Information processing device, information processing method, and information processing program

Abstract

To obtain an information processing device, an information processing method, and an information processing program capable of obtaining machined objects having excellent quality.SOLUTION: An information processing device 10 includes at least one processor. The processor acquires a state variable at a first time point being a dynamic state variable regarding an element correlated to quality of a machined object having been machined according to a set machining condition and a machining condition at the first time point, predicts a state variable at a second time point after the first time point on the basis of the state variable and the machining condition at the first time point, and derives a machining condition at the second time point required for achieving a previously determined target quality of the machined objects on the basis of the predicted state variable at the second time point.SELECTED DRAWING: Figure 5

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, there is known a technique for improving the quality of a workpiece by optimizing the machining conditions of the workpiece. For example, Patent Document 1 discloses a technique for determining command data for a machine tool from status data at a certain point in time using a trained machine learning model trained from status data related to the machine tool and accuracy data of the workpiece. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Patent Publication No. 2021-057030 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the state of tools and the like used to process workpieces may change dynamically. Since changes in the state of tools and the like can affect the quality of the workpieces, there is a demand for technology that can further improve the quality of workpieces by taking into account the dynamically changing state of tools and the like.

[0005] The present disclosure provides an information processing device, an information processing method, and an information processing program that can obtain a workpiece of good quality. [Means for solving the problem]

[0006] A first aspect of the present disclosure is an information processing device comprising at least one processor, wherein the processor acquires dynamic state variables relating to elements correlated with the quality of a workpiece processed according to set processing conditions, the state variables at a first point in time and the processing conditions at the first point in time, predicts state variables at a second point in time after the first point in time based on the state variables and processing conditions at the first point in time, and derives processing conditions at the second point in time required to achieve a predetermined target quality of the workpiece based on the predicted state variables at the second point in time.

[0007] In the first aspect, the processor may predict the state variables at the second time point using a trained model trained to take the state variables and processing conditions at the first time point as inputs and the state variables at the second time point as outputs.

[0008] In the first aspect, the processor may predict the quality of the workpiece at a second time point based on the state variables and processing conditions at a first time point, and derive processing conditions that minimize an evaluation value calculated based on the difference between the predicted quality of the workpiece at the second time point and the target quality.

[0009] In the first aspect above, the processor may predict the quality of the workpiece at a second time point using a trained model trained to take state variables and processing conditions at a first time point as inputs and the quality of the workpiece at a second time point as output.

[0010] In the first aspect, the second point in time may be a point in time after a predetermined amount of processing has been performed on the workpiece at the first point in time.

[0011] In the first aspect, the second point in time may be a point in time when a predetermined period has elapsed since the first point in time.

[0012] In the above-mentioned first aspect, the processor may acquire state variables at a second time point and processing conditions at the second time point, predict state variables at a third time point after the second time point based on the state variables and processing conditions at the second time point, and derive processing conditions at the third time point required to achieve a target quality based on the predicted state variables at the third time point.

[0013] In the first aspect, the processor may perform control to process the workpiece in accordance with the derived processing conditions.

[0014] In the first aspect, the workpiece may be substantially cylindrical and may be machined while rotating.

[0015] In the first aspect, the workpiece may be substantially cylindrical, and the tool used to machine the workpiece may machine the workpiece while rotating.

[0016] In the first aspect, the workpiece is a blade, and the processing of the workpiece is a grinding process in which the blade is ground using a grinding wheel, and the processing conditions may include at least one of the rotation speed of the grinding wheel, the cutting depth, the cutting time, the cutting speed and the number of cuttings, the rotation speed of the support that supports the blade, and the relative speed between the grinding wheel and the support.

[0017] In the first aspect, the workpiece is a blade, and the processing of the workpiece is a grinding process in which the blade is ground using a grinding wheel, and the state variables may include at least one of a drive motor load of the grinding wheel, a drive motor load of a support that supports the blade, axial vibration and axial acoustic emission of the support, and a grinding fluid temperature.

