This paper explores the application of various machine learning techniques to model the optimal measurement time required after machining with a probe on CNC machine tools. Specifically, the research employs four different machine learning models: Elastic Net, Neural Networks, Decision Trees, and Support Vector Machines, each chosen for their unique strengths in addressing different aspects of predictive modeling in an industrial context. The study examines the input parameters such as material type, post-processing wall thickness, cutting depth, and rotational speed over measurement time. This approach ensures that the models account for the variables that significantly affect CNC machine operations. Regression value, mean square error, root mean square error, mean absolute percentage error, and mean absolute error were used to evaluate the quality of the obtained models. As a result of the analyses, the best modeling results were obtained using neural networks. Their ability to accurately predict measurement times can significantly increase operational efficiency by optimizing schedules and reducing downtime in machining processes.
The subject of microbiological tests of coolants presented in the work is the cutting fluid (emulsifying oil) of Fuchs ECOCOOL 68 CF3. The liquid was taken from the tanks of three different numerically controlled machines (Lasertec 65, MillTap 700, CTX beta 1250 TC), used with different intensity. The five most characteristic and popular media were used in the study: nutrient agar - plain, TSA medium (tryptone-soy-agar), medium with dichloran, rose bengal and chloramphenicol, Sabouraud agar with Chloramphenicol, Czapka agar. The incubation time was dependent on the type of microorganisms. After the specified time, the plates inoculated on the medium were subjected to visual observations and under the Leica DM 500 microscope. As a result of the observation, the following types of microorganisms (fungi and bacteria) were detected: Aspergillus Niger Tiegh, Candida Albicans, Saphylococcus Aureus, Micrococcus Luteus and Escherchia Coli and Citrobacter Freundia. The assessments were made in fixed periods. The results are presented as a function of the intensity of the use of cutting fluids. Microbiological analysis of machining fluids will allow for optimizing the time periods of using coolants and will also contribute to the protection of the operator's health and indirectly "extending the life cycle" of the technological machine.
The paper presents an overview of high-performance milling techniques of thin-walled elements. Currently, the tendency to simplify semi-finished products is used in aviation. In that case even 95% of semi-finished product mass is converted into chips, hence the increasing interest in such technol-ogies as: High Performance Cutting and High Speed Cutting. The aim of the paper was to research high-performance milling techniques of thin-walled elements in reference to conventional machin-ing. The material was the EN AW-7075 T651 aluminium alloy. A thin-walled pocket structure was designed and manufactured. The aspects related to geometric accuracy, surface quality and cutting time were analysed. On the basis of the obtained results, it was found that in case of geometric accu-racy related to the wall deformation, the greatest deformation was obtained after HPC, while the smallest one after HSC. The difference was over 400% (comparing HPC to HSC). A similar relation-ship was also received for the quality of the machined surface. Analysing the cutting time, the best result was achieved after HPC in reference to HSC and conventional machining. Taking into ac-count all analysed variables, the best solution was a combination of HPC and HSC. Thanks to the use of high-speed machining as a finishing, it is possible to receive high geometric accuracy and quality of the machined surface, while the application of HPC for roughing allows to shorten the cutting time, translating into an increase in the efficiency of the milling process. Conventional ma-chining is slightly less advantageous in terms of geometric accuracy and surface quality and it could possibly be used alternatively with High Speed Cutting, but its weakness is significantly lower effi-ciency compared to high-performance machining.
The aim of the paper is a dynamic analysis of the starting and braking of the table of a numerically controlled CNC machine tool during idle motion. The experimental test was performed on the vertical table of the FV580A machining centre using the Phantom v1610 high-speed vision camera. The dynamics characteristics of the table movement were registered and the dynamics estimates of the movement were determined. The influence estimation of the parameters of the machine tool table motion on the value of the determined estimates was made. The results of measurements were discussed and guidelines and in order to minimise disturbances were formulated. The test results were summarised and discussed in the form of charts and tables. The directions of further research in the discussed subject area were also defined
The study attempts to assess the quality of various types of samples used in the adhesive joint testing. One great weakness of the scientific research conducted on this type of joints is that the published papers generally do not include an analysis of the samples quality. Although the standards define the tolerances of individual dimensions, detailed reports are in fact rarely presented. Above all, it is very important to control the thickness of the adhesive, which significantly affects the strength of adhesive bonds. It was found that obtaining high quality samples depends mainly on observing the technological discipline and using appropriate instrumentation. The paper presents the standards that should be a reliable model for the scientific research on adhesive joints.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.