE EVALUATED: K-NEAREST-NEIGHBOR, EXTREME GRADIENT BOOSTING AND SUPPORT VECTOR MACHINE. VARIABLE AND DIMENSIONALITY REDUCTION, CORRELATION ANALYSIS AND PRINCIPAL COMPONENT ANALYSIS WERE PERFORMED. THE RESULTS SHOWED THAT EXTREME GRADIENT BOOSTING ACHIEVED AN ACCURACY OF 76 % IN PREDICTING QUALITY SCORES. FINALLY, IT IS CONCLUDED THAT BOTH THE DATA ENGINEERING METHODOLOGY AND THE EVALUATED ALGORITHMS WERE EFFICIENT IN PREDICTING INDUSTRIAL DATA.

THE LUMBER INDUSTRY SECTOR FORMS A PRODUCTIVE CHAIN THAT BE SUMMARIZED IN THE THREE PROCESSES: SAWING, DRYING AND REMANUFACTURING. WHERE SATISFYING THE REQUESTED VOLUME AND MEET THE PLANNED DELIVERY DATES IS IMPORTANT TO BOTH, THE CLIENT AND EACH PRODUCTION CHAIN. THE NON-INTEGRATION PRESENTS COHERENCE ISSUES IN THE PRODUCTION PLANS. HENCE, AN INTEGRATED MODEL IN LUMBER SECTOR, THAT USES THE WORKING ADVANTAGES OF MULTI-AGENTS SYSTEMS, WORKS TO IMPROVE COHERENCE AND THE SYSTEM?S GLOBAL PRODUCTIVITY. THE INTEGRATION MODEL PRESENTED IN THIS PAPER MINIMIZES GLOBAL TARDINESS OF THE LUMBER TRANSFORMATION CHAIN, AT THE MOMENT OF DELIVERING PRODUCTION ORDERS. WITHIN THE SYSTEM, THE COMMUNICATION BETWEEN AGENTS IS DONE BY USING THE CONTRACT NET PROTOCOL. THE RESULTS SHOW THE SAWMILL, AS A FIRST STEP IN THE SYSTEM, IS WHERE THE BIGGEST TARDINESS AND BOTTLE NECK IN THE FULFILLING OF THE PRODUCTION ORDERS IS PRODUCED. IN AVERAGE, THE RESULTS SHOWED A TARDINESS BETWEEN 2 TO 4 DAYS IN THE COMPLIANCE OF CHAIN PRODUCTION ORDERS. THE MAXIMUM DELAY IS OF 20 DAYS.

THE PRODUCTION PLANNING PROBLEM IN THE PINUS RADIATA SAWMILL INDUSTRY REVOLVES AROUND DETERMINING HOW TO CUT A SET OF LOGS OF DIFFERENT DIAMETERS TO OBTAIN PIECES WITH A RECTANGULAR BASE, TYPICALLY OF THE SAME LENGTH AS THE ORIGINAL LOG. THE PRIMARY OBJECTIVE IS OFTEN TO MAXIMIZE THE VOLUMETRIC YIELD OR THE RATIO BETWEEN THE TOTAL VOLUME OF THE PRODUCED PIECES AND THE AVAILABLE VOLUME OF THE LOGS. GIVEN THE SCARCITY OF TIMBER FORESTS, SMALL AND MEDIUM-SIZED (SME) SAWMILLS MUST OPTIMIZE THEIR OPERATIONS TO MAXIMIZE THE VOLUMETRIC YIELD OF LOGS, USUALLY PROCURED FROM THIRD PARTIES AND MAY VARY IN QUALITY AND DIMENSIONS. IN THIS CONTEXT, THE ABSENCE OF DECISION SUPPORT TOOLS DIRECTLY CONTRIBUTES TO INEFFICIENT RAW MATERIAL UTILIZATION, CONSEQUENTLY IMPACTING THE BUSINESS?S PROFIT. THIS STUDY INTRODUCES A MULTI-OBJECTIVE MIXED-INTEGER LINEAR PROGRAMMING MODEL INCORPORATING LOG AVAILABILITY AND PRODUCT DEMAND AS INPUT PARAMETERS. THE OBJECTIVE FUNCTIONS AIM TO MINIMIZE THE TOTAL VOLUMETRIC LOSS OF UTILIZED LOGS AND THE SURPLUS QUANTITY ASSOCIATED WITH PRODUCTS EXCEEDING DEMAND. THE MODEL INTEGRATES CUTTING PATTERNS PRE-DETERMINED FOR EACH LOG DIAMETER AS AN ADDITIONAL INPUT. THE CUTLOG SOFTWARE WAS USED TO IDENTIFY ALL THE OPTIMAL CUTTING PATTERNS. THE ?-CONSTRAINT METHOD, IMPLEMENTED IN THE CPLEX SOLVER, WAS EMPLOYED TO SOLVE THE MODEL. THE MODEL WAS VALIDATED USING REPRESENTATIVE INSTANCES DESIGNED TO EMULATE THE CHALLENGES FACED BY SME SAWMILLS. REAL INDUSTRY DATA, SURVEYS, AND COMMERCIAL RECORDS FROM SME SAWMILLS IN SOUTHERN CHILE WERE UTILIZED. THE RESULTS CONFIRM THE EFFECTIVENESS OF THE PROPOSED MODEL IN ADDRESSING THE MULTI-OBJECTIVE CHALLENGES ENCOUNTERED BY THESE BUSINESSES. THE MODEL SUCCESSFULLY IDENTIFIES MULTIPLE SOLUTIONS ON THE PARETO FRONTIER, OFFERING VALUABLE INSIGHTS FOR DECISION-MAKING.