[0018] In the first aspect, the workpiece is a blade, the processing of the workpiece is a grinding process in which the blade is ground using a grinding wheel, and the quality of the workpiece may include at least one of the size and number of chippings on the cutting edge of the blade, the cutting edge radius, and the surface roughness.

[0019] A second aspect of the present disclosure is an information processing method that includes a process of acquiring dynamic state variables related to elements correlated with the quality of a workpiece processed according to set processing conditions, the state variables at a first point in time and the processing conditions at the first point in time, predicting the state variables at a second point in time after the first point in time based on the state variables and processing conditions at the first point in time, and deriving the processing conditions at the second point in time required to achieve a predetermined target quality of the workpiece based on the predicted state variables at the second point in time.

[0020] A third aspect of the present disclosure is an information processing program that causes a computer to execute a process of acquiring dynamic state variables related to elements correlated with the quality of a workpiece processed according to set processing conditions, the state variables at a first point in time and the processing conditions at the first point in time, predicting the state variables at a second point in time after the first point in time based on the state variables and processing conditions at the first point in time, and deriving the processing conditions at the second point in time required to achieve a predetermined target quality of the workpiece based on the predicted state variables at the second point in time. [Effects of the Invention]

[0021] According to the above aspects, the information processing device, information processing method, and information processing program of the present disclosure can obtain a workpiece of good quality. [Brief explanation of the drawings]

[0022] [Figure 1] FIG. 2 is a schematic configuration diagram of a control system. [Figure 2] 1A to 1C are diagrams showing specific examples of combinations of machining methods, tools, and workpieces. [Figure 3] FIG. 1 is a schematic diagram of a cylindrical grinding machine. [Figure 4] FIG. 2 is a block diagram illustrating an example of a hardware configuration of an information processing device. [Figure 5] FIG. 2 is a block diagram illustrating an example of a functional configuration of an information processing device. [Figure 6] FIG. 10 is a diagram for explaining the cutting edge radius. [Figure 7] FIG. 2 is a diagram for explaining input and output of information. [Figure 8] 1 is an example of training data for a state variable prediction model. [Figure 9] 1 is an example of training data for a quality prediction model. [Figure 10] This is an example of a target quality. [Figure 11] 10 is an example of optimal processing condition data. [Figure 12] FIG. 10 is a diagram illustrating quality according to an embodiment. [Figure 13] 10 is a flowchart illustrating an example of information processing. DETAILED DESCRIPTION OF THE INVENTION

[0023] Hereinafter, an example of an embodiment for implementing the technology of the present disclosure will be described in detail with reference to the drawings. First, an example of the configuration of a control system 1 according to this embodiment will be described with reference to Fig. 1. As shown in Fig. 1, the control system 1 includes an information processing device 10, a tool 2, and a workpiece 4.

[0024] The tool 2 is a tool, machine tool, tool, or the like for processing the workpiece 4. Processing of the workpiece 4 includes, for example, various mechanical processes such as grinding and cutting. Grinding may be, for example, cylindrical grinding, surface grinding, internal grinding, centerless grinding, thread grinding, gear grinding, profile grinding, and cutting. Cutting may be, for example, turning, drilling, boring, milling, planing, shaping, slotting, broaching, and sawing. FIG. 2 shows a specific example of a method for processing the workpiece 4 and a combination of the tool 2 and the workpiece 4.

[0025] FIG. 3 shows a schematic configuration of a cylindrical grinding machine 6 that uses a grinding wheel 2A to grind a substantially cylindrical cutting tool 4B. In the cylindrical grinding machine 6, the grinding wheel 2A is brought into contact with the cutting tool 4B to grind the cutting tool 4B. In this case, the grinding wheel 2A is rotated in the direction of arrow a about a rotation axis A, and the cutting tool 4B is supported by a support 2B that is rotated in the direction of arrow b about a rotation axis B. In other words, the cutting tool 4B (support 2B) is machined while rotating, and the grinding wheel 2A machines the cutting tool 4B while rotating. The support 2B and grinding wheel 2A are each rotated by a drive motor (not shown).

