Machining condition determination assistance device, machining condition determination assistance system, machining condition determination assistance method, and machining condition determination assistance program

Abstract

A machining condition determination assistance device (1) for assisting the determination of a machining condition is provided with: a simulation execution unit (11) that performs simulation on the basis of a material shape model (21) that represents the pre-machining shape of a workpiece, a tool model (22) that represents the shape of a tool, and tool movement command data (23) during a machining operation; processing simulation of the processed object is executed according to the processing conditions of the plurality of modes; and an adjustment direction determination unit (13) that accepts a selection from an operator with respect to the displayed simulation result, and on the basis of the accepted selection, determines and presents the adjustment direction of the machining condition for the next trial machining simulation.

Description

Technical Field

[0001] The present invention relates to a processing condition determination assisting device, a processing condition determination assisting system, a processing condition determination assisting method and a processing condition determination assisting program for assisting in determining processing conditions used when a working machine performs processing. Background Art

[0002] Whether the processing result by the machine tool is qualified or not is greatly affected by the setting content of the processing conditions. In the past, in order to determine the processing conditions that will produce the preferred processing results (hereinafter referred to as appropriate processing conditions), trial processing was actually carried out many times on site, and the final processing conditions were determined based on the results of the trial processing and the intuition and experience of the skilled person. In the case of this method, since the trial processing takes time, the patterns of processing conditions that can be tried are limited to a small number.

[0003] In recent years, machining simulation technology has been developed, which performs machining simulation on a computer instead of actual machining. This makes it possible to evaluate a large number of machining conditions in a short time, making it easy to determine appropriate machining conditions.

[0004] For example, the display device described in Patent Document 1 includes: an input unit such as a slide bar, which can continuously change at least one of the processing conditions; and a display unit, which displays the processing simulation results linked to the changed processing conditions. Thus, the display device allows the operator to recognize the processing simulation results linked to the continuous change of the processing conditions and to adjust the processing results.

[0005] Patent Document 1: Japanese Patent Application Publication No. 2004-280267 Summary of the invention

[0006] However, in the technology of the above-mentioned Patent Document 1, since the processing conditions are composed of multiple parameters, in order to find the appropriate processing conditions, it is necessary to consider a large number of processing conditions generated by the combination of multiple parameters. In the technology of the above-mentioned Patent Document 1, it can be said that the appropriate processing conditions can only be explored in a dialogue manner through cyclic trial and error, and the number of combinations of multiple parameters will increase explosively, so there is a problem that the appropriate processing conditions cannot be efficiently found in a short time.

[0007] The present invention has been made in view of the above-mentioned circumstances, and an object of the present invention is to provide a processing condition determination support device capable of efficiently obtaining appropriate processing conditions in a short time.

[0008] In order to solve the above-mentioned problems and achieve the purpose, the processing condition determination auxiliary device of the present invention assists in determining the processing conditions in the processing of a workpiece using a working machine, and the processing condition determination auxiliary device has a simulation execution unit, which performs processing simulation of the workpiece for multiple modes of processing conditions based on a material shape model representing the shape of the workpiece before processing, a tool model representing the shape of the tool used for processing, and tool movement instruction data that specifies the movement of the tool during the processing action. In addition, the processing condition determination auxiliary device of the present invention has a simulation display unit, which displays the result of the processing simulation, that is, the simulation result, on a display screen. In addition, the processing condition determination auxiliary device of the present invention has: a selection acceptance unit, which accepts the selection from the operator for the displayed simulation result; and an adjustment direction determination unit, which determines and prompts the adjustment direction of the processing conditions of the next trial processing simulation based on the selection accepted by the selection acceptance unit.

[0009] Effects of the Invention

[0010] The processing condition determination support device according to the present invention has the effect of being able to efficiently determine appropriate processing conditions in a short time. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 This is a block diagram showing the structure of the processing condition determination support device involved in the first embodiment.

[0012] Figure 2 This is a block diagram showing the structure of a simulation execution unit included in the machining condition determination support device according to the first embodiment.

[0013] Figure 3 This is a diagram for explaining the machining simulation results displayed by the machining condition determination support device involved in the first embodiment.

[0014] Figure 4 This is a diagram for explaining the machining condition adjustment direction calculated by the machining condition determination support device involved in the first embodiment.

[0015] Figure 5 It is used to describe the ability to Figure 4 A diagram showing an area for selecting machining conditions to be set based on the reference axis is shown.

[0016] Figure 6 This is a flowchart showing the processing procedure of the processing condition determination support processing performed by the processing condition determination support device involved in the first embodiment.

[0017] Figure 7 This is a block diagram showing the structure of a processing condition determination support device according to the second embodiment.

[0018] Figure 8 This is a diagram for explaining a neural network used by a learning unit according to the second embodiment.

[0019] Fig. 9 This is a flowchart showing the processing procedure of the processing of prompting the processing condition adjustment direction performed by the processing condition determination support device involved in the second embodiment.

[0020] Fig.10 This is a flowchart showing the processing procedure of the learning process executed by the learning unit involved in the second embodiment.

[0021] Fig.11 This is a flowchart showing the processing procedure of the estimation process performed by the estimation unit involved in the second embodiment.

[0022] Fig.12 This is a diagram showing an example of a hardware configuration for realizing a processing condition determination support device according to the first and second embodiments. DETAILED DESCRIPTION

[0023] Hereinafter, a processing condition determination support device, a processing condition determination support system, a processing condition determination support method, and a processing condition determination support program according to an embodiment of the present invention will be described in detail based on the accompanying drawings.

[0024] Implementation method 1.

[0025] Figure 1 1 is a block diagram showing the structure of a processing condition determination support device according to Embodiment 1. The processing condition determination support device 1 is a computer that supports the determination process of processing conditions used when a machine tool processes a workpiece. A user (operator) of the processing condition determination support device 1 uses the processing condition determination support device 1 to execute the determination process of processing conditions.

