Mold maintenance system, mold quality determination threshold generation device, mold quality determination method and program

Abstract

A die maintenance system (100) comprises: a TPP processing machine (1) that is provided with a plurality of dies and that selectively uses a die according to an NC program to perform processing; an NC data monitoring device (2) that acquires NC data which indicates the content of processing of the TPP processing machine (1); a sensing device (3) that generates measurement data obtained by measuring processing sounds which are generated when the die is used by the TPP processing machine (1); a die quality determination threshold value generation device (5) that, on the basis of the measurement data, generates threshold value data which serves as a reference for determining the quality of the die of the TPP processing machine (1); and a die quality determination device (6) that, on the basis of the NC data, the measurement data, and the threshold value data which serves as the reference for determining the quality of the die, determines the quality of the die of the TPP processing machine (1).

Description

Technical Field

[0001] The present disclosure relates to a mold maintenance system, a mold quality determination threshold value generation device, a learning device, a mold quality determination method, and a program.

Background Art

[0002] In a sheet metal processing site, there is a TPP (Turret Punch Press) processing machine as an automatic processing machine equipped with hundreds of types of general-purpose molds and capable of punching into a determined shape. Since the TPP processing machine has a large number of general-purpose molds, it is used for mass production of multiple varieties and small quantities such as individual order production. In the TPP processing machine, mold inspection is performed because the wear state of the edge portion of the mold (die and punch) has a significant impact on the quality of the processed product and the productivity of the equipment.

[0003] In the mold inspection of the TPP processing machine, when the wear state of the mold is confirmed and it is determined that the wear has progressed, maintenance or replacement is performed. Generally, the number of uses of the mold is used as an index for confirming the wear state of the mold. Hereinafter, the number of uses of the mold is referred to as the punch number. The punch number can be obtained from the equipment. However, in the TPP processing machine, there are various processing methods using molds such as piercing and nibbling. For example, in piercing, only a part of the mold is used, and the worn portion is limited. Also, the application frequency of each processing method varies depending on the product to be processed. Therefore, based only on the punch number, it is not possible to accurately grasp the wear state of the mold and determine the appropriate inspection timing.

[0004] There are two main problems with mold inspection: over-inspection and under-inspection. Over-inspection involves maintaining molds that are still usable. Ideally, molds should be usable in production without replacement, but if they become unusable, production using that equipment is impossible during the replacement period, leading to a decrease in productivity. Under-inspection involves failing to perform necessary maintenance because wear that cannot be determined by punch count alone is progressing. As mold wear progresses, burrs are more likely to occur on the cut surface of the workpiece, resulting in significant losses due to poor quality. Furthermore, processing with excessively worn molds can cause mold breakage and lead to equipment shutdown.

[0005] Currently, skilled workers must remove the molds from the equipment and directly inspect the processed surface to determine wear. However, this method of mold inspection by skilled workers increases costs because it requires equipment downtime and labor for the workers each time an inspection is performed. Furthermore, it is necessary to secure skilled workers who can properly inspect molds in the sheet metal workshop. In addition, the judgment of mold wear is subjective, and if proper mold inspection is not performed, quality deterioration and equipment downtime due to processing defects will occur. For these reasons, there is a need for technology that can detect mold wear and automatically determine the quality of the molds.

[0006] Patent Document 1 discloses a technology for detecting die wear in a TPP processing machine from characteristic data of punching sounds. [Prior art documents] [Patent Documents]

[0007] [Patent Document 1] Japanese Patent Application Publication No. 4-42024 [Overview of the Initiative] [Problems that the invention aims to solve]

[0008] In TPP processing machines, the processing conditions for the mold and workpiece (mold shape, processing method, sheet thickness, material, etc.) differ each time. Therefore, if the technology described in Patent Document 1 were applied to mold inspection of a TPP processing machine, a standard for determining the quality of the mold would be required for each processing condition. For example, if sheet metal processing is performed with 5 different sheet thicknesses, 5 different materials, and 300 types of molds, it would be necessary to prepare 7500 patterns (5 x 5 x 300) of standards for determining the quality of the mold. However, this would incur a huge cost for preparing and acquiring data to set the standards for determining the quality of the mold, making it impractical.

[0009] This disclosure is made to solve the problems described above, and aims to enable automatic mold quality determination for TPP processing machines and reduce the cost of setting criteria for mold quality determination. [Means for solving the problem]

[0010] To achieve the above objectives, the mold maintenance system relating to this disclosure is provided for TPP processing machines and , se A fitting device and a mold quality judgment criterion generation device. ,of The TPP processing machine is equipped with multiple dies and performs processing by selectively using the dies according to the NC program. . The measuring device measures the processing noise generated when using a mold in the TPP processing machine and generates measurement data. The mold quality judgment criterion generation device generates threshold data or a trained model that serves as the criterion for judging the quality of the mold in the TPP processing machine based on the measurement data. The mold quality judgment criterion generation device comprises: a threshold calculation unit that calculates a threshold value for mold quality judgment from experimental data, which is measurement data obtained in a previously conducted experiment, and generates threshold data that indicates the calculated threshold value; and a threshold estimation unit that estimates a threshold value for mold quality judgment under processing conditions other than the processing conditions used in the experiment, based on the threshold value calculated by the threshold calculation unit, and generates threshold data that indicates the estimated threshold value. . [Effects of the Invention]

[0011] According to this disclosure, threshold data or a trained model that serves as the basis for determining the quality of a TPP processing machine's mold is automatically generated based on measurement data. Based on NC data, measurement data, and the threshold data or trained model, the TPP processing machine's mold quality determination is performed automatically, thereby reducing the cost of setting criteria for determining the quality of a TPP processing machine's mold. [Brief explanation of the drawing]

[0012] [Figure 1] Figure showing a configuration example of the mold maintenance system according to Embodiment 1 [Figure 2] Figure showing a functional configuration example of the TPP processing machine, NC data monitoring device, and sensing device according to Embodiment 1 [Figure 3] Figure showing an example of the execution processing data according to Embodiment 1 [Figure 4] Figure showing an example of the mold quality determination criteria data [Figure 5] Figure showing a functional configuration example of the processing condition setting device, mold quality determination threshold generation device, and mold quality determination device according to Embodiment 1 <0​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​ [Figure 18] Figure showing the result of clustering the experimental data according to Embodiment 1 by the K-means method [Figure 19] Flowchart showing an example of the operation of the trained model generation process according to Embodiment 3 [Figure 20] Figure showing a configuration example of the die maintenance system according to the modification example [Figure 21] Figure showing a functional configuration example of the sensing device according to the modification example [Figure 22] Figure showing an example of the hardware configuration of the die quality determination threshold generation device, die quality determination device, NC program change device, and learning device according to Embodiments 1 to 3

Embodiments for Carrying out the Invention

[0013] Hereinafter, the die maintenance system, die quality determination threshold generation device, learning device, die quality determination method, and program according to Embodiment 1 of the present invention will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are denoted by the same reference numerals. In the present embodiment, "no" in the die quality determination means a state in which punching defects occur due to wear of the edge portions of the die and punch die, and replacement or polishing is required, regardless of whether the die can be used. Generally, as the wear of the die progresses, the shearing stress increases, resulting in an increase in the processing sound and impact during punching. The die maintenance system performs die quality determination by sensing the above phenomena associated with the wear of the die of the TPP processing machine.

[0014] (Embodiment 1) The configuration of the mold maintenance system 100 according to Embodiment 1 will be explained with reference to Figure 1. The mold maintenance system 100 includes a TPP processing machine 1 equipped with multiple molds that selectively uses the molds according to an NC program to perform processing such as drilling and molding; an NC data monitoring device 2 that reads and stores NC data indicating the processing content displayed on the TPP processing machine 1; a sensing device 3 that measures the processing sound generated when the molds are used by the TPP processing machine 1; a processing condition setting device 4 that accepts input of processing conditions for the TPP processing machine 1; a mold quality determination threshold generation device 5 that generates threshold data indicating thresholds that serve as the basis for determining the quality of the molds of the TPP processing machine 1; and a mold quality determination device 6 that performs mold quality determination of the TPP processing machine 1 using the thresholds. The NC data includes information such as an NC code indicating the processing content, the thickness of the workpiece, the material of the workpiece, and the processing date and time.