[0026] In addition, in the cylindrical grinding machine 6, the grinding wheel 2A and / or the support body 2B may be moved in the direction of the rotation axis B of the support body 2B (x direction in FIG. 3) to machine the entire blade 4B (so-called traverse machining). In addition, in the cylindrical grinding machine 6, wet grinding using a grinding fluid may be performed.

[0027] The information processing device 10 sets various processing conditions for the grinding stone 2A and the support body 2B and controls the operations of the grinding stone 2A and the support body 2B. That is, the blade 4B is processed according to the processing conditions set by the information processing device 10. The blade 4B is an example of a workpiece 4, and the grinding stone 2A and the support body 2B are an example of a tool 2.

[0028] Incidentally, the state of the tool 2 may dynamically change depending on the machining conditions set by the information processing device 10. If the state of the tool 2 changes, it may affect the quality of the workpiece 4. Therefore, the information processing device 10 according to this embodiment controls the tool 2 using machining conditions that take into account the dynamically changing state of the tool 2, in order to obtain a workpiece 4 of good quality. An example of the configuration of the information processing device 10 according to this embodiment will be described below.

[0029] First, an example of the hardware configuration of the information processing device 10 according to this embodiment will be described with reference to Fig. 4. As shown in Fig. 4, the information processing device 10 includes a CPU (Central Processing Unit) 21, a non-volatile storage unit 22, and a memory 23 as a temporary storage area. The information processing device 10 also includes a display 24 such as a liquid crystal display, an input unit 25 such as a keyboard and a mouse, and a network I / F (Interface) 26. The network I / F 26 communicates with the tool 2 via wired or wireless communication. The CPU 21, the storage unit 22, the memory 23, the display 24, the input unit 25, and the network I / F 26 are connected via a bus 28 such as a system bus and a control bus so as to be able to exchange various information with each other.

[0030] The storage unit 22 is realized by a storage medium such as a hard disk drive (HDD), a solid state drive (SSD), or a flash memory. The storage unit 22 stores an information processing program 27 for the information processing device 10. The CPU 21 reads the information processing program 27 from the storage unit 22, loads it into the memory 23, and executes the loaded information processing program 27. The CPU 21 is an example of a processor of the present disclosure. Various types of computers, such as a personal computer, a server computer, and a smartphone, can be used as the information processing device 10.

[0031] Next, an example of the functional configuration of the information processing device 10 according to this embodiment will be described with reference to Fig. 5. As shown in Fig. 5, the information processing device 10 includes an acquisition unit 30, a first prediction unit 32, a second prediction unit 34, a derivation unit 36, and a control unit 38. The CPU 21 executes the information processing program 27, thereby functioning as the acquisition unit 30, the first prediction unit 32, the second prediction unit 34, the derivation unit 36, and the control unit 38.

[0032] The acquiring unit 30 acquires a state variable X1 at a first time point and a machining condition Y1 at the first time point. A "state variable" is a dynamic variable related to an element correlated with the quality of the workpiece 4. For example, the acquiring unit 30 may acquire the state variable X1 obtained by a sensor (not shown) provided on the tool 2, such as the grinding wheel 2A and the support body 2B. Furthermore, for example, when the first time point is the start of machining, the acquiring unit 30 may acquire an initial condition that is predetermined as the machining condition Y1.

[0033] In the case of the cylindrical grinding machine 6 shown in FIG. 3, the state variable X1 is, for example, the load of the drive motor for rotating the grinding wheel 2A, the load of the drive motor for rotating the support body 2B, the axial vibration and axial acoustic emission (AE) of the support body 2B, and the temperature of the grinding fluid. The load of the drive motor for the grinding wheel 2A and the support body 2B may be expressed, for example, as an average value per sampling unit. The axial vibration and axial AE of the support body 2B may be expressed, for example, as an intensity average at a certain frequency.

