Management device, management method, management program, and recording medium

Abstract

To predict potential abnormality of a processing device.SOLUTION: A controller 30 includes: an acquisition section 31 for acquiring inspection result data showing each inspection result of a plurality of objects and working condition data showing working conditions used for each work of a plurality of objects; an analysis section 34 for selecting specified parameters with the inspection result and correlation from among a plurality of working parameters; and a prediction section 35 for predicting a potential abnormality of a processing device on the basis of secular changes of values of the specified parameter.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present disclosure relates to a management device, a management method, a management program, and a recording medium. [Background technology]

[0002] Processing such as heat treatment, plating, welding, and shot peening may be performed. For example, in the shot peening process, the quality is controlled by performing stress measurement and magnetic evaluation on selected products from the processed products (see, for example, Patent Document 1). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2015-525336 Summary of the Invention [Problem to be solved by the invention]

[0004] Each part of processing equipment (processing device) may deteriorate over time. The deterioration of the processing device may affect the quality of the product. Therefore, in this technical field, it is desired to predict future abnormalities in the processing device.

[0005] The present disclosure describes a management device, a management method, a management program, and a recording medium that are capable of predicting future abnormalities in a processing device. [Means for solving the problem]

[0006] A management device according to one aspect of the present disclosure is a device for managing a processing device that sequentially processes a plurality of objects under processing conditions including a plurality of processing parameters. The processing device includes an acquisition unit that acquires inspection result data indicating inspection results for each of the plurality of objects and processing condition data indicating processing conditions used to process each of the plurality of objects, an analysis unit that selects a specific parameter from the plurality of processing parameters that has a correlation with the inspection result, and a prediction unit that predicts a future abnormality of the processing device based on a change in the value of the specific parameter over time.

[0007] A management method according to another aspect of the present disclosure is a method for managing a processing device that sequentially processes a plurality of objects under processing conditions including a plurality of processing parameters, the management method including the steps of: acquiring inspection result data indicating inspection results for each of the plurality of objects and processing condition data indicating processing conditions used to process each of the plurality of objects; selecting a specific parameter from the plurality of processing parameters that has a correlation with the inspection result; and predicting a future abnormality of the processing device based on a change over time in the value of the specific parameter.

[0008] According to yet another aspect of the present disclosure, there is provided a management program for operating a computer to manage a processing device that sequentially processes a plurality of objects under processing conditions including a plurality of processing parameters. The management program causes the computer to execute the steps of acquiring inspection result data indicating inspection results for each of the plurality of objects and processing condition data indicating processing conditions used to process each of the plurality of objects, selecting a specific parameter from the plurality of processing parameters that has a correlation with the inspection result, and predicting a future abnormality in the processing device based on a change over time in the value of the specific parameter.

[0009] According to yet another aspect of the present disclosure, there is provided a computer-readable recording medium having recorded thereon a management program for operating a computer to manage a processing device that sequentially processes a plurality of objects under processing conditions including a plurality of processing parameters. The management program is a program for causing a computer to execute the steps of acquiring inspection result data indicating inspection results for each of the plurality of objects and processing condition data indicating processing conditions used to process each of the plurality of objects, selecting a specific parameter from the plurality of processing parameters that has a correlation with the inspection results, and predicting a future abnormality in the processing device based on a change over time in the value of the specific parameter.

[0010] In these management devices, management methods, management programs, and recording media, specific parameters correlated with inspection results are selected from multiple processing parameters, and future abnormalities in the processing device are predicted based on changes over time in the values ​​of the selected specific parameters. It is believed that if the values ​​of processing parameters that may affect the inspection results change over time, the processing accuracy of the target object will decrease. Therefore, by considering the changes over time in the values ​​of the specific parameters correlated with the inspection results, it is possible to predict deterioration of the processing device, i.e., future abnormalities in the processing device.

[0011] In some embodiments, the prediction unit may predict that the processing device will become abnormal in the future if the value of a specific parameter shows an increasing or decreasing trend. If a part of the processing device related to a processing parameter is deteriorating, the value of the processing parameter is likely to show an increasing or decreasing trend. If the value of a specific parameter correlated with the inspection result shows an increasing or decreasing trend, the processing accuracy of the object is likely to decrease. Therefore, with the above configuration, it is possible to improve the accuracy of predicting future abnormalities in the processing device.

[0012] In some embodiments, the processing device may include parts associated with each of a plurality of processing parameters. The prediction unit may predict future abnormalities in parts associated with specific parameters. In this case, parts of the processing device that will become abnormal in the future may be identified. Therefore, it is possible to perform maintenance, such as replacing the parts, before the parts become abnormal.

[0013] In some embodiments, the prediction unit may predict when the inspection results will show an abnormality based on changes in the inspection results over time. The object can be processed normally until the inspection results show an abnormality. Therefore, by predicting when the inspection results will show an abnormality, the processing device can be repaired before that time arrives.

[0014] In some embodiments, the management device may further include a determination unit that determines whether a sudden abnormality has occurred in the processing device based on the inspection results. Processing devices not only deteriorate over time, but can also suddenly develop abnormalities. This configuration makes it possible to detect not only future abnormalities in the processing device but also sudden abnormalities, thereby making it possible to more appropriately manage the processing device.

[0015] In some embodiments, the determination unit may set a normal range based on the inspection results of a properly processed object, and may determine that a sudden abnormality has occurred when the inspection results indicated by the inspection result data fall outside the normal range. If the inspection results fall outside the normal range, there is a possibility that some abnormality has occurred in the processing device. Therefore, with the above configuration, a sudden abnormality in the processing device can be appropriately detected.

