Information processing device, industrial system, and control method for machine tool

Abstract

This information processing device comprises: an acquisition unit (10) that acquires a thermal image showing the temperature distribution of industrial equipment having a movable part that can be moved by a drive mechanism; a pre-processing unit (12) that, on the basis of the position of the movable part when the thermal image was captured, changes, among a plurality of pixels that constitute the thermal image, the pixels from which temperature data is extracted; and a thermal displacement estimation unit (13) that, on the basis of the extracted temperature data, estimates the amount of thermal displacement of the industrial equipment. The information processing device is capable of easily estimating the amount of thermal displacement when a heat-generating site of industrial equipment moves.

Description

Information Processing Apparatus, Industrial System, and Control Method for Machine Tool

[0001] The present disclosure relates to an information processing apparatus, an industrial system, and a control method for a machine tool.

[0002] In industrial equipment that moves a movable part by a drive mechanism, the structure of the industrial equipment may be deformed by heat generation during the operation of the industrial equipment, and the positioning accuracy of the movable part may decrease. For example, in a machine tool that moves a tool attached to a spindle, when the structure of the machine tool is deformed by heat, the position of the tool with respect to the workpiece or the attitude of the tool with respect to the workpiece changes, resulting in a machining error. The change in the position of the tool with respect to the workpiece or the attitude of the tool with respect to the workpiece is referred to as the thermal displacement of the machine tool.

[0003] Patent Document 1 discloses an error analysis apparatus for analyzing errors in industrial equipment. A model is generated by machine learning of a dataset in which a thermal image and an error during the operation of the industrial equipment are paired, and the amount of thermal displacement of the industrial equipment is estimated based on the model and the acquired thermal image. The error analysis apparatus according to Patent Document 1 determines a mechanical structure having a large influence on thermal displacement and acquires the temperature of the mechanical structure having a large contribution to thermal displacement, thereby estimating the amount of thermal displacement.

[0004] International Publication No. 2023 / 188493

[0005] In the conventional technology disclosed in Patent Document 1, the case where the heat generation location of the industrial equipment moves as the movable part moves is not considered. Therefore, when estimating the amount of thermal displacement by the above conventional technology, it is necessary to acquire a thermal image when the mechanical structure of the industrial equipment is in the same position state as when the thermal image used for generating the model was taken. Further, when the heat generation location of the industrial equipment moves as the movable part moves, retraining using a thermal image in the state where the heat generation location has moved is required. Therefore, according to the above conventional technology, there is a problem that it is difficult to estimate the amount of thermal displacement when the heat generation location of the industrial equipment moves.

[0006] This disclosure has been made in view of the above, and aims to provide an information processing device that can easily estimate the amount of thermal displacement when a heat-generating part of industrial equipment moves.

[0007] To solve the above-mentioned problems and achieve the objective, the information processing device according to this disclosure includes: an acquisition unit that acquires a thermal image showing the temperature distribution of industrial equipment having a movable part that can be moved by a drive mechanism; a preprocessing unit that changes the pixels from which temperature data is extracted from among a plurality of pixels constituting the thermal image based on the position of the movable part when the thermal image was taken; and a thermal displacement estimation unit that estimates the amount of thermal displacement of the industrial equipment based on the extracted temperature data.

[0008] The information processing device described herein has the effect of easily estimating the amount of thermal displacement when a heat-generating part of industrial equipment moves.

[0009] Figures illustrating the configuration of an industrial system according to Embodiment 1; Figures illustrating the configuration of a machine tool in the industrial system according to Embodiment 1; Figure 1 for explaining a thermal image captured by a thermal image sensor in the industrial system according to Embodiment 1; Figure 2 for explaining a thermal image captured by a thermal image sensor in the industrial system according to Embodiment 1; Figure 3 for explaining a thermal image captured by a thermal image sensor in the industrial system according to Embodiment 1; Figure for explaining processing by a pre-processing unit in the industrial system according to Embodiment 1; Figure flowchart showing an example of the operation procedure of the industrial system according to Embodiment 1; Figures illustrating the configuration of an industrial system according to Embodiment 2; Figures illustrating the configuration of an industrial system according to Embodiment 3; Figures illustrating an example of the result of determining the presence or absence of an abnormality by a determination unit in the industrial system according to Embodiment 3; Figures illustrating an example of the display of a thermal image by a display unit in the industrial system according to Embodiment 3; Figures illustrating the configuration of an industrial system according to Embodiment 4; Figures illustrating an example of a hardware configuration for realizing a control device according to Embodiments 1 to 3; Figures illustrating an example of a hardware configuration for realizing a server device according to Embodiment 4.

[0010] The following describes in detail, with reference to the drawings, an information processing device, an industrial system, and a control method for a machine tool according to an embodiment.

[0011] Embodiment 1. Figure 1 shows an example of the configuration of an industrial system 1A according to Embodiment 1. The industrial system 1A comprises a control device 2A, an industrial machine tool 3, and a thermal image sensor 4. The control device 2A controls the machine tool 3. The thermal image sensor 4 captures a thermal image showing the temperature distribution of the machine tool 3. The control device 2A functions as an information processing device that processes the information shown in the thermal image captured by the thermal image sensor 4.

[0012] Figure 2 shows an example of the configuration of a machine tool 3 in the industrial system 1A according to Embodiment 1. In Embodiment 1, the machine tool 3 is a vertical orthogonal three-axis cutting machine. The X, Y, and Z axes are three mutually orthogonal axes. The machine tool 3 processes a workpiece by driving multiple axes, which are feed axes, to move the tool and workpiece relative to each other. In Figure 2, the direction of the arrow representing the X axis is the positive X direction, and the opposite direction of the positive X direction is the negative X direction. The direction of the arrow representing the Y axis is the positive Y direction, and the opposite direction of the positive Y direction is the negative Y direction. The direction of the arrow representing the Z axis is the positive Z direction, and the opposite direction of the positive Z direction is the negative Z direction.

[0013] The machine tool 3 comprises a bed 30 which is the base of the machine tool 3, a column 31 fixed to the bed 30, a table 32 on which the workpiece 35 is fixed, a head 33 supported by the column 31, and a spindle 34 attached to the head 33. The tool 36 is attached to the spindle 34.

[0014] The machine tool 3 comprises a spindle drive system, an X-axis drive system 37X, a Y-axis drive system 37Y, and a Z-axis drive system 37Z. The spindle drive system rotates the tool 36 attached to the spindle 34. The tool 36 rotates due to the driving force of the motor in the spindle drive system. Note that the spindle drive system is not shown in the illustration. The X-axis drive system 37X, the Y-axis drive system 37Y, and the Z-axis drive system 37Z are each linear feed drive systems.