[0026] The processing condition determination support device 1 includes a simulation execution unit 11, a simulation display unit 12, an adjustment direction determination unit 13, a processing condition update unit 14, a selection acceptance unit 15, and a storage unit 20. The processing condition determination support device 1 is connected to a display screen 50, a mouse 51, and a keyboard 52. The processing condition determination support device 1 accepts user instructions corresponding to operations performed by an operator on the mouse 51 and the keyboard 52. The processing condition determination support device 1 displays calculated information (such as simulation results described later) on the display screen 50.

[0027] The storage unit 20 stores a material shape model 21, a tool model 22, tool movement command data 23, and a processing condition set 24. The material shape model 21 is a model that represents the shape of the workpiece before processing, that is, the shape of the material. That is, the material shape model 21 is a model of the initial shape of the workpiece. The tool model 22 is a model that represents the shape of the tool used in processing.

[0028] The tool movement command data 23 is data indicating a movement command of a tool in a machining operation of the machine tool. The tool movement command data 23 is extracted from a control program or the like for controlling the machine tool. An example of the tool movement command data 23 is a G code.

[0029] The processing condition set 24 is data indicating the processing conditions when the machine tool performs processing. The processing condition set 24 includes a plurality of processing conditions. In addition, each processing condition includes a plurality of parameters. For example, each processing condition in the processing condition set 24 includes various parameters for controlling the operation of the numerical control, such as the tool feed speed called the F value and the spindle rotation speed called the S value.

[0030] The simulation execution unit 11 reads the material shape model 21, the tool model 22, the tool movement command data 23, and the processing condition set 24 from the storage unit 20. The simulation execution unit 11 simulates processing performed by the machine tool. An example of processing performed by the machine tool is cutting processing.

[0031] The simulation execution unit 11 simulates machining by the machine tool by sequentially moving the tool represented by the tool model 22 according to the tool movement command specified by the tool movement command data 23 with respect to the initial shape of the workpiece represented by the material shape model 21 .

[0032] The simulation execution unit 11 performs machining simulation of the workpiece for machining conditions of multiple modes. The simulation execution unit 11 simulates the cutting process by removing the area where the shape model of the workpiece, i.e., the material shape model 21, and the moving tool model 22 intersect. At this time, the simulation execution unit 11 applies specific machining conditions in the machining condition set 24 and calculates the simulation result for each machining condition. The simulation result calculated by the simulation execution unit 11 is the shape of the workpiece after the machining by the tool is completed. The simulation execution unit 11 sends the simulation result to the simulation display unit 12.

[0033] The simulation display unit 12 displays the machining simulation results for each machining condition executed by the simulation execution unit 11 in a row on the display screen 50. The simulation display unit 12 sends the machining simulation results displayed on the display screen 50 to the adjustment direction determination unit 13.

[0034] The selection accepting unit 15 accepts a selection from the operator with respect to the simulation results displayed on the display screen 50. The selection accepting unit 15 accepts the machining simulation result selected by the operator from the machining simulation results displayed on the display screen 50 through the mouse 51 or the keyboard 52. The machining simulation result selected by the operator is a machining simulation result corresponding to the machining result (shape of the machined workpiece, time required for machining, etc.) determined by the operator to be inappropriate.

[0035] The operator selects a machining simulation result judged as inappropriate from the machining simulation results displayed on the display screen 50 using the mouse 51 or the keyboard 52. Thus, the selection accepting unit 15 determines the machining simulation result judged as inappropriate from the machining simulation results displayed on the display screen 50.

[0036] The selection accepting unit 15 accepts the machining simulation result selected by the operator as inappropriate. Hereinafter, the machining simulation result selected by the operator as inappropriate may be referred to as an inappropriate simulation result. In addition, the machining conditions corresponding to the inappropriate simulation result may be referred to as inappropriate machining conditions.

[0037] The adjustment direction determining unit 13 determines and prompts the adjustment direction of the processing conditions of the next trial processing simulation based on the selection received by the selection receiving unit 15. Specifically, the adjustment direction determining unit 13 determines the adjustment direction (hereinafter sometimes referred to as the processing condition adjustment direction) for changing to the processing conditions estimated to be more preferable than the current situation based on the relationship between the processing conditions corresponding to the inappropriate simulation results and the processing conditions corresponding to the remaining processing simulation results not selected by the operator. In the following, the remaining processing simulation results not selected by the operator are sometimes referred to as the remaining simulation results. In addition, the processing conditions corresponding to the remaining simulation results are sometimes referred to as the remaining processing conditions. The adjustment direction determining unit 13 prompts the operator by displaying the processing condition adjustment direction on the display screen 50. In addition, the adjustment direction determining unit 13 sends the processing condition adjustment direction to the processing condition updating unit 14. The details of the processing condition adjustment direction will be described later.

[0038] The processing condition updating unit 14 receives the processing condition determined by the operator along the processing condition adjustment direction displayed on the display screen 50 from the mouse 51 or the keyboard 52. In this case, the operator refers to the processing condition adjustment direction displayed on the display screen 50, determines the processing condition predicted to obtain an appropriate processing result, and inputs it to the processing condition determination support device 1 using the mouse 51 or the keyboard 52. Thus, the processing condition updating unit 14 obtains the processing condition determined by the operator.

[0039] Upon receiving the machining conditions determined by the operator with reference to the machining condition adjustment direction, the machining condition updating unit 14 updates the machining conditions corresponding to the inappropriate machining simulation results in the machining condition set 24 to the new machining conditions determined by the operator.

[0040] The machining condition determination support device 1 repeats the machining simulation, the process of accepting the operator's operation, and the process of updating the machining conditions until a machining simulation result corresponding to good machining desired by the operator is obtained.

[0041] The operations performed by the operator include, as described above, an operation of selecting an inappropriate machining simulation result and an operation of determining a new machining condition along the direction of adjusting the presented machining conditions.

[0042] Next, the configuration of the simulation execution unit 11 will be described. Figure 2 This is a block diagram showing the structure of a simulation execution unit included in the machining condition determination support device according to the first embodiment.

[0043] The simulation execution unit 11 includes a movement command analysis unit 41, a numerical control unit 42, a machine response calculation unit 43, and a cutting simulation unit 44. The movement command analysis unit 41 reads the tool movement command data 23 from the storage unit 20. The movement command analysis unit 41 analyzes the tool movement command data 23 described in a standard format such as a G code, and calculates a movement command 61 for the tool. The movement command analysis unit 41 sends the calculated movement command 61 to the numerical control unit 42.

