Machine tool support device

Abstract

To provide a machine tool support device capable of improving an accuracy of an estimation result of machine learning.SOLUTION: A machine tool support device 2 comprises: a specification acquisition unit 42 for acquiring a sort of tool T used and a machining condition applied when data is detected by a sensor installed in a machine tool 1; a model storage unit 44 for storing a plurality of learned models generated for each classification classified according to at least the sort of tool T and the machining condition acquired by the specification acquisition unit 42; a model selection unit 45 that selects a learned model corresponding to the classification classified according to the sort of tool T and the machining condition acquired by the specification acquisition unit 42 from the plurality of learned models stored in the model storage unit 44 in an estimation phase; and an output unit 46 that outputs an estimated machining situation by the machine tool 1 based on the selected learned model and the data acquired by the data acquisition unit 41 in the estimation phase.SELECTED DRAWING: Figure 4

Description

[Technical field]

[0001] The present invention relates to a machine tool support device. [Background technology]

[0002] Patent documents 1 to 3 describe the use of machine learning to estimate the machining quality of workpieces and abnormality judgment of tools in machine tools. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-138279 A [Patent Document 2] JP 2019-067137 A [Patent Document 3] JP 2020-023040 A Summary of the Invention [Problem to be solved by the invention]

[0004] In order to obtain highly accurate estimation results of machining quality and tool abnormalities using machine learning, it is necessary to generate a different trained model for each type of tool and estimate the machining quality and tool abnormalities using the trained model corresponding to the type of tool used.

[0005] However, it was found that simply generating a trained model for each type of tool can result in errors in the estimation accuracy of the output estimation results. For example, even with the same tool or the same workpiece, the distribution and trends of data obtained during machining can change if the machining conditions or machining materials are different. For these reasons, it is believed that errors in the estimation accuracy can occur.

[0006] The present invention aims to provide a machine tool support device that can improve the accuracy of machine learning estimation results. [Means for solving the problem]

[0007] One aspect of the present invention is a data acquisition unit that acquires data detected by a sensor installed in the machine tool; a specification acquisition unit that acquires the type of tool used and the machining conditions applied when the data is detected by the sensor; a model storage unit that stores a plurality of trained models generated for each classification based on at least the type of tool and the machining conditions acquired by the specification acquisition unit, the trained models being machine learning trained models that use the data detected by the sensor as explanatory variables and the machining status of the machine tool as a target variable; and a model selection unit that selects, from the plurality of trained models stored in the model storage unit, a trained model corresponding to a classification based on the type of tool and the machining conditions acquired by the specification acquisition unit in an estimation phase; and an output unit that outputs an estimated machining status of the machine tool based on the selected trained model and the data acquired by the data acquisition unit in the estimation phase; The machining status is a degree of wear of the tool or the presence or absence of an abnormality of the tool, the model selection unit, in the estimation phase, when there is no trained model corresponding to a classification based on the tool type and the machining conditions acquired by the specification acquisition unit among the plurality of trained models stored in the model storage unit, selects a similar trained model; the output unit outputs an estimated value of a wear degree of the tool based on the selected similar trained model and the data acquired by the data acquisition unit in the estimation phase; The similar trained model is a trained model in a machine tool support device that is the same except for one item of the tool type or the machining conditions, and that corresponds to the closest specification for that one item. Another aspect of the present invention is a data acquisition unit that acquires data detected by a sensor installed in the machine tool; a specification acquisition unit that acquires the type of tool used and the machining conditions applied when the data is detected by the sensor; a model storage unit that stores a plurality of trained models generated for each classification based on at least the type of tool and the machining conditions acquired by the specification acquisition unit, the trained models being machine learning trained models that use the data detected by the sensor as explanatory variables and the machining status of the machine tool as a target variable; and a model selection unit that selects, from the plurality of trained models stored in the model storage unit, a trained model corresponding to a classification based on the type of tool and the machining conditions acquired by the specification acquisition unit in an estimation phase; and an output unit that outputs an estimated machining status of the machine tool based on the selected trained model and the data acquired by the data acquisition unit in the estimation phase; The machining status is a degree of wear of the tool or the presence or absence of an abnormality of the tool, the model selection unit, in the estimation phase, when there is no trained model among the plurality of trained models stored in the model storage unit that corresponds to a classification based on the tool type and the machining conditions acquired by the specification acquisition unit, does not select the trained model; The output unit is in a machine tool support device that, when the trained model is not selected by the model selection unit, outputs whether or not the tool has reached the end of its life without using the trained model, depending on whether or not the number of workpieces machined by the tool has reached a predetermined number.