[0015] The X-axis drive system 37X includes a ball screw, a motor that rotates the ball screw, and a mechanism that converts the rotational motion of the ball screw into linear motion in the X-axis direction. The X-axis drive system 37X drives the head 33 in the X-axis direction. The Y-axis drive system 37Y includes a ball screw, a motor that rotates the ball screw, and a mechanism that converts the rotational motion of the ball screw into linear motion in the Y-axis direction. The Y-axis drive system 37Y drives the table 32 in the Y-axis direction. The Z-axis drive system 37Z includes a ball screw, a motor that rotates the ball screw, and a mechanism that converts the rotational motion of the ball screw into linear motion in the Z-axis direction. The Z-axis drive system 37Z drives the head 33 in the Z-axis direction. The machine tool 3 moves the tool 36 using the X-axis drive system 37X and the Z-axis drive system 37Z, and moves the workpiece 35 using the Y-axis drive system 37Y, thereby moving the workpiece 35 and the tool 36 relative to each other.

[0016] The X-axis drive system 37X and the Z-axis drive system 37Z constitute a drive mechanism that drives the spindle 34 to which the tool 36 is attached. The Y-axis drive system 37Y constitutes a drive mechanism that drives the table 32 to which the workpiece 35 is fixed. The spindle 34 and the table 32 are both movable parts that can be moved by the drive mechanism.

[0017] Each of the spindle drive system, X-axis drive system 37X, Y-axis drive system 37Y, and Z-axis drive system 37Z is connected to the control device 2A. The control device 2A generates commands to control each drive system according to the machining program, which is an NC (Numerical Control) program, and sends commands to each drive system. The spindle drive system rotates the tool 36 according to the commands. The X-axis drive system 37X and the Z-axis drive system 37Z each drive the spindle 34 according to the commands. The Y-axis drive system 37Y drives the table 32 according to the commands.

[0018] In Embodiment 1, deformation of the machine tool 3's structure due to heat is referred to as thermal deformation. Structural deformation of the machine tool 3 refers to deformation of the structural members of the machine tool 3, or deformation of the components of each drive system of the machine tool 3. The structural members of the machine tool 3 are the bed 30, column 31, table 32, or head 33. When the position of the tool 36 relative to the workpiece 35 changes due to thermal deformation of the machine tool 3, the amount of movement of the tool 36 relative to the workpiece 35 is referred to as the thermal displacement of the machine tool 3.

[0019] In the above description, machine tool 3 is assumed to have a three-axis linear feed drive system. However, machine tool 3 is not limited to having a three-axis linear feed drive system. Machine tool 3 may also be a lathe or other machine with a two-axis linear feed drive system.

[0020] As shown in Figure 1, the control device 2A includes an acquisition unit 10, a recording unit 11, a preprocessing unit 12, a thermal displacement estimation unit 13, a correction amount generation unit 14, a control unit 15, a display unit 16, a learning unit 17, and a model holding unit 18.

[0021] The thermal image sensor 4 captures a thermal image showing the temperature distribution of the machine tool 3 and transmits the thermal image to the control device 2A. The acquisition unit 10 receives the thermal image transmitted by the thermal image sensor 4. As a result, the acquisition unit 10 acquires a thermal image showing the temperature distribution of the machine tool 3. The acquisition unit 10 outputs the acquired thermal image data to the recording unit 11. The recording unit 11 records the thermal image acquired by the acquisition unit 10.

[0022] The control device 2A may also convert the thermal image data acquired by the acquisition unit 10 into compressed data by compression encoding of the thermal image. In this case, the recording unit 11 records the compressed data obtained by compression encoding of the thermal image.

[0023] The preprocessing unit 12 reads thermal image data from the recording unit 11 and processes the read data. The preprocessing unit 12 extracts temperature data from the thermal image. The preprocessing unit 12 changes the pixels from which temperature data is extracted among the multiple pixels that make up the thermal image, based on the position of the movable part when the thermal image was taken. The preprocessing unit 12 outputs the extracted temperature data to the thermal displacement estimation unit 13.

[0024] The thermal displacement estimation unit 13 estimates the thermal displacement of the machine tool 3 based on the temperature data extracted by the preprocessing unit 12. The thermal displacement estimation unit 13 outputs information indicating the estimated thermal displacement to the correction amount generation unit 14.

[0025] The correction amount generation unit 14 calculates a correction amount for the position of the movable part, i.e., the main shaft 34 or the table 32, based on the amount of thermal displacement estimated by the amount of thermal displacement estimation unit 13. The correction amount generation unit 14 outputs information indicating the calculated correction amount to the control unit 15.

[0026] The control unit 15 generates commands according to the machining program and sends commands to each drive system of the machine tool 3. The control unit 15 controls the machine tool 3 by sending commands to each drive system. In addition, if information indicating a correction amount is input to the control unit 15, the control unit 15 generates a command that reflects the correction amount. As a result, the control unit 15 controls the machine tool 3 based on the command that reflects the correction amount calculated by the correction amount generation unit 14. The machine tool 3 sends information indicating the position of the spindle 34 in the X-axis and Z-axis directions and information indicating the position of the table 32 in the Y-axis direction to the control device 2A. That is, the control device 2A receives position information indicating the position of the movable parts from the machine tool 3. The control unit 15 adjusts the control of the machine tool 3 based on the error between the position indicated in the position information and the commanded position. The control unit 15 also outputs position information indicating the position of the movable parts to the pre-processing unit 12.

[0027] The display unit 16 reads the thermal image from the recording unit 11 and displays the thermal image. The control device 2A outputs the thermal image read from the recording unit 11 by displaying it on the display unit 16.

[0028] The learning unit 17 learns the relationship between the temperature of the machine tool 3 and the amount of thermal displacement of the machine tool 3. The learning unit 17 generates a model based on the learned relationship between the temperature of the machine tool 3 and the amount of thermal displacement of the machine tool 3. The learning unit 17 outputs the generated model to the model holding unit 18. The model holding unit 18 holds the model generated by the learning unit 17.

[0029] The thermal displacement estimation unit 13 reads the model from the model holding unit 18 and estimates the thermal displacement of the machine tool 3 by inputting temperature data extracted from the thermal image into the model. In other words, the thermal displacement estimation unit 13 estimates the thermal displacement of the machine tool 3 by inputting temperature data into a model that has learned the relationship between the temperature of the machine tool 3 and the thermal displacement of the machine tool 3.

[0030] The thermal image sensor 4 is equipped with multiple infrared detection elements corresponding to pixels. The thermal image sensor 4 outputs a value corresponding to the amount of infrared radiation captured by each infrared detection element over a predetermined period of time. When imaging is performed by the thermal image sensor 4 while the movable part is moving, the value output from the thermal image sensor 4 will fluctuate depending on the speed at which the movable part moves.

[0031] Therefore, the thermal image sensor 4 may take a thermal image when the speed at which the movable part moves is less than or equal to a preset speed. In other words, the acquisition unit 10 may acquire the thermal image taken when the speed at which the movable part moves is less than or equal to a preset speed. This makes it possible for the control device 2A to reduce errors in temperature data caused by the movement of the movable part and obtain a highly accurate thermal image.