[0044] The numerical control unit 42 reads one machining condition (here, the machining condition 24a) from the machining condition set 24 from the storage unit 20. The numerical control unit 42 reads the machining conditions one by one from the machining condition set 24. The numerical control unit 42 calculates a servo command 62 for moving the machine tool using the read machining condition 24a and the movement command 61. The servo command 62 for moving the machine tool is a command to a servo motor that drives a tool. The numerical control unit 42 sends the calculated servo command 62 to the machine response calculation unit 43.

[0045] The numerical control unit 42 receives servo FB (FeedBack) data 63 from the mechanical response calculation unit 43 as feedback data for the servo command 62. The numerical control unit 42 calculates the servo command 62 based on the servo FB data 63, thereby executing feedback control.

[0046] The machine response calculation unit 43 simulates the dynamic response of the machine tool to the calculated servo command 62 and calculates a tool movement trajectory 64 as a tool movement path as a result of the simulation. The machine response calculation unit 43 sends the calculated tool movement trajectory 64 to the cutting simulation unit 44 .

[0047] The cutting process simulation unit 44 reads the tool model 22 and the material shape model 21 from the storage unit 20. The cutting process simulation unit 44 simulates the cutting process of the workpiece based on the tool movement trajectory 64, the tool model 22 and the material shape model 21. That is, the cutting process simulation unit 44 simulates the processing using the material shape model 21 as the initial shape. The result of the simulation is the processed shape 45 of the workpiece. If the cutting process simulation unit 44 simulates the processing and calculates a new processed shape 45, the old processed shape is updated by the calculated processed shape 45. The cutting process simulation unit 44 sends the simulated result, i.e., the processed shape 45, to the simulation display unit 12.

[0048] In machining by a machine tool, the actual tool movement trajectory 64 may rotate inward or outward depending on machining conditions, and may move along a path different from the original tool movement trajectory assumed by the tool movement command data 23. Therefore, different simulation results are generated for each machining condition.

[0049] The machining simulation result data calculated by the simulation execution unit 11 may be any data that allows the operator to visually recognize whether the machining result is acceptable due to the difference in machining conditions, and is not limited to the example of the first embodiment.

[0050] Figure 3 FIG. 1 is a diagram for explaining the machining simulation results displayed by the machining condition determination support device according to the first embodiment. Figure 3 , there are shown a state where machining simulation results corresponding to a plurality of machining conditions are arranged and displayed (display screen 71 ) and a state where machining simulation results determined to be inappropriate from the viewpoint of machining are selected (display screen 72 ).

[0051] In the display screen 71 as an example of the display screen 50, the machining simulation results of the number of patterns of the machining conditions in the machining condition set 24 are displayed. Figure 3 , a case where four machining simulation results SA to SD are displayed as machining simulation results corresponding to four machining conditions is shown on the display screen 71 .

[0052] The operator selects a machining simulation result determined to be inappropriate from the machining simulation results SA to SD displayed on the display screen 71. The operator selects the machining simulation result determined to be inappropriate using the mouse 51, for example.

[0053] In the display screen 72 as an example of the display screen 50, the machining simulation result selected by the operator is highlighted. Figure 3 , it is shown that the machining simulation result SB selected by the operator is highlighted and displayed on the display screen 72. The selected machining simulation result SB is sent to the adjustment direction determination unit 13 via the selection receiving unit 15. Then, the machining conditions corresponding to the selected machining simulation result SB are updated.

[0054] As described above, the simulation execution unit 11 displays the machining simulation results in a row, so that the operator can understand the simulation results at a glance, and even an unskilled operator can easily select an appropriate or inappropriate machining simulation result.

[0055] In addition, an end button 75 is displayed on the display screen 71. When the operator presses the end button 75 on the display screen 71, the processing of determining the processing conditions ends. At the time when the end button 75 is pressed, the processing condition set 24 stored in the storage unit 20 is the determined processing condition. At the time when the end button 75 is pressed, the processing condition set 24 stored in the storage unit 20 is the latest combination of processing conditions after update.

[0056] Figure 4 1 is a diagram for explaining the processing condition adjustment direction calculated by the processing condition determination auxiliary device involved in the first embodiment. Figure 4 In the following, an example of the processing condition adjustment direction calculated by the adjustment direction determination unit 13 is described.

[0057] For example, the simulation execution unit 11 executes machining simulation for machining conditions including parameters P1 to P3 (here, machining conditions RA to RD (not shown)). The machining conditions RA to RD used when the simulation execution unit 11 executes machining simulation are plotted as points on a vector space based on the parameters P1 to P3 constituting the machining conditions.

[0058] exist Figure 4 In FIG. 1 , each point of the processing conditions RA to RD is shown as points QA to QD. That is, the processing condition RA corresponds to the point QA, and the processing condition RB corresponds to the point QB. In addition, the processing condition RC corresponds to the point QC, and the processing condition RD corresponds to the point QD.

[0059] The simulation display unit 12 arranges and displays inappropriate machining conditions and remaining machining conditions corresponding to the machining simulation results in a vector space based on machining parameters.

[0060] For example, when the operator selects the machining simulation result corresponding to the machining condition RB as an inappropriate machining simulation result, the machining simulation results corresponding to the machining conditions RA, RC, and RD are the remaining machining simulation results. In this case, the machining condition RB corresponding to the inappropriate machining simulation result is an inappropriate machining condition, and the machining conditions RA, RC, and RD corresponding to the remaining machining simulation results are the remaining machining conditions.

[0061] Furthermore, the machining condition determination support device 1 may use, instead of all of the machining conditions RA, RC, and RD, any one or two of the machining conditions RA, RC, and RD as the remaining machining simulation results.