[0008] According to the above machine tool support device, the multiple trained models stored in the model memory unit are generated for each classification classified according to the type of tool and the machining conditions. Then, in the estimation phase, the model selection unit selects a trained model corresponding to the classification classified according to the type of tool and the machining conditions acquired by the specification acquisition unit, and the output unit outputs an estimated machining status of the machine tool based on the selected trained model. In this way, the trained model used in the estimation phase is a model that takes into account not only the type of tool but also the machining conditions. Therefore, the estimated machining status output by the output unit has a higher accuracy. [Brief description of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing an entire system including a machine tool and a machine tool support device. [Diagram 2] FIG. 1 is a diagram showing an example of machining by a machine tool. [Diagram 3] 1 is a flowchart showing an example of a machining method using a machine tool. [Figure 4] FIG. 2 is a functional block diagram of the machine tool support device. [Diagram 5] A diagram showing the relationship between specifications acquired by a specification acquisition unit and a trained model. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010] (1. Overview of machine tool support equipment) The machine tool support device is a device that estimates the machining status of the machine tool by using machine learning based on data detected by a sensor installed in the machine tool. The estimated machining status includes the machining quality of the workpiece machined by the machine tool, the presence or absence of a machine tool malfunction, the deterioration state of the machine tool, the amount of thermal displacement of the machine tool, etc.

[0011] The machining quality of a workpiece includes the shape accuracy of the workpiece, the dimensional accuracy of the workpiece, the surface properties of the workpiece, the presence or absence of a machine-degraded layer on the workpiece, the presence or absence of scratches on the surface of the workpiece, etc. The presence or absence of a malfunction of the machine tool and the deterioration state of the machine tool include the presence or absence of a malfunction and the deterioration state of the parts that make up the machine tool. The presence or absence of a malfunction and the deterioration state of the parts include, for example, the presence or absence of an abnormality due to breakage or chipping of the tool (corresponding to the presence or absence of a malfunction), the degree of wear due to wear or the like of the tool (corresponding to the deterioration state), the deterioration state of the bearings, etc. The amount of thermal displacement of the machine tool includes the amount of deviation in the relative position between the tool and the workpiece due to the thermal displacement of the components of the machine tool, the amount of thermal displacement of each component of the machine tool alone, etc.

[0012] In addition, many trained models for machine learning are available. Specifically, in the learning phase of machine learning, a trained model is generated for each classification classified according to the type of tool used in machining, the applied machining conditions, the type of workpiece to be machined, etc. In addition, in the estimation phase of machine learning, a trained model corresponding to the type of tool, the machining conditions, the type of workpiece, etc. is selected, and an estimated machining status is output using the selected trained model.

[0013] In particular, the machine tool is suitable for constituting one of a production line made up of a plurality of machine tools. The production line can produce a plurality of types of workpieces or can produce workpieces by a plurality of processing types. In other words, the production line can perform a variety of processing. The machine tool can produce workpieces by a plurality of tools or a plurality of processing conditions corresponding to a plurality of types of workpieces or a plurality of processing types. In other words, each machine tool constituting the production line is capable of performing a plurality of types of processing. Here, the plurality of types of processing includes processing by different tools, processing by the same tool under different processing conditions, processing by different tools under different processing conditions, etc.

[0014] (2. Configuration of Support System 100) A support system 100 including a machine tool 1 and a machine tool support device 2 (hereinafter referred to as the "support device") will be described with reference to Fig. 1. For ease of explanation, only one machine tool 1 is shown in Fig. 1, but as described above, it is suitable for application to a production line made up of a plurality of machine tools 1.