[0032] Next, we will describe the thermal images captured by the thermal imaging sensor 4. Figure 3 is a first diagram illustrating the thermal images captured by the thermal imaging sensor 4 of the industrial system 1A according to Embodiment 1. Figure 4 is a second diagram illustrating the thermal images captured by the thermal imaging sensor 4 of the industrial system 1A according to Embodiment 1. Figure 5 is a third diagram illustrating the thermal images captured by the thermal imaging sensor 4 of the industrial system 1A according to Embodiment 1.

[0033] The thermal image captured by the thermal image sensor 4 consists of multiple pixels arranged in a two-dimensional direction. In the examples shown in Figures 3 to 5, it is assumed that six pixels are arranged vertically and six horizontally in the thermal image. A pixel is the smallest unit that constitutes a thermal image. The thermal image visually represents the temperature value shown in each pixel. In the examples shown in Figures 3 to 5, the thermal image sensor 4 is assumed to be capturing the side of the machine tool 3. Figure 3 shows a simplified side of the machine tool 3, and the shooting range of the thermal image sensor 4 is superimposed on the side of the machine tool 3. The dashed lines in Figure 3 represent the boundaries of pixels.

[0034] The value of each pixel in the thermal image represents the temperature detected by the thermal image sensor 4. In Figure 4, the temperature differences shown in each pixel are represented by the density of the halftone dots. In Figure 4, the darker the halftone dot, the higher the temperature. In Figure 5, the temperature shown in each pixel is represented numerically. In Figure 5, the unit of temperature is degrees Celsius.

[0035] The display unit 16 displays a thermal image as shown in Figure 4. The display unit 16 may also display a numerical representation of the temperature, as shown in Figure 5, along with the thermal image, or in place of the thermal image. The display unit 16 may also superimpose the thermal image as shown in Figure 4 onto a simplified diagram of the machine tool 3, as shown in Figure 3.

[0036] In Figure 3, the entire side of the machine tool 3 is captured by a single thermal image sensor 4, but this is not the only option. The orientation in which the thermal image sensor 4 captures the machine tool 3 is arbitrary. The industrial system 1A may also capture the machine tool 3 using multiple thermal image sensors 4. In this case, the acquisition unit 10 acquires the thermal image output from each of the multiple thermal image sensors 4. Furthermore, the thermal image sensors 4 may capture only a part of the machine tool 3, rather than the entire machine tool 3. In this case, the acquisition unit 10 acquires a thermal image of only a part of the machine tool 3, not a thermal image of the entire machine tool 3. The industrial system 1A may also acquire the temperature distribution of the entire machine tool 3 or a part of the machine tool 3 by stitching together multiple thermal images captured by multiple thermal image sensors 4. Furthermore, the number of pixels constituting the thermal image is not limited to the above and is arbitrary.

[0037] Next, the processing performed by the preprocessing unit 12 will be described. Here, a specific method for changing the pixels from which temperature data is extracted according to the position of the spindle 34 when the spindle 34, which is a movable part, is in motion, will be described. As a preliminary step, the preprocessing unit 12 determines the relationship between the distance traveled by the spindle 34 and the number of pixels in the thermal image that corresponds to the distance traveled by the spindle 34. After that, the preprocessing unit 12 performs a process to change the pixels from which temperature data is extracted based on the relationship determined in the preliminary step and the distance traveled by the spindle 34 from a predetermined reference position.

[0038] The preprocessing unit 12 performs the first and second steps described below in the preparation phase. As the first step, the preprocessing unit 12 creates a dataset that associates thermal images with the position information of the spindle 34. The control device 2A causes the machine tool 3 to perform an operation to position the spindle 34 at two predetermined points, a first position and a second position. The thermal image sensor 4 captures a thermal image when the spindle 34 is positioned at the first position and a thermal image when the spindle 34 is positioned at the second position. The acquisition unit 10 acquires the thermal image when the spindle 34 is positioned at the first position and the thermal image when the spindle 34 is positioned at the second position, and records these acquired thermal images in the recording unit 11. The preprocessing unit 12 reads these thermal images from the recording unit 11.

[0039] Furthermore, the preprocessing unit 12 receives position information of the spindle 34 when the spindle 34 is positioned at a first position and position information of the spindle 34 when the spindle 34 is positioned at a second position from the control unit 15. In other words, the preprocessing unit 12 obtains position information indicating the first position and position information indicating the second position from the control unit 15. As a result, the preprocessing unit 12 generates a dataset that associates the thermal image when the spindle 34 is positioned at a first position with the position information indicating the first position, and a dataset that associates the thermal image when the spindle 34 is positioned at a second position with the position information indicating the second position.

[0040] Figure 6 is a diagram illustrating the processing performed by the preprocessing unit 12 of the industrial system 1A according to Embodiment 1. Figure 6 shows a simplified side view of the machine tool 3, and superimposes the imaging range of the thermal image sensor 4 onto the side view of the machine tool 3. The dashed lines in Figure 6 represent pixel boundaries. The left side of Figure 6 shows the side view of the machine tool 3 and the imaging range when the spindle 34 is positioned in the first position. The vertical direction in the thermal image corresponds to the Z-axis direction, and the horizontal direction in the thermal image corresponds to the Y-axis direction. The right side of Figure 6 shows the side view of the machine tool 3 and the imaging range when the spindle 34 is positioned in the second position. Line L1 in Figure 6 represents the Z-axis position of the tip of the tool 36 when the spindle 34 is positioned in the first position. Line L2 in Figure 6 represents the Z-axis position of the tip of the tool 36 when the spindle 34 is positioned in the second position.

[0041] Next, as a second step, the preprocessing unit 12 determines the relationship between the movement distance of the main axis 34 and the number of pixels based on the dataset generated in the first step. Here, it is assumed that the movement of the main axis 34 from the first position to the second position is 300 mm in the negative Z direction. The double arrows shown in Figure 6 represent the movement distance of the main axis 34. Based on the position information indicating the first position and the position information indicating the second position, the preprocessing unit 12 determines that the direction of movement of the main axis 34 is the negative Z direction and that the movement distance of the main axis 34 is 300 mm. In this way, the preprocessing unit 12 calculates the direction of movement of the movable part and the movement distance of the movable part based on the position information contained in each dataset.

[0042] Furthermore, the preprocessing unit 12 determines the direction of movement of the image of the principal axis 34 on the thermal image and the number of pixels to which the image of the principal axis 34 has moved on the thermal image. In the example shown in Figure 6, the image of the principal axis 34 has moved 3 pixels from top to bottom on the thermal image. The preprocessing unit 12 determines the direction of movement of the image of the movable part and the number of pixels to which the image of the movable part has moved by analyzing the thermal images included in each dataset.

