A machine learning apparatus able to obtaining an optimal shift amount of an assist gas. The machine learning apparatus comprises a state-observation section configured to observe machining condition data included in a machining program given to the laser machine, and measurement data of a dimension of dross generated at a cutting spot of the workpiece when the machining program is executed, as a state variable representing a current state of an environment in which the workpiece is cut; and a learning section configured to learn the shift amount in association with cutting quality of the workpiece, using the state variable.

A machine learning device for performing machine learning with respect to a numerical control device which causes a machine tool to operate, and is provided with: a state information acquisition unit that causes the machine tool to perform cutting work, in which a cutting amount and a cutting rate are set, and acquires state information including the cutting amount and cutting rate; an action information output unit that outputs action information; a reward calculation unit that acquires determination information that is information about the strength of pressure applied to a tool at least during cutting work, the shape of the waveform of the pressure applied to the tool, and time it has taken to perform work, and outputs a reward value in reinforcement learning; and a value function update unit that updates a value function on the basis of the reward value, the state information, and the action information.

A numerical control device includes a control computation unit controlling a spindle as a rotation axis of a workpiece, a first shaft driving a tool performing vibration cutting machining on the workpiece, and a second shaft driving a tool performing vibration cutting machining on the workpiece. The computation unit includes: a storage unit storing a machining program; a determination unit determining whether the number of vibrations of the first shaft and the second shaft follows a rotation speed of the spindle specified by the machining program; and a number-of-vibrations calculation unit that, in response to the determination that the number of vibrations of at least one of the first shaft and the second shaft does not follow the rotation speed of the spindle, calculates the number of vibrations following the rotation speed of the spindle for the drive shaft assessed as not following it.

A machine tool includes: a spindle that causes a tool to rotate and move; a workpiece rotation mechanism that causes a workpiece W to rotate; a control unit that controls the spindle and the workpiece rotation mechanism in accordance with commands from a program; and a cutting load detection unit that detects a cutting load imparted on the workpiece by the tool, and the control unit controls a cutting route such that a cutting depth of the workpiece cut with the tool in a region with a small cutting load is greater than the cutting depth in a region with a large cutting load within such a range that the cutting load detected by the cutting load detection unit does not exceed a predetermined load.

A method for reducing vibrations originating in a mechanical processing for removal of swarf comprising monitoring the vibration resulting from contact between the tool and workpiece, detecting the occurrence of a regenerative vibratory phenomenon, calculating the frequency of the phenomenon, estimating a value representing a resonance frequency of the machine as a function of the frequency of the phenomenon and determining a threshold value on the basis of the value. Also, comparing the operating speed of the mandrel with the threshold value and reducing the intensity of the phenomenon by a first reduction strategy based on correction of the operating speed of the mandrel being greater than the threshold value or by a second reduction strategy based on a continuous modulation which imparts an oscillation to the speed around the value of the operating speed, when the operating speed of the mandrel is less than the threshold value.

A numerical control device for controlling a main shaft, which is a rotating shaft for a workpiece, a drive shaft that drives a tool for vibration cutting of the workpiece in an X-axis direction, and a drive shaft that drives the tool or the workpiece in a Z-axis direction, includes: a storage unit that stores a machining program for vibration cutting of the workpiece; and a control computation unit that calculates a specific point that the tool passes during vibration cutting on the basis of a tolerance value, which is an allowable error in machining of a corner of the workpiece, and generates a vibration waveform of the tool indicating a movement path of the tool passing the specific point, in which the control computation unit controls movement and vibration of the tool in accordance with the machining program and the vibration waveform.

Systems and methods of determining a difference of position between a malleable object and a target shape are described herein.

A numerical control device for controlling a main shaft, which is a rotating shaft for a workpiece, a drive shaft that drives a tool for vibration cutting of the workpiece in an X-axis direction, and a drive shaft that drives the tool or the workpiece in a Z-axis direction, includes: a storage unit that stores a machining program for vibration cutting of the workpiece; and a control computation unit that calculates a specific point that the tool passes during vibration cutting on the basis of a tolerance value, which is an allowable error in machining of a corner of the workpiece, and generates a vibration waveform of the tool indicating a movement path of the tool passing the specific point, in which the control computation unit controls movement and vibration of the tool in accordance with the machining program and the vibration waveform.

Described is method for reducing vibrations originating in a mechanical processing for removal of swarf comprising monitoring the vibration which results from the contact between the tool (103) and a workpiece (WP) being processed, detecting the occurrence of a regenerative vibratory phenomenon, calculating the frequency of the vibratory phenomenon (f.sub.C), estimating a value representing a resonance frequency (f.sub.R) of the machine as a function of the frequency of the vibratory phenomenon (f.sub.C) and determining at least one threshold value (.sub.TR) on the basis of the value representing a resonance frequency (f.sub.R). The method also comprises comparing the operating speed (.sub.L) of the mandrel (102) with the threshold value (.sub.TR) and reducing the intensity of the vibratory phenomenon by the performance of a first reduction strategy (SST) based on a correction of the operating speed (.sub.L) when the operating speed (.sub.L) of the mandrel (102) is greater than the threshold value (.sub.TR) or by means of a second reduction strategy (SSV) based on a continuous modulation which imparts an oscillation to the speed around the value of the operating speed (.sub.L), when the operating speed (.sub.L) of the mandrel (102) is less than the threshold value (.sub.TR).

A machine learning apparatus able to obtaining an optimal shift amount of an assist gas. The machine learning apparatus comprises a state-observation section configured to observe machining condition data included in a machining program given to the laser machine, and measurement data of a dimension of dross generated at a cutting spot of the workpiece when the machining program is executed, as a state variable representing a current state of an environment in which the workpiece is cut; and a learning section configured to learn the shift amount in association with cutting quality of the workpiece, using the state variable.