[0016] In some embodiments, the management device may further include an output unit that outputs the prediction result by the prediction unit. In this case, the prediction result can be made known to the manager of the processing device. Therefore, it is possible to have the processing device repaired before an abnormality occurs in the processing device. As a result, it is possible to maintain the processing accuracy of the object. [Effects of the Invention]

[0017] According to each aspect and embodiment of the present disclosure, it is possible to predict future abnormalities in a processing device. [Brief explanation of the drawings]

[0018] [Figure 1] FIG. 1 is a schematic diagram illustrating a processing device according to an embodiment. [Figure 2] FIG. 2 is a block diagram of the processing device shown in FIG. [Figure 3] FIG. 3 is a block diagram showing a functional configuration of the control device shown in FIG. [Figure 4] FIG. 4 is a flowchart showing a management method performed by the control device shown in FIG. [Figure 5] FIG. 5 is a diagram for explaining the mapping of the test results. [Figure 6] FIG. 6 is a diagram for explaining the threshold circle. [Figure 7] FIG. 7 is a diagram for explaining a method for calculating the correlation coefficient. [Figure 8] FIG. 8 is a diagram showing an example of the correlation coefficient between the inspection result and each processing parameter. [Figure 9] FIG. 9 is a diagram for explaining a method for predicting when the test results will show an abnormality. [Figure 10] FIG. 10 is a diagram showing the structure of a management program recorded on a recording medium. [Figure 11] FIG. 11 is a diagram showing an example of displaying the test results. [Figure 12] FIG. 12 is a diagram showing the relationship between the eddy current ratio and the penetration depth of the eddy current for each particle size of the projection material. [Figure 13] FIG. 13 is a diagram showing the relationship between stress value and sample distance. [Figure 14] FIG. 14 is a diagram showing the relationship between stress value and area value. DETAILED DESCRIPTION OF THE INVENTION

[0019] Hereinafter, embodiments of the present disclosure will be described in detail with reference to the drawings. In the description of the drawings, the same elements are designated by the same reference numerals, and duplicated description will be omitted.

[0020] A processing apparatus according to one embodiment will be described with reference to FIGS. 1 and 2. FIG. 1 is a schematic diagram illustrating the configuration of the processing apparatus according to one embodiment. FIG. 2 is a block diagram of the processing apparatus shown in FIG. 1. The processing apparatus 1 shown in FIGS. 1 and 2 is an apparatus that sequentially processes multiple objects W under predetermined processing conditions. Examples of the objects W include gear steel and spring steel. Examples of gear steel include chromium-molybdenum steel (JIS SCM420H), chromium steel (SCr420H), and nickel-chromium steel (JIS SNCM439). Examples of spring steel include manganese-chromium steel (JIS SUP9). In this embodiment, a shot peening apparatus will be used as an example of the processing apparatus 1. The processing conditions include multiple processing parameters. Each processing parameter is measured by a sensor provided in the processing apparatus 1. Examples of the processing parameters include pressure, projection amount, and processing time.

[0021] The processing device 1 includes an inspection table 11, an inspection table 12, and a cabinet 13. The inspection table 11 is a table on which an unprocessed object W is placed. The inspection table 11 is provided outside the cabinet 13 and is located in front of the entrance of the cabinet 13. Stress measurement is performed on the object W placed on the inspection table 11. The inspection table 12 is a table on which a processed object W is placed. The inspection table 12 is provided outside the cabinet 13 and is located in front of the entrance of the cabinet 13. Stress measurement is performed on the object W placed on the inspection table 12.

[0022] The cabinet 13 has a box-like shape that defines an internal space V. The internal space V of the cabinet 13 is provided with a plurality of rooms. The plurality of rooms include a carry-in room ST1, an examination room ST2, a projection room ST3, a projection room ST4, an examination room ST5, and a carry-out room ST6. The carry-in room ST1, the examination room ST2, the projection room ST3, the projection room ST4, the examination room ST5, and the carry-out room ST6 are arranged in that order around a rotation axis AX1 of a turntable 45, which will be described later. Two adjacent rooms are separated by a wall-shaped partition 14. Each room may also be referred to as a station.

[0023] The loading room ST1 is a room for loading the object W into the cabinet 13. The inspection room ST2 is a room for inspecting the electromagnetic characteristics of the object W before shot peening. Each of the projection rooms ST3 and ST4 is a room for performing shot peening. The inspection room ST5 is a room for inspecting the electromagnetic characteristics of the object W after shot peening. The unloading room ST6 is a room for unloading the object W from the cabinet 13.

[0024] The processing device 1 includes an input device 15, a display device 16, a conveying device 21, a reading device 22, a stress measuring device 23, a stress measuring device 24, a magnetic evaluation device 25, a magnetic evaluation device 26, an injection device 27, an injection device 28, and a control device 30.

[0025] The input device 15 is a device for operating the control device 30. Examples of the input device 15 include a touch panel, a mouse, and a keyboard. The display device 16 is a device for displaying various types of information. An example of the display device 16 is a display.

[0026] The transfer device 21 is a device that transfers the target object W. The transfer device 21 includes conveyors 41 to 43, a robot 44, a rotary table 45, and a plurality of (six in this embodiment) placement tables 46.