[0062] When the inappropriate processing condition is processing condition RB, the adjustment direction determination unit 13 calculates each vector from point QB toward points QA, QC, and QD corresponding to the remaining processing conditions (remaining processing conditions). That is, the adjustment direction determination unit 13 calculates the vector from point QB toward point QA, the vector from point QB toward point QC, and the vector from point QB toward point QD. Furthermore, the adjustment direction determination unit 13 calculates the composite vector of the vectors from point QB toward the remaining points QA, QC, and QD and presents it to the operator as the reference axis 80 of the adjustment direction. In the first embodiment, the direction of the composite vector, the adjustment direction, and the direction of the reference axis 80 are the same direction.

[0063] The operator determines the new machining conditions as the new machining conditions for the next machining simulation along the suggested reference axis 80. For example, the operator determines the new machining conditions at a point on the reference axis 80. In addition, the machining conditions at this moment are temporarily determined, and the machining conditions when the end button 75 is pressed are the final machining conditions.

[0064] In addition, the new machining conditions that can be set by the operator do not necessarily need to be limited to the machining conditions on the reference axis 80. The adjustment direction determination unit 13 may set a specific area around the reference axis 80 as an area where new machining conditions can be selected.

[0065] Figure 5 It is used to describe the ability to Figure 4The adjustment direction determination unit 13 sets, for example, the starting point QB of the reference axis 80 (the point corresponding to the processing condition RB selected as inappropriate by the operator) as the vertex, and the conical area 81 extending from the point QB in the direction of the reference axis 80 as the area where the new processing condition can be selected (the selectable range of the processing condition). In this case, the length of the reference axis 80 corresponds to the height of the conical area 81.

[0066] In addition, the adjustment direction determination unit 13 may select a point series at a specific interval on the reference axis 80 or in the conical area 81, and use the points included in the point series as points at which new machining conditions can be selected. As described above, when the machining condition determination support device 1 selects a simulation result corresponding to an inappropriate machining condition from the simulation results for the plurality of machining condition sets 24, it executes setting of a new machining condition along the machining condition adjustment direction calculated by the above method.

[0067] The processing condition determination auxiliary device 1 repeatedly performs processing simulation for processing conditions, calculates processing condition adjustment directions based on inappropriate processing conditions selected by the operator, and updates new processing conditions selected by the operator along the processing condition adjustment directions. Thus, the processing condition determination auxiliary device 1 can continuously adjust processing conditions toward a preferred processing result.

[0068] Figure 6 This is a flowchart showing the processing sequence of the machining condition determination auxiliary processing performed by the machining condition determination auxiliary device according to Embodiment 1. The simulation execution unit 11 uses the material shape model 21, the tool model 22, the tool movement command data 23 and the machining condition set 24 to perform machining simulation by the machine tool (step S10).

[0069] The simulation display unit 12 displays the simulation result of the machining simulation for each machining condition executed by the simulation execution unit 11 on the display screen 50 (step S20 ).

[0070] The machining condition determination support device 1 determines whether the operator has pressed the end button 75 (step S25). If the operator has not pressed the end button 75 (step S25, No), the operator selects the most inappropriate machining simulation result from the simulation results displayed on the display screen 50. The adjustment direction determination unit 13 receives the inappropriate machining simulation result selected by the operator via the selection receiving unit 15 (step S30).

[0071] The adjustment direction determination unit 13 calculates and presents a machining condition adjustment direction based on the relationship between the inappropriate machining conditions corresponding to the inappropriate machining simulation result and the remaining machining conditions corresponding to the remaining machining simulation result (step S40 ).

[0072] Thus, the operator can change the machining conditions along the machining condition adjustment direction displayed on the display screen 50. The machining condition update unit 14 receives the machining conditions determined by the operator along the machining condition adjustment direction displayed on the display screen 50 (step S50).

[0073] Upon receiving the machining conditions determined by the operator, the machining condition updating unit 14 updates the machining conditions corresponding to the inappropriate machining simulation results in the machining condition set 24 to the new machining conditions determined by the operator (step S60 ).

[0074] Then, the machining condition determination support device 1 returns to the process of step S10 and executes the processes of steps S10 and S20. Furthermore, the machining condition determination support device 1 determines whether the end button 75 is pressed by the operator (step S25).

[0075] The machining condition determination support device 1 repeats the processing of steps S30 to S60 and the processing of steps S10, S20, and S25 until the operator presses the end button 75. That is, the processing of steps S30 to S60 and the processing of steps S10, S20, and S25 are repeated until the desired simulation result is obtained.

[0076] When the operator presses the end button 75 (step S25, Yes), the machining condition determination support device 1 ends the machining condition determination support process. At this point in time, the latest machining condition becomes the machining condition determined by the machining condition determination support device 1.

[0077] In addition, the simulation execution unit 11, the simulation display unit 12, the adjustment direction determination unit 13, the processing condition update unit 14, the selection acceptance unit 15, and the storage unit 20 may be arranged in different places. In this case, at least a part of the simulation execution unit 11, the simulation display unit 12, the adjustment direction determination unit 13, the processing condition update unit 14, the selection acceptance unit 15, and the storage unit 20 is connected to a network, and data is sent and received via the network. That is, the processing condition determination auxiliary processing described in the first embodiment can be realized by a processing condition determination auxiliary system in which at least a part of the simulation execution unit 11, the simulation display unit 12, the adjustment direction determination unit 13, the processing condition update unit 14, the selection acceptance unit 15, and the storage unit 20 is connected to a network.

[0078] The processing condition determination auxiliary device 1 calculates the adjustment direction of the processing condition for the inappropriate processing condition, so that the appropriate processing condition can be obtained with a small number of trials compared with the case where the processing simulation is performed by the cyclic processing condition. Therefore, the processing condition determination auxiliary device 1 can efficiently determine the appropriate processing condition in a short time.

[0079] As described above, the processing condition determination auxiliary device 1 of embodiment 1 accepts the inappropriate simulation result selected by the operator from the viewpoint of whether the processing is qualified or not, with respect to the displayed simulation result. Moreover, the processing condition determination auxiliary device 1 determines and prompts the adjustment direction of the processing conditions of the next trial processing simulation based on the relationship between the inappropriate processing conditions corresponding to the inappropriate simulation result and the processing conditions corresponding to the remaining simulation results, i.e., the remaining processing conditions. In addition, the processing condition determination auxiliary device 1 accepts the next processing condition set by the operator along the prompted adjustment direction, and replaces the inappropriate processing condition with the next processing condition received. Thus, the processing condition determination auxiliary device 1 can continuously adjust the processing conditions toward the preferred processing result. Therefore, the processing condition determination auxiliary device 1 can efficiently obtain appropriate processing conditions in a short time.