[0015] The functional configuration of the TPP processing machine 1, the NC data monitoring device 2, and the sensing device 3 will be explained using Figure 2. The TPP processing machine 1 includes a press working unit 11 that performs processing such as drilling and forming according to an NC program, and an NC data display unit 12 that displays the NC data of the processing being performed in the press working unit 11. The press working unit 11 is a sheet metal processing device that positions the workpiece at the processing date and time included in the NC data, selectively uses a die based on the NC code, and performs processing such as drilling and forming. The NC data display unit 12 displays the NC data of the processing being performed in the press working unit 11. Hereinafter, the processing performed in the press working unit 11 as indicated by the NC data will be referred to as the executed processing.

[0016] The NC data monitoring device 2 includes an NC data acquisition unit 21 that reads NC data, an NC data storage unit 22 that stores the NC data read by the NC data acquisition unit 21, a mold NC code master storage unit 23 that stores a mold NC code master that links NC codes with molds used for machining, and an execution machining data generation unit 24 that generates execution machining data by adding data of the molds used for machining to the NC data based on the NC data and the mold NC code master.

[0017] The NC data acquisition unit 21 is a camera that reads the NC data displayed on the NC data display unit 12 of the TPP machining center 1. TPP machining centers are manufactured by various manufacturers, and while the NC program and NC data display unit may differ depending on the manufacturer, the basic configuration is the same. Therefore, if the NC data acquisition unit 21 is a camera, it can read the displayed NC data regardless of the manufacturer of the TPP machining center 1. The NC data acquisition unit 21 is not limited to a camera; it may also acquire NC data directly from the TPP machining center 1. In this case, it is necessary to develop an interface for each manufacturer of the TPP machining center 1. The NC data acquisition unit 21 stores the read NC data in the NC data storage unit 22.

[0018] The execution machining data generation unit 24 adds data on the mold used for machining to the NC data based on the NC data stored in the NC data storage unit 22 and the mold NC code master stored in the mold NC code master storage unit 23, and generates execution machining data that includes the type of mold used in the execution machining, the machining method, the plate thickness of the workpiece, the material of the workpiece, the date and time of machining, etc. The execution machining data generation unit 24 transmits the generated execution machining data to the mold quality determination device 6.

[0019] Here, the execution machining data will be explained using Figure 3. The example of execution machining data shown in Figure 3 has the following items: "NC data" indicating the NC data number of the processed sheet, "NC code" indicating the NC code included in the NC data read by the NC data acquisition unit 21, "mold shape" indicating the shape of the mold used for the execution machining, "machining method" indicating the machining method of the execution machining, "material" indicating the material of the workpiece for the execution machining, "plate thickness" indicating the plate thickness of the workpiece for the execution machining, and "date and time" indicating the date and time of the execution machining. The "mold shape" item is not limited to the shape of the mold, but can be any information that can identify the type of mold. For example, when machining at the position (100,100) with NC code XXXXX-XXX-X1 using mold T0000001, the mold shape used for the execution machining is 6-60, and the machining method is single-stroke. The material of the workpiece is SUS (Steel Use Stainless), and the plate thickness is 3.5 mm. The processing date and time is 13:00:25 on XX / XX / 20XX.

[0020] Returning to Figure 2, the sensing device 3 measures the processing noise generated when the mold is used in the TPP processing machine 1. The sensing device 3 includes a processing noise acquisition unit 31 that acquires the processing noise of the actual processing from sound sensors installed near the processing point of the TPP processing machine 1. The processing noise acquisition unit 31 transmits the acquired measurement data of the processing noise of the actual processing to the mold quality determination device 6.

[0021] To determine the quality of a mold using measurement data of processing sounds, it is necessary to create threshold data that indicates the threshold value used as the standard for determining the quality of the mold. This threshold data must be set for each processing condition, including the type of mold, the thickness and material of the workpiece, and the processing method. The TPP processing machine 1 can be equipped with hundreds of types of molds, and the material and thickness of the workpieces vary. Therefore, experimentally creating mold quality determination criterion data that indicates the threshold value for all processing conditions, as shown in Figure 4, would incur enormous costs and man-hours. Thus, the mold maintenance system 100 of this embodiment solves this problem by having a mold quality determination threshold generation device 5 that automatically generates threshold data that indicates the threshold value used as the standard for determining the quality of the mold.

[0022] The functional configurations of the processing condition setting device 4, the mold quality determination threshold generation device 5, and the mold quality determination device 6 will be explained with reference to Figure 5. The processing condition setting device 4 includes a processing condition acquisition unit 41 that receives input of processing conditions for the TPP processing machine 1 from the user and generates processing condition data, and a processing condition storage unit 42 that stores the processing condition data. The user inputs the type of mold provided by the TPP processing machine 1, the processing method for each mold, the plate thickness of the target workpiece, and the material of the target workpiece to the processing condition acquisition unit 41, and generates processing condition data that reflects the input content. The processing condition acquisition unit 41 may acquire processing condition data from an external device or system and store it in the processing condition storage unit 42.

[0023] Here, we will explain the processing condition data using Figure 6. The example of processing condition data shown in Figure 6 has the following items: "Die Shape" indicating the shape of the die, "Material" indicating the material of the workpiece to be processed by the die, "Sheet Thickness" indicating the plate thickness of the workpiece to be processed by the die, and "Processing Method" indicating the processing method of the die. The "Die Shape" item is not limited to the shape of the die, but can be any information that can identify the type of die. For example, if the die shape is 6-60, the material of the workpiece is SUS, and the plate thickness is 3.5 mm, then the processing method is punching.

[0024] Returning to Figure 5, the mold quality judgment threshold generation device 5 comprises an experimental data storage unit 51 that stores experimental data, which is measurement data acquired in a previous experiment; a threshold calculation unit 52 that calculates a threshold that serves as the criterion for mold quality judgment from the experimental data; and a threshold estimation unit 53 that estimates the threshold for mold quality judgment under processing conditions other than the processing conditions used in the experiment. The mold quality judgment threshold generation device 5 is an example of a mold quality judgment criterion generation device. Hereinafter, processing conditions other than the processing conditions used in the experiment will be referred to as other processing conditions.

[0025] The experimental data storage unit 51 stores in advance, as experimental data, measurement data acquired from the sensing device 3 during processing that was previously performed as an experiment, for normal molds that should be judged as "good" (hereinafter referred to as "normal molds") and molds that are worn and require replacement or polishing that should be judged as "bad" (hereinafter referred to as "abnormal molds").

[0026] The threshold calculation unit 52 uses a statistical analysis method (e.g., principal component analysis) to calculate a threshold for determining whether a mold is good or bad from experimental data of normal and abnormal molds, and stores the threshold data representing the calculated threshold in the threshold storage unit 54.

[0027] The threshold estimation unit 53 estimates the threshold under other conditions based on the threshold data stored in the threshold storage unit 54 by the threshold calculation unit 52, and stores the threshold data indicating the threshold under other conditions in the threshold storage unit 54. For threshold estimation, it is necessary to create an algorithm for each processing parameter such as "plate thickness," "material," and "processing method."

[0028] Here, as an example, we will explain the method for calculating and estimating the threshold when the plate thickness is different. In the experiment, workpieces of the same material and plate thickness are processed using the same processing method with both a normal die and an abnormal die, and measurement data of the processing sound is obtained for each. The experimental data storage unit 51 stores the measurement data of the processing sound obtained from the normal die and the abnormal die as experimental data.

[0029] First, let's explain how to calculate the threshold. The threshold calculation unit 52 calculates the maximum value of the sound waveform of the measurement sound data included in the experimental data stored in the experimental data storage unit 51, and performs a Fast Fourier Transform (FFT) on the measurement sound data. Hereafter, the process of performing a Fast Fourier Transform on the measurement sound data will be abbreviated as FFT analysis. Figure 7 shows a graph comparing the integration results of the FFT analysis of the experimental data. In the graph in Figure 7, the first axis is the maximum value of the sound waveform, and the second axis is the integral value of the FFT analysis. The graph clearly shows that there is a difference between normal molds and abnormal molds. Abnormal molds tend to have larger values ​​on both the first and second axes compared to normal molds. This is because the wear on the edges of the mold increases friction with the workpiece, resulting in louder processing noise. The threshold calculation unit 52 calculates a threshold for determining whether a mold is good or bad based on the difference in experimental data between normal molds and abnormal molds. For example, the threshold could be the maximum value of the sum of the values ​​on the first and second axes of the graph for a normal mold, as shown in Figure 7. Alternatively, the threshold calculation unit 52 could output a graph comparing the integral results obtained by FFT analysis, as shown in Figure 7, and the user could input a threshold to the threshold calculation unit 52 by looking at the difference between the experimental data of the normal mold and the abnormal mold in the output graph.

