Tuesday, January 18, 2022
More
    HomeIndustryMachine ToolsNUM Introduces NUMai AI Software to Facilitate Condition Monitoring of CNC Machine...

    NUM Introduces NUMai AI Software to Facilitate Condition Monitoring of CNC Machine Tools

    TEUFEN, Switzerland, Jan 29, 2021 – NUM has launched innovative artificial intelligence software that provides CNC machine tool users with highly cost-effective condition monitoring capabilities.

     

    PR_ConditionMonitoring_01
    NUM’s new NUMai software provides CNC machine tool users with very cost-effective condition monitoring capabilities. This schematic shows the neural network’s prediction of a variable (blue) and the measured value of the variable (red). The residual error is shown in yellow.

     

    csm_PR_ConditionMonitoring_02_95389b89eb
    NUM’s new NUMai software provides CNC machine tool users with very cost-effective condition monitoring capabilities. This schematic shows the increase in residual error of an estimated variable after a fault condition, resulting in a warning being set.

     

    Compatible with all of NUM’s latest-generation Flexium+ CNC systems, the NUMai software package is a complete, fully integrated solution for CNC machine tools – it does not require any additional sensors, and runs on the same industrial PC as the CNC system’s HMI (human-machine interface).

    NUMai software can be utilized as soon as a machine tool has been commissioned and is ready to start production, or on a machine that is already being employed for production purposes. The software initially acquires all pertinent operating data over a period of time, typically a number of hours, while the machine is being used for normal production tasks. Ideally, a diversity of part programs is run, involving a variety of different machining conditions, in order to ensure that the data is as comprehensive and reliable as possible.

    The collected data is used to teach a neural network so that any deviation from the ‘good’ machine behavior and performance can then be detected and predicted; a suitable PC program for subsequent online performance monitoring and diagnostic purposes is generated automatically.

    During the software’s development, NUM beta tested the technology on a CNC milling machine equipped with three axes and a spindle, which required a neural network comprising 36 neurons with three hidden layers. In this particular instance, 396 parameters needed their values to be accurately defined; this required the acquisition of more than 2 million ‘known good’ data points and 300 iterations of the teaching phase, which took about four hours per axis.

    NUMai condition monitoring software capitalizes on the inherent flexibility of NUM’s latest-generation Flexium+ CNC platform. As standard, every Flexium+ CNC system includes a PC which can handle data from the servo drives’ measurement points, a PLC that has direct access to machine parameters, and an NCK oscilloscope feature capable of reading values in real-time. All system communications are handled by FXServer, using fast real-time Ethernet (RTE) networking.

    During everyday use in the production environment, NUMai software runs in the background on the industrial PC that forms part of the machine tool’s CNC system, continuously monitoring and evaluating the machine’s performance. Any discrepancy or deviation beyond user-defined thresholds is notified to the PLC, which decides what action should be taken – from a simple advisory message to an emergency disengagement.

    The new NUMai condition monitoring software option can be installed and used on any Flexium+ CNC system running NUM’s Flexium software version 4.1.10.10 or higher.

    For more information, visit https://num.com.

    Sachin R Nalawadehttps://dailycadcam.com
    Founder and Editor DailyCADCAM. A highly-driven astute professional and avid marketer; equipped with a solid foundation in Academia; Manufacturing, CAD, CAM, CAE industry and Implementing Marketing Initiatives for Global Brands (All Design Software and Hardware Vendors).
    RELATED ARTICLES
    - Advertisment -

    Most Popular

    Recent Comments