No abstract

No abstract

We use machine learning to generate metamodels for sawing simulation. Simulation is widely used in the wood industry for decision making. These simulators are particular since their response for a given input is a structured object, i.e., a basket of lumbers. We demonstrate how we use simple machine learning algorithms (e.g., a tree) to obtain a good approximation of the simulator's response. The generated metamodels are guaranteed to output physically realistic baskets (i.e., there exists at least one log that can produce the basket). We also propose to use kernel ridge regression. While having the power to exploit the structure of a basket, it can predict previously unseen baskets. We finally evaluate the impact of possibly predicting unrealistic baskets using ridge regression jointly with a nearest neighbor approach in the output space. All metamodels are evaluated using standard machine learning metrics and novel metrics especially designed for the problem.

Hardwood flooring mills transform rough wood into several boards of smaller dimensions. For each piece of raw material, the system tries to select the cutting pattern that will generate the greatest value, taking into account the characteristics of the raw material. However, it is often necessary to choose less profitable cutting patterns in order to respect market constraints. This reduces production value, but it is the price to pay in order to satisfy the market. We propose an approach to improve production value. We first use simulation on a training set of virtual boards in order to generate a database associating cutting patterns to expected production value. Then, we use an optimization model to generate a production schedule maximizing the expected production value while satisfying production constraints. The approach is evaluated using industrial data. This allows recovering approximately 30 % of the value lost when using the original system.