Fanuc Corporation

Takaki Shimoda

Satoshi Ikai

Ryoutarou Tsuneki

Yuuki Shirakawa

An object is to make it possible to acquire a parameter or a first physical quantity that has been learned and an evaluation function value and thereby check the progress or the result of machine learning. An output device includes: an information acquisition unit which acquires, from a machine learning device that performs machine learning on a servo control device for controlling a servo motor driving the axis of a machine tool, a robot or an industrial machine, a parameter or a first physical quantity of a constituent element of the servo control device that is being machine learned or has been machine learned and an evaluation function value; and an output unit which outputs information indicating a relationship between the acquired parameter, the first physical quantity or a second physical quantity determined from the parameter and the evaluation function value.

Output device, control device and method of outputting evaluation function value

A plurality of evaluation functions and a machine learning result of each of the evaluation functions are output so that a relation between the evaluation function and the learning result can be ascertained. An output device includes: an output unit that outputs a plurality of evaluation functions used by a machine learning device that performs machine learning of parameters of components of a servo control device that controls a servo motor that drives an axis of a machine tool, a robot, or an industrial machine and a machine learning result of each of the evaluation functions; and an information acquisition unit that acquires the machine learning result from at least one of the servo control device and the machine learning device.

Output device, control device, and method for outputting evaluation functions and machine learning results

A machine learning device that searches for a first parameter of a component of a servo control device that controls a servo motor includes: a solution detection unit that acquires a set of evaluation function values used during machine learning or after machine learning, plots the set of evaluation function values in a search range of the first parameter or a second parameter used for searching for the first parameter, and detects whether a search solution is at an edge of the search range or is in a predetermined range from the edge; and a range changing unit that changes the search range to a new search range of the first parameter or the second parameter based on the estimation made on evaluation function values of an evaluation function expression when the search solution is at the edge of the search range or is in the predetermined range.

Machine learning device, control device, and machine learning search range setting method

A servo motor controller is provided which enables an offset to be set more easily and accurately, in comparison to the conventional technique. A servo motor controller for controlling a servo motor of an industrial machine includes: a position detection unit that detects a position of the servo motor; a magnetic-pole detection unit that detects a magnetic-pole phase of the servo motor; and a phase calculation unit that determines a calculation-based phase based on position data of the servo motor and magnetic-pole gap information of the servo motor. The servo motor controller is configured to acquire an offset relationship between the magnetic-pole phase detected by the magnetic-pole detection unit and the calculation-based phase determined by the phase calculation unit, after a reference position is passed through.

Servo motor controller

To provide a servo motor controller allowing to eliminate the risk of abnormal driving in a servo motor caused due to the inability to detect abnormality prior to establishment of absolute position. A device is configured to control a servo motor of an industrial machine. The device includes a position detection part configured to detect a position of the servo motor, a magnetic pole detection part configured to detect a magnetic pole position of the servo motor, and a pole position calculation part configured to, at least in initial calculation, obtain the magnetic pole position detected by the magnetic pole detection part as an initial magnetic pole position, prior to establishment of absolute position, and in the following calculation, incrementally obtain the magnetic pole position on the basis of data of the position detected by the position detection part and a magnetic pole interval of the motor.

An object is to provide a servo controller which constantly optimizes parameters according to the state of a machine. A servo controller for controlling an electric motor which drives the axis of an industrial machine includes: a state value derivation unit which derives, from an operation program and/or operation plan information of the industrial machine, the chronological or event-sequential data of the state value of the electric motor or a driven member that is operated with the electric motor; and a parameter change unit which changes at least one parameter of a velocity gain, a position gain, a feedforward gain, a filter frequency and an acceleration/deceleration time constant after interpolation based on the chronological or event-sequential data derived in the state value derivation unit either chronologically or event-sequentially.

Servo controller

Setting of parameters that determine filter characteristics is facilitated. Machine learning of optimizing the coefficients of a filter provided in a motor control device that controls rotation of a motor for a machine tool, a robot, or an industrial machine is performed on the basis of measurement information of an external measuring instrument provided outside the motor control device and a control command input to the motor control device.

Machine learning device, control system, and machine learning method

A motor control apparatus including a controller that controls a servo motor or a spindle motor and includes a switching determining part that determines a switching condition of the controller based on axis position information on a motor related to control of the motor control apparatus, a machine learning part that adjusts one or more parameters for the controller by machine learning for each switching condition, and a parameter holding part that holds the parameter adjusted by the machine learning part for each switching condition. The switching determining part, when determining the switching condition after adjustment of the parameter, uses the adjusted parameter corresponding to the switching condition in the controller. The apparatus enables changing, and automatic adjustment, of a parameter or controller to be used depending on a switching condition of the parameter related to axis position information or a switching condition of the controller using the parameter.

Growing community of inventors

Yamanashi, Japan

Takaki Shimoda