[0080] Implementation method 2.

[0081] Next, use Figures 7 to 11 Embodiment 2 is described. In embodiment 2, the processing condition determination support device learns the relationship between inappropriate processing conditions, remaining processing conditions, and processing condition adjustment directions corresponding to processing conditions set by the operator to generate a trained model as a learning result. Furthermore, the processing condition determination support device applies the inappropriate processing conditions and remaining processing conditions to the trained model to infer the processing condition adjustment direction corresponding to the processing conditions predicted to be set by the operator.

[0082] Figure 7 Detailed description of the invention Figure 2 is a block diagram showing the structure of a processing condition determination support device according to the second embodiment. Figure 7 Among the structural elements of Figure 1 The same reference numerals are used to indicate the same components of the machining condition determination support device 1 of the first embodiment, and duplicate descriptions are omitted. The following description will focus on the differences from the first embodiment.

[0083] The processing condition determination support device 2 learns the processing condition adjustment direction, infers the processing condition adjustment direction using the learning result, and presents it to the operator. The processing condition determination support device 2 includes a learning unit 31, an inference unit 32, and a learning data storage unit 30 on the basis of the structural elements of the processing condition determination support device 1. The learning unit 31 is connected to the adjustment direction determination unit 13 and the processing condition update unit 14, but the illustration of the connection line is omitted.

[0084] The learning unit 31 generates learning data obtained by learning the relationship between the inappropriate machining conditions and the remaining machining conditions and the machining condition adjustment direction corresponding to the machining conditions set by the operator, that is, a trained model 33. The machining condition adjustment direction corresponding to the machining conditions set by the operator corresponds to the direction of the vector from the point representing the inappropriate machining condition toward the point representing the machining condition set by the operator in the vector space based on the machining parameters.

[0085] The trained model 33 is a model for estimating the machining condition adjustment direction based on the inappropriate machining conditions and the remaining machining conditions. The learning data storage unit 30 stores the trained model 33 generated by the learning unit 31 .

[0086] The inference unit 32 infers the processing condition adjustment direction corresponding to the inappropriate processing condition and the remaining processing condition by applying the inappropriate processing condition and the remaining processing condition to the trained model 33. In addition, the inference unit 32 calculates the selectable range of the processing condition based on the inferred processing condition adjustment direction. The details of the learning unit 31 and the inference unit 32 will be described later.

[0087] The adjustment direction determining unit 13 calculates the machining condition adjustment direction based on the machining condition corresponding to the inappropriate simulation result selected by the operator and the machining conditions corresponding to the remaining simulation results. In addition, the machining condition adjustment direction calculated by the adjustment direction determining unit 13 also considers the case where it is not the shortest path to the final machining condition.

[0088] Therefore, the processing condition determination support device 2 of the second embodiment uses the learning unit 31 and the inference unit 32 as the learning inference mechanism to learn and infer the processing condition adjustment direction each time the processing condition adjustment direction is determined. The inferred processing condition adjustment direction becomes the processing condition adjustment direction after the processing condition adjustment direction determined by the adjustment direction determination unit 13 is corrected. That is, the processing condition adjustment direction inferred by the learning unit 31 and the inference unit 32 becomes the processing condition adjustment direction corresponding to the processing condition predicted to be determined by the operator. The processing condition determination support device 2 can reach the appropriate processing condition in fewer steps than the first embodiment by prompting the operator with the inferred processing condition adjustment direction.

[0089] The learning unit 31 can use a known algorithm such as supervised learning, unsupervised learning, reinforcement learning, etc. As a learning algorithm, the learning unit 31 can use a known algorithm such as supervised learning, unsupervised learning, or reinforcement learning. As an example, a case where a neural network is applied to the learning algorithm used by the learning unit 31 will be described.

[0090] The learning unit 31 learns the processing condition adjustment direction corresponding to the inappropriate processing condition and the remaining processing condition through so-called tutored learning, for example, according to the neural network model. Here, tutored learning refers to the following method, that is, by giving a data set (learning data) of input and result (label) to the learning unit 31, the features included in the learning data are learned, and the result is inferred based on the input.

[0091] A neural network is composed of an input layer composed of multiple neurons, an intermediate layer (hidden layer) composed of multiple neurons, and an output layer composed of multiple neurons. The intermediate layer can be one layer or more than two layers.

[0092] Figure 8 is a diagram for explaining a neural network used by a learning unit according to Embodiment 2. Figure 8 In the three-layer neural network shown, after multiple inputs are input to the input layer (X1 to X3), the values ​​are multiplied by weights W1 (w11 to w16) and input to the intermediate layer (Y1 to Y2). Furthermore, the result is further multiplied by weights W2 (w21 to w26) and output from the output layer (Z1 to Z3). The output result changes according to the values ​​of weights W1 and W2.

[0093] The neural network used by the learning unit 31 is based on learning data created based on a combination of inappropriate processing conditions and remaining processing conditions and processing condition adjustment directions corresponding to the processing conditions set by the operator, and learns the processing condition adjustment directions corresponding to the inappropriate processing conditions and remaining processing conditions through so-called supervised learning.

[0094] That is, the neural network learns by adjusting weights W1 and W2 so that the inappropriate processing conditions and remaining processing conditions as the first input are input, and the result output from the output layer is close to the processing condition adjustment direction as the second input (correct).

[0095] The neural network learns the correspondence between the inappropriate processing conditions and the remaining processing conditions and the processing condition adjustment direction, thereby generating a trained model 33 that can output an appropriate processing condition adjustment direction when the inappropriate processing conditions and the remaining processing conditions are input. As described above, the learning unit 31 learns the trained model 33 that can output a correct processing condition adjustment direction when the inappropriate processing conditions and the remaining processing conditions are input.

