A thermal displacement correction system performs thermal displacement correction in cooperation with a thermal displacement correction device and a computer connected via a network. The thermal displacement correction system that corrects thermal displacement caused by processing performed by a machine comprises: the thermal displacement correction device connected to the machine; and the computer connected to the thermal displacement correction device via the network. The computer comprises: a data acquisition unit that acquires environmental data on an external environment of the machine via the network; a correction value inference unit that calculates a correction value using the environmental data; and a correction value output unit that outputs the correction value to the network. The thermal displacement correction device comprises: a correction value acquisition unit that acquires the correction value via the network; and a correction execution unit that performs thermal displacement correction using the correction value.

A thermal displacement correction system performs thermal displacement correction in cooperation with a thermal displacement correction device and a computer connected via a network. The thermal displacement correction system that corrects thermal displacement caused by processing performed by a machine comprises: the thermal displacement correction device connected to the machine; and the computer connected to the thermal displacement correction device via the network. The computer comprises: a data acquisition unit that acquires environmental data on an external environment of the machine via the network; a correction value inference unit that calculates a correction value using the environmental data; and a correction value output unit that outputs the correction value to the network. The thermal displacement correction device comprises: a correction value acquisition unit that acquires the correction value via the network; and a correction execution unit that performs thermal displacement correction using the correction value.

A machine learning device that can optimize an equation for estimating a thermal displacement amount of a machine element based on the operating state of the machine element. The device acquires operating state data of the machine element, acquires a measured value for the thermal displacement amount, stores the operating state data and measured values for the thermal displacement amount of the machine element as training data associated together as a label, sets an equation for calculation the thermal displacement amount based on the operating state data, calculates an estimated value for the thermal displacement amount by substituting the operating state data into this equation, determines whether a difference between the estimated value for the thermal displacement amount and the measured value for the thermal displacement amount is no more than a predetermined threshold.

A machine tool includes a workpiece holding unit to hold a workpiece. A tool holding unit holds a tool. At least one of the workpiece holding unit and the tool holding unit is drivingly rotatable or drivingly movable in a predetermined direction to machine the workpiece with the tool. Temperature sensors are attached to members constituting the machine tool. An estimator calculates an environmental temperature system thermal displacement amount due to a heat source outside the machine tool. A correction magnification processor calculates an environmental temperature system thermal displacement correction amount. Another estimator calculates a driving system thermal displacement amount due to a heat source in the machine tool. A thermal displacement correction amount adder obtains and outputs a total thermal displacement correction amount based on which the machine tool performs thermal displacement correction control.

A machining apparatus is provided with a machine learning device that performs machine learning. The machine learning device performs the machine learning by receiving the input of machining accuracy between a machining shape of a workpiece measured on-machine and design data on the workpiece and machining time of the workpiece measured by a measurement device. Based on a result of the machine learning, the machining apparatus changes machining conditions such that the machining accuracy increases and the machining time becomes as short as possible.

Disclosed are a method and an apparatus for compensating thermal displacement of a machine tool, the apparatus including: a compensation quantity calculating unit configured to calculate a compensation quantity by using temperature data and a predetermined compensation parameter; a smoothing filter configured to exponentially smooth the calculated compensation quantity; a scaling unit configured to scale the exponentially smoothed compensation quantity; a time-dispersion compensating unit configured to calculate a final compensation quantity by time-dispersion compensation for the scaled compensation quantity according to a time-dispersion compensating period; and a control unit configured to compensate each axis of equipment according to the final compensation quantity, and adjusts the time-dispersion compensating period of the time-dispersion compensating unit according to an error absolute value representing a difference between an input value and an output value of the time-dispersion compensating unit.

A machine learning device that can optimize an equation for estimating a thermal displacement amount of a machine element based on the operating state of the machine element. The device acquires operating state data of the machine element, acquires a measured value for the thermal displacement amount, stores the operating state data and measured values for the thermal displacement amount of the machine element as training data associated together as a label, sets an equation for calculation the thermal displacement amount based on the operating state data, calculates an estimated value for the thermal displacement amount by substituting the operating state data into this equation, determines whether a difference between the estimated value for the thermal displacement amount and the measured value for the thermal displacement amount is no more than a predetermined threshold.

A machine tool includes a workpiece holding unit to hold a workpiece. A tool holding unit holds a tool. At least one of the workpiece holding unit and the tool holding unit is drivingly rotatable or drivingly movable in a predetermined direction to machine the workpiece with the tool. Temperature sensors are attached to members constituting the machine tool. An estimator calculates an environmental temperature system thermal displacement amount due to a heat source outside the machine tool. A correction magnification processor calculates an environmental temperature system thermal displacement correction amount. Another estimator calculates a driving system thermal displacement amount due to a heat source in the machine tool. A thermal displacement correction amount adder obtains and outputs a total thermal displacement correction amount based on which the machine tool performs thermal displacement correction control.

A machining apparatus is provided with a machine learning device that performs machine learning. The machine learning device performs the machine learning by receiving the input of machining accuracy between a machining shape of a workpiece measured on-machine and design data on the workpiece and machining time of the workpiece measured by a measurement device. Based on a result of the machine learning, the machining apparatus changes machining conditions such that the machining accuracy increases and the machining time becomes as short as possible.