No abstract

This paper presents the particle-size distribution of dust created by the drilling of selected wood composites, which was carried out using a CNC machine. The particle-size distribution was studied through two methods. Two analyses were performed: the sieve analysis of samples from the whole mass of collected dust and the laser diffraction analysis of the finest fraction isolated by sieving. The results presented general information about the particle-size distribution of the dust, as well as detailed information on the content of the finest particles. This information revealed that the particles might pose a potential risk to the health of workers employed in the woodworking industry. This potential risk is due to the possibility of their dispersion in the atmosphere surrounding the workplace and their size, which allows them to be respirable. The relationship between the fineness of the dust and the type of wood composite was also tested. Most ultrafine particles are formed during the drilling of fibreboards and are especially produced in traditional wet technology.

No abstract

The paper presents the idea of using support vector machine algorithm in a tool wear identification system in chipboard drilling. The indirect sources of information about tool wear were: feed force, cutting torque, acceleration of jig vibration, audible noise, and ultrasonic acoustic emission signals. The drills were classified (analogous to traffic rules) as "Green" (able to work), "Yellow" (warning state) or "Red" (unable to work-replacement needed).

This paper presents an improved method for recognizing the drill state on the basis of hole images drilled in a laminated chipboard, using convolutional neural network (CNN) and data augmentation techniques. Three classes were used to describe the drill state: red -- for drill that is worn out and should be replaced, yellow -- for state in which the system should send a warning to the operator, indicating that this element should be checked manually, and green -- denoting the drill that is still in good condition, which allows for further use in the production process. The presented method combines the advantages of transfer learning and data augmentation methods to improve the accuracy of the received evaluations. In contrast to the classical deep learning methods, transfer learning requires much smaller training data sets to achieve acceptable results. At the same time, data augmentation customized for drill wear recognition makes it possible to expand the original dataset and to improve the overall accuracy. The experiments performed have confirmed the suitability of the presented approach to accurate class recognition in the given problem, even while using a small original dataset.