Machine learning-based models of sawmills for better wood allocation planning

Morin, Michael; Gaudreault, Jonathan; Brotherton, Edith; Paradis, F.; Rolland, Amélie; Wery, Jean; Laviolette, François

doi:10.1016/j.ijpe.2019.09.029

Cited by 24 publications

(23 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A solution to the lumber production prediction problem is a forecast of the lumber products resulting from the break down of a given log at a given sawmill. In practice, solving this problem with a sufficient accuracy on a given log can lead better decisions for various planning problems which require forecasting the output of a sawmill for a batch of logs [1].…”

Section: Prediction Problem Formulationmentioning

confidence: 99%

“…In the industry, a combination of lumber products resulting from a log processing is called the product basket. Previous works state the lumber production prediction problem in terms of a supervised learning problem [1,10]. That is, pairs of feature vectors and product baskets are given to a supervised learning algorithm, such as Random Forest, and the algorithm builds a model from the feature space to the basket space.…”

Section: Prediction Problem Formulationmentioning

confidence: 99%

“…In practice, good production forecasts can lead tremendous gains to a forest-product company due to better planning opportunities [1]. One may, for instance, improve the assignment of cutting blocks to sawmills.…”

Section: Introductionmentioning

confidence: 99%

“…Depending on the configuration of the simulator, the simulation can take anywhere from a few seconds to a few hours per log. Such a lengthy simulation time is impractical in some decision-making contexts involving an optimization process that needs to assess the quality of all possible log and sawmill pairs, e.g., for wood allocation planning [1] or for short-term decision-making such as operation scheduling [5].…”

Section: Introductionmentioning

confidence: 99%

“…As an answer to the issue of lengthy simulation time, previous studies have shown that it is possible to use machine learning to solve the problem of predicting the output of a sawmill with precision sufficient for decision-making in the context of wood allocation planning [1]. Our goal is therefore to find an approach that allows us to learn on a small batch of simulated logs to predict the optimal product basket for a large number of logs in a short time.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Neural Network Architectures and Feature Extraction for Lumber Production Prediction

Martineau

Morin

Gaudreault

et al. 2021

Proceedings of the Canadian Conference on Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

We tackle the problem of predicting the lumber products resulting from the break down of the logs at a given sawmill. Although previous studies have shown that supervised learning is well suited for that prediction problem, to our knowledge, there exists only one approach using the 3D log scans as inputs and it is based on the iterative closest-point algorithm. In this paper, we evaluate the combination of neural network architectures (multilayer perceptron, residual network and PointNet) and log representation as input (industry know-how-based features, 2D projections, and 3D point clouds) in the context of lumber production prediction. Our study not only shows that it is possible to predict the output of a sawmill using neural networks, but also that there is value in combining industry know-how-based features and 3D point clouds in various network architectures.

show abstract

Section: Prediction Problem Formulationmentioning

confidence: 99%

Section: Prediction Problem Formulationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Neural Network Architectures and Feature Extraction for Lumber Production Prediction

Martineau

Morin

Gaudreault

et al. 2021

Proceedings of the Canadian Conference on Artificial Intelligence

Self Cite

View full text Add to dashboard Cite

show abstract

Dissimilarity to Class Medoids as Features for 3D Point Cloud Classification

Chabanet

Chazelle

Thomas

et al. 2021

Advances in Production Management Systems. Artificial Intelligence for Sustainable and Resilient Production Systems

View full text Add to dashboard Cite

Several sawmill simulators exist in the forest-product industry. They are able to simulate the sawing of a log to generate the set of lumbers that would be obtained by transforming a log at a sawmill.In particular, such simulators are able to use a 3D scan of the exterior shape of the logs as input for the simulation. However, it was observed that they can be computationally intensive. Therefore, several authors have proposed to use Artificial Intelligence metamodel, which, in general, can make predictions extremely fast once trained. Such models can approximate the results of a simulator using a vector of descriptive features representing a log, or, alternatively, the full 3D log scans. This paper proposes to use dissimilarity to representative log scans as features to train a Machine Learning classifier. The concept of class Medoids as representative elements of a class will be presented, and a Simlarity Discrimant Analysis was chosen as a good candidate ML classier. This classifier will be compared with two others models studied by the authors.

show abstract