[0043] In the example described here, a movement of 300 mm in the minus Z direction corresponds to a movement of three pixels from top to bottom on the thermal image. From this, it is found that for every 100 mm movement of the main shaft 34 in the minus Z direction, the image of the main shaft 34 moves one pixel from top to bottom in the thermal image. In this way, the preprocessing unit 12 determines the relationship between the movement distance of the main shaft 34 and the number of pixels. Also, the preprocessing unit 12 grasps the relationship between the movement direction of the movable part and the movement direction of the image on the thermal image.

[0044] Note that in the above, the preprocessing unit 12 is to determine the relationship between the number of pixels by which the image of the main shaft 34 has moved in the thermal image and the movement distance of the main shaft 34. The preprocessing unit 12 may also determine the relationship between the number of pixels by which a part where a feature appears in the thermal image, for example, a part with a higher temperature than the surroundings, has moved and the movement distance of the main shaft 34.

[0045] When a thermal image for estimating the thermal displacement amount is acquired, the preprocessing unit 12 executes the third and fourth steps described below. In the third step, the preprocessing unit 12 determines the movement direction of the part on the thermal image from which temperature data is extracted and the number of pixels by which the part from which temperature data is extracted has moved. The part from which temperature data is extracted is a part where a feature appears in the thermal image, for example, a part of the machine tool 3 that has a higher temperature than the surroundings. Hereinafter, the part from which temperature data is extracted is also referred to as a feature part.

[0046] Here, a state in which the main shaft 34 is positioned at a preset reference position is defined as a reference state. The preprocessing unit 12 determines the movement direction of the feature part on the thermal image and the number of pixels by which the feature part has moved when the main shaft 34 moves from the reference state to the state when the thermal image is acquired.

[0047] When a thermal image for estimating the thermal displacement amount is captured by the thermal image sensor 4, the acquisition unit 10 acquires the captured thermal image and records the acquired thermal image in the recording unit 11. The preprocessing unit 12 reads out the thermal image for estimating the thermal displacement amount from the recording unit 11. Further, the preprocessing unit 12 receives, from the control unit 15, the position information of the main shaft 34 when the main shaft 34 is positioned at a preset reference position, and the position information of the main shaft 34 when the thermal image for estimating the thermal displacement amount is captured. Here, the preset reference position is the first position described above.

[0048] The preprocessing unit 12 calculates the moving direction and the moving distance of the main shaft 34 when the main shaft 34 moves from the reference state to the state when the thermal image is acquired. The preprocessing unit 12 calculates the moving direction and the moving distance of the main shaft 34 based on the position information of the main shaft 34 in the reference state and the position information of the main shaft 34 when the thermal image for estimating the thermal displacement amount is captured. Here, it is assumed that the moving direction of the main shaft 34 is the minus Z direction and the moving distance of the main shaft 34 is calculated to be 500 mm.

[0049] Based on the above calculation results of the moving direction and the moving distance, and the above relationship between the moving distance of the main shaft 34 and the number of pixels obtained in the second step, the preprocessing unit 12 obtains the moving direction of the feature part on the thermal image and the number of pixels by which the feature part has moved. The above relationship is such that every time the main shaft 34 moves 100 mm in the minus Z direction, the image of the main shaft 34 in the thermal image moves one pixel from top to bottom. The preprocessing unit 12 estimates that the movement of the feature part on the thermal image is a movement of five pixels from top to bottom of the thermal image based on the above calculation results and the above relationship.

[0050] Next, the preprocessing unit 12 performs a process of changing the pixels for extracting the temperature data in the fourth step. The preprocessing unit 12 specifies the position of the feature part in the thermal image captured in the reference state.

[0051] Here, pixels in a thermal image are represented by coordinates (a, b). "a" is a variable representing the position in the left-right direction of the thermal image. "b" is a variable representing the position in the up-down direction of the thermal image. Each pixel is assigned a value of "a" such that a = 0, 1, 2, ... from left to right in the thermal image, and a value of "b" such that b = 0, 1, 2, ... from bottom to top in the thermal image.

[0052] For example, suppose the location of a feature region in a thermal image taken under a baseline condition is identified as (5,10). Also, as described above, in the third step, the movement of the feature region on the thermal image is estimated to be a movement of 5 pixels from top to bottom. Based on this estimation result, the preprocessor 12 estimates that the location of the feature region has moved to (5,5) in the thermal image used to estimate the amount of thermal displacement. As a result, the preprocessor 12 changes the pixel from which temperature data is extracted from the (5,10) pixel to the (5,5) pixel. In this way, in the thermal image used to estimate the amount of thermal displacement, the pixel from which temperature data is extracted is changed to a different pixel from the pixel from which temperature data is extracted in the thermal image under the baseline condition.

[0053] The preprocessing unit 12 extracts temperature data from the (5,5) pixel upon completing the fourth step. The preprocessing unit 12 outputs the extracted temperature data to the thermal displacement estimation unit 13.

[0054] In this way, when the movable part moves, the control device 2A estimates the direction and distance of movement of the feature area on the thermal image and changes the pixels from which temperature data is extracted. Even when the movable part moves, the control device 2A can estimate the amount of thermal displacement based on the temperature data for the same feature area. As a result, the control device 2A can accurately estimate the amount of thermal displacement even when the thermal image is taken with the movable part having moved since the thermal image used to generate the model was taken.

[0055] Next, the estimation of thermal displacement by the thermal displacement estimation unit 13 will be explained. The thermal displacement estimation unit 13 estimates the thermal displacement of the machine tool 3 based on the temperature data extracted by the preprocessing unit 12. The thermal displacement estimation unit 13 estimates the thermal displacement by inputting the temperature data into the model read from the model holding unit 18.

[0056] For example, the thermal displacement estimation unit 13 estimates the amount of thermal displacement by inputting the temperature data shown in the acquired thermal image into the model. As one example, the model used for estimating the amount of thermal displacement is generated by performing machine learning using a neural network on the learning unit 17. The neural network consists of an input layer consisting of multiple neurons, a hidden layer which is an intermediate layer consisting of multiple neurons, and an output layer consisting of multiple neurons. The input layer receives temperature data extracted by the preprocessing unit 12. The output layer outputs the amount of thermal displacement. The neural network is generated by adjusting the weights so that the output approaches the label for each input. The number of neurons in the input layer is determined by the number of pieces of information selected as input data. The number of neurons in the intermediate layer is arbitrary.

[0057] The models used to estimate thermal displacement are not limited to those generated by machine learning using neural networks. The models used to estimate thermal displacement may also be models generated by finite element analysis. In finite element analysis, the structure of the machine tool 3 is divided into multiple minute elements, and a regression model is set for each of the multiple minute elements. In this case, the thermal stress when the measured temperature is applied to each minute element is determined, and the thermal displacement of the machine tool 3 is calculated from the thermal stress obtained for each minute element.