[0015] The machine tool 1 is a machine that processes a workpiece W, and performs various processes such as cutting, grinding, etc. In this example, the machine tool 1 is a machining center that performs cutting, as shown in Fig. 1.

[0016] The machine tool 1 shown in FIG. 1 is a device that processes a workpiece W by moving the tool T relative to the workpiece W. The machine tool 1 is configured to be tool replaceable, and is capable of processing according to the attached tool T. For example, the replaceable tool T may be a cutting tool such as an end mill, a milling tool, a drill, a turning tool, a threading tool, a tooth profile generating tool, or a grinding tool. Note that a tool exchange device and a tool magazine that stores the tool T are not shown in FIG. 1. In this example, the machine tool 1 is basically configured as a horizontal machining center. However, the machine tool 1 may be configured in other ways, such as a vertical machining center.

[0017] As shown in FIG. 1, the machine tool 1 has, for example, three mutually orthogonal linear axes (X-axis, Y-axis, and Z-axis) as drive axes. Here, the direction of the rotation axis of the tool T (equal to the rotation axis of the tool spindle) is defined as the Z-axis direction, and two axes perpendicular to the Z-axis direction are defined as the X-axis direction and the Y-axis direction. In FIG. 1, the horizontal direction is the X-axis direction, and the vertical direction is the Y-axis direction. Furthermore, the machine tool 1 further has, as drive axes, two rotation axes (A-axis and B-axis) for changing the relative attitude of the tool T and the workpiece W. The machine tool 1 also has a Ct axis as a rotation axis for rotating the tool T.

[0018] That is, machine tool 1 is a 5-axis machine (a 6-axis machine when the tool spindle (Ct-axis) is taken into consideration) capable of machining free-form surfaces. Here, machine tool 1 may be configured to have a Cw-axis (a rotation axis about the Z-axis in the reference state) and a B-axis, or may be configured to have an A-axis and a Cw-axis, instead of an A-axis (a rotation axis about the X-axis in the reference state) and a B-axis (a rotation axis about the Y-axis in the reference state).

[0019] In the machine tool 1, the configuration for relatively moving the tool T and the workpiece W can be appropriately selected. In this example, the machine tool 1 allows the tool T to move linearly in the Y-axis and Z-axis directions, allows the workpiece W to move linearly in the X-axis direction, and further allows the workpiece W to rotate about the A-axis and B-axis. In addition, the tool T can rotate about the Ct axis.

[0020] The machine tool 1 includes a bed 10, a workpiece holding device 20, and a tool holding device 30. The bed 10 is formed in any shape, such as a substantially rectangular shape, and is placed on the floor surface. The workpiece holding device 20 enables the workpiece W to move linearly in the X-axis direction relative to the bed 10 and to rotate about the A-axis and B-axis. The workpiece holding device 20 mainly includes an X-axis moving table 21, a B-axis rotating table 22, and a workpiece spindle device 23.

[0021] The X-axis moving table 21 is provided so as to be movable in the X-axis direction relative to the bed 10. Specifically, a pair of X-axis guide rails extending in the X-axis direction (front-rear direction in FIG. 1) are provided on the bed 10, and the X-axis moving table 21 is driven by a driving device such as a linear motor or a ball screw mechanism (not shown) to reciprocate in the X-axis direction while being guided by the pair of X-axis guide rails.

[0022] The B-axis rotating table 22 is placed on the upper surface of the X-axis moving table 21, and moves back and forth in the X-axis direction integrally with the X-axis moving table 21. The B-axis rotating table 22 is provided so as to be rotatable about the B axis relative to the X-axis moving table 21. A rotary motor (not shown) is housed in the B-axis rotating table 22, and the B-axis rotating table 22 is rotatable about the B axis by being driven by the rotary motor.

