Even out wearing of machine components during machining

Patent metadata

Field	Value
Publication number	US-12427615-B2
Application number	US-202117477420-A
Country	US
Kind code	B2
Filing date	Sep 16, 2021
Priority date	Sep 16, 2020
Publication date	Sep 30, 2025
Grant date	Sep 30, 2025

Abstract

Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design and manufacture of physical structures using subtractive manufacturing systems and techniques include, in one aspect, a method including obtaining information regarding a geometry of a part to be machined by a computer-controlled manufacturing system from a workpiece; based on the information regarding the geometry, identifying machine components to be used by the computer-controlled manufacturing system during machining the part; determining a position for the machining of the part with respect to at least one of the machine components, to even out wear on the machine components, based on data indicating previous positions, movements and wear of components associated with the computer-controlled manufacturing system; and providing instructions usable by the computer-controlled manufacturing system, wherein the instructions are configured to cause the computer-controlled manufacturing system to use the position for the machining.

First claim

What is claimed is:

1. A computer-implemented method comprising:
obtaining information regarding a geometry of a part to be machined by a computer-controlled manufacturing system from a workpiece;
based on the information regarding the geometry, identifying a set of machine components to be used by the computer-controlled manufacturing system during machining the part from the workpiece;
determining a position for the workpiece within a machining envelope of the computer-controlled manufacturing system to machine the part, wherein the position is determined as to even out wear on at least one of the set of machine components, based on data indicating previous positions, movements and wear of machine components associated with the computer-controlled manufacturing system; and
providing instructions to position the workpiece at the determined position within the machining envelope of the computer-controlled manufacturing system to even out wear on the at least one of the set of machine components, thereby causing the part to be machined by the computer-controlled manufacturing system from the workpiece positioned at the determined position within the machining envelope of the computer-controlled manufacturing system.

2. The computer-implemented method of claim 1 , wherein the information includes a toolpath specification for the geometry of the part or a three-dimensional model of the geometry of the part.

3. The computer-implemented method of claim 1 , further comprising generating at least a portion of the data indicating the previous positions, movements and wear of machine components, the generating comprising:
tracking positions and movements of machine components associated with the computer-controlled manufacturing system; and
collecting wear data for the machine components associated with the computer-controlled manufacturing system.

4. The computer-implemented method of claim 1 , further comprising:
generating training data that tracks movement and velocity of a machining tool during machining of parts, wherein the training data is collected for points defined over a grid on a surface of the machining envelope associated with at least one of the set of machine components; and
in response to the training data, determining a correlation between i) increase in wear at points on the surface and ii) movement and velocity of the machining tool determined during machining at the respective points, wherein the determined correlation is used to determine the position for the workpiece for the machining of the part on the surface of the machining envelope.

5. The computer-implemented method of claim 1 , further comprising:
determining predicted wear of the at least one of the set of machine components at points on a surface of the machining envelope based on collected training data and initial wear of the at least one of the set of machine components, wherein the training data is a paired data set defined for the points on the surface, wherein the paired data set defines for each point on the surface i) a number of times that a machining tool had crossed over the respective point while machining one or more parts and ii) a velocity vector amount experienced at the respective point based on machining using the machining tool of the computer-controlled manufacturing system.

6. The computer-implemented method of claim 5 , wherein determining the position for the workpiece within the machining envelope is based on the predicted wear of the at least one of the set of machine components determined based on the training data, wherein the training data is used to learn a correlation between an increase in wear at specific points on the surface based on the number of times of the machining tool's crossing over the respective specific points and an average velocity experienced at the respective specific points.

7. The computer-implemented method of claim 1 , wherein the position for the workpiece within the machining envelope of the computer-controlled manufacturing system is determined based on a determined correlation between i) an increase in wear at a point on a surface of the machining envelope associated with the at least one of the set of machine components and ii) movement and velocity of a machining tool during used to machine parts.

8. The computer-implemented method of claim 1 , further comprising:
training a neural network to predict an increase in wear at points on a surface of the machining envelope associated with at least one of the set of machine components according to training data generated based on repeatedly machining the part from workpieces by using a machining tool;
based on the information regarding the geometry comprising a toolpath specification usable by the computer-controlled manufacturing system to machine at least a portion of the geometry of the part from the workpiece, determining a number of times that the machining tool passes over the points on the surface associated with the at least one of the set of machine components and velocities associated with passing the machining tool through the points on the surface; and
feeding, to the neural network, information defining the number of times that the machining tool passes over the points to predict an increase in wear over the surface of the machining envelope, wherein the position for the workpiece within the machining envelope when machining the part is determined relative to the predicted increase in wear for the points on the surface.

9. The computer-implemented method of claim 1 , wherein determining the position for the workpiece comprises:
providing the information regarding the geometry and an identification of the set of machine components to a machine learning program to determine the position for the workpiece within the machining envelope, wherein the machine learning program has been trained based on the data indicating the previous positions, the movements and the wear of components associated with the computer-controlled manufacturing system; and
receiving the position for the workpiece to even wearing out of at least one of the set of machine components from the machine learning program.

10. The computer-implemented method of claim 9 , wherein the information is obtained at a computer-aided manufacturing program, and wherein the information regarding the geometry comprises a toolpath specification usable by the computer-controlled manufacturing system to machine at least a portion of the geometry of the part from the workpiece, and the machine learning program comprises an online reinforcement learning program.

11. The computer-implemented method of claim 10 , wherein the computer-controlled manufacturing system is a type of computer-controlled manufacturing system used in multiple locations, and the online reinforcement learning program receives the data from multiple instances of the computer-controlled manufacturing system operated at the multiple locations.

12. The computer-implemented method of claim 1 , wherein the position for the workpiece within the machining envelope indicates a new location in which to fixture the workpiece within the machining envelope of the computer-controlled manufacturing system so as to increase usage of the machining envelope and decrease uneven wear of a working bed included in the set of machine components.

13. The computer-implemented method of claim 1 , further comprising:
training a neural network using at least the data to generate machine-learning rules defining associations between positions of workpieces when machining in relation to one or more of machine components of the computer-controlled manufacturing system, wear of

Assignees

• Autodesk Inc

Inventors

• Sanders Lee
• Bin Abu Bakar Akmal Ariff

Classifications

• B23Q17/20

  for indicating or measuring workpiece characteristics, e.g. contour, dimension, hardness · CPC title

• B23Q17/10

  for indicating or measuring cutting speed or number of revolutions · CPC title

• B23Q17/0966

  by measuring a force on parts of the machine other than a motor · CPC title

• G06N3/08

  Learning methods · CPC title

• B23Q17/0995

  Tool life management · CPC title