Product-adapted grading of Scots pine sawn timber by an industrial CT-scanner using a visually-trained machine-learning method

Computed tomography (CT) scanning of logs makes appearance-grading virtual sawn timber possible before the log is sawn. A CT-scanner can measure the knot structure inside a scanned log, inferring how to saw the log. The knot structure of virtual sawn timber was graded as being suitable or not for a specific product by the existing rule-based approach and used to create a set of descriptive statistical variables used by two machine learning models. The PLS models were trained on two quality references; the quality grade of the finished product or the image-grade based on images of the sawn timber, extracted from the dry-sorting station's automatic grading system and graded by two experienced researchers. The results show that the two PLS models perform equally well when sorting sawn timber to the customer, indicating that the quality references are equally useful for training a PLS model. The PLS models both delivered 93% of the dried sawn timber to the customer, leaving very little sawn timber with customer-specific properties at the sawmill, of which 89% and 90% of the delivered sawn timber passed the intended product's quality demands. The rule-based approach delivered 85% dried sawn timber with a 73% pass rate.

Automated summary

CT scanning enables appearance grading of virtual sawn timber before sawing, with the use of rule-based approach and machine learning models for knot structure grading. The results show that the two PLS models perform equally well in sorting sawn timber to the customer, with high pass rates for the intended product's quality demands.