[0096] The learning unit 31 generates and outputs the trained model 33 by executing the above-described learning. The learned data storage unit 30 stores the trained model 33 output from the learning unit 31 .

[0097] In the learning phase, the learning unit 31 receives machining conditions corresponding to the inappropriate simulation results and the remaining simulation results selected by the operator from the adjustment direction determination unit 13. In addition, the learning unit 31 receives machining condition adjustment directions corresponding to the machining conditions set by the operator along the machining condition adjustment directions from the machining condition update unit 14.

[0098] In the second embodiment, the processing condition adjustment direction is Figure 5 The machining condition shown is presented to the operator as a combination of a reference axis 80 in the adjustment direction and a conical region 81 set around the reference axis 80 .

[0099] The learning unit 31 generates a trained model 33 by learning the relationship between the inappropriate machining conditions, the remaining machining conditions, and the machining condition adjustment direction corresponding to the machining conditions set by the operator, with respect to each trial (machining simulation) performed so far. In this case, the learning unit 31 improves the trained model 33 so that the deviation between the reference axis of the adjustment direction of the machining condition presented to the operator and the reference axis of the adjustment direction of the machining condition (machining condition to be tried next) expected to be selected by the operator is minimized.

[0100] In the inference stage, the inference unit 32 receives the inappropriate processing conditions and the remaining processing conditions from the adjustment direction determination unit 13. The inference unit 32 applies the inappropriate processing conditions and the remaining processing conditions to the trained model 33, and infers the reference axis of the adjustment direction of the processing conditions to be tried next. Moreover, the inference unit 32 calculates the selectable range of the processing conditions based on the inferred reference axis of the adjustment direction of the processing conditions, and presents it to the operator via the adjustment direction determination unit 13 and the display screen 50. As a result, the processing condition determination auxiliary device 2 can obtain the appropriate processing conditions with fewer trials than the processing condition determination auxiliary device 1.

[0101] Fig. 91 is a flowchart showing the processing sequence of the processing of prompting the processing of the processing condition adjustment direction performed by the processing condition determination support device according to Embodiment 2. The learning unit 31 of the processing condition determination support device 2 receives the inappropriate processing condition corresponding to the inappropriate simulation result selected by the operator from the adjustment direction determination unit 13 (step S110). In addition, the learning unit 31 receives the remaining processing conditions corresponding to the remaining simulation results from the adjustment direction determination unit 13 (step S120).

[0102] In addition, the learning unit 31 receives the processing condition adjustment direction corresponding to the processing condition set by the operator along the processing condition adjustment direction from the processing condition updating unit 14 (step S130). In addition, the remaining simulation results are determined by selecting the inappropriate simulation results, and then the operator sets the processing conditions, but the processing of steps S110 to S130 can be performed in any order. That is, the learning unit 31 can receive the inappropriate processing conditions, the remaining processing conditions, and the processing condition adjustment direction corresponding to the processing conditions set by the operator in any order.

[0103] The learning unit 31 outputs the trained model 33 for estimating the machining condition adjustment direction based on the inappropriate machining conditions and the remaining machining conditions (step S140 ). The trained model 33 is stored in the learning data storage unit 30 .

[0104] Then, when the machining condition adjustment direction is presented, the machining condition determination support device 2 estimates the machining condition adjustment direction using the trained model 33. Specifically, the estimation unit 32 reads the trained model 33 from the learning data storage unit 30 (step S150).

[0105] In addition, the inference unit 32 receives the inappropriate processing conditions corresponding to the inappropriate simulation results from the adjustment direction determination unit 13 (step S160). In addition, the inference unit 32 receives the remaining processing conditions corresponding to the remaining simulation results from the adjustment direction determination unit 13 (step S170). In addition, the processing of steps S150 to S170 can also be performed in any order.

[0106] The inference unit 32 applies the inappropriate processing conditions and the remaining processing conditions to the trained model 33, and infers the processing condition adjustment direction corresponding to the processing condition predicted to be set by the operator (step S180). The inference unit 32 calculates the selectable range of the processing condition according to the processing condition adjustment direction, and sends the selectable range of the processing condition to the adjustment direction determination unit 13.

[0107] The estimation unit 32 displays the selectable range of machining conditions on the display screen 50 via the adjustment direction determination unit 13, thereby presenting the selectable range of machining conditions to the operator (step S190). The selectable range of machining conditions includes information on the machining condition adjustment direction (reference axis).

[0108] Here, use Fig.10 , which explains the processing order of the learning unit 31 to learn the trained model 33. Fig.10 This is a flowchart showing the processing procedure of the learning process executed by the learning unit involved in the second embodiment.

[0109] The learning unit 31 acquires learning data used for learning (step S210 ). Specifically, the learning unit 31 acquires inappropriate machining conditions and remaining machining conditions and machining condition adjustment directions corresponding to the machining conditions set by the operator.

[0110] In addition, in step S210, the learning unit 31 simultaneously obtains the inappropriate processing conditions and the remaining processing conditions and the processing condition adjustment direction corresponding to the processing conditions set by the operator, but they can be obtained at any timing. That is, the learning unit 31 can input the inappropriate processing conditions and the remaining processing conditions and the processing condition adjustment direction corresponding to the processing conditions set by the operator in association, and can obtain the inappropriate processing conditions, the remaining processing conditions, and the processing condition adjustment direction corresponding to the processing conditions set by the operator at different timings.

[0111] The learning unit 31 performs learning processing using the inappropriate processing conditions and the remaining processing conditions and the processing condition adjustment direction corresponding to the processing conditions set by the operator (step S220). Specifically, the learning unit 31 learns the processing condition adjustment direction corresponding to the inappropriate processing conditions and the remaining processing conditions through so-called supervised learning according to the learning data created based on the combination of the acquired inappropriate processing conditions and the remaining processing conditions and the processing condition adjustment direction corresponding to the processing conditions set by the operator, and generates a trained model 33.

[0112] After generating the trained model 33, the learning unit 31 outputs the trained model 33 to the learning data storage unit 30 (step S230). The learning data storage unit 30 stores the trained model 33 generated by the learning unit 31.