[0027] The conveyor 41 is a conveyor for carrying in the object W. The conveyor 41 extends from the upstream process to the vicinity of the inspection table 11 and transports the object W from the upstream process. The conveyor 42 is a conveyor for carrying out the object W. The conveyor 42 extends from the vicinity of the inspection table 12 to the downstream process and transports the object W to the downstream process. The conveyor 43 is a conveyor for discarding the object W. The conveyor 43 extends, for example, from the vicinity of the inspection table 12 to an inspection device (not shown) for performing destructive inspection and transports the object W to the inspection device.

[0028] The robot 44 is a robot for transporting the object W. The robot 44 is, for example, a six-axis robot. The robot 44 moves the object W from the conveyor 41 to the inspection table 11. The robot 44 moves the object W that has been stress-tested from the inspection table 11 to the carry-in chamber ST1 inside the cabinet 13. The robot 44 moves the object W from the carry-out chamber ST6 to the inspection table 12. The robot 44 moves the object W that has been stress-tested from the inspection table 12 to the conveyor 42 or the conveyor 43.

[0029] The rotary table 45 is a disk-shaped table for transporting the object W from the loading chamber ST1, the examination chamber ST2, the projection chamber ST3, the projection chamber ST4, the examination chamber ST5, and the unloading chamber ST6 in this order. The rotary table 45 is disposed within the cabinet 13. The rotary table 45 is provided across the loading chamber ST1, the examination chamber ST2, the projection chamber ST3, the projection chamber ST4, the examination chamber ST5, and the unloading chamber ST6. The rotary table 45 is provided to be rotatable around a rotation axis AX1 passing through the center of the rotary table 45. The rotary table 45 rotates intermittently around the rotation axis AX1 so that a loading table 46 located in one room stops at a predetermined position in the adjacent room. The rotation axis AX1 is surrounded by the loading chamber ST1, the examination chamber ST2, the projection chamber ST3, the projection chamber ST4, the examination chamber ST5, and the unloading chamber ST6.

[0030] The loading table 46 is a disk-shaped table on which the object W is placed. The loading tables 46 are provided on the upper surface of the turntable 45 and are arranged in a ring shape at regular intervals around the circumferential direction of the turntable 45. The diameter of each loading table 46 is smaller than the diameter of the turntable 45. Each loading table 46 is rotatable around a rotation axis AX2 passing through the center of the loading table 46. The direction in which each rotation axis AX2 extends is substantially the same as the direction in which the rotation axis AX1 extends. As the turntable 45 rotates, each loading table 46 circulates through each station in the order of loading chamber ST1, inspection chamber ST2, projection chamber ST3, projection chamber ST4, inspection chamber ST5, and unloading chamber ST6. The partition 14 has an opening through which the loading table 46 can pass.

[0031] The reading device 22 is a device that acquires object information related to the object W. The object information includes, for example, an object ID and the type of the object W. The object ID is information that can uniquely identify the object W. In this embodiment, the reading device 22 is a device (reader) that reads the object information held in a tag attached to the object W. Examples of tags include an RFID (Radio Frequency Identification) tag, a QR code (registered trademark), and a barcode. The reading device 22 is provided, for example, on the side of the downstream end of the conveyor 41. The reading device 22 outputs the object information to the control device 30.

[0032] Each of the stress measuring devices 23, 24 is a device that measures the residual stress on the surface of the object W. The stress measuring device 23 measures the residual stress on the surface of the object W placed on the inspection table 11. The stress measuring device 24 measures the residual stress on the surface of the object W placed on the inspection table 12. Each of the stress measuring devices 23, 24 performs residual stress measurement using, for example, X-ray stress measurement. The X-ray stress measurement method is a method that measures crystal strain from changes in the crystal lattice spacing of a material such as a metal using X-ray diffraction and calculates a stress value. An example of an X-ray stress measurement method is the cos α method. X-ray stress measurement techniques such as the cos α method are well known, so detailed description thereof will be omitted here. Each of the stress measuring devices 23, 24 outputs the measured residual stress value to the control device 30.

[0033] Each of the magnetic evaluation devices 25 and 26 measures the electromagnetic properties of the object W. The magnetic evaluation device 25 measures the electromagnetic properties of the object W parked in the inspection chamber ST2. The magnetic evaluation device 26 measures the electromagnetic properties of the object W parked in the inspection chamber ST5. If the object W is a conductor, the permeability and conductivity of the conductor change due to changes in internal structural distortion, such as elasticity and plasticity, caused by surface processing or phase transformation caused by processing. Each of the magnetic evaluation devices 25 and 26 evaluates the presence or absence of mottle and the state of the metal structure in the object W, for example, using an eddy current method. Eddy currents are currents generated in a conductor by a time-varying magnetic field. Eddy currents have the characteristic of changing the depth of penetration into the object W depending on the frequency of the magnetic field (excitation frequency). Therefore, in addition to being able to inspect the interior of the object W, by setting the excitation frequency to match the depth from the surface of the object W, the tendency of the surface processing can be more specifically evaluated.

[0034] Each of the magnetic evaluation devices 25 and 26 includes a cylindrical core and a coil wound around the outer periphery of the core. The object W is placed in the internal space defined by the core so that the surface of the object W to be inspected faces the inner periphery of the core. In this state, an AC magnetic field is generated by supplying AC power of a predetermined frequency to the coil. This excites eddy currents on the surface of the object W, which flow in a direction that intersects with the AC magnetic field. A frequency sweep eddy current method may also be used. The frequency sweep eddy current method involves sweeping the excitation frequency over a wide range, gradually infiltrating eddy currents into the object W up to a maximum of approximately 200 μm from the outermost surface, and measuring the eddy current response at each excitation frequency. Each of the magnetic evaluation devices 25 and 26 outputs the excitation frequency and measurement values ​​to the control device 30.