[0058] The thermal displacement estimation unit 13 may estimate the amount of thermal displacement based on the temperature data shown in one thermal image, or it may estimate the amount of thermal displacement based on the temperature data shown in each of multiple thermal images. The thermal displacement estimation unit 13 may also estimate the amount of thermal displacement based on the temperature data shown in the currently acquired thermal image and the temperature data shown in thermal images acquired in the past.

[0059] Here, we will explain an example of estimating thermal displacement based on temperature data shown in a currently acquired thermal image and temperature data shown in a previously acquired thermal image. The thermal displacement estimation unit 13 calculates the difference between the temperature data shown in the currently acquired thermal image and the temperature data shown in a previously acquired thermal image. The thermal displacement estimation unit 13 calculates the thermal displacement based on the temperature change obtained by multiplying this difference by a coefficient. For example, when using a multiple regression model, the thermal displacement estimation unit 13 calculates the thermal displacement using the following formula: Thermal displacement = (T1_t1-T1_t0)*K1+(T2_t1-T2_t0)*K2+・・・+(Tn_t1-Tn_t0)*Kn

[0060] Here, let t1 be the time when the current thermal image was taken, and t2 be the time when the past thermal image was taken. Assume that each pixel in the thermal image is assigned a pixel number 1, 2, ..., n to identify the pixel. T1_t1, T2_t1, ..., Tn_t1 are the temperatures indicated by pixels with pixel numbers 1, 2, ..., n in the thermal image at time t1. T1_t0, T2_t0, ..., Tn_t0 are the temperatures indicated by pixels with pixel numbers 1, 2, ..., n in the thermal image at time t0. K1, K2, ..., Kn are coefficients set for pixels with pixel numbers 1, 2, ..., n.

[0061] When the thermal displacement estimation unit 13 estimates the amount of thermal displacement based on the temperature data shown in each of the multiple thermal images, it may also calculate the average value of the temperature data for each pixel. By estimating the amount of thermal displacement based on the average value, the thermal displacement estimation unit 13 can reduce the influence of noise contained in the temperature data of each thermal image.

[0062] The model used to estimate the amount of thermal displacement may be the result of learning the relationship between temperature data shown in a thermal image acquired at a certain time, temperature data shown in a thermal image acquired at a predetermined time Δt prior to that time, and the amount of thermal displacement. In this case, the thermal displacement estimation unit 13 estimates the amount of thermal displacement by inputting the temperature data shown in a thermal image acquired at a certain time and the temperature data shown in a thermal image acquired at a time Δt prior to that time into the model.

[0063] In the above description, the learning unit 17 is assumed to be located inside the control device 2A. That is, the thermal displacement estimation unit 13 estimates the thermal displacement based on the model generated by the learning unit 17 inside the control device 2A. The control device 2A may use a model generated outside the control device 2A, rather than a model generated inside the control device 2A, to estimate the thermal displacement. In this case, the control device 2A acquires a model generated by a learning device outside the control device 2A and uses the acquired model to estimate the thermal displacement.

[0064] Next, the operation procedure of the industrial system 1A will be described. Figure 7 is a flowchart showing an example of the operation procedure of the industrial system 1A according to Embodiment 1. Here, the operation in which the machine tool 3 is controlled by estimating the amount of thermal displacement of the machine tool 3 when processing a workpiece 35 with the machine tool 3 will be described.

[0065] In step S1, the machine tool 3 starts machining the workpiece 35. The machine tool 3 processes the workpiece 35 according to commands sent from the control device 2A. The thermal image sensor 4 captures a thermal image of the machine tool 3. In step S2, the acquisition unit 10 of the control device 2A acquires the thermal image captured by the thermal image sensor 4. The thermal image acquired by the acquisition unit 10 is recorded in the recording unit 11.

[0066] In step S3, the preprocessing unit 12 changes the pixels from which temperature data is extracted among the multiple pixels that make up the thermal image. The preprocessing unit 12 reads the thermal image data from the recording unit 11. The preprocessing unit 12 changes the pixels from which temperature data is extracted based on the position of the movable part when the thermal image was taken. Here, the preprocessing unit 12 changes the pixels from which temperature data is extracted based on the position of the main axis 34 when the thermal image was taken. The preprocessing unit 12 extracts temperature data from the changed pixels.

[0067] In step S4, the thermal displacement estimation unit 13 estimates the thermal displacement of the machine tool 3 based on the temperature data extracted by the preprocessing unit 12. The thermal displacement estimation unit 13 outputs information indicating the estimated thermal displacement to the correction amount generation unit 14.

[0068] In step S5, the correction amount generation unit 14 calculates a correction amount for the position of the main shaft 34 based on the thermal displacement amount estimated in step S4. The correction amount generation unit 14 outputs information indicating the calculated correction amount to the control unit 15.

[0069] In step S6, the control unit 15 controls the machine tool 3 based on a command that reflects the correction amount calculated in step S5. The control unit 15 generates a command that reflects the correction amount and sends the command to each drive system of the machine tool 3, thereby controlling the machine tool 3 based on the command that reflects the correction amount.

[0070] In step S7, the machine tool 3 determines whether or not to finish machining the workpiece 35. If the machining of the workpiece 35 is not to be finished (step S7, No), the industrial system 1A repeats the procedures from step S2 to step S7. On the other hand, if the machining of the workpiece 35 is to be finished (step S7, Yes), the industrial system 1A terminates the operation according to the procedure shown in Figure 7.

[0071] According to Embodiment 1, the control device 2A includes an acquisition unit 10 that acquires a thermal image, a preprocessing unit 12 that changes the pixels from which temperature data is extracted from among a plurality of pixels constituting the thermal image based on the position of the movable part when the thermal image was taken, and a thermal displacement estimation unit 13 that estimates the amount of thermal displacement of the industrial equipment based on the extracted temperature data. By changing the pixels from which temperature data is extracted based on the position of the movable part, the control device 2A can estimate the amount of thermal displacement based on the temperature data for the same heat-generating point when the heat-generating point of the industrial equipment moves due to the movement of the movable part. The control device 2A can estimate the amount of thermal displacement without performing retraining using a thermal image when the heat-generating point has moved. As a result, the control device 2A has the effect of being able to easily estimate the amount of thermal displacement when the heat-generating point of the industrial equipment moves. By including the control device 2A, the industrial system 1A can easily estimate the amount of thermal displacement when the heat-generating point of the industrial equipment moves.

[0072] Furthermore, the control device 2A includes a recording unit 11 that records the thermal images acquired by the acquisition unit 10. The control device 2A outputs the thermal images read from the recording unit 11. This allows the control device 2A to present the temperature distribution in the industrial equipment to the operator of the machine tool 3 in an easily understandable manner.

[0073] Furthermore, the recording unit 11 stores compressed data obtained by the compression encoding of the thermal image. As a result, the control device 2A can reduce the amount of data, allowing it to record the thermal image in a recording unit 11 with a smaller capacity.

