Fanuc Corporation

Yao Liang

Satoshi Ikai

Ryoutarou Tsuneki

Yuuki Kumamoto

A machine learning device performs machine learning with respect to a plurality of servo control units corresponding to a plurality of axes. A first servo control unit related to an axis receiving interference includes a compensation unit that compensates for at least one of a position error, a velocity command, and a torque command of the first servo control unit based on at least one of a variable related to a position command and a variable related to position feedback information of a second servo control unit related to an axis generating the interference. The machine learning device acquires state information including first and second servo control information and a coefficient of the function, outputs action information and a reward value for reinforcement learning, and updates a value function on the basis of the reward value, the state information, and the action information.

Machine learning device, servo control device, servo control system, and machine learning method

A motor controller includes: a command unit which outputs a command value for controlling a motor that drives a driven unit; a motor control unit which controls the motor based on the command value; a compensation filter which compensates for the command value; and a preprocessing unit which is provided in a stage preceding the compensation filter, the compensation filter has a frequency region in which a gain is greater than 1 and the preprocessing unit executes, when a variation in the command value before being compensated for with the compensation filter is equal to or less than a predetermined value, preprocessing in which a past command value is used as a current command value.

Motor controller with preprocessing of a command value

An object is to read the information of a feature shape included in a machining program so as to calculate a control command suitable for machining processing on the feature shape. A numerical controller () includes: a feature detection unit () which detects the feature of a machined shape from a machining program that commands the movement of a tool or a workpiece; an inward-turning amount calculation unit () which calculates, based on a servo parameter of a servo controller () that drives the tool or the workpiece, the feature of the machined shape detected from the machining program and a machining requirement that specifies a machining condition, a relation formula that determines the inward-turning amount of a machining path with respect to a program path; and a feedrate determination unit () which determines a feedrate that is optimized with the relation formula.

Numerical controller, CNC machine tool, numerical control method and non-transitory computer readable medium recording a numerical control program

A controller includes a storage unit storing a plurality of sets of recommended setting values or recommended setting ranges regarding parameters for controlling an axis of a machine tool or an industrial machine or for controlling a motor, wherein set contents of the plurality of sets of recommended setting values or recommended setting ranges vary depending on a property of the machine tool, the industrial machine, or the motor; a comparing unit configured to compare input parameters with the recommended setting values or the recommended setting ranges corresponding to the property of a control target; and a comparison result presenting unit configured to present a warning when the input parameters differ from the recommended setting values or deviate from the recommended setting ranges corresponding to the property of the control target.

Controller

A machine learning device performs machine learning related to optimization of a compensation value of a compensation generation unit with respect to a servo control device that includes a compensation generation unit configured to generate a compensation value to be added to a control command for controlling a servo motor and a limiting unit configured to limit the compensation value or the control command to which the compensation value is added so as to fall within a setting range. During a machine learning operation, when the compensation value or the control command is outside the setting range and the limiting unit limits the compensation value or the control command so as to fall within the setting range, the machine learning device applies the compensation value to the learning and continues with a new search to optimize the compensation value generated by the compensation generation unit.

Growing community of inventors

Yamanashi, Japan

Yao Liang