[0113] Next, use Fig.11 , which explains the processing sequence of the inference unit 32 using the trained model 33 to infer the processing condition adjustment direction. Fig.11 This is a flowchart showing the processing procedure of the estimation process performed by the estimation unit involved in the second embodiment.

[0114] The inference unit 32 obtains inference data used for inference of the machining condition adjustment direction (step S310 ). Specifically, the inference unit 32 obtains inappropriate machining conditions and surplus machining conditions. The inference unit 32 reads out the trained model 33 from the learning data storage unit 30 .

[0115] The inference unit 32 inputs the inappropriate processing conditions and the remaining processing conditions into the trained model 33 (step S320 ) to obtain the appropriate processing condition adjustment direction.

[0116] The inference unit 32 outputs the data inferred using the trained model 33 (step S330). Specifically, the inference unit 32 outputs the appropriate processing condition adjustment direction obtained by the trained model 33, thereby prompting the operator with the appropriate processing condition adjustment direction via the adjustment direction determination unit 13 and the display screen 50.

[0117] Here, the hardware configuration of the machining condition determination support devices 1 and 2 will be described. Fig.12 This is a diagram showing an example of a hardware configuration for realizing a processing condition determination support device according to the first and second embodiments.

[0118] In addition, the processing condition determination auxiliary devices 1 and 2 have the same hardware structure, so the hardware structure of the processing condition determination auxiliary device 1 is described here. The processing condition determination auxiliary device 1 can be implemented by an input device 300, a processor 100, a memory 200, and an output device 400. An example of the processor 100 is a CPU (also called a Central Processing Unit, a central processing unit, a processing device, an arithmetic device, a microprocessor, a microcomputer, a DSP (Digital Signal Processor)) or a system LSI (Large Scale Integration). An example of the memory 200 is a RAM (Random Access Memory) and a ROM (Read Only Memory).

[0119] The processing condition determination support device 1 is implemented by the processor 100 reading and executing a processing condition determination support program executable by a computer and stored in the memory 200 for executing the operation of the processing condition determination support device 1. The processing condition determination support program, which is a program for executing the operation of the processing condition determination support device 1, can be said to be a procedure or method for causing a computer to execute the processing condition determination support device 1.

[0120] The processing condition determination support program executed by the processing condition determination support device 1 has a module structure including a simulation execution unit 11, a simulation display unit 12, an adjustment direction determination unit 13, a selection acceptance unit 15, and a processing condition update unit 14. The processing condition determination support program is the simulation execution unit 11, the simulation display unit 12, the adjustment direction determination unit 13, the selection acceptance unit 15, and the processing condition update unit 14 downloaded to the main storage device, and the simulation execution unit 11, the simulation display unit 12, the adjustment direction determination unit 13, the selection acceptance unit 15, and the processing condition update unit 14 are generated on the main storage device.

[0121] The input device 300 receives an operation performed by an operator and sends it to the processor 100. The memory 200 corresponds to the storage unit 20. The memory 200 stores a material shape model 21, a tool model 22, tool movement instruction data 23, and a processing condition set 24. In addition, the memory 200 stores processing simulation results calculated by the processor 100, adjustment directions of processing conditions, and the like.

[0122] The output device 400 outputs the machining conditions used by the processor 100 during machining simulation, the machining simulation results calculated by the processor 100, etc. to the display screen 50. In addition, the output device 400 outputs the adjustment direction of the machining conditions calculated by the processor 100 to the display screen 50. In addition, the output device 400 outputs the machining conditions set by the operator to the display screen 50.

[0123] The material shape model 21, the tool model 22, the tool movement command data 23, and the machining condition set 24 in the memory 200 are read by the processor 100. The memory 200 is used as a temporary memory when the processor 100 executes various processes.

[0124] The processing condition determination auxiliary program can be provided as a computer program product by storing a file in an installable form or an executable form in a computer-readable storage medium. In addition, the processing condition determination auxiliary program can also be provided to the processing condition determination auxiliary device 1 via a network such as the Internet. In addition, regarding the functions of the processing condition determination auxiliary device 1, part of it can be realized by dedicated hardware such as a dedicated circuit, and part of it can be realized by software or firmware.

[0125] In addition, one or more of the simulation execution unit 11, the simulation display unit 12, the adjustment direction determination unit 13, the selection acceptance unit 15 and the processing condition update unit 14 can be implemented by the above-mentioned input device 300, the processor 100, the memory 200 and the output device 400.

[0126] In addition, the simulation execution unit 11, the simulation display unit 12, the adjustment direction determination unit 13, the selection acceptance unit 15, the processing condition update unit 14, the storage unit 20, the learning unit 31, the inference unit 32, and the learning data storage unit 30 may be arranged in different places. In this case, at least a part of the simulation execution unit 11, the simulation display unit 12, the adjustment direction determination unit 13, the selection acceptance unit 15, the processing condition update unit 14, the storage unit 20, the learning unit 31, the inference unit 32, and the learning data storage unit 30 is connected to a network, and data is sent and received via the network. That is, the processing condition determination auxiliary processing described in the second embodiment can be realized by a processing condition determination auxiliary system in which at least a part of the simulation execution unit 11, the simulation display unit 12, the adjustment direction determination unit 13, the selection acceptance unit 15, the processing condition update unit 14, the storage unit 20, the learning unit 31, the inference unit 32, and the learning data storage unit 30 is connected to a network.

[0127] As described above, in the second embodiment, the processing condition determination auxiliary device 2 learns the relationship between the inappropriate processing conditions and the remaining processing conditions and the processing condition adjustment direction corresponding to the processing conditions set by the operator to generate a trained model. Moreover, the processing condition determination auxiliary device 2 applies the inappropriate processing conditions and the remaining processing conditions to the trained model, thereby inferring the processing condition adjustment direction corresponding to the processing conditions predicted to be set by the operator. As a result, the processing condition determination auxiliary device 2 can suggest a more appropriate processing condition adjustment direction than the processing condition determination auxiliary device 1, and can therefore efficiently obtain appropriate processing conditions in a shorter time than the processing condition determination auxiliary device 1.