[0074] Furthermore, the acquisition unit 10 acquires thermal images when the speed at which the movable part moves is less than or equal to a set speed. This allows the control device 2A to reduce errors in temperature data caused by the movement of the movable part, thereby enabling the acquisition of highly accurate thermal images.

[0075] Furthermore, the thermal displacement estimation unit 13 estimates the thermal displacement of industrial equipment by inputting temperature data into a model that has learned the relationship between the temperature of industrial equipment and the thermal displacement of industrial equipment. As a result, the control device 2A can accurately estimate the thermal displacement of industrial equipment based on the relationship between the temperature of industrial equipment and the thermal displacement of industrial equipment.

[0076] Embodiment 2. Figure 8 shows an example of the configuration of industrial system 1B according to Embodiment 2. In Embodiment 2, the same reference numerals are used for the same components as in Embodiment 1, and the configuration that differs from Embodiment 1 will be described in detail.

[0077] Industrial system 1B comprises a control device 2B, an industrial machine tool 3, a thermal image sensor 4, and a temperature sensor 5. Control device 2B has the same configuration as control device 2A shown in Figure 1. The temperature sensor 5 comprises a thermistor or thermocouple. The temperature sensor 5 is installed on the machine tool 3. The temperature sensor 5 measures the temperature of the machine tool 3. The temperature sensor 5 transmits temperature information indicating the measured temperature to control device 2B.

[0078] The acquisition unit 10 receives the thermal image transmitted by the thermal image sensor 4 and the temperature information transmitted by the temperature sensor 5. The acquisition unit 10 outputs the thermal image data and temperature information to the recording unit 11. The recording unit 11 records the thermal image and temperature information.

[0079] The preprocessor 12 reads thermal image data and temperature information from the recording unit 11. The preprocessor 12 extracts temperature data from the thermal image. The preprocessor 12 also corrects the temperature data shown in the thermal image based on the temperature information. That is, the preprocessor 12 corrects the temperature data shown in the thermal image based on the temperature measurement results from the temperature sensor 5 installed on the machine tool 3.

[0080] Here, a specific example of how the preprocessor 12 corrects temperature data will be described. The preprocessor 12 refers to the temperature data shown in the thermal image for the same part of the machine tool 3 where the temperature was measured by the temperature sensor 5. The preprocessor 12 calculates the difference between the temperature shown in the referenced temperature data and the temperature measured by the temperature sensor 5. The preprocessor 12 corrects the temperature data by adding this difference to the temperature value shown in each pixel of the thermal image, or by subtracting this difference from the temperature value shown in each pixel of the thermal image. Note that the method of correcting the temperature data is not limited to the method described here and is arbitrary.

[0081] Errors may occur in the temperature shown in the thermal image due to drift that occurs when thermal image acquisition is performed for a long period of time. According to Embodiment 2, the control device 2B corrects the temperature data shown in the thermal image based on the temperature measurement results from the temperature sensor 5, thereby enabling highly accurate temperature measurement using thermal images. As a result, the control device 2B can estimate the amount of thermal displacement with high accuracy.

[0082] Embodiment 3. Figure 9 shows an example of the configuration of industrial system 1C according to Embodiment 3. In Embodiment 3, the same reference numerals are used for components that are the same as those in Embodiment 1 or 2, and the configuration that differs from Embodiment 1 or 2 will be described in detail.

[0083] Industrial system 1C comprises a control device 2C, an industrial machine tool 3, and a thermal image sensor 4. The control device 2C has the same configuration as the control device 2A shown in Figure 1. Furthermore, the control device 2C includes a determination unit 19.

[0084] The determination unit 19 reads thermal image data from the recording unit 11. The determination unit 19 extracts temperature data from the thermal image. The determination unit 19 determines whether or not there is an abnormality in the machine tool 3 based on the temperature data extracted from the thermal image. The determination unit 19 outputs the result of the determination of whether or not there is an abnormality to the display unit 16. The display unit 16 displays information indicating whether or not there is an abnormality. The control device 2C outputs the determination result from the determination unit 19 by displaying the information indicating whether or not there is an abnormality on the display unit 16.

[0085] Figure 10 shows an example of the result of determining whether or not there is an abnormality by the determination unit 19 of the industrial system 1C according to Embodiment 3. For example, suppose that the temperature near the spindle 34 of the machine tool 3 is measured to be 60 degrees, which is higher than normal, by thermal imaging.

[0086] Here, a specific example of how the determination unit 19 determines whether or not there is an abnormality will be described. The determination unit 19 obtains the highest temperature value measured by the thermal image, the lowest temperature value measured by the thermal image, and the difference between the highest and lowest values. The determination unit 19 determines whether or not the highest or lowest value is within a preset range. This range represents the temperature range when the machine tool 3 is functioning normally. The determination unit 19 determines that there is an abnormality if the highest value is outside this range. The determination unit 19 determines that there is an abnormality if the lowest value is outside this range. Furthermore, the determination unit 19 determines that there is an abnormality if the difference between the highest and lowest values ​​exceeds a preset threshold.

[0087] In the example shown in Figure 10, the highest temperature measured by the thermal image is 60 degrees, and the lowest temperature measured by the thermal image is 20 degrees. The difference between the highest and lowest values ​​is calculated to be 40 degrees. Here, 60 degrees is a value outside the preset range, and 20 degrees is a value within that range. The determination unit 19 determines that the highest value of 60 degrees is abnormal, and that the lowest value of 20 degrees is normal. Furthermore, the difference of 40 degrees between the highest and lowest values ​​is considered to exceed a preset threshold. The determination unit 19 determines that this difference is abnormal.

[0088] As one example, the display unit 16 displays a table showing the judgment results as shown in Figure 10. In the example shown in Figure 10, the words "spindle motor," indicating the part where the highest value was measured, and "bed," indicating the part where the lowest value was measured, are displayed along with the judgment results. This allows the control device 2C to present the judgment results regarding the presence or absence of abnormalities to the operator in an easy-to-understand manner. The display unit 16 may, for example, display a thermal image, which represents the temperature differences shown in each pixel in grayscale, superimposed on a simplified diagram of the machine tool 3. This allows the control device 2C to present the temperature of each part of the machine tool 3 to the operator in an easy-to-understand manner. The display unit 16 may also display a table showing the judgment results along with the thermal image superimposed on the simplified diagram of the machine tool 3.

[0089] Furthermore, the criteria for determining whether or not there is an abnormality may be set within a certain range for the entire machine tool 3, or different ranges may be set for each part of the machine tool 3. Also, the display method of the determination result is not limited to that shown in Figure 10, but is arbitrary.