[0023] The workpiece spindle device 23 is mounted on the B-axis rotating table 22 and rotates about the B-axis integrally with the B-axis rotating table 22. The workpiece spindle device 23 supports the workpiece W so that it can rotate about the A-axis. The workpiece spindle device 23 is equipped with a rotary motor (not shown) that rotates the workpiece W. In this manner, the workpiece holding device 20 enables the workpiece W to move in the X-axis direction relative to the bed 10 and to rotate about the A-axis and B-axis.

[0024] The tool holding device 30 mainly includes a column 31, a saddle 32, and a tool spindle device 33. The column 31 is provided so as to be movable in the Z-axis direction relative to the bed 10. Specifically, the bed 10 is provided with a pair of Z-axis guide rails extending in the Z-axis direction (left-right direction in FIG. 1), and the column 31 is driven by a driving device such as a linear motor or a ball screw mechanism (not shown) to reciprocate in the Z-axis direction while being guided by the pair of Z-axis guide rails.

[0025] The saddle 32 is disposed on the side surface of the column 31 facing the workpiece W (the left side surface in FIG. 1), which is parallel to a plane perpendicular to the Z-axis direction. A pair of Y-axis guide rails extending in the Y-axis direction (the up-down direction in FIG. 1) are provided on the side surface of the column 31, and the saddle 32 reciprocates in the Y-axis direction by being driven by a driving device such as a linear motor or a ball screw mechanism (not shown).

[0026] The tool spindle device 33 is mounted on the saddle 32 and moves in the Y-axis direction together with the saddle 32. The tool spindle device 33 supports the tool T so that it can rotate about the Ct axis. The tool spindle device 33 is equipped with a rotation motor (not shown) that rotates the tool T. In this way, the tool holding device 30 holds the tool T so that it can move in the Y-axis and Z-axis directions relative to the bed 10 and can rotate about the Ct axis.

[0027] The support device 2 is connected to a sensor installed in the machine tool 1, acquires data detected by the sensor, and uses machine learning to estimate the machining status of the machine tool 1, such as the machining quality of the workpiece W, the presence or absence of an abnormality (breakdown) in the tool T, the degree of wear of the tool T, the amount of thermal displacement of the machine tool 1, etc.

[0028] (3. Examples of processing methods) To facilitate the explanation of the support device 2, an example of a machining method by the machine tool 1 will be explained with reference to Figs. 2 and 3. The example of the machining method is hole-making using a drill, as shown in Fig. 2. That is, this machining method is a case where a drill is used as the tool T of the machine tool 1 to perform hole-making (cutting) on ​​a workpiece W. However, the target machining method by the support device 2 is not limited to hole-making, and can be applied to other machining methods.

[0029] In this example, the feed rate is changed during drilling. In Fig. 2, in a range A at the beginning of machining, the feed rate of the tool T is a first speed Va, in a range B at the middle of machining, the feed rate of the tool T is a second speed Vb, and in a range C at the end of machining, the feed rate of the tool T is a third speed Vc. Here, the first speed Va and the third speed Vc are the same, and the second speed Vb is faster than the first speed Va and the third speed Vc. In other words, machining is performed slowly immediately after the start of machining, and high-speed machining is performed after stabilization, and the speed is slowed down before approaching the machining end depth.

[0030] More specifically, as shown in Fig. 3, first, the tool T is moved close to the workpiece W by a fast forward operation, and the tool T is moved to a drilling position on the workpiece W (S1). Next, while moving the tool T at a first speed Va, drilling is performed on the workpiece W (S2). The range of drilling at this time is the initial processing range A in Fig. 2.

[0031] Next, immediately after the tool T is temporarily stopped, the tool T is moved at a second speed Vb faster than the first speed Va while drilling the workpiece W further (S3). The range of the drilling at this time is the range B of the middle stage of machining in FIG. 2. Next, the tool T is changed to a third speed Vc slower than the second speed Vb, and the workpiece W is drilled further (S4). The range of the drilling at this time is the range C of the final stage of machining in FIG. 2. Next, the tool T is moved out of the machined hole (S5), and the tool T is moved away from the workpiece W by a fast forward motion (S6).