[0035] The ratio (hereinafter referred to as "eddy current ratio") between the impedance of the coil with respect to the object W before processing and the impedance of the coil with respect to the object W after processing can be obtained from the measurement values ​​by the magnetic evaluation device 25 and the measurement values ​​by the magnetic evaluation device 26 at the same excitation frequency. The eddy current ratio is calculated, for example, by the control device 30.

[0036] Each of the injectors 27, 28 is a device that injects blast material at the target W, and is, for example, an air nozzle type shot peening machine. Each of the injectors 27, 28 injects compressed air containing blast material from a nozzle, causing the blast material to collide with the target W. Nozzle 27a of the injector 27 is provided on the side wall of the projection chamber ST3. The injection port of the nozzle 27a is set to face the target W stopped in the projection chamber ST3. Nozzle 28a of the injector 28 is provided on the side wall of the projection chamber ST4. The injection port of the nozzle 28a is set to face the target W stopped in the projection chamber ST4.

[0037] The control device 30 is a device (controller) that performs overall control of the processing device 1 and manages the processing device 1. The control device 30 is configured as a computer including, for example, a processor such as a CPU (Central Processing Unit), memories such as RAM (Random Access Memory) and ROM (Read Only Memory), and a communication device such as a network card.

[0038] Next, the functional configuration of the control device 30 will be described with reference to Fig. 3. Fig. 3 is a block diagram showing the functional configuration of the control device shown in Fig. 2. As shown in Fig. 3, the control device 30 functionally includes an acquisition unit 31, a storage unit 32, a determination unit 33, an analysis unit 34, a prediction unit 35, and an output unit 36. The function (operation) of each functional unit will be described in detail in the explanation of the management method given below, so here, the function of each functional unit will be briefly described.

[0039] The acquisition unit 31 is a functional unit that acquires various information. The acquisition unit 31 acquires, for example, object information for each of the multiple objects W, processing condition data for each of the multiple objects W, and inspection result data for each of the multiple objects W. Specifically, the acquisition unit 31 acquires object information, processing time, processing condition data, and inspection result data for each object W, and outputs inspection data that associates these data to the storage unit 32. The processing time is, for example, the time when the reading device 22 reads the object information from the object W identified by the object ID. The processing condition data is data that indicates the processing conditions used to process the object W identified by the object ID. Specifically, the processing condition data indicates the values ​​of each processing parameter. The inspection result data is data that indicates the inspection result of the object W identified by the object ID. In this embodiment, the inspection results include a residual stress value before processing, a residual stress value after processing, and an eddy current ratio.

[0040] In response to the control device 30 receiving an analysis command, the acquisition unit 31 acquires test data for a predetermined period from the storage unit 32. The acquisition unit 31 acquires test data for, for example, one day, one week, one month, and one year.

[0041] The storage unit 32 is a functional unit that stores (stores) the inspection data received from the acquisition unit 31. The storage unit 32 stores the inspection data for each object W.

[0042] The determination unit 33 is a functional unit that determines whether a sudden abnormality has occurred in the processing device 1 based on the inspection results. The determination unit 33 sets a normal range based on the inspection results of a normally processed object (a non-defective sample), and determines that a sudden abnormality has occurred when the inspection results acquired by the acquisition unit 31 fall outside the normal range. Note that the determination unit 33 may determine that a sudden abnormality has occurred in the processing device 1 or that noise has been mixed in when the inspection results fall outside the normal range. In the following description, it is assumed that the determination unit 33 determines that a sudden abnormality has occurred in the processing device 1 when the inspection results fall outside the normal range.

[0043] The analysis unit 34 is a functional unit that analyzes the inspection data. The analysis unit 34 selects a specific parameter from among multiple processing parameters. The specific parameter is a processing parameter that has a correlation with the inspection result. The analysis unit 34 calculates the correlation coefficient between the inspection result and each processing parameter, and if the absolute value of the correlation coefficient is greater than a correlation threshold, selects the processing parameter having that correlation coefficient as the specific parameter. The correlation coefficient ranges from -1 to +1. The closer the correlation coefficient is to -1, the stronger the negative correlation between the inspection result and the processing parameter. The closer the correlation coefficient is to +1, the stronger the positive correlation between the inspection result and the processing parameter. The correlation threshold is a value that indicates a strong correlation between the inspection result and the processing parameter, and is set to, for example, 0.7.

[0044] The prediction unit 35 is a functional unit that predicts a future abnormality of the processing device 1 based on a change over time in the value of a specific parameter. The prediction unit 35 predicts that the processing device 1 will become abnormal in the future when the value of the specific parameter shows an increasing or decreasing trend. The prediction unit 35 predicts, for example, a future abnormality of a part related to the specific parameter. The prediction unit 35 may predict a time when the inspection result will show an abnormality based on a change over time in the inspection result.

[0045] The output unit 36 ​​is a functional unit that outputs various information, such as the determination result of the determination unit 33 and the prediction result of the prediction unit 35.

[0046] Next, a management method performed by the control device 30 will be described with reference to FIGS. 4 to 9. FIG. 4 is a flowchart showing the management method performed by the control device shown in FIG. 2. FIG. 5 is a diagram for explaining mapping of inspection results. FIG. 6 is a diagram for explaining a threshold circle. FIG. 7 is a diagram for explaining a method for calculating a correlation coefficient. FIG. 8 is a diagram showing an example of a correlation coefficient between the inspection result and each processing parameter. FIG. 9 is a diagram for explaining a method for predicting when the inspection result will show an abnormality. The series of processes shown in FIG. 4 is started, for example, when the control device 30 receives an analysis command from the input device 15. Note that the processing device 1 has already processed a sufficient number of objects W, and a sufficient amount of inspection data is stored in the memory unit 32.

