Real-Time Predictive Modeling of Wood Composite Products Utilizing the Data Warehouse of Manufacturing Facilities

摘要

Wood composite and engineered panel manufacturers store large amounts of process datarnin data-warehouses. Destructive panel strength tests are performed at periodic intervalsrnduring the production runs to assess conformance of product properties. The linkagernbetween process data and destructive test data is antipodal in most instances andrnknowledge gaps exist for operations personnel. The proper ‘fusion’ of destructive test datarnwith real-time process data creates a database foundation for real-time predictive modelingrnusing statistical and non-statistical methods.rnThe study presents successful case studies of real-time predictive modeling systems atrnwood composite and engineered panel mill test sites. Statistical algorithms predictedrnstrength of materials (e.g., IB, MOR, EI, etc.) within 10% of actual test values at mill testrnsites. Real-time predictions of strength of materials may prevent the manufacture of failingrnpanels and may also reduce unnecessary high operational targets (e.g., density, resin,rnetc.) given improved knowledge of the process. Important variables in statistical modelsrnmay also improve root-cause investigations of sources of product and process variation.