[0030] Next, we will explain the method for estimating thresholds under other conditions. Figure 8 is a graph comparing the integral results of FFT analysis of experimental data obtained by processing four different thicknesses of the same material using the same mold. Similar to the graph in Figure 7, the first axis of the graph in Figure 8 is the maximum value of the sound waveform, and the second axis is the integral value of the FFT analysis. The graph shows that there is a positive correlation that increases as the thickness of the sheet metal increases. From Figures 7 and 8, it can be inferred that there is also a correlation between the sheet metal thickness and the threshold for determining the quality of the mold.

[0031] For example, the loudness of the processing sound during blanking is proportional to the magnitude of the elastic energy released mainly from the punch frame during a breakthrough, known as the breakthrough phenomenon (see Research and Development Grant AF-93012, FY1993). The sound energies Q1 and Q2 generated when processing workpieces of the same material with thicknesses t1 and t2 (t1>t2) can be expressed by the following equations 1 and 2, respectively, where k is the spring constant, x1 is the elongation value of the frame during breakthrough for the workpiece with thickness t1, x2 is the elongation value of the frame during breakthrough for the workpiece with thickness t2, and α is the conversion rate from elastic energy to sound energy.

[0032]

number

[0033]

number

[0034] If the relationship between plate thicknesses t1 and t2 and the frame elongation values ​​x1 and x2 can be expressed as t1:t2=x1:x2, then the relationship between sound energy and plate thickness can be expressed by the following equation 3.

[0035]

number

[0036] From equation 3, we can see that there is a squared relationship between plate thickness and sound energy. For example, if the plate thickness doubles, the sound energy quadruples. Figure 9 is a graph of the experimental data shown in Figure 8, with the first axis representing plate thickness and the second axis representing the integral value of the FFT analysis. The graph in Figure 9 shows the maximum, minimum, median, and mean values ​​of the integral value of the FFT analysis for each plate thickness. From the graph in Figure 9, we can see that the sound energy increases as the plate thickness increases.

[0037] As shown in Figures 8 and 9, experiments are conducted in advance in which workpieces of the same material but with different plate thicknesses are processed using the same die. Based on the experimental data, the threshold estimation unit 53 calculates an estimation formula that reflects the change in the integral value of the FFT analysis, which changes with increasing plate thickness, as the threshold. The threshold estimation unit 53 estimates the threshold for processing conditions with different plate thicknesses by substituting the die judgment threshold and plate thickness values ​​calculated by the threshold calculation unit 52 into the calculated estimation formula.

[0038] Up to this point, we have explained the method for calculating and estimating thresholds when the plate thickness differs. The threshold estimation unit 53 calculates estimation formulas similarly for parameters other than plate thickness. Parameters other than plate thickness include not only material and processing method, but also, for example, if there is a mold that is the same shape as the mold used in the experiment but is of a different size, the estimation formula may be calculated similarly.

[0039] The threshold estimation unit 53 acquires processing condition data from the processing condition storage unit 42 of the processing condition setting device 4. The threshold estimation unit 53 may also accept processing condition data input from the user. In this case, the mold maintenance system 100 and the processing condition setting device 4 do not need to be provided. The threshold storage unit 54 may also store threshold data in advance that indicates the threshold for the processing conditions at the time of the experiment. In this case, the mold quality judgment threshold generation device 5 does not need to include the experimental data storage unit 51 and the threshold calculation unit 52.

[0040] The threshold estimation unit 53 estimates the thresholds for the other processing conditions indicated by the processing condition data, using an estimation formula for each parameter, based on the threshold data stored in the threshold storage unit 54 by the threshold calculation unit 52 and the processing condition data obtained from the processing condition storage unit 42. The threshold estimation unit 53 stores the threshold data indicating the thresholds for all other processing conditions indicated by the processing condition data in the threshold storage unit 54. Since the threshold storage unit 54 already stores the threshold data indicating the thresholds for the processing conditions at the time of the experiment by the threshold calculation unit 52, the threshold storage unit 54 will end up storing the threshold data indicating the thresholds for all processing conditions indicated by the processing condition data.

[0041] The mold quality determination device 6 includes a processing measurement data generation unit 61 that generates processing measurement data by associating measurement data with execution processing data, a processing measurement data storage unit 62 that stores the processing measurement data, a quality determination unit 63 that performs mold quality determination based on the processing measurement data and threshold data, a determination result storage unit 64 that stores determination result data indicating the determination result of the mold quality determination, and a determination result output unit 65 that outputs the determination result data.

[0042] The machining measurement data generation unit 61 generates machining measurement data by associating the measurement data acquired from the sensing device 3 with the execution machining data acquired from the NC data monitoring device 2, and stores it in the machining measurement data storage unit 62. The quality determination unit 63 acquires threshold data corresponding to the machining measurement data stored in the machining measurement data storage unit 62 from the threshold storage unit 54 of the mold quality determination threshold generation device 5. For each mold used in the execution machining indicated by the machining measurement data stored in the machining measurement data storage unit 62, the quality determination unit 63 performs a mold quality determination using the threshold indicated by the threshold data acquired from the mold quality determination threshold generation device 5. For example, the quality determination unit 63 determines a mold as good if the number of times the machining noise level indicated by the machining measurement data exceeds the threshold does not exceed a predetermined number (n≧1), and determines a mold as bad if it exceeds the predetermined number (n≧1). The quality determination unit 63 stores the determination result data indicating the determination result in the determination result storage unit 64. The judgment result output unit 65 outputs the judgment result data stored in the judgment result storage unit 64.

[0043] The judgment result data includes the NC data of the machining operation performed using the mold in question. The method of outputting the judgment result data may be, for example, by displaying it on a screen, by sending it to a terminal used by the user, or by sending it to an external device or system. The user and the external device or system determine, based on the NC data included in the judgment result data, which machining operation of the TPP machining center 1 the mold used for was judged. The information identifying the machining operation is not limited to NC data; for example, it may be a number that uniquely identifies the machining operation.

[0044] Next, the flow of the mold quality determination threshold generation process and the mold quality determination process executed in the mold maintenance system 100 will be explained using Figures 10 and 11. The mold quality determination threshold generation process shown in Figure 10 starts, for example, when a threshold generation instruction is input to the mold quality determination threshold generation device 5. When a threshold generation instruction is input to the mold quality determination threshold generation device 5, the threshold calculation unit 52 uses a statistical analysis method (e.g., principal component analysis) to calculate the mold quality determination threshold from the experimental data of normal and abnormal molds stored in the experimental data storage unit 51 (step S11), and stores the threshold data indicating the calculated threshold in the threshold storage unit 54 (step S12).

[0045] The threshold estimation unit 53 acquires processing condition data from the processing condition storage unit 42 of the processing condition setting device 4 (step S13). The threshold estimation unit 53 calculates an estimation formula for each parameter based on the threshold data stored in the threshold storage unit 54 by the threshold calculation unit 52 and the processing condition data acquired from the processing condition storage unit 42 (step S14). Using the calculated estimation formula, the threshold estimation unit 53 estimates the threshold for determining the quality of the mold for the other processing conditions indicated by the processing condition data (step S15). The threshold estimation unit 53 stores the threshold data indicating the thresholds for the other processing conditions indicated by the processing condition data in the threshold storage unit 54 (step S16), and terminates the process. Since the threshold storage unit 54 already stores the threshold data indicating the thresholds for the processing conditions at the time of the experiment by the threshold calculation unit 52 in step S12, in step D16, the threshold data indicating the thresholds for all processing conditions indicated by the processing condition data will be stored in the threshold storage unit 54.

[0046] The mold quality determination process shown in Figure 11 starts, for example, when a mold quality determination instruction is input to the mold quality determination device 6. When a mold quality determination instruction is input to the mold quality determination device 6, the machining measurement data generation unit 61 associates the measurement data acquired from the sensing device 3 with the executed machining data acquired from the NC data monitoring device 2 and generates machining measurement data (step S21). The machining measurement data generation unit 61 stores the generated machining measurement data in the machining measurement data storage unit 62 (step S22). The quality determination unit 63 acquires threshold data corresponding to the executed measurement data stored in the machining measurement data storage unit 62 from the threshold storage unit 54 of the mold quality determination threshold generation device 5 (step S23).