[0047] First, the acquiring unit 31 acquires test data (step S11). In step S11, the acquiring unit 31 acquires test data for a predetermined period, including the most recent test data, from the test data stored in the storage unit 32. Then, the acquiring unit 31 outputs the test data to the determining unit 33 and the analyzing unit 34.

[0048] Next, the determination unit 33 determines whether or not a sudden abnormality has occurred (step S12). In step S12, upon receiving the test data from the acquisition unit 31, the determination unit 33 determines whether or not a sudden abnormality has occurred by comparing each test result included in each test data with a normal range. The normal range is set in advance.

[0049] Specifically, as shown in FIG. 5, the determination unit 33 maps points representing the first and second inspection results obtained from each non-defective sample in a coordinate space in which the vertical axis represents the first inspection result and the horizontal axis represents the second inspection result. For example, the first inspection result is an inspection result related to stress measurement, and the second inspection result is an inspection result related to magnetic evaluation. Examples of inspection results related to stress measurement include residual stress values ​​after processing and full width at half maximum. Examples of inspection results related to magnetic evaluation include eddy current ratio. Then, as shown in FIG. 6, the determination unit 33 performs multivariate analysis on the mapped points to model and set the threshold circle Rth. The MT method may be used for the multivariate analysis. In this case, the threshold circle Rth is set based on the Mahalanobis distance.

[0050] The determination unit 33 maps points indicating the first and second inspection results of each piece of inspection data onto the coordinate space and determines whether each point is within the threshold circle Rth or outside the threshold circle Rth. If any point is outside the threshold circle Rth, the determination unit 33 calculates the distance between that point and the circumference of the threshold circle Rth. If the distance is greater than the determination threshold, the determination unit 33 determines that a sudden abnormality has occurred. If all points are inside the threshold circle Rth, the determination unit 33 determines that no sudden abnormality has occurred. Even if some points are outside the threshold circle Rth, the determination unit 33 determines that no sudden abnormality has occurred if the distances between each of the outside points and the threshold circle Rth are all smaller than the determination threshold.

[0051] If it is determined in step S12 that a sudden abnormality has occurred (step S12: YES), the determination unit 33 outputs the determination result to the output unit 36. Then, the output unit 36 ​​outputs the determination result (step S13). The output unit 36 ​​outputs the determination result to, for example, the display device 16. As shown in FIG. 6, upon receiving the determination result from the output unit 36, the display device 16 displays a graph showing a threshold circle and a point indicating the occurrence of a sudden abnormality. This completes the series of processes of the management method.

[0052] Then, if it is determined in step S12 that no sudden abnormality has occurred (step S12: NO), the analysis unit 34 selects a specific parameter from the multiple processing parameters that has a correlation with the inspection result (step S14). In step S14, the analysis unit 34 first calculates a correlation coefficient between the inspection result and each processing parameter using the inspection data received from the acquisition unit 31. For example, the analysis unit 34 calculates a correlation coefficient between the first inspection result (residual stress value) and each of the processing parameters, such as the pressure, projection amount, and processing time.

[0053] As shown in FIG. 7, the analysis unit 34 maps points representing the first inspection result and the value of the processing parameter when the first inspection result was obtained in a coordinate space in which, for example, the vertical axis represents the first inspection result and the horizontal axis represents one processing parameter. The analysis unit 34 then calculates a correlation coefficient between the first inspection result and the processing parameter using a known method. Similarly, the analysis unit 34 calculates correlation coefficients between the first inspection result and the remaining processing parameters. Similarly, the analysis unit 34 calculates correlation coefficients between the second inspection result and each of the processing parameters.

[0054] As shown in Fig. 8, when a correlation coefficient between each inspection result and each processing parameter (processing parameters MP1 to MP8) is obtained, the analysis unit 34 compares the absolute value of the correlation coefficient with a correlation threshold. If the absolute value of the correlation coefficient is greater than the correlation threshold, the analysis unit 34 selects the processing parameter having the correlation coefficient as a specific parameter. The analysis unit 34 then outputs information indicating the specific parameter to the prediction unit 35. Note that the analysis unit 34 may select multiple specific parameters.

[0055] Next, the prediction unit 35 determines whether there is a high possibility (high or low) that the processing device 1 will become abnormal in the future (step S15). In step S15, the prediction unit 35 predicts a future abnormality of the processing device 1 based on the change over time in the value of the specific parameter selected by the analysis unit 34. Specifically, the prediction unit 35 determines whether the value of the specific parameter shows an increasing or decreasing trend, or whether the value of the specific parameter shows neither an increasing nor decreasing trend. More specifically, the prediction unit 35 approximates the specific parameter with a linear expression of time, for example, by performing a simple regression analysis on the time-series data of the value of the specific parameter. The prediction unit 35 determines that the value of the specific parameter shows an increasing or decreasing trend when the absolute value of the slope of this approximate line is greater than a predetermined slope.

[0056] Then, when the value of the specific parameter shows an increasing or decreasing trend, the prediction unit 35 predicts that there is a high possibility (high) that the processing device 1 will become abnormal in the future. When the value of the specific parameter shows neither an increasing nor decreasing trend, the prediction unit 35 predicts that there is no possibility (low) that the processing device 1 will become abnormal in the future. Note that when the value of the specific parameter shows an increasing or decreasing trend, it is considered that a part related to the specific parameter has deteriorated. For example, if the specific parameter is pressure, it is considered that a part for supplying compressed air (such as a compressor and an air flow control valve) has deteriorated. Therefore, the prediction unit 35 may predict a future abnormality in a part related to the specific parameter.

