For modern metalworking machine tool systems, which operate with limited operator participation, there is a need to develop methods for automatic control and recognition of the states of cutting tools. It provides the possibility of predicting their residual resource and timely replacement. In recognizing the cutting tools (CT) states, data mining methods are increasingly used: decision trees, genetic algorithms, fuzzy logic, and neural networks. Therefore, the task of improving the quality of CT wear zones textures classes’ recognition (based on convolutional models’ application) is relevant. The article aims to create a new fuzzy neural net classifier to improve the quality of cutting tool wear zones recognition texture classes. The scientific novelty consists in creating convolutional models and a new fuzzy neural net classifier of CT wear zone textures – for recognizing wear mechanisms on the flanks of cutters in finishing turning conditions. Practical usefulness consists in improving the quality of textures classes of CT wear zones recognition to the level of almost 100%. An example of a corrective influence on the turning process is a change in the feed rate S – in the case of concentrated wear traces recognition on the near-vertex section of the cutter’s flank surface.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Improvement of the Quality of Wear Zones for Cutting Tools Textures Classes Recognition Based on Convolutional Models


    Additional title:

    Lect.Notes Mechanical Engineering



    Conference:

    Design, Simulation, Manufacturing: The Innovation Exchange ; 2023 ; High Tatras, Slovakia June 06, 2023 - June 09, 2023



    Publication date :

    2023-05-23


    Size :

    10 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Automatic defect recognition in cutting tools

    James,R.D. / Leishman,I.R. / Randeree,K. et al. | Automotive engineering | 1999


    Automatic Defect Recognition in Cutting Tools

    James, R. D. / Leishman, I. R. / Randeree, K. et al. | British Library Conference Proceedings | 1999


    The technological provision of machine parts and cutting tools wear resistance

    Pamfilov,E. / STEA,US | Automotive engineering | 2000


    Laser scanning techniques for defect recognition on cutting tools

    Dalgleish,G.F. / James,R.D. / Randeree,K. et al. | Automotive engineering | 1998


    Laser Scanning Techniques for Defect Recognition on Cutting Tools

    Dalgleish, G. F. / James, R. D. / Randeree, K. | British Library Conference Proceedings | 1998