Digitalisation of sawmill industry

Novel artificial intelligence and machine vision solutions for handling material flows. Machine Vision and Pattern Recognition Laboratory and Applied Mathematics at Lappeenranta University of Technology (LUT) in collaboration with three companies, Finnos Oy, FinScan Oy, and Stora Enso Oyj are advancing the digitalisation of sawmill industry. One of the main objectives of the collaboration is to build an information system connecting all the production steps of the mill so that it is possible to track the life cycle of raw material from the beginning to the end product. The raw material and its characteristics become individually traceable (e.g., logs and their parts) in real-time in the industrial environment. This makes the use of raw material more efficient. At the same time, resource-efficient processes become more sustainable which benefits the conservation of nature, especially in controlling the climate change.digisaw-kuva

Currently, a typical sawmill contains various measuring devices, such as X-ray scanners and RGB-cameras that measure both the raw material and end products during different process stages. These measurements are typically not connected with each other which prevents to utilize the full potential of the measured information, for example, in process control (e.g., sawing angle) and predicting the quality of the end products in the early stages of the process.

During the project, modern sensor systems, new computational methods, and more robust mathematical models are utilized in developing novel machine vision based measurements and prediction models for quality control systems. The capabilities of the systems can be extended by using measured information from the sawmill processes and raw material. The obtained quality information can be connected with the preceding stages of the process such as sorting of the logs with the potential to optimize the sawing processes. The innovations developed during the project are tested in the real industrial environment. The project involves collaboration between LUT, a sawmill company (Stora Enso Oyj), sensor system and measurement device manufacturers (Finnos Oy and FinScan Oy), as well as international collaboration with the Computer Graphics Research Group at Brno University of Technology and the Uncertainty Quantification Group at Massachusetts Institute of Technology.

Prof. Heikki Kälviäinen, LUT,

Prof. Heikki Haario, LUT,