Machining system

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.

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 workpiece in the fixture;
• causing the automated manipulator, when in the machining configuration, when the workpiece is held in the fixture, and based on the determined coordinate data, to return to a position of the at least one reference feature and machine, using a tool, the workpiece held in the fixture;
• measuring 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 with respective nominal positions defined by the template;
• and
• updating the machine learning agent based on the comparison;
• wherein the machine learning agent is configured to predict a machining accuracy of a future machining process to be performed on a future workpiece in accordance with the template based on coordinate data associated with the at least one reference feature of the template.

A machining system comprising:

• an automated manipulator comprising a tool;
• a position probe;
• a sensor configured to sense a parameter of the machining system;
• and
• a controller configured to:
• receive at least one of position data from the position probe and parameter data from the sensor;
• provide the received data to a machine learning algorithm, which is trained to provide an estimate of machining coordinate deviation based on the received data, wherein the estimate of machining coordinate deviation is a prediction of a discrepancy between nominal coordinates on a template and actual machining coordinates on a workpiece;
• and
• when the estimated coordinate deviation is below a threshold coordinate deviation, cause the automated manipulator to process the workpiece using the tool.