[0047] The quality determination unit 63 performs a mold quality determination for each mold used in the machining process indicated by the machining measurement data stored in the machining measurement data storage unit 62, using the threshold values ​​indicated by the threshold data obtained from the mold quality determination threshold generation device 5 (step S24). The quality determination unit 63 stores the determination result data indicating the mold quality determination result in the determination result storage unit 64 (step S25). The determination result output unit 65 outputs the determination result data stored in the determination result storage unit 64 (step S26) and terminates the process. The method of outputting the determination result data in step S26 may be, for example, by displaying it on the screen, by sending it to a terminal used by the user, or by sending it to an external device or system.

[0048] According to the mold maintenance system 100 of Embodiment 1, threshold data that serves as the basis for determining the quality of a TPP processing machine's mold is automatically generated based on measurement data. Based on NC data, measurement data, and threshold data, the TPP processing machine's mold quality determination is performed automatically, thereby reducing the cost of setting criteria for mold quality determination. Furthermore, by outputting the mold quality determination result data, users can determine the appropriate timing for mold replacement or polishing, preventing excessive and insufficient maintenance. In addition, the mold quality determination result data can be used as a basis for deciding when to order molds, contributing to improved equipment utilization.

[0049] (Embodiment 2) In Embodiment 2, if the mold quality judgment result is "fail," that is, if the mold used in the actual machining is determined to be an abnormal mold, countermeasures are taken. During manned hours when an operator is present (e.g., daytime), the operator is notified that the mold is an abnormal mold. During unmanned hours when no operator is present (e.g., nighttime), the NC program of the TPP machining center 1 is modified to avoid using the abnormal mold.

[0050] The configuration of the mold maintenance system 200 according to Embodiment 2 will be explained with reference to Figure 12. The mold maintenance system 200 includes a TPP processing machine 1, an NC data monitoring device 2, a sensing device 3, a processing condition setting device 4, a mold quality determination threshold generation device 5, a mold quality determination device 6, and an NC program changing device 7 for changing the NC program of the TPP processing machine 1.

[0051] The functional configuration of the NC program change device 7 will be explained using Figure 13. The NC program change device 7 includes a judgment result storage unit 71 that stores judgment result data received from the mold quality judgment device 6, an NC program change command unit 72 that instructs a change in the NC program based on the judgment result data, a mold replacement master storage unit 73 that shows the mold shape and the combination of replaceable molds for each mold, a same-shape mold replacement execution unit 74 that replaces a mold of an abnormal mold in the NC program with a normal mold of the same shape, a different-shape mold replacement execution unit 75 that replaces a mold of an abnormal mold in the NC program with a normal mold of a different shape, a schedule change unit 76 that postpones the processing date and time when an abnormal mold is used in the NC program, and an NC program storage unit 77 that stores the NC program of the TPP processing machine 1. In Embodiment 2, the TPP processing machine 1 performs processing according to the NC program stored in the NC program storage unit 77.

[0052] When the NC program change command unit 72 receives a "fail" judgment result from the mold quality determination device 6, that is, judgment result data indicating that the mold is abnormal, stored in the judgment result storage unit 71, it first determines whether the current time is during a time when the machine is staffed. If it is during a time when the machine is staffed, the NC program change command unit 72 outputs alarm data warning that an abnormal mold is being used. The method of outputting the alarm data may be, for example, by displaying it on the screen or by sending it to a terminal used by the operator.

[0053] If the current time is during an unmanned period, the NC program change command unit 72 determines whether or not there is a normal mold with the same shape as the abnormal mold, based on the determination result data stored in the determination result storage unit 71. If it determines that there is a normal mold with the same shape, the NC program change command unit 72 instructs the same-shape mold replacement execution unit 74 to replace the mold of the abnormal mold in the NC program with a normal mold of the same shape. The same-shape mold replacement execution unit 74 changes the NC program stored in the NC program storage unit 77 that uses the abnormal mold to a program that uses the normal mold of the same shape. If it determines that there is no normal mold with the same shape, the NC program change command unit 72 refers to the mold replacement master stored in the mold replacement master storage unit 73 and determines whether or not there is a normal mold of a different shape that can replace the abnormal mold.

[0054] Here, the mold replacement master will be explained using Figure 14. In the example in Figure 14, the mold replacement master has the following items: "Mold Shape" which indicates the shape of the mold, "Processing Method" which indicates the processing method for the mold, and "Replacement Mold" which indicates a mold of a different shape that can be replaced with the mold in question. For example, a mold with a shape of 6-110 can be replaced with a mold with a shape of 6-60 in single-stroke and double-punching processing methods.

[0055] Returning to Figure 13, if it is determined that there is a replaceable normal mold of a different shape, the NC program change command unit 72 instructs the different-shape mold replacement execution unit 75 to replace the mold of the abnormal mold in the NC program with a replaceable normal mold of a different shape. The different-shape mold replacement execution unit 75 changes the NC program stored in the NC program storage unit 77 from a program that uses the abnormal mold to a program that uses a replaceable normal mold of a different shape.

[0056] If there is no other normal mold of a suitable shape that can be used as a replacement, the NC program change command unit 72 instructs the schedule change unit 76 to postpone the machining of the NC program that uses the abnormal mold. The schedule change unit 76 delays the machining date and time of the NC program that uses the abnormal mold, among the NC programs stored in the NC program storage unit 77, by a certain period. The period for delaying the machining date and time may be set in advance or set by the user. The functions of the other devices are the same as in Embodiment 1.

[0057] Next, the flow of the NC program change process executed by the NC program change device 7 will be explained using Figure 15. The NC program change process shown in Figure 15 starts, for example, when judgment result data indicating that the mold is abnormal is stored in the judgment result storage unit 71. When judgment result data indicating that the mold is abnormal is stored in the judgment result storage unit 71, the NC program change command unit 72 determines whether the current time is during a staffed time period (step S31). If it is during a staffed time period (step S31; YES), the NC program change command unit 72 outputs alarm data warning that an abnormal mold is being used (step S32), and terminates the process. The method of outputting the alarm data may be, for example, by displaying it on the screen or by sending it to a terminal used by the operator.

[0058] If the current time is not during a staffed time, that is, if the current time is during an unstaffed time (Step S31; NO), the NC program change command unit 72 determines whether or not there is a normal mold with the same shape as the abnormal mold based on the determination result data stored in the determination result storage unit 71 (Step S33). If it is determined that there is a normal mold with the same shape (Step S33; YES), the NC program change command unit 72 instructs the same-shape mold replacement execution unit 74 to replace the mold of the abnormal mold in the NC program with a normal mold of the same shape. The same-shape mold replacement execution unit 74 changes the NC program stored in the NC program storage unit 77 that uses the abnormal mold to a program that uses the normal mold of the same shape (Step S34), and terminates the process. If it is determined that there is no normal mold with the same shape (Step S33; NO), the NC program change command unit 72 refers to the mold replacement master stored in the mold replacement master storage unit 73 and determines whether or not there is a normal mold of a different shape that can replace the abnormal mold (Step S35).

[0059] In the example shown in Figure 14, the mold replacement master includes the following items: "Mold Shape" indicating the shape of the mold, "Processing Method" indicating the processing method for the mold, and "Replacement Mold" indicating a mold of a different shape that can be replaced by the mold in question. For example, a mold with a shape of 6-110 can be replaced by a mold with a shape of 6-60 in single-stroke and double-punching processing methods.

[0060] Returning to Figure 15, if it is determined that there is a replaceable normal mold of a different shape (step S35; YES), the NC program change command unit 72 instructs the different-shape mold replacement execution unit 75 to replace the mold of the abnormal mold in the NC program with a replaceable normal mold of a different shape. The different-shape mold replacement execution unit 75 changes the NC program stored in the NC program storage unit 77 that uses the abnormal mold to a program that uses the replaceable normal mold of a different shape (step S36), and then terminates the process.

[0061] If there is no normal mold that can replace the abnormal mold (step S35; NO), the NC program change command unit 72 instructs the schedule change unit 76 to postpone the machining of the NC program that uses the abnormal mold. The schedule change unit 76 delays the machining date and time of the NC program that uses the abnormal mold among the NC programs stored in the NC program storage unit 77 by a certain period of time (step S37), and then terminates the process. The NC program change device 7 repeats the NC program change process each time it acquires determination result data indicating that the mold is abnormal. Alternatively, the process from steps S33 to S37 may be executed regardless of whether the current time is during a manned time or not. In this case, steps S31 and S32 can be omitted.