[0034] In the case of the cylindrical grinding machine 6 of Fig. 3, the processing condition Y1 may be, for example, at least one of the rotation speed of the grinding wheel 2A, the cutting depth of the grinding wheel 2A relative to the cutting tool 4B, the cutting time, the cutting speed, and the number of cuttings. Also, for example, it may be at least one of the rotation speed of the support body 2B and the relative speed of the grinding wheel 2A and the support body 2B in the direction of the rotation axis B (x direction in Fig. 3). The rotation speeds of the grinding wheel 2A and the support body 2B may be expressed, for example, as the number of rotations and / or the rotation distance per unit time.

[0035] In the case of the cylindrical grinding machine 6 shown in FIG. 3, the quality Z1 is, for example, at least one of the size and number of chippings on the cutting edge of the blade 4B, the blade tip radius R, and surface roughness. The size and number of chippings may be expressed, for example, as the size and number of chippings contained in an arbitrarily extracted region, or as representative values ​​such as the average, median, minimum, and maximum values ​​of the size and number of chippings per unit area. FIG. 6 shows a cross-sectional view of the blade 4B in the xy plane in the region RO surrounded by the dashed line in FIG. 3. FIG. 6 also shows an example of the blade tip radius R. Note that the blade tip radius R may be expressed as representative values ​​such as the average, median, minimum, and maximum values ​​of the radius of curvature of the tip of each blade 4B. The surface roughness may be expressed, for example, as the arithmetic mean roughness Ra and the surface roughness Rz.

[0036] The functions of the first prediction unit 32, the second prediction unit 34, and the derivation unit 36 ​​will be described with reference to Fig. 7. Fig. 7 illustrates inputs and outputs to and from each functional unit.

[0037] The first prediction unit 32 predicts a predicted value Xp2 of the state variable at a second time point after the first time point, based on the state variable X1 and the machining condition Y1 at the first time point acquired by the acquisition unit 30. The second time point may be determined by the machining amount of the workpiece 4 and / or the elapsed time since the first time point. For example, the second time point may be a time point after a predetermined amount (e.g., 2 μm) of machining has been performed on the workpiece 4 at the first time point. Alternatively, for example, the second time point may be a time point after a predetermined period (e.g., 2 seconds) has elapsed since the first time point.

[0038] Specifically, the first prediction unit 32 may predict the predicted value Xp2 of the state variable at the second time point using a state variable prediction model M1 that has been trained so that the input is the state variable X1 and the processing condition Y1 at the first time point and the output is the predicted value Xp2 of the state variable at the second time point. The state variable prediction model M1 includes a neural network such as a convolutional neural network (CNN) or a recurrent neural network (RNN).

[0039] FIG. 8 shows an example of learning data of the state variable prediction model M1. As shown in FIG. 8, the learning data of the state variable prediction model M1 includes actual data of the machining conditions Yt and state variables Xt at a certain time point t, and the state variables Xt+1 at a time point t+1 after the certain time point t. That is, the learning data of the state variable prediction model M1 is data indicating how the state variables have changed up to the subsequent time point t+1 when machining according to the machining conditions is performed at the certain time point t. The interval between the certain time point t and the subsequent time point t+1 is the same as the interval between the first time point and the second time point. The axis AE of the support is the average value of the AE intensity at 120 kHz, and the same applies to the following FIGS. 9, 11 and 12.

[0040] The second prediction unit 34 predicts a predicted value Zp2 of the quality of the workpiece 4 at the second time point, based on the state variable X1 and machining condition Y1 at the first time point acquired by the acquisition unit 30. Specifically, the second prediction unit 34 may predict the predicted value Zp2 of the quality of the workpiece 4 at the second time point using a quality prediction model M2 that has been trained to take the state variable X1 and machining condition Y1 at the first time point as input and to take the predicted value Zp2 of the quality of the workpiece 4 at the second time point as output. The quality prediction model M2 includes a neural network such as a CNN or an RNN.

[0041] An example of the learning data of the quality prediction model M2 is shown in Fig. 9. As shown in Fig. 9, the learning data of the quality prediction model M2 includes performance data of the machining conditions Yt and state variables Xt at a certain time point t, and the quality Zt+1 of the workpiece 4 at a time point t+1 that is later than the time point t. In other words, the learning data of the quality prediction model M2 is data that indicates the quality of the workpiece 4 after machining according to the machining conditions Yt is performed by a tool 2 with state variable Xt at a certain time point t.

