Predictive detection device and predictive detection method

Abstract

To prevent defects from occurring in pressed parts, we provide a predictive defect detection device and method capable of detecting signs of defects that may occur in pressed parts obtained during future press working. [Solution] The predictive detection device 1 includes a measuring device 3 that measures the temperature distribution on the surface of each press part P obtained after each press working operation, a calculation unit 11 that calculates a temperature change distribution, which is the difference between the temperature distribution on the surface of the press part P obtained in the current press working operation and a reference temperature distribution, based on the measurement results from the measuring device 3, and a predictive detection unit 12 that stores the temperature change distribution calculated by the calculation unit 11 as temperature change data and detects signs of defects that may occur in future press parts P based on the multiple stored temperature change data.

Description

Technical Field

[0001] Embodiments of the present invention relate to a sign detection apparatus and a sign detection method.

Background Art

[0002] There is known a defect detection apparatus for pressed parts, which is intended to automatically and reliably detect defects such as cracks of pressed parts in a pressing process at low cost. The defect detection apparatus comprises: a detection means that detects heat distribution on a surface of a pressed part after press molding; an analysis means that analyzes the detected heat distribution; and a determination means that determines whether a defect exists based on an analysis result of the heat distribution. The defect detection apparatus detects a defect that has occurred in a pressed part after press molding.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problem to be Solved by the Invention

[0004] In pressed parts, defects such as cracks and / or necking may occur. When a defect occurs in a pressed part, the yield of the pressed parts decreases, and the manufacturability of the pressed parts deteriorates. Therefore, it is desirable to be able to prevent the occurrence of defects in pressed parts.

[0005] However, conventional defect detection apparatuses detect defects that have already occurred in pressed parts, and cannot detect signs of defects that may occur in pressed parts obtained in subsequent pressing processes. In other words, conventional defect detection apparatuses cannot prevent the occurrence of defects in pressed parts.

[0006] Therefore, the present invention aims to provide a predictive detection device and predictive detection method that can detect signs of defects that may occur in press-formed parts obtained through future press working, in order to prevent defects from occurring in press-formed parts. [Means for solving the problem]

[0007] To solve the aforementioned problems, the predictive mark detection device according to an embodiment of the present invention includes: a measuring device that measures the temperature distribution on the surface of each press part obtained for each press working operation; a calculation unit that calculates a temperature change distribution, which is the difference between the temperature distribution on the surface of the press part obtained in the current press working operation and a reference temperature distribution, based on the measurement results from the measuring device; and a predictive mark detection unit that stores the temperature change distribution calculated by the calculation unit as temperature change data and detects signs of defects that may occur in the press part obtained in future press working operations based on a plurality of stored temperature change data.

[0008] Furthermore, in order to solve the above-mentioned problems, the predictive inspection method according to the embodiment of the present invention includes: an acquisition step of acquiring the surface temperature distribution of each press part obtained for each press work; a calculation step of calculating a temperature change distribution, which is the difference between the surface temperature distribution of the press part obtained in the current press work and a reference temperature distribution, for each press work; and a predictive inspection step of accumulating the temperature change distribution calculated in the calculation step as temperature change data, and detecting a precursor of a defect that may occur in the press part obtained in the upcoming press work based on the accumulated plurality of temperature change data. [Effects of the Invention]

[0009] According to the present invention, it is possible to provide a predictive detection device and predictive detection method that can detect signs of defects that may occur in press-formed parts obtained in future press-formed parts, in order to prevent defects from occurring in press-formed parts. [Brief explanation of the drawing]

[0010] [Figure 1] A schematic diagram of a predictive detection device according to an embodiment of the present invention. [Figure 2] A schematic diagram showing the measurement of the surface temperature distribution of a pressed part by a measuring device of a predictive detection device according to an embodiment of the present invention. [Figure 3] A schematic diagram of the surface temperature distribution of a pressed part, measured by a measuring device of a predictive detection device according to an embodiment of the present invention. [Figure 4] A schematic diagram showing the temperature change data for one batch when defective pressed parts occur within a single batch during press working. [Figure 5] A schematic diagram showing the temperature change data for one batch of press-formed parts, assuming no defective press-formed parts are produced within that batch. [Figure 6] A schematic diagram showing a portion of the temperature change data corresponding to at least a portion of the surface area of ​​a pressed part, which is analyzed by the predictive detection unit of the predictive detection device according to an embodiment of the present invention. [Figure 7] A flowchart illustrating the operation of a predictive detection device according to an embodiment of the present invention. [Modes for carrying out the invention]

[0011] Embodiments of the predictive maintenance device and predictive maintenance method according to the present invention will be described with reference to Figures 1 to 7. Note that identical or corresponding components are denoted by the same reference numerals in multiple drawings.