ESTE ARTÍCULO ANALIZA LAS POLÍTICAS PÚBLICAS Y LAS REDES PARA EL DESARROLLO DE LAS TECNOLOGÍAS 4.0 EN CHILE, A PARTIR DEL ESTUDIO DE LA CARTERA DE PROYECTOS FONDEF-IDEA, DESDE 2012 A 2017. MEDIANTE UN ANÁLISIS SINTÁCTICO DE LOS TÍTULOS, OBJETIVOS Y RESÚMENES SE SELECCIONARON LAS INICIATIVAS ESPECÍFICAS QUE TIENEN DIRECTA O INDIRECTA APLICACIÓN DE LAS TECNOLOGÍAS 4.0, SOBRE UNA BASE INICIAL DE 530 INICIATIVAS PÚBLICAS. SE ANALIZARON LAS DIFERENTES ESPECIALIZACIONES SECTORIALES Y LA RED SOCIAL. NUESTRA CONCLUSIÓN ES QUE TODAVÍA NO OBSERVAMOS AL NIVEL DE POLÍTICAS PÚBLICAS EN CHILE UNA ESTRATEGIA QUE ESTIMULE EL DESARROLLO DESCENTRALIZADO DE ESTAS NUEVAS TECNOLOGÍAS. SE COMPRUEBA UNA ALTA CENTRALIDAD EN LA RED DE LAS APLICACIONES DE SENSORES EN LA MINERÍA DEL COBRE, DEL MONITOREO Y LA CONVERSIÓN DEL DATO A LA INFORMACIÓN, EXISTIENDO TODAVÍA UNA IMPORTANTE BRECHA A SER CUBIERTA POR LAS POLÍTICAS PÚBLICAS. A NUESTRO JUICIO ES URGENTE CONTAR CON UNA ESTRATEGIA DE DESARROLLO TECNOLÓGICO QUE ACORTE LA BRECHA CON LOS PAÍSES QUE SE ENCUENTRAN EN UNA ETAPA MÁS AVANZADA.

WOOD INDUSTRY IS KEY FOR SUSTAINABILITY AND AN IMPORTANT ECONOMIC ACTIVITY IN MANY COUNTRIES. IN MANUFACTURING PLANTS, WOOD VARIABILITY TURNS OPERATION MANAGEMENT MORE COMPLEX. IN A COMPETITIVE SCENARIO, ASSETS AVAILABILITY IS CRITICAL TO ACHIEVE HIGHER PRODUCTIVITY. IN A NEW FOURTH INDUSTRIAL REVOLUTION, INDUSTRY 4.0, DATA ENGINEERING PERMITS EFFICIENT DECISIONS MAKING. PHENOMENA DIFFICULT TO MODEL WITH CONVENTIONAL TECHNIQUES ARE TURNED POSSIBLE WITH ALGORITHMS BASED ON ARTIFICIAL INTELLIGENCE. SENSORS AND MACHINE LEARNING TECHNIQUES ALLOW INTELLIGENT ANALYSIS OF DATA. HOWEVER, ALGORITHMS ARE HIGHLY SENSITIVE OF THE PROBLEM AND HIS STUDY TO DECIDE ON WHICH WORK IS CRITICAL. FOR THE MANUFACTURING WOOD PROCESSES, INDUSTRY 4.0 IS A GREAT OPPORTUNITY. WOOD IS A MATERIAL OF BIOLOGICAL ORIGIN AND GENERATES VARIABILITIES OVER THE MANUFACTURING PROCESSES. FOR EXAMPLE, IN THE VENEER DRYING, DENSITY AND ANATOMICAL STRUCTURE IMPACT THE PRODUCT QUALITY. SCANNERS HAVE BEEN DEVELOPED TO MEASURE VARIABLES AND OUTCOMES, BUT DECISIONS ARE MADE YET BY HUMANS. TODAY, ROBUST SENSORS, COMPUTING CAPACITY, COMMUNICATIONS AND INTELLIGENT ALGORITHMS PERMIT TO MANAGE WOOD VARIABILITY. REAL-TIME ACTIONS CAN BE ACHIEVED BY LEARNING FROM DATA. THIS PAPER PRESENTS TRENDS AND OPPORTUNITIES PROVIDED BY INDUSTRY 4.0 COMPONENTS. SENSORS, DECISION SUPPORT SYSTEMS AND INTELLIGENT ALGORITHMS USE ARE REVIEWED. SOME APPLICATIONS ARE PRESENTED.

BECAUSE 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 VE-NEERS 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 CON-DITIONS, AND VENEER TEMPERATURE. USING KNOWLEDGE DISCOVERY IN DATABASES DATA ANALYTICS METHODOLOGY, ARTIFI-CIAL 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.