MACHINE LEARNING FEATURE FEED RATES FOR 3D PRINTING

    公开(公告)号:US20240272612A1

    公开(公告)日:2024-08-15

    申请号:US18168126

    申请日:2023-02-13

    CPC classification number: G05B19/4099 G06N20/00 G05B2219/49023

    Abstract: Systems for and methods of providing a feed rate for three-dimensional printing a part are presented. The disclosed techniques include: obtaining computer readable toolpath instructions for the part, where the toolpath instructions specify a nominal feed rate for a toolpath segment and spatial toolpath data of the toolpath segment; providing an input including the spatial toolpath data to a trained machine learning system, where the trained machine learning system has been trained using training data including: training spatial toolpath data, training closed loop gain data, and training feed rate data; obtaining a revised feed rate for the toolpath segment different from the nominal feed rate for the toolpath segment, where the revised feed rate is output from the trained machine learning system; and providing revised computer readable toolpath instructions, where the revised machine learning toolpath instructions include the revised feed rate.

    SYSTEM AND METHOD FOR SCHEDULING PRINTHEAD PURGING IN AN INKJET PRINTER

    公开(公告)号:US20230347651A1

    公开(公告)日:2023-11-02

    申请号:US17661708

    申请日:2022-05-02

    CPC classification number: B41J2/1652

    Abstract: A method of inkjet printer operation indicates a need for printhead purging without requiring analysis of printed images to detect streakiness in the images. The method compares terms of a histogram of a filtered response of an inkjet status vector to a streakiness metric to determine whether the distribution of inoperative inkjets in a printhead enables missing ink techniques to be used to compensate for inoperative inkjets in the printhead.

    System and method for closed loop regulation of ink drop volumes in a printhead

    公开(公告)号:US10814620B1

    公开(公告)日:2020-10-27

    申请号:US16598356

    申请日:2019-10-10

    Abstract: A printer includes a plurality of printheads, a plurality of printhead drivers, and an optical sensor configured to generate image data of a substrate after the substrate has been printed by the plurality of printheads. A controller operates the printheads using the printhead drivers to print a pattern of ink drops on the substrate, determine from image data of the ink drop pattern received from the optical sensor whether a density response for the pattern of ink drops for each printhead is within a predetermined range about a reference density response for the pattern of ink drops, identify a peak voltage for each printhead determined to have the density response outside the predetermined range, and store the identified peak voltage in the printhead driver for the printhead. The printhead driver uses the identified peak voltage to generate firing signals for the printhead operatively connected to the printhead driver.

    Device calibration using augmented data with hadamard variation

    公开(公告)号:US09631977B2

    公开(公告)日:2017-04-25

    申请号:US14109566

    申请日:2013-12-17

    CPC classification number: G01J3/2846 G01J3/462 G01J3/524

    Abstract: A method, non-transitory computer readable medium, and apparatus for calibrating a device using augmented data are disclosed. For example, the method measures k spectral values of each patch for a first plurality of patches generated by the device and a second plurality of patches generated by the reference device, creates a first augmented data set by selecting a delta (δ), wherein the first augmented data set comprises the δ applied k times to each one of the k spectral values of each one of the first plurality of patches, initializes initializing a function to create a second augmented data set for the reference device, solves the function to obtain a matrix of calibration values of the device that is based upon the first augmented data set and the second augmented data set and calibrates the device using the matrix of calibration values.

Patent Agency Ranking