Machining system

Patent metadata

Field	Value
Publication number	US-12565334-B2
Application number	US-202519062455-A
Country	US
Kind code	B2
Filing date	Feb 25, 2025
Priority date	Feb 29, 2024
Publication date	Mar 3, 2026
Grant date	Mar 3, 2026

Abstract

A machining system includes an automated manipulator configurable between a measuring configuration, in which a position probe is operable, and a machining configuration, in which a tool is operable, a fixture for holding a template or a workpiece, and a controller. The controller is configured cause the automated manipulator, in the measuring configuration, to move the position probe to at least one reference feature of the template held in the fixture, to determine coordinate data associated with the at least one reference feature. Then, the controller provides the determined coordinate data to a machine learning agent which is trained to provide an estimate of machining coordinate deviation based on the determined coordinate data. If the estimated machining coordinate deviation is below a threshold coordinate deviation, the automated manipulator is allowed to proceed to machine a workpiece.

First claim

The invention claimed is:

1 . A machining system comprising:
an automated manipulator configurable between a measuring configuration, in which a position probe is operable, and a machining configuration, in which a tool is operable; a fixture configured for alternately holding a template and a workpiece; and a controller configured to:
when the template is held in the fixture, cause the automated manipulator, in the measuring configuration, to move the position probe to at least one reference feature of the template to determine coordinate data associated with the at least one reference feature;
provide the determined coordinate data to a machine learning agent, which is trained to provide an estimate of machining coordinate deviation based on the determined coordinate data, wherein the estimate of machining coordinate deviation is a prediction of a discrepancy between coordinate data associated with the at least one reference feature of the template and corresponding coordinate data associated with a workpiece once machined in accordance with the template; and
when the estimated coordinate deviation is below a threshold coordinate deviation, cause the automated manipulator to proceed in the machining configuration.

2 . The machining system of claim 1 , wherein, when the workpiece is held in the fixture and the automated manipulator is in the machining configuration, the controller is configured to, based on the determined coordinate data, cause the automated manipulator to return to a position of the at least one reference feature and machine, using the tool, the workpiece held in the fixture.

3 . The machining system of claim 2 , further comprising a coordinate measurement machine (CMM), wherein the controller is further configured, after the workpiece is machined, to:
cause the CMM to measure a position of one or more machined features of the workpiece machined by the automated manipulator; compare the position of each of the one or more machined features measured by the CMM with respective nominal positions defined by the template; and based on the comparison, update the training of the machine learning agent.

4 . The machining system of claim 1 , wherein, in response to the estimated coordinate deviation being above the threshold coordinate deviation, the controller is configured to stop the automated manipulator from proceeding in the machining configuration.

5 . The machining system of claim 4 , wherein, when the estimated coordinate deviation is above the threshold coordinate deviation, the controller is further configured to provide an alert to an operator of the machining system that the estimated coordinate deviation is above the threshold coordinate deviation.

6 . The machining system of claim 5 , wherein the alert comprises an indication of a hypothesis of a cause for the estimated coordinate deviation being above the threshold coordinate deviation.

7 . The machining system of claim 1 , further comprising at least one sensor configured to sense a parameter of the machining system, wherein the controller is further configured to:
read a parameter value from the at least one sensor; and provide the parameter value to the machine learning agent, which is trained to provide the estimate of the machining coordinate deviation further based on the parameter value.

8 . The machining system of claim 7 , wherein:
the at least one sensor comprises a temperature sensor; and the parameter comprises a temperature of the machining system.

9 . The machining system of claim 7 , wherein:
the at least one sensor comprises a force sensor; and the parameter comprises a force present within the machining system.

10 . The machining system of claim 1 , further comprising a memory for storing historical operational data associated with the machining system, wherein the controller is further configured to:
read the historical operational data from the memory; and provide the historical operational data to the machine learning agent, which is trained to provide the estimate of the machining coordinate deviation further based on the historical operational data.

11 . The machining system of claim 10 , wherein the historical operational data comprise one or more of:
historical temperature data; historical force data; and historical coordinate data associated with the at least one reference feature.

12 . The machining system of claim 1 , wherein the automated manipulator comprises a parallel kinematic machine (PKM).

13 . An aircraft comprising an aircraft structure machined by the machining system of claim 1 .

14 . The aircraft according to claim 13 , wherein the aircraft structure comprises all of a wing structure or a component part of the wing structure.

15 . A method of machining, the method comprising:
holding a template in a fixture of a machining system; setting an automated manipulator of the machining system in a measuring configuration; causing the automated manipulator, when in the measuring configuration, to move a position probe to at least one reference feature of the template held in the fixture; determining, with the position probe, coordinate data associated with the at least one reference feature; providing the determined coordinate data to a machine learning agent, which is trained to provide an estimate of machining coordinate deviation based on the determined coordinate data, wherein the estimate of machining coordinate deviation is a prediction of a discrepancy between coordinate data associated with the at least one reference feature of the template and corresponding coordinate data associated with a workpiece once machined in accordance with the template; and when the estimated coordinate deviation is below a threshold coordinate deviation, causing the automated manipulator to proceed in a machining configuration, in which a tool is operable to machine the workpiece when held in the fixture.

16 . The method of claim 15 , further comprising, when the workpiece is held in the fixture, when the automated manipulator is in the machining configuration, and based on the determined coordinate data, causing the automated manipulator to return to a position of the at least one reference feature and machine, using the tool, the workpiece held in the fixture.

17 . The method of claim 16 , further comprising:
causing a coordinate measurement machine (CMM) to measure a position of one or more machined features of the workpiece machined by the automated manipulator; comparing the position of each of the one or more machined features measured by the CMM with respective nominal positions defined by the template; and updating the machine learning agent based on the comparison.

18 . A computer program comprising a set of instructions, which, when the computer program is executed by a computer, cause the computer to carry out the method of claim 16 .

19 . A method of training a machine learning agent for estimating a machining accuracy of a machining process, the method comprising:
holding a template in a fixture of a machining system; setting an automated manipulator of the machining system in a measuring configuration; causing the automated manipulator, when in the measuring configuration, to move a position probe to at least one reference feature of the template held in the fixture; determining, with the position probe, coordinate data associated with the at least one reference feature; setting the automated manipulator in a machining configuration; holding a w

Assignees

• Airbus Operations Ltd
• Univ Sheffield
• Univ Sheffield

Inventors

• Chacin Marco
• Madhavan Navein
• Mejia Melgarejo Yuri
• Tiwari Ashutosh

Classifications

• B25J11/005

  Manipulators for mechanical processing tasks · CPC title

• B25J9/163

  learning, adaptive, model based, rule based expert control · CPC title

• B25J9/16

  Program controls (total factory control, i.e. centrally controlling a plurality of machines, G05B19/418) · CPC title

• G05B19/401 Primary

  characterised by control arrangements for measuring, e.g. calibration and initialisation, measuring workpiece for machining purposes (G05B19/19 takes precedence) · CPC title

• G05B19/404

  characterised by control arrangements for compensation, e.g. for backlash, overshoot, tool offset, tool wear, temperature, machine construction errors, load, inertia (G05B19/19, G05B19/41 take precedence) · CPC title