[0032] (4. Configuration of Support Device 2) The configuration of the support device 2 will be described with reference to Figures 4 and 5. The support device 2 estimates the machining status of the machine tool 1, such as the machining quality of the workpiece W, the presence or absence of an abnormality (breakdown) of the tool T, the degree of wear of the tool T, the amount of thermal displacement of the machine tool 1, and the like, through machine learning using data detected by a sensor installed in the machine tool 1.

[0033] The support device 2 is configured to include a processor, a storage device, an interface, etc. As shown in FIG 4, the support device 2 includes a data acquisition unit 41, a specification acquisition unit 42, a model generation unit 43, a model storage unit 44, a model selection unit 45, and an output unit 46.

[0034] The data acquiring unit 41 acquires data detected by a sensor installed in the machine tool 1. The data acquiring unit 41 acquires, for example, time-series data of the load of the operation of the machine tool 1. The load generated on the machine tool 1 can be, for example, a force detected by a force sensor installed in the tool spindle device 33, a current value of a current sensor installed in a motor in the tool spindle device 33, a magnitude of vibration detected by a vibration sensor installed in the tool spindle device 33, or the like. The load can also be the magnitude of vibration detected by a vibration sensor installed in a member supporting the workpiece W, or a force detected by a force sensor installed in the member.

[0035] Furthermore, the data acquiring unit 41 may acquire control position data of each moving body indicating the relative position of the tool T with respect to the workpiece W, in addition to the time-series data of the load acting on the machine tool 1. Furthermore, the data acquiring unit 41 may acquire data such as shape information and surface property information of the workpiece W during machining.

[0036] When data is detected by the sensor, the specification acquisition unit 42 acquires specification information including the type of tool T used, the applied machining conditions, and the type of workpiece W. The types of tool T include cutting tools such as end mills, milling tools, drills, turning tools, thread cutting tools, and tooth profile generating tools, and grinding tools such as cylindrical grindstones, formed grindstones, and thread cutting grindstones. Furthermore, the types of tool T may be classified according to the material of tool T, the shape of tool T, and the like.

[0037] The processing conditions include cutting speed, feed rate, cutting depth, etc. in cutting, and include grinding speed, feed rate, cutting depth, etc. in grinding. The processing conditions may be classified according to information such as the presence or absence of a vibration prevention device and the configuration of a device that supports the workpiece W. The type of workpiece W is classified according to information such as the material of the workpiece W, the presence or absence of heat treatment, and the type of heat treatment.

[0038] As a learning phase of machine learning, the model generation unit 43 generates a trained model for each classification classified according to the type of tool T, the machining conditions, and the type of workpiece W. The trained model is a machine learning model that uses the data acquired by the data acquisition unit 41 as explanatory variables and the machining status of the machine tool 1 as a target variable. The classification corresponding to the trained model is classified according to the type of tool T, the machining conditions, and the type of workpiece W acquired by the specification acquisition unit 42.

[0039] The relationship between the classification according to the type of tool T, the machining conditions, and the type of workpiece W acquired by the specification acquisition unit 42 and the learned models is as shown in Fig. 5. For example, there are T1 and T2 as the types of tool T, C1 and C2 as the machining conditions, and W1 and W2 as the types of workpiece W. In this case, for example, the learned model corresponding to the classification of the type of tool T, T1, the machining condition C1, and the type of workpiece W, W1, is M1. In this way, for example, eight types of learned models M1-M8 are generated according to the type of tool T, the machining conditions, and the type of workpiece W.

[0040] For example, in the drilling process shown in Fig. 2, the tool T1 is a drill tool, and the machining conditions C1 are classified separately into conditions for drilling at a first speed Va and a third speed Vc in ranges A and C, and conditions for drilling at a second speed Vb in range B. The type of workpiece W is the same. In this example, a trained model M1 corresponding to the drilling process in ranges A and C, and a trained model M2 corresponding to the drilling process in range B are generated.

