Improving OSB wood panel production by vision-based systems for granulometric estimation

Abstract

Oriented Strand Board (OSB) is a kind of engineered wood particle board widely adopted in manufacturing, construction and logistics. The production of OSB panels requires rectangular-shaped wood strands of specific size, arranged in layers to form the so-called "mattress" (mat) and bonded together with glue. The structural properties of the panel rely directly on the layer forming. In particular, the size distribution-namely granulometry-of the strands should fulfill standard measures to reach the mechanical properties expected from the panel. Offline granulometry of particle materials is the most commonly procedure used to evaluate the production process, but it is prone to several drawbacks owing to the manual intervention of human operators. Vision-based systems, instead, allow for performing granulometric analyses in an automatic and contactless manner. We propose a computer vision approach to estimate the granulometry of wood strands. The designed framework analyzes images of a mat of strands placed over a moving conveyor belt, and provides useful information and measurements to enhance the production of OSB panels. Because of the very large amount of wood strands on the mat, particle-overlapping is frequent and represents a main issue for measurement algorithms. In order to overcome this problem, our framework joins image processing and computational intelligence methods, such as edge detection and fuzzy color clustering. We tested the framework with real and synthetic images, useful to variate the conditions of the material's shape. The obtained results demonstrate the ability of our approach to evaluate the granulometry of the strands in real conditions, and robustness against the simulated variations of the production process.

Analyzing images in frequency domain to estimate the quality of wood particles in OSB production

“…In the first step, the algorithm segments the image to identify the objects that appear in it, then, in the second step, it evaluates their properties and aggregates them. This approach has been applied to the field of wood panel production, with a framework that joins image processing and computational intelligence to segment and measure woods strands [6]. Furthermore, many approaches have followed this methodology in other fields, such as: biology [7], mining industry [8], [9], [10], or powder classification [11], [12].…”

Computational intelligence for industrial and environmental applications

“…In industrial applications, vision-based monitoring and control systems are often employed to perform a touchless, noninvasive, and non-destructive supervision of the process, and as a low-complexity alternative to the use of several sensors for measuring different characteristics of the raw materials or the final product, such as granulometry [20]- [22], volume [23], and surface defects [24]. Moreover, Wireless Sensor Networks (WSNs) are being increasingly used for industrial monitoring due to their low cost, ease of installation, adaptivity, and selforganization [6], [25].…”

“…Moreover, Wireless Sensor Networks (WSNs) are being increasingly used for industrial monitoring due to their low cost, ease of installation, adaptivity, and selforganization [6], [25]. In industrial applications, CI techniques can be used to map the features extracted from the images or from the sensors to the observed quantities [20], [21], [23], [24], and they can be used as a general approach to monitor the quality of the industrial production process, by learning the relationship between the features of the raw materials and the quality of the obtained product [26]- [31], or to detect faults in the machinery by learning from the normal operating parameters [5], [6], [32]- [34].…”

“…In the case of images, these operations are useful to enhance some characteristics of the image for human visual inspection. For instance, recent works have proposed to use neural networks to segment suitable areas for bee foraging in satellite images [57] or fuzzy methods to segment time-series in chemical processes [58] or wood particles in panel production images [20].…”

3-D Granulometry Using Image Processing

“…Third, this configuration permits to observe only the topmost particles because smaller particles tend to remain at the bottom layer of material. Fourth, the particles are usually deposed densely and are much more difficult to detect and segment with respect to falling particles because frequently the particles have uniform color and overlap or touch each other [7].…”