[0057] In step S15, if it is determined that there is no (low) possibility that the processing device 1 will become abnormal in the future (step S15: NO), the series of processes of the management method ends. On the other hand, if it is determined that there is a (high) possibility that the processing device 1 will become abnormal in the future (step S15: YES), the prediction unit 35 predicts the time when the inspection result will become abnormal (NG) (step S16).

[0058] In step S16, the prediction unit 35 first predicts which test result will be abnormal based on a specific parameter that indicates an increasing or decreasing trend. The prediction unit 35 predicts which of the first and second test results will be abnormal, for example, by simple regression analysis. The prediction unit 35 may predict which of the first and second test results has a larger correlation coefficient with the specific parameter as the abnormal test result. Then, the prediction unit 35 predicts when the test result will be abnormal based on changes in the predicted test result over time. The prediction unit 35 predicts when the test result will be abnormal, for example, by performing simple regression analysis on time-series data of the test results.

[0059] Specifically, as shown in FIG. 9, the prediction unit 35 approximates the test results with a linear expression of time by performing a simple regression analysis on the time-series data of the test results. The prediction unit 35 then calculates the time (period) at which the line L representing the linear expression exceeds the upper limit or falls below the lower limit of the normal range as the time at which the test results indicate an abnormality. In the example shown in FIG. 9, the line L falls below the lower limit at time Ta. The prediction unit 35 then outputs the prediction result to the output unit 36. The prediction result includes, for example, a specific parameter that indicates an increasing or decreasing trend, test results that become abnormal due to the specific parameter, and the time at which the test results indicate an abnormality.

[0060] Next, the output unit 36 ​​outputs the prediction result (step S17). The output unit 36 ​​outputs the prediction result to, for example, the display device 16. Then, the display device 16 displays the prediction result. For example, as shown in FIG. 9, the display device 16 may graphically display the time-series data of the test result and the time Ta at which the test result indicates an abnormality. This completes the series of processes of the management method.

[0061] Note that the processing from step S14 onwards may be performed after step S13, in which case the subsequent processing is performed using test data other than test data of sudden abnormalities.

[0062] Next, a management program P for causing a computer to function as a control device 30 (management device) and a recording medium MD on which the management program P is recorded will be described with reference to Fig. 10. Fig. 10 is a diagram showing the configuration of the management program recorded on the recording medium.

[0063] 10, the management program P includes a main module P30, an acquisition module P31, a determination module P33, an analysis module P34, a prediction module P35, and an output module P36. The main module P30 is a part that performs overall control of processing related to the control device 30. The functions realized by executing the acquisition module P31, the determination module P33, the analysis module P34, the prediction module P35, and the output module P36 are similar to the functions of the acquisition unit 31, the determination unit 33, the analysis unit 34, the prediction unit 35, and the output unit 36 ​​in the above embodiment, respectively.

[0064] The management program P is provided by a computer-readable recording medium MD such as a CD-ROM (Compact Disc Read Only Memory), a DVD-ROM (Digital Versatile Disc Read Only Memory), or a semiconductor memory. The management program P may also be provided as a data signal over a network.

[0065] In the control device 30, management method, management program P, and recording medium MD described above, a specific parameter correlated with the inspection results is selected from among multiple processing parameters, and a future abnormality of the processing device 1 is predicted based on the change in the value of the specific parameter over time. It is believed that the value of each processing parameter changes over time due to deterioration of the processing device 1. If the value of a processing parameter that may affect the inspection results changes over time, it is believed that the processing accuracy of the target object W will decrease. Therefore, by considering the change in the value of the specific parameter correlated with the inspection results over time, it is possible to predict the deterioration of the processing device 1, i.e., a future abnormality of the processing device 1.

[0066] When a part (component) of the processing device 1 related to a processing parameter is degraded, the value of the processing parameter is considered to show an increasing or decreasing trend. When the value of a specific parameter correlated with the inspection result among the processing parameters shows an increasing or decreasing trend, the processing accuracy of the target object W is considered to decrease. In response to this, the prediction unit 35 predicts that the processing device 1 will become abnormal in the future when the value of the specific parameter shows an increasing or decreasing trend. Therefore, it is possible to improve the accuracy of predicting future abnormalities of the processing device 1.

[0067] The processing device 1 has parts associated with each of a plurality of processing parameters. The prediction unit 35 predicts future abnormalities in parts associated with specific parameters. This configuration makes it possible to identify parts in the processing device 1 that will become abnormal in the future. Therefore, it becomes possible to perform maintenance such as replacing the part at an appropriate time before the part becomes abnormal. As a result, it becomes possible to maintain the processing accuracy of the target object W and reduce the occurrence of defectively processed products. By predicting the timing for replacement, the number of parts that need to be replaced can be reduced.

[0068] The prediction unit 35 predicts when the inspection results will show an abnormality based on changes over time in the inspection results. Until the inspection results show an abnormality, the object W can be processed normally. Therefore, by predicting when the inspection results will show an abnormality, the processing device 1 can be repaired before that time arrives.

[0069] The processing device 1 not only deteriorates over time but may also suddenly develop an abnormality. In response to this, the determination unit 33 determines whether or not a sudden abnormality has occurred in the processing device 1 based on the inspection results. This configuration makes it possible to detect not only future abnormalities in the processing device 1 but also sudden abnormalities, thereby enabling more appropriate management of the processing device 1.