[0062] According to the mold maintenance system 200 of Embodiment 2, threshold data that serves as the basis for determining the quality of a TPP processing machine's mold is automatically generated based on measurement data. Based on NC data, measurement data, and threshold data, the TPP processing machine's mold quality is determined, enabling automatic mold quality determination and reducing the cost of setting criteria for mold quality determination. Furthermore, by taking the above-mentioned countermeasures based on the mold quality determination result data, operators can know the timing for mold replacement or polishing, preventing excessive and insufficient maintenance. In addition, even during times when no operators are present, the use of abnormal molds can be avoided, preventing significant losses due to poor quality and equipment downtime due to mold damage.

[0063] (Embodiment 3) In embodiments 1 and 2, it is necessary to prepare a normal mold and a non-normal mold, conduct experiments, and store the experimental data in order to generate threshold data that serves as the basis for determining the quality of the mold. However, in actual sheet metal processing sites, it is difficult to stop production and conduct experiments because the TPP processing machine, which is already in operation, is the starting point of the sheet metal process. Therefore, in embodiment 3, instead of threshold data that serves as the basis for determining the quality of the mold, a trained model that has learned mold quality determination is used.

[0064] The configuration of the mold maintenance system 300 according to Embodiment 3 will be explained with reference to Figure 16. The mold maintenance system 300 comprises a TPP processing machine 1, an NC data monitoring device 2, a sensing device 3, a mold quality determination device 6, and a learning device 8 for learning mold quality determination.

[0065] The functional configurations of the mold quality determination device 6 and the learning device 8 will be explained using Figure 17. The learning device 8 includes a learning data generation unit 81 that generates learning data from measurement data of processing sounds acquired from the sensing device 3, a model generation unit 82 that learns mold quality determination based on the learning data and generates a learned model, and a learned model storage unit 83 that stores the learned model. The learning device 8 is an example of a mold quality determination criterion generation device.

[0066] The trained model generated by the model generation unit 82 is a model for classifying when the mold is not worn (hereinafter referred to as "good") and when the mold is worn (hereinafter referred to as "bad"). The case in which the K-means algorithm, which is an unsupervised learning method, is applied as the learning algorithm used by the model generation unit 82 will be explained. The model generation unit 82 performs clustering using the K-means method on the training data and learns the mold good / bad judgment through so-called unsupervised learning.

[0067] As a method to evaluate the accuracy of clustering, we use Pseudo F, which can consider, for example, the cohesiveness within clusters and the discreteness between clusters. For example, Figure 18 shows the results of clustering the experimental data shown in Figure 7 using the K-means method in an unlabeled state. When applying Pseudo F using the results shown in Figure 18 as an example, the dataset consists of the integral value of the FFT analysis of the mold processing sound and the maximum value of the sound waveform. There are two clusters: good and bad, and the cluster with the larger variance is the bad cluster. The Jaccard coefficient between the good and bad clusters is calculated to be 0.0833. The closer the Jaccard coefficient is to 0, the lower the similarity between clusters, indicating that the good and bad classifications are being made.

[0068] The learning data generation unit 81 generates learning data from measurement data acquired from the sensing device 3, which is a combination of the integral value of the FFT analysis of the mold processing sound and the maximum value of the sound waveform. The model generation unit 82 learns mold quality judgment by unsupervised learning according to the learning data generated by the learning data generation unit 81 and generates a trained model. The trained model storage unit 83 stores the trained model generated by the model generation unit 82.

[0069] The mold quality determination device 6 includes an inference unit 66 instead of a quality determination unit 63. The inference unit 66 determines the quality of the mold used in the machining indicated by the machining measurement data, based on the machining measurement data and the trained model stored in the trained model storage unit 83 of the learning device 8. Specifically, the inference unit 66 generates a dataset of the integral value of the FFT analysis of the machining sound of the mold and the maximum value of the sound waveform from the measurement data included in the machining measurement data, and inputs it into the trained model. The trained model outputs a determination result indicating whether it belongs to a good judgment cluster or a bad judgment cluster. If it belongs to a good judgment cluster, the inference unit 66 determines that the mold used in the actual machining indicated by the machining measurement data is good. On the other hand, if it belongs to a bad judgment cluster, the inference unit 66 determines that the mold used in the actual machining indicated by the machining measurement data is bad. The inference unit 66 stores the determination result data indicating the determination result of the mold quality determination in the determination result storage unit 64. The functions of the other devices are the same as in Embodiments 1 and 2.

[0070] Next, the flow of the trained model generation process executed by the learning device 8 will be explained using Figure 19. The trained model generation process shown in Figure 19 starts, for example, when a learning instruction for mold quality judgment is input to the learning device 8. When a learning instruction for mold quality judgment is input to the learning device 8, the learning data generation unit 81 acquires measurement data from the sensing device 3 (step S41). The learning data generation unit 81 generates learning data from the measurement data acquired from the sensing device 3, which is a combination of the integral value of the FFT analysis of the mold processing sound and the maximum value of the sound waveform (step S42). The model generation unit 82 learns mold quality judgment by unsupervised learning according to the learning data generated by the learning data generation unit 81 and generates a trained model (step S43). The trained model storage unit 83 stores the trained model generated by the model generation unit 82 (step S44) and terminates the process. The measurement data acquired in step S41 may be stored. As a result, the amount of training data increases as the pre-trained model generation process is repeated, and the accuracy of the pre-trained model improves.

[0071] According to the mold maintenance system 300 of Embodiment 3, a trained model that serves as the criterion for determining the quality of a TPP processing machine's mold is automatically generated based on measurement data. Based on NC data, measurement data, and the trained model, the TPP processing machine's mold quality determination is performed automatically, thereby reducing the cost of setting criteria for determining mold quality. Furthermore, threshold data for detecting mold abnormalities can be created without conducting experiments to calculate thresholds using worn molds, contributing to improved equipment utilization. In addition, by using a trained model that has learned mold quality determination as the criterion for determining mold quality, mold quality determination can be performed even in sheet metal processing sites where experimental data for the TPP processing machine 1 has not been obtained in advance and the TPP processing machine 1 is already in operation, without stopping production and conducting experiments. Moreover, the accuracy of the trained model can be improved by repeatedly performing the trained model generation process.

[0072] In embodiments 1 to 3 described above, the mold maintenance system 100, mold maintenance system 200, and mold maintenance system 300 are equipped with one TPP processing machine 1, one NC data monitoring device 2, and one sensing device 3, but are not limited to this. Multiple sets of TPP processing machine 1, NC data monitoring device 2, and sensing device 3 may be provided. Figure 20 shows an example of the configuration of the mold maintenance system 400 when this modified example is applied to embodiment 1.

[0073] The mold maintenance system 400 comprises TPP machining centers 1-1...TPP machining centers 1-n, NC data monitoring devices 2-1...NC data monitoring devices 2-n, and sensing devices 3-1...Sensing devices 3-n. Each of the NC data monitoring devices 2-1...NC data monitoring devices 2-n transmits the machining data to the mold quality determination device 6 via a data transfer device 9. Each of the sensing devices 3-1...Sensing devices 3-n transmits the measurement data to the mold quality determination device 6 via a data transfer device 9. By transmitting the machining data and measurement data from multiple NC data monitoring devices 2 and sensing devices 3 to the mold quality determination device 6 via a data transfer device 9, a single mold quality determination device 6 can centrally determine the quality of molds for multiple TPP machining centers. This modified form is also applicable to embodiments 2 and 3.

[0074] In embodiments 1 to 3 described above, the characteristic that friction with the workpiece increases as mold wear progresses, resulting in louder processing noise, is taken into consideration, and mold quality is determined based on measurement data of processing noise acquired by a sound sensor. However, in sheet metal processing sites, there are various processes other than the processing by the TPP processing machine, such as welding and cutting, and there are many noise disturbances. For this reason, even if a microphone with good directionality is used as the sound sensor, it is difficult to completely block out the noise. Therefore, the sensing device 3 may use contact-type sensors that can be directly attached to the TPP processing machine 1, such as a vibration sensor or a load sensor, in addition to the sound sensor. In the case of a sound sensor, it is difficult to distinguish between the processing noise of the target being measured and processing noise caused by external disturbances, but with a contact-type sensor, the processing phenomenon of the target being measured can be reliably sensed, and highly accurate data can be obtained. A modified example of the sensing device 3 equipped with a vibration sensor in addition to a sound sensor is shown in Figure 21.