[0042] The derivation unit 36 ​​derives machining conditions Y2 at the second time point required to achieve a predetermined target quality Zr of the workpiece 4, based on the predicted value Xp2 of the state variable at the second time point predicted by the first prediction unit 32. An example of the predetermined target quality Zr is shown in Fig. 10. The target quality Zr may be stored in advance in, for example, the storage unit 22, or may be arbitrarily set by the user.

[0043] 11 shows an example of optimal machining condition data in which machining conditions Yt are predetermined to obtain good quality Zt that satisfies target quality Zr when the state variable of tool 2 at a certain time point t is Xt. The derivation unit 36 ​​may derive machining conditions Y2 that are likely to obtain good quality at the second time point by comparing the predicted value Xp2 of the state variable at the second time point predicted by the first prediction unit 32 with the optimal machining condition data. The optimal machining condition data may be stored in advance in, for example, the storage unit 22.

[0044] Furthermore, the derivation unit 36 ​​may derive machining conditions Y2 that minimize an evaluation value calculated according to the difference between the predicted value Zp2 of the quality of the workpiece 4 at the second time point predicted by the second prediction unit 34 and the target quality Zr. For example, the quality of the workpiece 4 may be in a trade-off relationship with the time required for machining. Therefore, the derivation unit 36 ​​may use an evaluation value calculated using the quality of the workpiece 4 and the time required for machining as variables to derive machining conditions Y2 that can shorten the time required for machining as much as possible within a range in which the predicted value Zp2 of the quality of the workpiece 4 satisfies the target quality Zr.

[0045] The control unit 38 controls the tool 2 so as to machine the workpiece 4 in accordance with the machining conditions Y2 derived by the derivation unit 36.

[0046] Furthermore, the control unit 38 may control the processes of the acquisition unit 30, the first prediction unit 32, the second prediction unit 34, and the derivation unit 36 ​​to be repeatedly performed. Specifically, the acquisition unit 30 may acquire a state variable X2 at a second time point and a machining condition Y2 at the second time point derived by the derivation unit 36. The first prediction unit 32 may predict a predicted value Xp3 of the state variable at a third time point after the second time point, based on the state variable X2 and the machining condition Y2 at the second time point acquired by the acquisition unit 30. The second prediction unit 34 may predict a predicted value Zp3 of the quality of the workpiece 4 at the third time point, based on the state variable X2 and the machining condition Y2 at the second time point acquired by the acquisition unit 30. The derivation unit 36 ​​may derive machining conditions Y3 at the third time point required to achieve the target quality Zr, based on the predicted value Xp3 of the state variable at the third time point predicted by the first prediction unit 32.

[0047] The third point in time may be determined by the amount of processing of the workpiece 4 and / or the elapsed time since the second point in time. For example, the third point in time may be a point in time after a predetermined amount (e.g., 2 μm) of processing has been performed on the workpiece 4 at the second point in time. Also, for example, the third point in time may be a point in time when a predetermined period (e.g., 2 seconds) has elapsed since the second point in time.

[0048] Similarly, from the fourth time point onwards, the control unit 38 may control the acquisition unit 30, the first prediction unit 32, the second prediction unit 34 and the derivation unit 36 ​​to repeatedly perform the processes until the machining of the workpiece 4 is completed. Furthermore, the control unit 38 may determine that the machining of the workpiece 4 is completed when the amount of machining from the start of machining reaches a predetermined amount (for example, 20 μm).

[0049] (Example) Fig. 12 shows the quality results of the workpiece 4 processed according to the processing conditions derived by the information processing device 10 according to this embodiment. As a comparative example, Fig. 12 also shows the quality results of the workpiece 4 processed according to processing conditions arbitrarily set by the user. It can be seen from Fig. 12 that the quality of the workpiece 4 can be improved by the information processing device 10 according to this embodiment.

