Skip to Main Content
Statistical process control for residential treated woodAuthor(s): Patricia K. Lebow; Timothy M. Young; Stan Lebow
Source: In: McCowan, C.; Gothard, T.; Staula, B., eds. Proceedings, One hundred thirteenth annual meeting of the American wood protection association. Birmingham, AL: American Wood Protection Association: 234-247.
Publication Series: Paper (invited, offered, keynote)
Station: Forest Products Laboratory
PDF: Download Publication (7.0 MB)
DescriptionThis paper is the first stage of a study that attempts to improve the process of manufacturing treated lumber through the use of statistical process control (SPC). Analysis of industrial and auditing agency data sets revealed there are differences between the industry and agency probability density functions (pdf) for normalized retention data. Resampling of batches of treated wood without replacement appears to affect the pdf of the industrial data. The best-fitting pdf for the agency data is the Largest Extreme Value (LEV) pdf. Assumptions of a normal or a Gaussian pdf may not be valid. The process of treated residential lumber is hard to predict due to special-cause variation. A capability analysis revealed that from 2.25% to 3.16% of the charges are below the AWPA Lower Confidence Limit (LCL) for an industrial data set and 1.57% to 6.63% are below the LCL for an agency data set, with both varying by product type.
- We recommend that you also print this page and attach it to the printout of the article, to retain the full citation information.
- This article was written and prepared by U.S. Government employees on official time, and is therefore in the public domain.
CitationLebow, Patricia K.; Young, Timothy M.; Lebow, Stan. 2017. Statistical process control for residential treated wood. In: McCowan, C.; Gothard, T.; Staula, B., eds. Proceedings, One hundred thirteenth annual meeting of the American wood protection association. Birmingham, AL: American Wood Protection Association: 234-247.
KeywordsResidential treated lumber, statistical process control, probability density function, largest Extreme Value, natural variation, capability analysis
- Statistical process control and related methods for improvement of the treated-wood industries
- A protocol for implementing statistical process control in the treated wood industry
- The application of near infrared (NIR) spectroscopy to inorganic preservative-treated wood
XML: View XML