SIMULATION APPARATUS OF WIRE ELECTRIC DISCHARGE MACHINE HAVING FUNCTION OF DETERMINING WELDING POSITIONS OF CORE USING MACHINE LEARNING

• US 20170151618A1
• Filed: 11/28/2016
• Published: 06/01/2017
• Est. Priority Date: 11/30/2015
• Status: Active Grant

• Current Assignee: Fanuc Corporation
• Original Assignee: Fanuc Corporation
• Inventors: SHIRAI, Kenichiro
• Granted Patent: US 10,442,023 B2
• Time in Patent Office: Days
• CPC Class Codes: B23H 5/00 Combined machining
• CPC Class Codes: B23H 7/02 Wire-cutting
• CPC Class Codes: B23H 7/20 for programme-control, e.g. adaptive programme-control systems in general G05B19/00
• CPC Class Codes: B23H 9/00 Machining specially adapted for treating particular metal objects or for obtaining special effects or results on metal objects heat treatment by cathodic discharge C21D1/38
• CPC Class Codes: G05B 13/0265 the criterion being a learning criterion
• CPC Class Codes: G05B 19/25 for continuous-path control
• CPC Class Codes: G05B 19/402 characterised by control arrangements for positioning, e.g. centring a tool relative to a hole in the workpiece, additional detection means to correct position G05B19/19 takes precedence
• CPC Class Codes: G05B 2219/45221 Edm, electrical discharge machining, electroerosion, ecm, chemical
• CPC Class Codes: G06N 20/00 Machine learning

Abstract

A simulation apparatus of a wire electric discharge machine that performs machining to cut out a core from a workpiece calculates a position and a length of a welding part used to weld the core to the workpiece, calculates an evaluation value of the position and the length, and performs machine learning of the adjustment of the position and the length. In the machine learning, the position and the length of the welding part and the evaluation value are acquired as state data, a reward is calculated based on the state data and calculated reward conditions, and the machine learning of the adjustment of the position and the length of the welding part is performed using the calculated reward.

Claims

1. A simulation apparatus of a wire electric discharge machine that performs machining to cut out a core from a workpiece based on machining preconditions including a program, the simulation apparatus comprising:

a welding part calculation section that calculates and outputs, when the core is cut out from the workpiece, a position and a length of a welding part formed on a machining path for the machining to weld the core to the workpiece;

an operation evaluation section that calculates an evaluation value used to evaluate the position and the length of the welding part output from the welding part calculation section; and

a machine learning device that performs machine learning of an adjustment of the position and the length of the welding part, wherein

the machine learning device has

a state observation section that acquires the position and the length of the welding part and the evaluation value as state data on the welding part,

a reward conditions setting section that sets reward conditions,

a reward calculation section that calculates a reward based on the state data and the reward conditions,

a welding-part adjustment learning section that performs the machine learning of the adjustment of the position and the length of the welding part, and

a welding-part adjustment output section that determines and outputs an adjustment target and adjustment amounts of the position and the length of the welding part as an adjustment action based on the state data and a machine learning result of the adjustment of the position and the length of the welding part by the welding-part adjustment learning section, wherein

the welding part calculation section is configured to recalculate and output the position and the length of the welding part based on the adjustment action output from the welding-part adjustment output section, and

the welding-part adjustment learning section is configured to perform the machine learning of the adjustment of the position and the length of the welding part based on

the adjustment action,

the state data acquired by the state observation section based on the position and the length of the welding part recalculated by the welding part calculation section, and

the reward calculated by the reward calculation section based on the state data.

2. The simulation apparatus of the wire electric discharge machine according to claim 1, wherein

the evaluation value includes at least any of a force by which the core is supported calculated from the position and the length of the welding part, a force for dropping the core calculated from the position and the length of the welding part, and balance of positions for supporting the core calculated from the position and the length of the welding part.

3. The simulation apparatus of the wire electric discharge machine according to claim 1, further comprising:

a learning result storage section that stores a result of learning by the welding-part adjustment learning section, wherein

the welding-part adjustment output section is configured to adjust the position and the length of the welding part based on the learning result of the adjustment of the position and the length of the welding part learned by the welding-part adjustment learning section and the learning result of the adjustment of the position and the length of the welding part stored in the learning result storage section.

4. The simulation apparatus of the wire electric discharge machine according to claim 1, wherein

the reward conditions are set such that a positive reward is given when the number of the welding parts is small or when a position for supporting the core is well balanced and such that a negative reward is given when the number of the welding parts is large, when a length of the welding part is shorter than a previously-set welding-parts minimum distance, when a magnitude of a force by which the core is supported is smaller than a previously-set prescribed threshold, when a magnitude of a force for dropping the core is large, or when the position for supporting the core is poorly balanced.

5. The simulation apparatus of the wire electric discharge machine according to claim 1, wherein

the simulation apparatus is connected to at least one another simulation apparatus and configured to mutually exchange or share the machine learning result with the other simulation apparatus.

6. A machine learning device that performs machine learning of an adjustment of a position and a length of a welding part formed on a machining path for machining to weld a core to a workpiece when the core is cut out from the workpiece by a wire electric discharge machine that performs the machining to cut out the core from the workpiece based on machining preconditions including a program, the machine learning device comprising:

a state observation section that acquires, as state data on the welding part, the position and the length of the welding part and an evaluation value used to evaluate the position and the length of the welding part,

a reward conditions setting section that sets reward conditions,

a reward calculation section that calculates a reward based on the state data and the reward conditions,

a welding-part adjustment learning section that performs the machine learning of the adjustment of the position and the length of the welding part, and

a welding-part adjustment output section that determines and outputs an adjustment target and adjustment amounts of the position and the length of the welding part as an adjustment action based on the state data and a machine learning result of the adjustment of the position and the length of the welding part by the welding-part adjustment learning section, wherein

the welding-part adjustment learning section is configured to perform the machine learning of the adjustment of the position and the length of the welding part based on

the output adjustment action,

the state data acquired by the state observation section based on the position and the length of the welding part recalculated based on the adjustment action, and

the reward calculated by the reward calculation section based on the state data.