[0050] Next, the operation of the information processing device 10 according to this embodiment will be described with reference to Fig. 13. In the information processing device 10, the CPU 21 executes the information processing program 27, thereby executing the information processing shown in Fig. 13. The information processing is executed, for example, when a user issues an instruction to start execution via the input unit 25.

[0051] In step S10, the control unit 38 sets time t to 1. In step S12, the acquisition unit 30 acquires the state variable Xt(X1) and the machining condition Yt(Y1) at time t (first time point). In step S14, the first prediction unit 32 predicts a predicted value Xpt+1(Xp2) of the state variable at time t+1 (second time point) based on the state variable Xt(X1) and the machining condition Yt(Y1) acquired in step S12. In step S16, the second prediction unit 34 predicts a predicted value Zpt+1(Zp2) of the quality of the workpiece at time t+1 (second time point) based on the state variable Xt(X1) and the machining condition Yt(Y1) acquired in step S12.

[0052] In step S18, the derivation unit 36 ​​derives machining conditions Yt+1(Y2) at the t+1th time point (second time point) based on the predicted value Xpt+1(Xp2) of the state variable predicted in step S14. In this case, the derivation unit 36 ​​may derive machining conditions Yt+1(Y2) that minimize an evaluation value calculated according to the difference between the predicted value Zpt+1(Zp2) of the workpiece quality predicted in step S16 and the target quality Zr. In step S20, the control unit 38 performs control to machine the workpiece in accordance with the machining conditions Yt+1(Y2) derived in step S18.

[0053] In step S22, control unit 38 determines whether or not processing of the workpiece is complete. If processing of the workpiece is not complete (N in step S22), the process proceeds to step S24, where control unit 38 increments time t (increases t by 1) and repeats the processes of steps S12 to S22. On the other hand, if processing of the workpiece is complete (Y in step S22), this information processing ends.

[0054] As described above, the information processing device 10 according to one aspect of the present disclosure includes at least one processor, and the processor acquires dynamic state variables related to elements correlated with the quality of a workpiece at a first time point to be machined according to set machining conditions and the machining conditions at the first time point, predicts state variables at a second time point after the first time point based on the state variables and machining conditions at the first time point, and derives machining conditions at the second time point required to achieve a predetermined target quality of the workpiece based on the predicted state variables at the second time point. In other words, the information processing device 10 according to this embodiment can control the tool 2 using machining conditions that take into account the dynamically changing state of the tool 2, thereby improving the quality of the workpiece.

[0055] In the above embodiment, the derivation unit 36 ​​derives the machining conditions using the predicted value Zp2 of the quality of the workpiece 4 predicted by the second prediction unit 34. However, the present invention is not limited to this. For example, if the quality of the workpiece 4 can be measured in real time using various sensors, the derivation unit 36 ​​may derive the machining conditions using the actual measured value of the quality of the workpiece 4 instead of the predicted value Zp2 of the quality of the workpiece 4 predicted by the second prediction unit 34. In this case, the information processing device 10 does not need to have the functionality of the second prediction unit 34.

[0056] In the above embodiment, the first prediction unit 32 and the second prediction unit 34 predict the predicted value Xp2 of the state variable and the predicted value Zp2 of the quality at the second time point using learning models such as CNN and RNN. However, the present invention is not limited to this. For example, the first prediction unit 32 may predict the predicted value Xp2 of the state variable at the second time point using correlation data between the state variable Xt and the machining condition Yt at a certain time point t and the state variable Xt+1 at a subsequent time point t+1. For example, the second prediction unit 34 may predict the predicted value Zp2 of the quality of the workpiece 4 at the second time point using correlation data between the state variable Xt and the machining condition Yt at a certain time point t and the quality Zt+1 of the workpiece 4 at a subsequent time point t+1. These correlation data may be derived in advance and stored in the storage unit 22.