[0075] The machining vibration acquisition unit 32 acquires machining vibrations of the actual machining operation from a uniaxial vibration sensor attached to, for example, the ram mechanism of the TPP machining machine 1. The machining vibration acquisition unit 32 transmits the acquired measurement data of the machining vibrations of the actual machining operation to the mold quality determination device 6. The quality determination unit 63 detects the machining timing from the measurement data of the machining vibrations of the actual machining operation and samples measurement data of the machining sound in synchronization with the machining timing. The learning data generation unit 81 generates learning data from the measurement data of the machining sound and machining vibrations acquired from the sensing device 3.

[0076] In embodiments 1 to 3 described above, die quality determination is performed based on processing measurement data, including measurement data of processing sounds acquired by a sound sensor. However, as mentioned above, there is a lot of noise that acts as a disturbance in sheet metal processing sites. Therefore, in order to improve the accuracy of die quality determination, the die quality determination device 6 may take into account the number of punches for each die when determining die quality. In this case, the quality determination unit 63 may calculate the number of punches for each die based on the NC data included in the processing measurement data, or it may calculate the number of punches for each die based on the measurement data included in the processing measurement data. Alternatively, punch count data indicating the number of punches for each die may be acquired directly from the TPP processing machine 1.

[0077] The quality determination unit 63 performs mold quality determination by weighting, for example, by making the threshold judgment heavier as the number of punches in the mold increases. The weighting is, for example, when mold quality determination is performed using measurement data of processing sound, as in Embodiments 1 and 2, and a rejection judgment is made for the mold if the number of times the processing sound magnitude exceeds a threshold exceeds a predetermined number (n≧1), the predetermined number (n≧1) is reduced as the number of punches increases. Alternatively, when a trained model for mold quality determination is generated using the K-means method, as in Embodiment 3, and the cluster is trained to be able to determine mold quality when the Jaccard coefficient is less than or equal to a predetermined value A, the predetermined value A may be reduced as the number of punches increases. Furthermore, in combination with the above-described modifications, the quality determination unit 63 may also incorporate measurement data of processing vibrations during the actual processing into the mold quality determination. The learning data generation unit 81 may generate learning data from measurement data of processing sound and processing vibrations and punch count data acquired from the sensing device 3.

[0078] The mold maintenance system 200 of Embodiment 2 adds an NC program change device 7 to the mold maintenance system 100 of Embodiment 1, but the NC program change device 7 may also be added to the mold maintenance system 300 of Embodiment 3.

[0079] The hardware configuration of the mold quality determination threshold generation device 5, the mold quality determination device 6, the NC program change device 7, and the learning device 8 will be explained using Figure 22. As shown in Figure 22, the mold quality determination device 6, the NC program change device 7, and the learning device 8 each include a temporary storage unit 101, a storage unit 102, a calculation unit 103, an input unit 104, a transmitting / receiving unit 105, and a display unit 106. The temporary storage unit 101, the storage unit 102, the input unit 104, the transmitting / receiving unit 105, and the display unit 106 are all connected to the calculation unit 103 via a BUS.

[0080] The calculation unit 103 is, for example, a CPU (Central Processing Unit). The calculation unit 103 executes the processing of the threshold calculation unit 52 and threshold estimation unit 53 of the mold quality determination threshold generation device 5, the processing measurement data generation unit 61, quality determination unit 63 and determination result output unit 65 of the mold quality determination device 6, the NC program change command unit 72, same-shape mold replacement execution unit 74, different-shape mold replacement execution unit 75 and schedule change unit 76 of the NC program change device 7, and the learning data generation unit 81 and model generation unit 82 of the learning device 8, according to the control program stored in the storage unit 102.

[0081] The temporary storage unit 101 is, for example, RAM (Random-Access Memory). The temporary storage unit 101 loads the control program stored in the storage unit 102 and uses it as a work area for the calculation unit 103.

[0082] The memory unit 102 is a non-volatile memory such as flash memory, hard disk, DVD-RAM (Digital Versatile Disc - Random Access Memory), or DVD-RW (Digital Versatile Disc - ReWritable). The memory unit 102 pre-stores programs for causing the calculation unit 103 to perform processing for the mold quality judgment threshold generation device 5, the mold quality judgment device 6, the NC program change device 7, and the learning device 8. It also supplies data stored in this program to the calculation unit 103 according to the instructions of the calculation unit 103, and stores the data supplied from the calculation unit 103. The experimental data storage unit 51 of the mold quality judgment threshold generation device 5, the processing measurement data storage unit 62 and the judgment result storage unit 64 of the mold quality judgment device 6, the judgment result storage unit 71 of the NC program change device 7, the mold replacement master storage unit 73 and the NC program storage unit 77, and the learned model storage unit 83 of the learning device 8 are all configured in the memory unit 102.

[0083] Furthermore, the experimental data storage unit 51 of the mold quality judgment threshold generation device 5, the machining measurement data storage unit 62 and judgment result storage unit 64 of the mold quality judgment device 6, the judgment result storage unit 71 of the NC program change device 7, the mold replacement master storage unit 73 and NC program storage unit 77, and the learned model storage unit 83 of the learning device 8 may be provided by external devices or systems.

[0084] The input unit 104 is an interface device that connects input devices such as keyboards, pointing devices, and voice input devices to the BUS. Information entered by the user is supplied to the calculation unit 103 via the input unit 104. When the threshold estimation unit 53 of the mold quality judgment threshold generation device 5 receives processing condition data from the user, the input unit 104 functions as the threshold estimation unit 53.

[0085] The transmitting / receiving unit 105 is a network termination device or wireless communication device connected to a network, and a serial interface or LAN (Local Area Network) interface connected to them. The transmitting / receiving unit 105 functions as the threshold estimation unit 53 of the mold quality judgment threshold generation device 5, the processing measurement data generation unit 61 and the judgment result output unit 65 of the mold quality judgment device 6, and the learning data generation unit 81 of the learning device 8.

[0086] The display unit 106 is a display device such as an LCD (Liquid Crystal Display) or an organic EL (electroluminescence) display. In a configuration where the judgment result output unit 65 of the mold quality judgment device 6 outputs judgment result data on a screen display, the display unit 106 functions as the judgment result output unit 65.

[0087] The processing of the experimental data storage unit 51, threshold calculation unit 52, and threshold estimation unit 53 of the mold quality determination threshold generation device 5 shown in Figures 5, 13, and 17; the processing measurement data generation unit 61, processing measurement data storage unit 62, quality determination unit 63, determination result storage unit 64, and determination result output unit 65 of the mold quality determination device 6; the determination result storage unit 71, NC program change command unit 72, mold replacement master storage unit 73, same-shape mold replacement execution unit 74, different-shape mold replacement execution unit 75, schedule change unit 76, and NC program storage unit 77 of the NC program change device 7; and the learning data generation unit 81, model generation unit 82, and learned model storage unit 83 of the learning device 8 is performed by the control program using resources such as the temporary storage unit 101, calculation unit 103, storage unit 102, input unit 104, transmission / reception unit 105, and display unit 106.

[0088] Furthermore, the aforementioned hardware configuration and flowchart are examples only and can be changed and modified as needed.

[0089] The core components of the mold quality determination threshold generation device 5, mold quality determination device 6, NC program modification device 7, and learning device 8, including the calculation unit 103, temporary storage unit 101, storage unit 102, input unit 104, transmission / reception unit 105, and display unit 106, can be implemented using a standard computer system rather than a dedicated system. For example, the computer program for executing the above operations may be stored on a computer-readable recording medium such as a flexible disk, CD-ROM (Compact Disc - Read Only Memory), or DVD-ROM (Digital Versatile Disc - Read Only Memory) and distributed, and the mold quality determination threshold generation device 5, mold quality determination device 6, NC program modification device 7, and learning device 8 can be configured by installing the computer program on a computer. Alternatively, the computer program may be stored on a storage device of a server on a communication network such as the Internet, and the mold quality determination threshold generation device 5, mold quality determination device 6, NC program modification device 7, and learning device 8 can be configured by downloading it from a standard computer system.

[0090] Furthermore, if the functions of the mold quality judgment threshold generation device 5, the mold quality judgment device 6, the NC program change device 7, and the learning device 8 are realized through a division of labor between the OS (Operating System) and the application program, or through cooperation between the OS and the application program, then only the application program portion may be stored in the recording medium or storage device.

