Wood moisture monitoring and classification in kiln‐dried timber

Abstract

Summary Different mass timber structures require a specific range of wood moisture. Thus, moisture monitoring is a crucial quality control task during timber drying that impacts the properties and quality of the subsequent timber structures. Variations in the average and distribution of the final moisture can result in significant variations in the timber properties and thus negatively affect performance in service. This necessitates rigorous moisture monitoring and timber grading during and after kiln drying. This study aims to estimate the kiln‐dried population final moisture distribution based on green timber characteristics and machine learning. This will facilitate the timber grading process by reducing the variation in the mechanical properties of the kiln‐dried timber, as timbers with a higher chance of moisture variation will be identified before the drying process. Timber initial moisture, initial weight, basic density, and target moisture were used to train machine learning models. Linear discriminant analysis and decision tree were used for moisture classification. Principal component and variable clustering analysis were performed to study the critical parameters affecting the timber overdrying and underdrying. The results indicated that initial moisture level and weight are the essential variables, while density had the least significant effect on the performance of classification models. The decision tree approach exhibited better performance than discriminant analysis with ~91% classification accuracy proving the effectiveness of using initial timber properties for quality control and grading of kiln‐dried timber.

Benchmarking moisture prediction in kiln-dried Pacific Coast hemlock wood

“…The odd groups (1, 3, and 5) had high M i variation, while even groups (2, 4, and 6) had low M i variation. The clustering and categorization of the kiln specimens were elaborated on and represented in the previous research (Rahimi, Nasir et al 2021).…”

“…All six batches were dried under an identical schedule slightly different from the modified typical industrial schedule for PCH (Shahverdi et al 2017). The drying schedule was tabulated, and drying trends were represented in former research (Rahimi, Avramidis et al 2021; Rahimi, Nasir et al 2021; Rahimi and Avramidis 2022).…”

“…Researchers applied ANNs to sort green PCH timbers with near-infrared spectroscopy (NIRS) and utilized networks for online species identification of PCH based on NIRS and chemometrics (Zhou et al 2020). In addition, machine learning (ML) methods have been applied to kiln-dried PCH to predict M f and categorize dried timbers accordingly (Rahimi, Nasir et al 2021; Rahimi and Avramidis 2022).…”

The Role of Drying Schedule and Conditioning in Moisture Uniformity in Wood: A Machine Learning Approach

“…Kiln-drying scheduling is also covered in some studies [ 30 , 31 ] as an important factor impacting the final moisture content and drying defects [ 32 ]. In addition, previous studies focused on characterizing and modeling final moisture and its spread in air-dried [ 33 ], radio-frequency kiln-dried [ 34 , 35 , 36 ], heat treated [ 37 ], and heat-and-vent kiln-dried batches [ 38 , 39 , 40 ]. Additionally, previous studies investigated moisture prediction in kiln-dried lumber merely based on wood properties; however, the combined effects of drying conditions and wood properties on the moisture uniformity after kiln-drying still represent a knowledge gap [ 41 ].…”