[0057] Furthermore, in the above embodiment, the following various processors can be used as the hardware structure of processing units that perform various processes, such as the acquisition unit 30, the first prediction unit 32, the second prediction unit 34, the derivation unit 36, and the control unit 38. As described above, the various processors include a CPU, which is a general-purpose processor that executes software (programs) and functions as various processing units, as well as dedicated electrical circuits that are processors having a circuit configuration specifically designed to perform specific processes, such as a programmable logic device (PLD), a processor whose circuit configuration can be changed after manufacture, such as an FPGA (Field Programmable Gate Array), and an ASIC (Application Specific Integrated Circuit).

[0058] A single processing unit may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, multiple processing units may be configured with a single processor.

[0059] Examples of configuring multiple processing units with a single processor include, first, a form in which one processor is configured with a combination of one or more CPUs and software, and this processor functions as multiple processing units, as typified by computers such as client and server. Second, a form in which a processor is used to realize the functions of the entire system including multiple processing units with a single IC (Integrated Circuit) chip, as typified by systems on chips (SoCs). In this way, various processing units are configured using one or more of the above-mentioned various processors as a hardware structure.

[0060] Furthermore, more specifically, the hardware structure of these various processors can be an electric circuit that combines circuit elements such as semiconductor elements.

[0061] In the above embodiment, the information processing program 27 is pre-stored (installed) in the storage unit 22, but this is not limiting. The information processing program 27 may be provided in a form recorded on a recording medium such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a USB (Universal Serial Bus) memory. The information processing program 27 may also be downloaded from an external device via a network. Furthermore, the technology disclosed herein extends to not only information processing programs but also storage media that non-temporarily store information processing programs.

[0062] The technology of the present disclosure can also be appropriately combined with the above-described exemplary embodiments and examples. The above-described description and illustrations are detailed descriptions of the parts related to the technology of the present disclosure and are merely examples of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or new elements may be replaced with other parts from the description and illustrations shown above, within the scope of the gist of the technology of the present disclosure. [Explanation of symbols]

[0063] 1. Control System 2 tools 2A Grindstone 2B Support 4 Workpiece 4B Cutlery 6 Cylindrical grinding machine 10. Information processing equipment 21 CPU 22 Memory section 23 Memory 24 displays 25 Input section 26 Network I / F 27 Information Processing Program 28 Bus 30 Acquisition Department 32 First Prediction Section 34 Second Prediction Section 36 Derivation part 38 Control Unit A and B rotation axes M1 State variable prediction model M2 quality prediction model R cutting edge radius RO area

Claims

1. at least one processor; The processor: Acquiring dynamic state variables relating to elements correlated with the quality of a workpiece processed according to set processing conditions, the state variables at a first time point and the processing conditions at the first time point; predicting the state variables at a second time point that is later than the first time point based on the state variables and the processing conditions at the first time point; predicting quality of the workpiece at the second time point based on the state variables and the processing conditions at the first time point; Derive the machining conditions at the second time point required to achieve a predetermined target quality of the workpiece based on the predicted state variables at the second time point, the machining conditions minimizing an evaluation value calculated according to a difference between the predicted quality of the workpiece at the second time point and the target quality. Information processing device.

2. The processor: The quality of the workpiece at the second time point is predicted using a trained model that has been trained so that inputs are the state variables and the machining conditions at the first time point and output is the quality of the workpiece at the second time point. The information processing device according to claim 1 .

3. at least one processor; The processor: Acquiring dynamic state variables relating to elements correlated with the quality of a workpiece processed according to set processing conditions, the state variables at a first time point and the processing conditions at the first time point; predicting the state variables at a second time point that is later than the first time point based on the state variables and the processing conditions at the first time point; deriving the machining conditions at the second time point required to achieve a predetermined target quality of the workpiece based on the predicted state variables at the second time point; acquiring the state variables at the second time point and the machining conditions at the second time point; predicting the state variables at a third time point after the second time point based on the state variables and the processing conditions at the second time point; Deriving the processing conditions at the third time point required to achieve the target quality based on the predicted state variables at the third time point. Information processing device.

