Abstract:
A machine learning system that optimizes coefficients of at least one filter provided in a servo control device that controls a motor includes: an initial setting unit that sets initial values of the coefficients of the filter so as to attenuate at least one specific frequency component; a frequency characteristic calculation unit that calculates at least one of an input/output gain and an input/output phase delay of the servo control device based on an input signal and an output signal of the servo control device, of which the frequencies change; and a filter characteristic removing unit that removes filter characteristics of an initial filter in which the initial values are set to the filter from at least one of the input/output gain and the input/output phase delay obtained based on the input signal and the output signal obtained using the initial filter at the start of machine learning.
Abstract:
Adjustment is performed such that vibration does not occur when a control parameter of a control device is changed, a jig or workpiece is changed, a tool is changed, the presence or absence of machining or the type of machining is changed, an industrial machine or the temperature around it has changed, or the state of lubricating oil associated with an industrial machine has changed. In particular, parameters are optimized that have the potential for causing vibration. The vibration detection device detects vibration in an industrial machine, and includes a state change detection unit for detecting a change in the state of a control device that controls the industrial machine, and a vibration determination unit for determining whether the industrial machine is vibrating. When a change in the state of the control device is detected, the presence or absence of vibration in the industrial machine is determined.
Abstract:
A machine learning apparatus determines a control parameter of an active vibration isolation apparatus on which an industrial machine is mounted. The industrial machine includes a movable part, a drive source that drives the movable part, and a drive source control section that controls the drive source to position the movable part at a command position. The machine learning apparatus includes: an acquiring section that acquires, as teacher data, a positional deviation, which is a difference between the command position and an actual position of the movable part; a storage section that stores a learning model that outputs the control parameter corresponding to a state quantity concerning the industrial machine; and a learning section that updates the learning model using the teacher data.
Abstract:
A machining machine system includes: a machining machine; a numerical control device which generates a command for driving an axis of the machining machine; an interior information acquisition unit which acquires interior information of the numerical control device; a tentative determination unit which determines acceptance/rejection of a workpiece as machined by the machining machine based on a comparison result between the interior information and a threshold value; a final determination unit which determines acceptance/rejection of workpieces which are targets of an accuracy inspection which include at least a workpiece as determined to be accepted/rejected by the tentative determination unit based on a measurement result with respect to an accuracy of the workpiece; and a threshold value update unit which updates the threshold value used for determination processing by the tentative determination unit based on determination results by the tentative determination unit and the final determination unit.
Abstract:
In a motor controller according to the present invention, a speed control unit 24m includes an integrator calculating an integrated value Sm of a speed error ωm-ωm′ between a speed command value wm and a rotation speed ωm′ and generates a torque command value Tm based on ωm-ωm′, a predetermined value, a proportional gain and an integration gain. A speed control unit 24s includes an integrator calculating an integrated value Ss of a speed error ωs-ωs′ between a speed command value ωs and a rotation speed ωs′ and generates a torque command value Ts based on ωs-ωs′, the predetermined value, a proportional gain and an integration gain. An integrated value selecting unit 28 selects any one of Sm and Ss as the predetermined value, depending on a drive status of a main motor 6m and a sub motor 6s.