[0090] The method by which the determination unit 19 determines whether or not there is an abnormality in the machine tool 3 is not limited to the method described above, but is arbitrary. For example, the determination unit 19 may determine whether or not there is an abnormality using a model generated by machine learning. As one example, the determination unit 19 may use thermal images labeled as normal or abnormal as training data, and determine whether or not there is an abnormality based on a model generated by supervised learning.

[0091] Figure 11 shows an example of thermal image display by the display unit 16 of the industrial system 1C according to Embodiment 3. In the example described here, the display unit 16 reads two thermal images acquired at different times from the recording unit 11 and displays the two thermal images. The control device 2C outputs the two thermal images read from the recording unit 11 by displaying them on the display unit 16.

[0092] In the example shown in Figure 11, the display unit 16 displays two thermal images side by side. In the example shown in Figure 11, each thermal image represents the temperature difference shown in each pixel using grayscale, and is displayed superimposed on a simplified diagram of the machine tool 3.

[0093] Here, the display unit 16 will display the information shown in Figure 11 when the determination unit 19 determines that there is an abnormality. Of the two thermal images, the thermal image shown on the right in Figure 11 is the thermal image taken at the present time when an abnormality has been determined. Of the two thermal images, the thermal image shown on the left in Figure 11 is a thermal image taken in the past when the machine tool 3 was functioning normally. By presenting the two thermal images, the control device 2C can clearly show the operator the difference in temperature distribution between the two thermal images. Furthermore, by displaying the thermal image taken when an abnormality has been determined along with the thermal image taken when the machine tool 3 is functioning normally, the control device 2C can clearly indicate the part causing the abnormality.

[0094] In the above description, the display unit 16 displays two thermal images, but it may also display three or more thermal images. That is, the display unit 16 may display three or more thermal images acquired at different times. The control device 2C may output three or more thermal images read from the recording unit 11.

[0095] According to Embodiment 3, the control device 2C includes a determination unit 19 that determines whether or not there is an abnormality in the industrial equipment based on temperature data extracted from the thermal image. The control device 2C outputs the determination result from the determination unit 19. As a result, the control device 2C can clearly inform the operator of any abnormalities in the industrial equipment and encourage them to make improvements in response to the abnormality.

[0096] Furthermore, the recording unit 11 records two or more thermal images acquired at different times. The control device 2C outputs the two or more thermal images read from the recording unit 11. This allows the control device 2C to clearly present to the operator the differences in temperature distribution between the two thermal images.

[0097] Embodiment 4. Figure 12 shows an example of the configuration of industrial system 1D according to Embodiment 4. In Embodiment 4, the same reference numerals are used for the same components as in Embodiments 1 to 3, and the configuration that differs from Embodiments 1 to 3 will be described in detail.

[0098] The industrial system 1D comprises a control device 2D, an industrial machine tool 3, a thermal image sensor 4, a server device 6, and a display device 7. The control device 2D controls the machine tool 3. The thermal image sensor 4 captures a thermal image showing the temperature distribution of the machine tool 3.

[0099] The server device 6 functions as an information processing device that processes information shown in the thermal image captured by the thermal image sensor 4. The server device 6 is composed of, for example, one or more cloud servers. A cloud server is a server built in a cloud environment that includes computer resources provided on a cloud service platform. The server device 6 is communicated with the control device 2D, the thermal image sensor 4, and the display device 7 via a network such as a VPN (Virtual Private Network).

[0100] The server device 6 comprises an acquisition unit 10, a recording unit 11, a preprocessing unit 12, a thermal displacement estimation unit 13, a correction amount generation unit 14, a learning unit 17, and a model holding unit 18. The server device 6 does not have the control unit 15 and display unit 16 shown in Figure 1. The control device 2D performs the same functions as the control unit 15 shown in Figure 1.

[0101] The display device 7 performs the same functions as the display unit 16 shown in Figure 1. The display device 7 is, for example, a display such as an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display.

[0102] The thermal image sensor 4 captures a thermal image showing the temperature distribution of the machine tool 3 and transmits the thermal image to the server device 6. The acquisition unit 10 receives the thermal image transmitted by the thermal image sensor 4. As a result, the acquisition unit 10 acquires a thermal image showing the temperature distribution of the machine tool 3.

[0103] The correction amount generation unit 14 calculates a correction amount for the position of the movable part based on the thermal displacement amount estimated by the thermal displacement amount estimation unit 13. The correction amount generation unit 14 transmits information indicating the calculated correction amount to the control device 2D.

[0104] The control device 2D generates commands according to the machining program and sends them to each drive system of the machine tool 3. The control device 2D controls the machine tool 3 by sending commands to each drive system. In addition, when the control device 2D receives information indicating a correction amount, it generates a command that reflects the correction amount. As a result, the control device 2D controls the machine tool 3 based on the command that reflects the correction amount calculated by the correction amount generation unit 14.

[0105] According to Embodiment 4, the server device 6 includes an acquisition unit 10 for acquiring a thermal image, a preprocessing unit 12 for changing the pixels from which temperature data is extracted among a plurality of pixels constituting the thermal image based on the position of the movable part when the thermal image was taken, and a thermal displacement estimation unit 13 for estimating the amount of thermal displacement of the industrial equipment based on the extracted temperature data. Similar to the control device 2A according to Embodiment 1, the server device 6 can easily estimate the amount of thermal displacement when the heat-generating part of the industrial equipment moves. By including the server device 6, the industrial system 1D can easily estimate the amount of thermal displacement when the heat-generating part of the industrial equipment moves.

[0106] Next, the hardware configuration for realizing the control devices 2A, 2B, and 2C according to Embodiments 1 to 3 will be described. Figure 13 is a diagram showing an example of the hardware configuration for realizing the control devices 2A, 2B, and 2C according to Embodiments 1 to 3. The control devices 2A, 2B, and 2C are realized by a computer system comprising a processing circuit 20, an input unit 21, a display unit 24, and an output unit 25. The processing circuit 20 comprises a processor 22 and a memory 23. The processing circuit 20 is a circuit in which the processor 22 executes software.

[0107] The functions of the preprocessing unit 12, thermal displacement estimation unit 13, correction amount generation unit 14, control unit 15, and learning unit 17, which are processing units of control devices 2A, 2B, and 2C, as well as the function of the determination unit 19, which is a processing unit of control device 2C, are realized by software, firmware, or a combination of software and firmware. The software or firmware is written as a program and stored in memory 23.

[0108] The processing circuit 20 implements the processing units of the control devices 2A, 2B, and 2C by having the processor 22 read and execute a program stored in the memory 23. In other words, the processing circuit 20 includes a memory 23 for storing a program that will ultimately result in the execution of the processing of the control devices 2A, 2B, and 2C. The program stored in the memory 23 is a program that causes the computer to execute the procedures and methods of processing of the control devices 2A, 2B, and 2C.