[0070] If the inspection result falls outside the normal range of the inspection result, there is a possibility that some abnormality has occurred in the processing device 1. In response to this, the determination unit 33 determines that a sudden abnormality has occurred if the inspection result falls outside the normal range set based on the inspection result of the normally processed object W. With this configuration, a sudden abnormality in the processing device 1 can be appropriately detected.

[0071] The output unit 36 ​​outputs the prediction result by the prediction unit 35. With this configuration, the prediction result can be made known to the manager of the processing device 1. Therefore, it becomes possible to have the processing device 1 repaired before an abnormality occurs in the processing device 1. As a result, it becomes possible to maintain the processing accuracy of the target object W. Since abnormalities in the processing device 1 can be prevented in advance, it becomes possible to reduce the number of managers managing the processing device 1.

[0072] The analysis unit 34 selects, as the specific parameter, a processing parameter whose absolute value of the correlation coefficient between the inspection result and the processing parameter is greater than the correlation threshold value. Therefore, even if the manager of the processing device 1 is not familiar with the processing device 1, it is possible to estimate the processing parameter that affects the processing accuracy (quality of the target object W).

[0073] The management device, management method, management program, and recording medium according to the present disclosure are not limited to the above-described embodiments.

[0074] The processing device 1 is not limited to a shot peening device, but may also be a heat treatment device, a casting device, or a machining device such as a polishing device or a grinding device.

[0075] In the above embodiment, the control device 30 has the function of a management device for the processing device 1 (the functional unit shown in FIG. 3), but a server device provided outside the processing device 1 may have the function of a management device. In this case, IoT (Internet of Things) technology is utilized in the processing device 1 such as a shot peening device, enabling next-generation "manufacturing" using surface evaluation technology.

[0076] The acquisition unit 31 may further acquire processing process data indicating physical quantities in the processing process. Examples of such physical quantities include vibration, sound, and surface temperature. These physical quantities can be measured by sensors provided in the processing device 1. By analyzing the processing process data, it is possible to detect abnormalities in the processing device 1 during the processing process.

[0077] The output unit 36 ​​may display the inspection data of multiple objects W on the display device 16. For example, as shown in FIG. 5, the display device 16 may map points representing the first inspection result and the second inspection result in a coordinate space and display them. As shown in FIG. 11, the display device 16 may display the inspection results for each inspection result in chronological order. In the display example shown in FIG. 11, the upper and lower limits of the normal range are displayed, and the inspection results are displayed in chronological order. An inspection result Da determined to be a sudden abnormality is displayed in a different display mode from normal inspection results. Furthermore, change points CP1 and CP2 are displayed. The change point CP1 is a change point caused by a change in the material lot. The change point CP2 is a change point caused by the replacement of a part in the processing device 1. The causes of the change points CP1 and CP2 may be input by the administrator of the processing device 1 via the input device 15 and displayed together with the inspection results.

[0078] According to this configuration, the manager of the processing device 1 can check changes in the inspection results related to the quality of the target object W in chronological order. The normal range can be easily set even if the manager does not have experience or intuition in using the processing device 1. This normal range is set based on statistical inspection results that take processing variations into account, rather than on vague criteria such as the manager's intuition, making it possible to improve the accuracy of determining sudden abnormalities.

[0079] The analysis unit 34 may output the analysis results to the output unit 36. The analysis results include a graph mapping each test result with points indicating the values ​​of the processing parameters when the test result was obtained, and a correlation coefficient between each test result and each processing parameter. The output unit 36 ​​may output the analysis results to the display device 16, and the display device 16 may display the analysis results. The display device 16 may display graphs such as those shown in FIGS. 7 and 8, for example.

[0080] The analysis unit 34 may perform other analyses using the inspection data of multiple objects W. The analysis unit 34 outputs each analysis result to the output unit 36, and the output unit 36 ​​causes the display device 16 to display each analysis result.

[0081] As shown in FIG. 12, the analysis unit 34 may analyze the relationship between the eddy current ratio and the penetration depth of the eddy current for each particle size of the projection material. In FIG. 12, the vertical axis represents the eddy current ratio, and the horizontal axis represents the penetration depth. The penetration depth is obtained by converting the excitation frequency. As the particle size increases, the processing depth increases. Therefore, as the particle size increases, the penetration depth of the eddy current increases and the eddy current ratio also increases.

[0082] As shown in FIG. 13, the analysis unit 34 may analyze the relationship between the stress value and the sample distance. In FIG. 13, the vertical axis represents the sample distance, and the horizontal axis represents the residual stress value. The sample distance is the distance from the stress measuring devices 23, 24 to the object W. The analysis unit 34 may also analyze the relationship between the stress value and MS (MISS SET). MS is an index indicating the optimal value of the sample distance. A larger MS value indicates that the stress measuring devices 23, 24 are farther away from the object W, and a smaller MS value indicates that the stress measuring devices 23, 24 are closer to the object W. The closer the MS value is to 0, the closer the sample distance is to the optimal value (optimal distance). If the stress value deviates from a predetermined threshold (normal range) when MS is fluctuating around 0 (for example, −500 to +500), it is inferred that sufficient shot peening has not been performed. If the stress value falls outside the threshold (normal range) when the sample distance changes significantly, it is expected that the alignment between the object W and the stress measuring devices 23 and 24 is insufficient.