[0041] For example, the trained model M1 is generated by the data acquisition unit 41 through machine learning using data from drilling in the ranges A and C as a training data set. In this case, the trained model M1 is a model that can output the machining status of the machine tool 1, such as the machining quality of the workpiece W, the presence or absence of an abnormality in the tool T, and the degree of wear of the tool T, when the data from drilling in the ranges A and C is used as input data. The other trained models M2-M8 are generated by the same process, with only different training data sets. In this way, the trained models M1-M8 are generated for each classification classified not only by the type of tool T but also by the machining conditions and the type of workpiece W.

[0042] The model storage unit 44 stores the multiple trained models M1-M8 generated by the model generation unit 43. Furthermore, the model storage unit 44 stores the multiple trained models M1-M8 in association with classifications of the corresponding attributes.

[0043] In the estimation phase of machine learning, the model selection unit 45 selects a trained model corresponding to a classification based on the type of tool T, machining conditions, and type of workpiece W acquired by the specification acquisition unit 42, from among a plurality of trained models M1-M8 stored in the model storage unit 44. For example, as shown in Fig. 5, in the case of type T1 of tool T, machining conditions C2, and type W2 of workpiece W, trained model M4 is selected.

[0044] Here, in the estimation phase of machine learning, there may be no trained model among the multiple trained models M1-M8 stored in the model memory unit 44 that corresponds to the classification based on the type of tool T, machining conditions, and type of workpiece W acquired by the specification acquisition unit 42.

[0045] In this case, the model selection unit 45 can take the following two measures. The first measure is to select a similar trained model. For example, when the type of tool T and the type of workpiece W are the same, but the feed rates among the machining conditions are different, a trained model corresponding to the specifications with the closest feed rate is selected.

[0046] The second method is to not select a trained model. If the trained model is different, the estimated processing status to be output will change. In other words, the selection of a trained model has a significant impact on the estimated processing status to be output. Therefore, a trained model is not selected and no output is obtained by machine learning. However, even if it is once decided not to select a trained model, by accumulating the information and performing training again, the next time the same specifications appear, a newly generated trained model will be selected.

[0047] In the estimation phase of machine learning, the output unit 46 outputs an estimated machining status by the machine tool 1 based on the trained model selected by the model selection unit 45 and the data acquired by the data acquisition unit 41. That is, the output unit 46 uses the selected trained model and the data acquired by the data acquisition unit 41 as input data to output the estimated machining status. Note that the input data does not need to be the data acquired by the data acquisition unit 41 itself, and a feature extracted from the data may be used.

[0048] For example, the output unit 46 outputs, as the estimated machining status, estimated values ​​such as the machining quality of the workpiece W, the presence or absence of an abnormality in the tool T, and the degree of wear of the tool T. Here, as described above, when there is no trained model corresponding to the classification of the specifications acquired by the specification acquisition unit 42, if the model selection unit 45 selects a similar trained model, the output unit 46 outputs the estimated machining status using the similar trained model.

[0049] On the other hand, when the model selection unit 45 does not select a trained model, the output unit 46 may output the machining status by other means without using the trained model. For example, when outputting the wear degree of the tool T as the machining status, the output unit 46 outputs whether the life of the tool T has been reached depending on whether the number of times the tool T has processed the workpiece W has reached a predetermined number. In this way, when machine learning cannot be used, it is selected to output the estimated machining status by other means without relying on machine learning.

[0050] (5. Effects) According to the above-mentioned support device 2, the multiple trained models M1-M8 stored in the model storage unit 44 are generated for each classification classified according to the type of tool T, machining conditions, type of workpiece W, etc. Then, in the estimation phase, the model selection unit 45 selects a trained model corresponding to the classification classified according to the type of tool T, machining conditions, and type of workpiece W acquired by the specification acquisition unit 42, and the output unit 46 outputs an estimated machining status of the machine tool 1 based on the selected trained model. In this way, the trained model used in the estimation phase is a model that takes into account not only the type of tool T but also the machining conditions, type of workpiece W, etc. Therefore, the estimated machining status output by the output unit 46 has a higher accuracy. [Explanation of symbols]