[0109] The functions of the recording unit 11 and model holding unit 18 of the control devices 2A, 2B, and 2C are realized by using the memory 23. The memory 23 is also used as temporary memory when the processor 22 performs various processes. The input unit 21 is an interface circuit that receives data from outside the control devices 2A, 2B, and 2C and provides it to the processor 22. The functions of the acquisition unit 10 of the control devices 2A, 2B, and 2C are realized by using the input unit 21. The output unit 25 is an interface circuit that sends data from the processor 22 or the memory 23 to the outside of the control devices 2A, 2B, and 2C.

[0110] The processor 22 is a CPU (Central Processing Unit). The processor 22 may also be a central processing unit, processing unit, arithmetic unit, microprocessor, microcomputer, processor, or DSP (Digital Signal Processor). The memory 23 may be, for example, a non-volatile or volatile semiconductor memory such as RAM (Random Access Memory), ROM (Read Only Memory), flash memory, EPROM (Erasable Programmable Read Only Memory), EEPROM® (Electrically Erasable Programmable Read Only Memory), magnetic disk, flexible disk, optical disk, compact disk, minidisc, or DVD (Digital Versatile Disc).

[0111] The display unit 24 is a display that shows information. The display unit 24 is, for example, an LCD or an organic EL display. The functions of the display unit 16 of the control devices 2A, 2B, and 2C are realized by using the display unit 24, which is a display.

[0112] Next, the hardware configuration for realizing the server device 6 according to Embodiment 4 will be described. Figure 14 is a diagram showing an example of the hardware configuration for realizing the server device 6 according to Embodiment 4. The server device 6 is realized by a computer system comprising a processing circuit 20, an input unit 21, and an output unit 25. In other words, the server device 6 corresponds to the same hardware configuration as the hardware configuration shown in Figure 13, but with the display unit 24 removed. The control device 2D according to Embodiment 4 is realized using the same hardware configuration as the hardware configuration shown in Figure 14.

[0113] The processing circuits 20 of each of the control devices 2A, 2B, 2C and the server device 6 may be dedicated circuits. Dedicated circuits include single circuits, composite circuits, programmed processors, parallel programmed processors, ASICs (Application Specific Integrated Circuits), FPGAs (Field Programmable Gate Arrays), or circuits combining these.

[0114] In embodiments 1 to 4, the industrial equipment is assumed to be a machine tool 3. In embodiments 1 to 4, the industrial equipment may be equipment other than the machine tool 3, for example, a robot. The robot is equipped with an arm, which is a movable part that can be moved by a drive mechanism. When the information processing device according to embodiments 1 to 4 is applied to the robot, the information processing device estimates the amount of thermal displacement of the robot and corrects the position of the arm. The information processing device can easily estimate the amount of thermal displacement when the heat-generating part of the robot moves, similar to the case of the machine tool 3.

[0115] The configurations shown in each of the embodiments described above are examples of the content of this disclosure. The configurations of each embodiment can be combined with other known technologies. The configurations of each embodiment may be combined with each other as appropriate. It is possible to omit or modify parts of the configurations of each embodiment without departing from the gist of this disclosure.

[0116] 1A, 1B, 1C, 1D Industrial systems, 2A, 2B, 2C, 2D Control devices, 3 Machine tools, 4 Thermal image sensors, 5 Temperature sensors, 6 Server devices, 7 Display devices, 10 Acquisition unit, 11 Recording unit, 12 Preprocessing unit, 13 Thermal displacement estimation unit, 14 Correction amount generation unit, 15 Control unit, 16, 24 Display units, 17 Learning unit, 18 Model holding unit, 19 Judgment unit, 20 Processing circuit, 21 Input unit, 22 Processor, 23 Memory, 25 Output unit, 30 Bed, 31 Column, 32 Table, 33 Head, 34 Spindle, 35 Workpiece, 36 Tool, 37X X-axis drive system, 37Y Y-axis drive system, 37Z Z-axis drive system, L1, L2 Lines.

Claims

An acquisition unit that acquires a thermal image showing the temperature distribution of industrial equipment having movable parts that can be moved by a drive mechanism, A preprocessing unit that changes the pixels from which temperature data is extracted among the plurality of pixels constituting the thermal image based on the position of the movable part when the thermal image was taken, The system includes a thermal displacement estimation unit that estimates the amount of thermal displacement of the industrial equipment based on the extracted temperature data. An information processing device characterized by the following features. 　 The system includes a recording unit on which the thermal image acquired by the acquisition unit is recorded, The thermal image read from the recording unit is output. The information processing apparatus according to claim 1, characterized in that 　 The recording unit records two or more of the thermal images acquired at different times. The recording unit outputs two or more of the thermal images read from the recording unit. The information processing apparatus according to claim 2, characterized in that 　 The recording unit records the compressed data obtained by the compression encoding of the thermal image. The information processing apparatus according to claim 2 or 3, characterized in that 　 The system includes a determination unit that determines whether or not there is an abnormality in the industrial equipment based on the temperature data extracted from the thermal image, The determination result from the determination unit is output. An information processing apparatus according to any one of claims 1 to 4, characterized in that 　 The acquisition unit acquires the thermal image when the speed at which the movable part moves is less than or equal to the set speed. An information processing apparatus according to any one of claims 1 to 5, characterized in that 　 The thermal displacement estimation unit estimates the thermal displacement of the industrial equipment by inputting the temperature data into a model that has learned the relationship between the temperature of the industrial equipment and the thermal displacement of the industrial equipment. An information processing apparatus according to any one of claims 1 to 6, characterized in that 　 The preprocessing unit corrects the temperature data shown in the thermal image based on the temperature measurement results from the temperature sensor installed in the industrial equipment. An information processing apparatus according to any one of claims 1 to 7, characterized in that 　 A machine tool having a drive mechanism and a movable part that can be moved by the drive mechanism, A thermal image sensor that captures a thermal image showing the temperature distribution of the machine tool, The system comprises an information processing device for processing information shown in the thermal image, The aforementioned information processing device is The acquisition unit acquires the aforementioned thermal image, A preprocessing unit that changes the pixels from which temperature data is extracted among the multiple pixels constituting the acquired thermal image based on the position of the movable part when the thermal image was taken, It includes a thermal displacement estimation unit that estimates the amount of thermal displacement of the machine tool based on the extracted temperature data. An industrial system characterized by the following features. 　 A method for controlling a machine tool having a drive mechanism and a movable part that can be moved by the drive mechanism, using a computer system, The steps include: acquiring a thermal image showing the temperature distribution of the machine tool; The steps include changing the pixels from which temperature data is extracted among the multiple pixels constituting the acquired thermal image based on the position of the movable part when the thermal image was taken, A step of estimating the amount of thermal displacement of the machine tool based on the extracted temperature data, A step of calculating a correction amount for the position of the movable part based on the estimated amount of thermal displacement, The step of controlling the machine tool based on a command that reflects the calculated correction amount, is included. A method for controlling a machine tool, characterized by the features described herein.

Images