[0083] As shown in FIG. 14, the analysis unit 34 may analyze the relationship between the residual stress value and the area value. In FIG. 14, the vertical axis represents the residual stress value, and the horizontal axis represents the area value. The area value is a value representing the area of ​​the region surrounded by a curve drawn based on the measurement values ​​(eddy current ratios) output from the magnetic evaluation devices 25, 26 within a specified depth range and a straight line representing the reference ratio. The specified depth is the depth range to be evaluated. The reference ratio is a predetermined impedance ratio (eddy current ratio). If the processing device 1 is a shot peening device, if the absolute value of the residual stress value tends to decrease and the area value tends to decrease, it is expected that sufficient shot peening has not been performed.

[0084] The processing parameters may be not only directly measurable by a sensor or the like, but also indirectly measurable processing parameters. An example of such a processing parameter is the particle size of the shot material. As shown in FIG. 12, the penetration depth of the eddy current at the peak value of the eddy current ratio decreases as the particle size of the shot material decreases. The particle size of the shot material can be measured indirectly using this relationship. [Explanation of symbols]

[0085] 1... processing device, 16... display device, 23, 24... stress measuring device, 25, 26... magnetic evaluation device, 27, 28... injection device, 27a, 28a... nozzle, 30... control device (management device), 31... acquisition unit, 32... memory unit, 33... judgment unit, 34... analysis unit, 35... prediction unit, 36... output unit, MD... recording medium, P... management program, W... object.

Claims

1. A management device that manages a shot peening device that processes a plurality of objects in sequence under processing conditions including a plurality of processing parameters, an acquiring unit that acquires inspection result data indicating inspection results of each of the plurality of objects, the inspection result data including electromagnetic characteristics and residual stresses before and after shot peening, and processing condition data indicating the processing conditions used in the shot peening of each of the plurality of objects, the processing condition data being measured by a sensor provided in the shot peening device; an analysis unit that selects a specific parameter that has a correlation with the inspection result from among the plurality of processing parameters; a prediction unit that predicts a future abnormality of the shot peening apparatus based on a change over time in the value of the specific parameter; Equipped with The analysis unit calculates a correlation coefficient between the inspection result and each of the plurality of processing parameters, and if the absolute value of the correlation coefficient is greater than a correlation threshold, selects the processing parameter having the correlation coefficient as the specific parameter.

2. The management device according to claim 1 , wherein the prediction unit predicts that the shot peening device will become abnormal in the future when the value of the specific parameter shows an increasing or decreasing trend.

3. the shot peening apparatus includes components associated with each of a plurality of processing parameters; The management device according to claim 1 , wherein the prediction unit predicts a future abnormality of the part related to the specific parameter.

4. 4. The management device according to claim 1, wherein the prediction unit predicts a time when the test result will show an abnormality based on a change in the test result over time.

5. 5. The management device according to claim 1, further comprising a determination unit that determines whether a sudden abnormality has occurred in the shot peening device based on the inspection result.

6. The management device of claim 5, wherein the determination unit sets a normal range based on the inspection results of an object that has been normally processed, and determines that the sudden abnormality has occurred when the inspection results indicated by the inspection result data fall outside the normal range.

7. The management device according to claim 1, further comprising an output unit that outputs a prediction result by said prediction unit.

8. A management method for managing a shot peening apparatus that processes a plurality of objects in sequence under processing conditions including a plurality of processing parameters, comprising: acquiring inspection result data indicating inspection results of each of the plurality of objects, the inspection result data including electromagnetic characteristics and residual stresses before and after shot peening, and processing condition data indicating the processing conditions used in the shot peening of each of the plurality of objects, the processing condition data being measured by a sensor provided in the shot peening device; calculating a correlation coefficient between the inspection result and each of the plurality of processing parameters, and if an absolute value of the correlation coefficient is greater than a correlation threshold, selecting the processing parameter having the correlation coefficient as a specific parameter; predicting a future abnormality of the shot peening apparatus based on a change in the value of the specific parameter over time; Management methods including.

9. A management program that causes a computer to operate to manage a shot peening apparatus that processes a plurality of objects in sequence under processing conditions including a plurality of processing parameters, the management program comprising: acquiring inspection result data indicating inspection results of each of the plurality of objects, the inspection result data including electromagnetic characteristics and residual stresses before and after shot peening, and processing condition data indicating the processing conditions used in the shot peening of each of the plurality of objects, the processing condition data being measured by a sensor provided in the shot peening device; calculating a correlation coefficient between the inspection result and each of the plurality of processing parameters, and if an absolute value of the correlation coefficient is greater than a correlation threshold, selecting the processing parameter having the correlation coefficient as a specific parameter; predicting a future abnormality of the shot peening apparatus based on a change in the value of the specific parameter over time; A management program that allows a computer to execute the following.

10. A computer-readable recording medium having recorded thereon a management program for operating a computer to manage a shot peening apparatus that processes a plurality of objects in sequence under processing conditions including a plurality of processing parameters, The management program acquiring inspection result data indicating inspection results of each of the plurality of objects, the inspection result data including electromagnetic characteristics and residual stresses before and after shot peening, and processing condition data indicating the processing conditions used in the shot peening of each of the plurality of objects, the processing condition data being measured by a sensor provided in the shot peening device; calculating a correlation coefficient between the inspection result and each of the plurality of processing parameters, and if an absolute value of the correlation coefficient is greater than a correlation threshold, selecting the processing parameter having the correlation coefficient as a specific parameter; predicting a future abnormality of the shot peening apparatus based on a change in the value of the specific parameter over time; A recording medium that is a program for causing a computer to execute the above.

Images