[0051] 1: machine tool, 2: machine tool support device, 10: bed, 20: workpiece holding device, 30: tool holding device, 41: data acquisition unit, 42: specification acquisition unit, 43: model generation unit, 44: model storage unit, 45: model selection unit, 46: output unit, 100: support system, M1-M8: trained model, T: tool, W: workpiece

Claims

1. a data acquisition unit that acquires data detected by a sensor installed in the machine tool; a specification acquisition unit that acquires the type of tool used and the machining conditions applied when the data is detected by the sensor; a model storage unit that stores a plurality of trained models generated for each classification based on at least the type of tool and the machining conditions acquired by the specification acquisition unit, the trained models being machine learning trained models that use the data detected by the sensor as explanatory variables and the machining status of the machine tool as a target variable; and a model selection unit that selects, from the plurality of trained models stored in the model storage unit, a trained model corresponding to a classification based on the type of tool and the machining conditions acquired by the specification acquisition unit in an estimation phase; and an output unit that outputs an estimated machining status of the machine tool based on the selected trained model and the data acquired by the data acquisition unit in the estimation phase; The machining status is a degree of wear of the tool or the presence or absence of an abnormality of the tool, the model selection unit, in the estimation phase, when there is no trained model corresponding to a classification based on the tool type and the machining conditions acquired by the specification acquisition unit among the plurality of trained models stored in the model storage unit, selects a similar trained model; the output unit outputs an estimated value of a wear degree of the tool based on the selected similar trained model and the data acquired by the data acquisition unit in the estimation phase; A machine tool support device, wherein the similar learned model is a learned model that is the same except for one item of the tool type or the machining conditions, and the one item corresponds to the closest specification.

2. a data acquisition unit that acquires data detected by a sensor installed in the machine tool; a specification acquisition unit that acquires the type of tool used and the machining conditions applied when the data is detected by the sensor; a model storage unit that stores a plurality of trained models generated for each classification based on at least the type of tool and the machining conditions acquired by the specification acquisition unit, the trained models being machine learning trained models that use the data detected by the sensor as explanatory variables and the machining status of the machine tool as a target variable; and a model selection unit that selects, from the plurality of trained models stored in the model storage unit, a trained model corresponding to a classification based on the type of tool and the machining conditions acquired by the specification acquisition unit in an estimation phase; and an output unit that outputs an estimated machining status of the machine tool based on the selected trained model and the data acquired by the data acquisition unit in the estimation phase; The machining status is a degree of wear of the tool or the presence or absence of an abnormality of the tool, the model selection unit, in the estimation phase, when there is no trained model among the plurality of trained models stored in the model storage unit that corresponds to a classification based on the tool type and the machining conditions acquired by the specification acquisition unit, does not select the trained model; The output unit, when the trained model is not selected by the model selection unit, outputs whether or not the tool has reached the end of its life without using the trained model, depending on whether or not the number of workpieces machined by the tool has reached a predetermined number. This is a machine tool support device.

3. the tool is a cutting tool, The machine tool support device according to claim 1 or 2, wherein the machining conditions include at least one of a cutting speed and a feed rate.

4. The specification acquisition unit further includes information about the type of workpiece to be machined when the data is detected by the sensor, the model storage unit stores the plurality of trained models generated for each classification classified by at least the type of the tool, the machining conditions, and the type of the workpiece acquired by the specification acquisition unit; A machine tool support device as described in any one of claims 1 to 3, wherein the model selection unit selects, in the estimation phase, from the plurality of trained models stored in the model memory unit, the trained model corresponding to a classification classified by the type of tool, the machining conditions, and the type of workpiece acquired by the specification acquisition unit.

5. The machine tool constitutes one of a production line made up of a plurality of the machine tools, The production line is capable of producing a plurality of types of workpieces or producing workpieces by a plurality of types of processing, 5. The machine tool support device according to claim 1, wherein the machine tool produces a plurality of types of workpieces or a plurality of types of machining conditions corresponding to a plurality of types of workpieces or a plurality of types of machining operations.

Images