[0128] The configuration described in the above embodiment is merely an example, and may be combined with other known technologies, the embodiments may be combined with each other, and part of the configuration may be omitted or changed without departing from the gist.

[0129] Description of the label

[0130] 1, 2 machining condition determination auxiliary device, 11 simulation execution unit, 12 simulation display unit, 13 adjustment direction determination unit, 14 machining condition update unit, 15 selection acceptance unit, 20 storage unit, 21 material shape model, 22 tool model, 23 tool movement instruction data, 24 machining condition set, 24a machining condition, 30 learning data storage unit, 31 learning unit, 32 inference unit, 33 trained model, 41 movement instruction analysis unit, 42 numerical control unit, 43 mechanical response calculation unit, 44 cutting simulation unit, 45 processed shape, 50 display screen, 51 mouse, 52 keyboard, 61 movement instruction, 62 servo instruction, 63 servo FB data, 64 tool movement trajectory, 71, 72 display screen, 75 end button, 80 reference axis, 81 cone area, 100 processor, 200 memory, 300 input device, 400 output device, P1~P3 parameters, QA~QD points, RA~RD machining conditions, SA~SD machining simulation results.

Claims

1. A processing condition determination assisting device for assisting in determining processing conditions in processing a workpiece using a machine tool, The processing condition determining auxiliary device is characterized by having: a simulation execution unit that executes machining simulation of the workpiece for each of a plurality of machining conditions based on a material shape model representing the shape of the workpiece before machining, a tool model representing the shape of a tool used for machining, and tool movement instruction data that specifies movement of the tool during machining operations; A simulation display unit, which displays the result of the machining simulation, i.e., the simulation result, on a display screen; a selection accepting unit for accepting a selection from an operator with respect to the displayed simulation result; as well as An adjustment direction determination unit determines and presents an adjustment direction of machining conditions of a machining simulation to be tried next based on the selection accepted by the selection acceptance unit.

2. The processing condition determination auxiliary device according to claim 1, characterized in that: The selection accepting unit accepts an inappropriate simulation result selected by the operator as the most inappropriate simulation result from the viewpoint of whether the machining is acceptable or not, among the displayed simulation results. The adjustment direction determination unit determines and prompts the adjustment direction of the processing conditions of the next trial processing simulation based on the relationship between the processing conditions corresponding to the inappropriate simulation result, i.e., the inappropriate processing conditions, and the processing conditions corresponding to the remaining simulation results that have not been selected, i.e., the remaining processing conditions.

3. The processing condition determination auxiliary device according to claim 2, characterized in that: The processing condition updating unit is further provided, the processing condition updating unit receiving a next processing condition set by the operator along the presented adjustment direction and replacing the inappropriate processing condition with the received next processing condition.

4. The processing condition determination auxiliary device according to claim 2, characterized in that: The processing conditions include multiple processing parameters. The adjustment direction determination unit determines an adjustment direction of the machining conditions of the machining simulation to be tried next based on a vector from the inappropriate machining condition to the remaining machining conditions in a vector space based on the machining parameters.

5. The processing condition determination auxiliary device according to claim 4, characterized in that: The simulation display unit displays the adjustment direction of the machining condition determined by the adjustment direction determination unit in a vector space based on the machining parameters.

6. The processing condition determination auxiliary device according to any one of claims 1 to 5, characterized in that: The simulation display unit displays the simulation results by arranging the simulation results.

7. The processing condition determination auxiliary device according to claim 2, characterized in that: Also features: a learning unit that generates a trained model for inferring an adjustment direction of the next processing condition based on the inappropriate processing condition, the remaining processing conditions, and the processing condition set by the operator; and An inference unit infers an adjustment direction of the next processing condition corresponding to the inappropriate processing condition and the remaining processing conditions using the trained model.

8. A processing condition determination support system for supporting the determination of processing conditions in processing a workpiece using a machine tool The processing condition determination auxiliary system is characterized by having: a simulation execution unit that executes machining simulation of the workpiece for each of a plurality of machining conditions based on a material shape model representing the shape of the workpiece before machining, a tool model representing the shape of a tool used for machining, and tool movement instruction data that specifies movement of the tool during machining operations; A simulation display unit, which displays the result of the machining simulation, i.e., the simulation result, on a display screen; a selection accepting unit for accepting a selection from an operator with respect to the displayed simulation result; as well as an adjustment direction determining unit that determines and presents an adjustment direction of a machining condition of a machining simulation to be tried next based on the selection received by the selection receiving unit, At least a part of the simulation execution unit, the simulation display unit, the selection acceptance unit, and the adjustment direction determination unit is connected to a network.

9. A method for assisting in determining a processing condition in processing a workpiece using a machine tool, The processing condition determination auxiliary method is characterized by comprising the following steps: A simulation execution step, wherein the processing condition determination auxiliary device executes the processing simulation of the processing object for a plurality of processing conditions respectively based on a material shape model representing the shape of the processing object before processing, a tool model representing the shape of a tool used for processing, and tool movement instruction data for specifying the movement of the tool during processing; A simulation display step, wherein the processing condition determination auxiliary device displays the result of the processing simulation, i.e., the simulation result, on a display screen; a selection acceptance step, wherein the processing condition determination auxiliary device accepts a selection from an operator with respect to the displayed simulation result; as well as In the adjustment direction determination step, the machining condition determination support device determines and presents an adjustment direction of machining conditions for a machining simulation to be tried next based on the selection.

10. A processing condition determination support program for supporting the determination of processing conditions in processing a workpiece using a machine tool, The processing condition determination auxiliary program is characterized in that the computer is caused to execute the following steps: A simulation execution step of executing machining simulation of the workpiece for a plurality of modes of machining conditions, based on a material shape model representing the shape of the workpiece before machining, a tool model representing the shape of a tool used for machining, and tool movement instruction data for specifying the movement of the tool during machining; A simulation display step, displaying the result of the machining simulation, i.e., the simulation result, on a display screen; A selection acceptance step of accepting a selection from an operator with respect to the displayed simulation result; as well as The adjustment direction determination step determines and presents the adjustment direction of the machining conditions of the machining simulation to be tried next based on the selection.

Images