[0091] Furthermore, it is possible to superimpose a computer program onto the carrier wave and provide it via a communication network. For example, the computer program may be posted on a bulletin board system (BBS) on the communication network and provided via the communication network. The system may then be configured to execute the aforementioned processing by starting this computer program and running it under the control of the OS, just like other application programs. The various aspects of this disclosure are summarized below as an appendix. (Note 1) A TPP machining center equipped with multiple molds that selectively uses the molds according to an NC program to perform machining, An NC data monitoring device that acquires NC data indicating the processing details of the TPP processing machine, A sensing device that generates measurement data by measuring the processing sound generated when using a mold in the aforementioned TPP processing machine, A mold quality judgment criterion generation device that generates threshold data or a trained model that serves as a criterion for determining the quality of the mold of the TPP processing machine based on the measurement data, A mold quality determination device that performs mold quality determination of the TPP processing machine based on the NC data and measurement data and threshold data or a trained model that serves as a criterion for determining mold quality, A mold maintenance system equipped with the following features. (Note 2) The aforementioned NC data monitoring device is An NC data acquisition unit that reads the aforementioned NC data, An execution machining data generation unit generates execution machining data by adding data on the mold used for machining to the aforementioned NC data, Equipped with, The mold quality judgment criterion generation device is, A threshold calculation unit calculates a threshold value that serves as the criterion for determining the quality of a mold from experimental data, which is the measurement data obtained in a prior experiment, and generates threshold data that shows the calculated threshold value. A threshold estimation unit estimates the threshold for determining the quality of a mold under processing conditions other than the processing conditions used during the experiment, based on the threshold calculated by the threshold calculation unit, and generates threshold data that shows the estimated threshold. Equipped with, The mold quality determination device is, A machining measurement data generation unit generates machining measurement data by associating the aforementioned measurement data with the aforementioned machining data, A quality determination unit that determines the quality of the mold of the TPP processing machine based on the processing measurement data and the threshold data, Equipped with, The mold maintenance system described in Appendix 1. (Note 3) The TPP processing machine further includes a processing condition setting device that receives input of processing conditions, The threshold estimation unit, The processing condition setting device estimates the threshold for determining the quality of the mold under processing conditions other than those used in the experiment, among the processing conditions input to the device. The mold maintenance system described in Appendix 2. (Note 4) The aforementioned NC data monitoring device is An NC data acquisition unit that reads the aforementioned NC data, An execution machining data generation unit generates execution machining data by adding data on the mold used for machining to the aforementioned NC data, Equipped with, The mold quality judgment criterion generation device is, A learning data generation unit that generates learning data from the aforementioned measurement data, A model generation unit that learns the mold quality judgment of the TPP processing machine based on the aforementioned training data and generates a trained model, Equipped with, The mold quality determination device is, A machining measurement data generation unit generates machining measurement data by associating the aforementioned measurement data with the aforementioned machining data, An inference unit that determines the quality of the mold of the TPP processing machine based on the processing measurement data and the trained model, Equipped with, The mold maintenance system described in Appendix 1. (Note 5) The system comprises multiple TPP processing machines, multiple NC data monitoring devices, and multiple NC data monitoring devices. Each of the aforementioned NC data monitoring devices transmits the executed machining data to the mold quality determination device via a data transfer device. Each of the plurality of sensing devices transmits the measurement data to the mold quality determination device via the data transfer device. A mold maintenance system as described in any of the appendices 2 to 4. (Note 6) The system further includes an NC program changing device that changes the NC program of the TPP processing machine based on the determination result of the mold quality determination device, The mold quality determination device is, The judgment result data indicating the judgment result of the mold quality judgment of the TPP processing machine is output to the NC program change device. The NC program change device is If the judgment result data indicates that the mold is abnormal, the NC program change command unit determines whether there is a normal mold with the same shape as the abnormal mold, and if it is determined that there is a normal mold with the same shape, it replaces the abnormal mold in the NC program with a normal mold of the same shape, and if it is determined that there is no normal mold with the same shape as the abnormal mold, it determines whether there is a normal mold with a different shape that can be replaced with the abnormal mold, and if it is determined that there is a normal mold with a different shape that can be replaced with the abnormal mold, it replaces the abnormal mold in the NC program with a normal mold with a different shape, and if it is determined that there is no normal mold with a different shape that can be replaced with the abnormal mold, it postpones the machining of the NC program that uses the abnormal mold. A mold replacement execution unit that, in accordance with instructions from the NC program change command unit, replaces the abnormal mold in the NC program with a normal mold of the same shape, A different-shape mold replacement execution unit that, in accordance with instructions from the NC program change command unit, replaces the abnormal mold in the NC program with a normal mold of a different shape, A schedule change unit that postpones the processing date and time in the NC program when the abnormal mold is used, in accordance with instructions from the NC program change command unit, Equipped with, A mold maintenance system as described in any of the appendices 1 to 5. (Note 7) The NC program change command unit, Furthermore, the system determines whether the current time is a staffed time zone or not. If it is a staffed time zone, it outputs alarm data warning that an abnormal mold is being used. If it is an unstaffed time zone, it determines whether there is a normal mold of the same shape as the abnormal mold. If it determines that there is a normal mold of the same shape, it replaces the abnormal mold in the NC program with a normal mold of the same shape. If it determines that there is no normal mold of the same shape as the abnormal mold, it determines whether there is a replaceable normal mold of a different shape. If it determines that there is a replaceable normal mold of a different shape, it replaces the abnormal mold in the NC program with a replaceable normal mold of a different shape. If it determines that there is no replaceable normal mold of a different shape, it postpones the machining process of the NC program using the abnormal mold. The mold maintenance system described in Appendix 6. (Note 8) A threshold calculation unit calculates a threshold value that serves as the criterion for determining the quality of a mold for the TPP processing machine from experimental data obtained from experiments conducted in advance, which measured the processing sound generated when a mold was used in the TPP processing machine, and generates threshold data that shows the calculated threshold value. A threshold estimation unit estimates the threshold for determining the quality of a mold under processing conditions other than the processing conditions used during the experiment, based on the threshold calculated by the threshold calculation unit, and generates threshold data that shows the estimated threshold. Equipped with, Mold quality judgment threshold generation device. (Note 9) A learning data generation unit generates learning data from measurement data obtained by measuring the processing sound generated when using a mold in a TPP processing machine, A model generation unit that learns the mold quality judgment of the TPP processing machine based on the aforementioned training data and generates a trained model, Equipped with Learning device. (Note 10) The NC data monitoring device performs the following actions: A step of acquiring NC data indicating the processing details of a TPP machining machine equipped with multiple molds that selectively uses molds according to an NC program for processing, The sensing device performs the following: The steps include: generating measurement data by measuring the processing sound generated when using a mold in the TPP processing machine; The steps include generating threshold data or a trained model that serves as a criterion for determining the quality of the mold of the TPP processing machine based on the measurement data, A step of determining the quality of the mold of the TPP processing machine based on the NC data and the measurement data and threshold data or a trained model that serves as a criterion for determining the quality of the mold, A mold quality determination method comprising the following features. (Note 11) Computers, A threshold calculation unit calculates a threshold value that serves as the criterion for determining the quality of a mold for the TPP processing machine from experimental data obtained from experiments conducted in advance, which measured the processing noise generated when a mold was used in the TPP processing machine, and generates threshold data that shows the calculated threshold value, and A threshold estimation unit estimates the threshold for determining the quality of a mold under processing conditions other than those used during the experiment, based on the threshold calculated by the threshold calculation unit, and generates threshold data that shows the estimated threshold. A program that makes it function as such. (Note 12) Computers, A learning data generation unit that generates learning data from measurement data obtained by measuring the processing sound generated when using a mold in a TPP processing machine, and A model generation unit that learns the mold quality judgment of the TPP processing machine and generates a trained model based on the aforementioned training data. A program that makes it function as such.

[0092] Furthermore, this disclosure allows for various embodiments and modifications without departing from its broad spirit and scope. The embodiments described above are for illustrative purposes only and do not limit the scope of this disclosure. That is, the scope of this disclosure is indicated by the claims, not by the embodiments. Various modifications made within the scope of the claims and the equivalent significance of the disclosure are considered to be within the scope of this disclosure. [Explanation of Symbols]

[0093] 1,1-1~1-n TPP processing machine, 2,2-1~2-n NC data monitoring device, 3,3-1~3-n Sensing device, 4 Processing condition setting device, 5 Mold quality judgment threshold generation device, 6 Mold quality judgment device, 7 NC program change device, 8 Learning device, 9 Data transfer device, 11 Press working unit, 12 NC data display unit, 21 NC data acquisition unit, 22 NC data storage unit, 23 Mold NC code master storage unit, 24 Execution processing data generation unit, 31 Processing sound acquisition unit, 32 Processing vibration acquisition unit, 41 Processing condition acquisition unit, 42 Processing condition storage unit, 51 Experimental data storage unit, 52 Threshold calculation unit, 53 Threshold estimation unit, 54 Threshold storage unit, 61 Processing measurement data generation unit, 62 Processing measurement data storage unit, 63 Quality judgment unit, 64 Judgment result storage unit, 65 Judgment result output unit, 66 71 Inference unit, 72 Judgment result storage unit, 73 NC program change command unit, 74 Same shape mold replacement execution unit, 75 Different shape mold replacement execution unit, 76 Schedule change unit, 77 NC program storage unit, 81 Learning data generation unit, 82 Model generation unit, 83 Learned model storage unit, 100, 200, 300, 400 Mold maintenance system, 101 Temporary storage unit, 102 Storage unit, 103 Calculation unit, 104 Input unit, 105 Transmit / receive unit, 106 Display unit.

