A machine learning device includes a virtual temperature model calculating unit having an equation including a first coefficient for determining a heat generation amount and a second coefficient for determining a heat dissipation amount. The virtual temperature model calculating unit is configured to calculate virtual temperature data by estimating a temperature of a specific portion of a machine by the equation using heat generation factor data. A thermal displacement model calculating unit is configured to calculate, using the calculated virtual temperature data and actual temperature data acquired from at least one temperature sensor mounted to a portion other than the specific portion, an error between thermal displacement estimated by the equation and actually measured thermal displacement, in which the virtual temperature model calculating unit performs machine learning to search for the first coefficient and the second efficient so that the error is minimized.

A thermal compensation system for machine tools includes a thermal compensation-monitoring device and a cloud processing device. The thermal compensation-monitoring device receives a plurality of temperature signals of a workpiece and corresponding processing tolerance data to build or update a thermal compensation database. The cloud processing device provides a thermal compensation model, and applies the model with the characterized temperature signals and the tolerance data to generate a compensation value so as to decide whether or not to modify the model or to run a compensation is necessary.

A thermal displacement correction method is provided, including a first step of setting an initial tool temperature, a second step of estimating a temperature of a tool or a position measurement sensor based on the initial tool temperature and a temperature of a spindle, a third step of estimating an amount of thermal displacement of the tool or the position measurement sensor with a preliminarily set tool thermal displacement estimation formula based on the estimated temperature, and a fourth step of moving a feed shaft of the machine tool based on the estimated amount of thermal displacement to perform a correction. In the second step, the temperature of the spindle is measured, then a tool-mounted portion temperature of the spindle is estimated from the measured temperature.

Provided is a thermal displacement correction method using a machine learning method but making it possible to, on a user side, calculate a thermal displacement amount appropriate to a machine tool of the user and correct the thermal displacement. In a machine tool on a target user side, a thermal displacement amount between workpiece and tool corresponding to a temperature at a preset measurement point is calculated based on a parameter defining a relation between the temperature and the thermal displacement amount, and a positioning position for workpiece and tool is corrected in accordance with the calculated thermal displacement amount. On a manufacturer side, operational status information of the machine tool on the target user side is obtained, an operational status identical to the obtained operational status on the target user side is reproduced with a machine tool of a same type as the machine tool on the target user side based on the obtained operational status information, a temperature at a measurement point identical to the measurement point on the machine tool on the target user side and a thermal displacement amount between workpiece and tool are measured during reproduction, and the parameter is calculated by machine learning based on the measured temperature and thermal displacement amount. The parameter in the machine tool on the target user side is updated with the calculated parameter.

To provide an abnormality determination apparatus, a computer readable medium, an abnormality determination system and an abnormality determination method which can simply detect an abnormality of a temperature in a machine tool without incurring cost. An abnormality determination apparatus which determines abnormality of a temperature sensor in a plurality of machine tools, in which the plurality of machine tools is equivalent machine type, is arranged in equivalent environments, are provided with a temperature sensor at equivalent positions, the abnormality determination apparatus including: a temperature data acquisition unit which acquires temperature data outputted by the temperature sensors from each of the plurality of machine tools; a comparison unit which compares the temperature data acquired by the temperature data acquisition unit; and an abnormality determination unit which determines abnormality of the temperature sensor based on a comparison result by the comparison unit.

Provided are a fluctuation amount estimation device (9) capable of evaluating reliability of an estimated value and a correction amount calculation device (1) including the fluctuation amount estimation device (9). The correction amount calculation device (1) includes the fluctuation amount calculation device (9), a correction amount calculation unit (5), and a correction amount output unit (7). The fluctuation amount estimation device (9) includes a parameter storage (3) storing parameters as constituent elements of a neural network obtained by machine learning, an estimation unit (2) estimating a fluctuation amount relevant to a position of an element arranged in a machine tool (11) or a fluctuation amount of a distance between elements arranged in the machine tool (11) for each physical condition information of the machine tool (11) by means of the neural network with a parameter freely selected from the parameters being omitted, and a reliability evaluation unit (4) evaluating reliability of estimated multiple fluctuation amounts based on the estimated fluctuation amounts. The correction amount calculation unit (5) calculates a correction amount for the estimated fluctuation amounts based on the fluctuation amounts, and the correction amount output unit (7) outputs the calculated correction amount to outside.

A controller includes data collect circuitry configured to collect machining data including a date and a time when at least one machined portion of a workpiece has been machined by a machine tool, temperature circuitry configured to obtain, at predetermined time intervals, temperature data at positions on the machine tool, dimension data input circuitry configured to receive dimension measurement data which includes a dimension of the machined portion after the machined portion has been machined, learning data generate circuitry configured to generate learning data based on the machining data and the dimension measurement data, and machine learning circuitry configured to execute a machine learning based on the temperature data and the learning data to obtain a correction coefficient based on which a displacement caused by a change in a temperature of the machine tool is corrected according to a thermal displacement correction equation.

The present invention relates to an apparatus and a method of automatically converting thermal displacement compensation parameters of a machine tool, which automatically convert a compensation parameter of a thermal displacement compensation equation of a machine tool so that the compensation parameter is optimized to a current thermal displacement state of the machine tool in real time based on Z-directional or Y-directional displacement data of a tool tip end of a reference tool measured by a tool measuring unit according to an operation state of the machine tool or various kinds of machine tools or thermal displacement data of the machine tool calculated by measuring a processed portion of a processed material, and temperature data measured by a temperature measuring unit, to minimize a processing error according to thermal displacement and improve processing accuracy of the machine tool.

The present invention relates to methods and devices for compensating for a thermally induced change in position on a numerically controlled machine tool, wherein: a characteristic map describing the thermoelastic behaviour of the machine tool is provided to a control system of the machine tool; one or more temperature values are determined by means of one or more temperature sensors on the machine tool; one or more compensation parameters are determined on the control system of the machine tool on the basis of the one or more temperature values determined and of the characteristic map provided; and wherein a temperature-dependent change in position on the machine tool is performed according to the one or more compensation values determined. According to the invention, the characteristic map provided is adjusted or updated by means of a neural network running on a computer.

Provided is a thermal displacement correction method using a machine learning method but making it possible to, on a user side, calculate a thermal displacement amount appropriate to a machine tool of the user and correct the thermal displacement. In a machine tool on a target user side, a thermal displacement amount between workpiece and tool corresponding to a temperature at a preset measurement point is calculated based on a parameter defining a relation between the temperature and the thermal displacement amount, and a positioning position for workpiece and tool is corrected in accordance with the calculated thermal displacement amount. On a manufacturer side, operational status information of the machine tool on the target user side is obtained, an operational status identical to the obtained operational status on the target user side is reproduced with a machine tool of a same type as the machine tool on the target user side based on the obtained operational status information, a temperature at a measurement point identical to the measurement point on the machine tool on the target user side and a thermal displacement amount between workpiece and tool are measured during reproduction, and the parameter is calculated by machine learning based on the measured temperature and thermal displacement amount. The parameter in the machine tool on the target user side is updated with the calculated parameter.