4. at least one processor; The processor: Acquiring dynamic state variables relating to elements correlated with the quality of a workpiece processed according to set processing conditions, the state variables at a first time point and the processing conditions at the first time point; predicting the state variables at a second time point that is later than the first time point based on the state variables and the processing conditions at the first time point; deriving the machining conditions at the second time point required to achieve a predetermined target quality of the workpiece based on the predicted state variables at the second time point; The workpiece is generally cylindrical and is machined while rotating. Information processing device.

5. at least one processor; The processor: Acquiring dynamic state variables relating to elements correlated with the quality of a workpiece processed according to set processing conditions, the state variables at a first time point and the processing conditions at the first time point; predicting the state variables at a second time point that is later than the first time point based on the state variables and the processing conditions at the first time point; deriving the machining conditions at the second time point required to achieve a predetermined target quality of the workpiece based on the predicted state variables at the second time point; The workpiece is generally cylindrical, The tool used to process the workpiece processes the workpiece while rotating. Information processing device.

6. the workpiece is a blade, The processing of the workpiece is a grinding process in which the blade is ground using a grindstone, The processing conditions include at least one of the rotation speed of the grindstone, the cutting amount, the cutting time, the cutting speed and the number of cuttings, the rotation speed of a support that supports the blade, and the relative speed between the grindstone and the support.

6. The information processing device according to claim 4 or claim 5.

7. the workpiece is a blade, The processing of the workpiece is a grinding process in which the blade is ground using a grindstone, The state variables include at least one of a drive motor load of the grinding wheel, a drive motor load of a support that supports the cutting tool, an axial vibration and an axial acoustic emission of the support, and a grinding fluid temperature.

7. The information processing device according to claim 4.

8. at least one processor; The processor: Acquiring dynamic state variables relating to elements correlated with the quality of a workpiece processed according to set processing conditions, the state variables at a first time point and the processing conditions at the first time point; predicting the state variables at a second time point that is later than the first time point based on the state variables and the processing conditions at the first time point; deriving the machining conditions at the second time point required to achieve a predetermined target quality of the workpiece based on the predicted state variables at the second time point; the workpiece is a blade, The processing of the workpiece is a grinding process in which the blade is ground using a grindstone, The quality of the workpiece includes at least one of the size and number of chippings on the cutting edge of the blade, the cutting edge radius, and the surface roughness. Information processing device.

9. The processor: The state variables at the second time point are predicted using a trained model that has been trained so that inputs are the state variables and the machining conditions at the first time point and outputs are the state variables at the second time point. The information processing device according to any one of claims 1 to 8.

10. The second time point is a time point after a predetermined amount of processing has been performed on the workpiece at the first time point. The information processing device according to any one of claims 1 to 9.

11. The second time point is a time point when a predetermined period has elapsed since the first time point. The information processing device according to any one of claims 1 to 9.

12. The processor: Controlling the machining of the workpiece in accordance with the derived machining conditions The information processing device according to any one of claims 1 to 11.

13. Acquiring dynamic state variables relating to elements correlated with the quality of a workpiece processed according to set processing conditions, the state variables at a first time point and the processing conditions at the first time point; predicting the state variables at a second time point that is later than the first time point based on the state variables and the processing conditions at the first time point; predicting quality of the workpiece at the second time point based on the state variables and the processing conditions at the first time point; Derive the machining conditions at the second time point required to achieve a predetermined target quality of the workpiece based on the predicted state variables at the second time point, the machining conditions minimizing an evaluation value calculated according to a difference between the predicted quality of the workpiece at the second time point and the target quality. Information processing methods including processing.

14. Acquiring dynamic state variables relating to elements correlated with the quality of a workpiece processed according to set processing conditions, the state variables at a first time point and the processing conditions at the first time point; predicting the state variables at a second time point that is later than the first time point based on the state variables and the processing conditions at the first time point; predicting quality of the workpiece at the second time point based on the state variables and the processing conditions at the first time point; Derive the machining conditions at the second time point required to achieve a predetermined target quality of the workpiece based on the predicted state variables at the second time point, the machining conditions minimizing an evaluation value calculated according to a difference between the predicted quality of the workpiece at the second time point and the target quality. An information processing program that causes a computer to execute a process.

Images