Claims

1. A TPP processing machine equipped with multiple molds that selectively uses the molds according to an NC program to perform processing, A sensing device that generates measurement data by measuring the processing sound generated when using a mold in the TPP processing machine, A mold quality judgment criterion generation device that generates threshold data or a trained model that serves as a criterion for determining the quality of the mold of the TPP processing machine based on the aforementioned measurement data, Equipped with, The mold quality judgment criterion generation device is, A threshold calculation unit calculates a threshold value that serves as a criterion for determining the quality of a mold from experimental data, which is the measurement data obtained in a prior experiment, and generates threshold data that shows the calculated threshold value. A threshold estimation unit estimates the threshold for determining the quality of a mold under processing conditions other than the processing conditions used during the experiment, based on the threshold calculated by the threshold calculation unit, and generates threshold data that shows the estimated threshold. A mold maintenance system equipped with the following features.

2. An NC data monitoring device that acquires NC data indicating the processing details of the TPP processing machine, A mold quality determination device that performs mold quality determination of the TPP processing machine based on the NC data and measurement data and threshold data or a trained model that serves as a criterion for determining mold quality, Furthermore, The mold maintenance system according to claim 1.

3. The NC data monitoring device is An NC data acquisition unit that reads the aforementioned NC data, An execution machining data generation unit generates execution machining data by adding data on the mold used for machining to the aforementioned NC data, Equipped with, The mold quality determination device is, A machining measurement data generation unit generates machining measurement data by associating the aforementioned measurement data with the aforementioned machining data, A quality determination unit that determines the quality of the mold of the TPP processing machine based on the processing measurement data and the threshold data, Equipped with, The mold maintenance system according to claim 2.

4. The TPP processing machine is further equipped with a processing condition setting device that receives input of processing conditions, The threshold estimation unit, The processing condition setting device estimates the threshold for determining the quality of the mold under processing conditions other than those used in the experiment, among the processing conditions input to the device. The mold maintenance system according to claim 3.

5. The NC data monitoring device is An NC data acquisition unit that reads the aforementioned NC data, An execution machining data generation unit generates execution machining data by adding data on the mold used for machining to the aforementioned NC data, Equipped with, The mold quality judgment criterion generation device is, A learning data generation unit that generates learning data from the aforementioned measurement data, A model generation unit that learns the mold quality judgment of the TPP processing machine based on the aforementioned training data and generates a trained model, Equipped with, The mold quality determination device is, A machining measurement data generation unit generates machining measurement data by associating the aforementioned measurement data with the aforementioned machining data, An inference unit that determines the quality of the mold of the TPP processing machine based on the processing measurement data and the trained model, Equipped with, The mold maintenance system according to claim 2.

6. The system comprises multiple TPP processing machines, multiple NC data monitoring devices, and multiple NC data monitoring devices. Each of the aforementioned NC data monitoring devices transmits the executed machining data to the mold quality determination device via a data transfer device. Each of the plurality of sensing devices transmits the measurement data to the mold quality determination device via the data transfer device. The mold maintenance system according to claim 3 or 4.

7. A TPP processing machine equipped with multiple molds, which selectively uses the molds according to an NC program to perform processing, An NC data monitoring device that acquires NC data indicating the processing details of the TPP processing machine, A sensing device that generates measurement data by measuring the processing sound generated when using a mold in the TPP processing machine, A mold quality judgment criterion generation device that generates threshold data or a trained model that serves as a criterion for determining the quality of the mold of the TPP processing machine based on the aforementioned measurement data, A mold quality determination device that performs mold quality determination of the TPP processing machine based on the NC data and measurement data and threshold data or a trained model that serves as a criterion for determining mold quality, An NC program changing device that changes the NC program of the TPP processing machine based on the judgment result of the mold quality determination device, A mold maintenance system equipped with the following features.

8. The mold quality determination device is The judgment result data indicating the judgment result of the mold quality judgment of the TPP processing machine is output to the NC program change device. The NC program change device is If the judgment result data indicates that the mold is abnormal, the NC program change command unit determines whether there is a normal mold with the same shape as the abnormal mold, and if it determines that there is a normal mold with the same shape, it replaces the abnormal mold in the NC program with a normal mold of the same shape, and if it determines that there is no normal mold with the same shape as the abnormal mold, it determines whether there is a normal mold with a different shape that can be replaced with the abnormal mold, and if it determines that there is a normal mold with a different shape that can be replaced with the abnormal mold, it replaces the abnormal mold in the NC program with a normal mold with a different shape that can be replaced, and if it determines that there is no normal mold with a different shape that can be replaced with the abnormal mold, it postpones the machining of the NC program that uses the abnormal mold. A mold replacement execution unit that, in accordance with instructions from the NC program change command unit, replaces the abnormal mold in the NC program with a normal mold of the same shape, A different-shape mold replacement execution unit that, in accordance with instructions from the NC program change command unit, replaces the abnormal mold in the NC program with a normal mold of a different shape, A schedule change unit that, in accordance with instructions from the NC program change command unit, postpones the processing date and time in the NC program when the abnormal mold is used, Equipped with, The mold maintenance system according to claim 7.

9. The NC program change command unit, Furthermore, the system determines whether the current time is a staffed time zone. If it is a staffed time zone, it outputs alarm data warning that an abnormal mold is being used. If it is an unstaffed time zone, it determines whether there is a normal mold with the same shape as the abnormal mold. If it determines that there is a normal mold with the same shape, it replaces the abnormal mold in the NC program with a normal mold of the same shape. If it determines that there is no normal mold with the same shape as the abnormal mold, it determines whether there is a replaceable normal mold with a different shape. If it determines that there is a replaceable normal mold with a different shape, it replaces the abnormal mold in the NC program with a replaceable normal mold with a different shape. If it determines that there is no replaceable normal mold with a different shape, it postpones the machining process in the NC program that uses the abnormal mold. The mold maintenance system according to claim 8.

10. A threshold calculation unit calculates a threshold value that serves as the criterion for determining the quality of a mold in a TPP processing machine from experimental data obtained by measuring the processing sound generated when a mold is used in a TPP processing machine in a prior experiment, and generates threshold data that shows the calculated threshold value. A threshold estimation unit estimates the threshold for determining the quality of a mold under processing conditions other than the processing conditions used during the experiment, based on the threshold calculated by the threshold calculation unit, and generates threshold data that shows the estimated threshold. Equipped with, Mold quality judgment threshold generation device.

11. The sensing device performs the following: A step to generate measurement data by measuring the processing sound generated when using a mold in a TPP processing machine, The mold quality judgment criteria generation device performs the following: The steps include generating threshold data or a trained model that serves as a criterion for determining the quality of the mold of the TPP processing machine based on the measurement data, Equipped with, From the experimental data, which is the measurement data obtained in a previous experiment, a threshold value that serves as the criterion for determining the quality of the mold is calculated, and threshold data representing the calculated threshold value is generated. A mold quality determination method that estimates a threshold for determining the quality of a mold under processing conditions other than those used during the experiment, based on a calculated threshold, and generates threshold data indicating the estimated threshold.

12. Computers, A threshold calculation unit calculates a threshold value that serves as the criterion for determining the quality of a mold in a TPP processing machine, based on experimental data obtained from experiments conducted in advance, which measured the processing noise generated when a mold was used in the TPP processing machine, and generates threshold data that shows the calculated threshold value. A threshold estimation unit estimates the threshold for determining the quality of a mold under processing conditions other than those used during the experiment, based on the threshold calculated by the threshold calculation unit, and generates threshold data that shows the estimated threshold. A program that makes it function as such.

Images