[0012] Figure 1 is a schematic diagram of a predictive detection device according to an embodiment of the present invention.

[0013] The predictive detection device 1 according to this embodiment, shown in Figure 1, measures the temperature distribution on the surface of a press-formed part immediately after pressing to detect potential defects in the press-formed part obtained from the upcoming pressing process. In other words, the predictive detection device 1 does not detect defects that have already occurred in the press-formed part, but rather detects potential defects in the press-formed part obtained from future pressing processes, and is a system that supports the manufacturing management of press-formed parts. Hereinafter, the press-formed part obtained from the upcoming pressing process may be referred to as the "future press-formed part."

[0014] In this embodiment, the pressed part refers to a vehicle body part (vehicle part). In this embodiment, the defect of the pressed part refers to cracks and necking that occur in the pressed part. Necking refers to a condition in which the thickness of a part that should be uniformly stretched becomes locally thinner, resulting in a constriction in the pressed part.

[0015] As shown in Figure 1, the predictive detection device 1 comprises a measuring device 3 and a controller 5. The predictive detection device 1 may also further include a notification device 7 that provides a predetermined notification.

[0016] Figure 2 is a schematic diagram showing the measurement of the surface temperature distribution of a pressed part by a measuring device of a predictive detection device according to an embodiment of the present invention.

[0017] Figure 3 is a schematic diagram of the surface temperature distribution of a pressed part measured by a measuring device of a predictive detection device according to an embodiment of the present invention.

[0018] Note that the schematic diagram of the temperature distribution on the surface of the pressed part P shown in FIG. 3 is merely an example, and the temperature distribution on the surface of the pressed part P and the range of the surface to be measured of the pressed part P, that is, the surface region, may vary depending on the type and material of the pressed part P. Further, the surface region to be measured of the pressed part P includes a region of a defect D that may occur in the pressed part P in the future. Further, FIG. 3 is an infrared image captured when the measuring device 3 is an infrared camera, and for convenience of explanation, the temperature distribution on the surface of the pressed part P is represented by isotherms. In addition, in FIG. 3, regions R1 to R3 indicated by isotherms are different regions from each other. The temperature T1 of the region R1, the temperature T2 of the region R2, and the temperature T3 of the region R3 satisfy the following relational expression (1). (Temperature T1)>(Temperature T2)>(Temperature T3) (1)

[0019] As shown in FIG. 2 and FIG. 3, the measuring device 3 measures the temperature distribution on the surface of each obtained pressed part P for each press working performed by the press working apparatus 100. The measuring device 3 outputs measurement data (temperature distribution data) to the controller 5.

[0020] In general, in press working, the surface temperature of a pressed part immediately after press working rises because frictional heat is generated due to friction occurring on the contact surface between the die and the plate-shaped member that is the material before being formed into the pressed part. Further, when the plate-shaped member undergoes plastic deformation, part of the deformation energy is converted into heat, so the surface temperature of the pressed part rises. In particular, among press working, in drawing processing that is frequently used for pressed parts as vehicle components, large deformation occurs, so heat is easily generated. In this way, the working state of the pressed part is reflected in the temperature distribution on the surface of the pressed part immediately after press working. Therefore, the processing state of the pressed part P is reflected in the measurement data obtained by the measuring device 3 measuring the temperature distribution on the surface of the pressed part P.

[0021] The press working apparatus 100 comprises a die 101, an upper section 102, and a lower section 103. The press working apparatus 100 may also be equipped with a cooling device (not shown) for cooling the die 101. The die 101 includes an upper die 101u provided on the upper section 102 and a lower die 101b provided on the lower section 103. The upper section 102 is also called a slide. In the press working performed by the press working apparatus 100, the upper section 102 descends and applies pressure, processing the plate-like member between the upper die 101u and the lower die 101b before it becomes a press part P, thereby manufacturing the press part P. When the upper section 102 rises and the pressurized state is released, the press part P is sent to the next process.

[0022] The measuring device 3 measures the temperature distribution on the surface of the pressed part P when the upper part 102 of the press working device 100 rises and the cam angle of the upper part 102 becomes greater than or equal to a predetermined value, that is, when the upper die 101u is lifted and the position of the upper die 101u becomes greater than or equal to a predetermined height. Also, the time required for one press working is usually constant. Therefore, the measuring device 3 may also measure the temperature distribution on the surface of the pressed part P when a predetermined time has elapsed after the press working until the upper die 101u is lifted.

[0023] The measuring device 3 is, for example, an infrared camera. The infrared camera captures infrared radiation emitted from an object and measures its radiation intensity to generate an infrared image of the temperature distribution on the object's surface. In other words, the infrared camera captures an infrared image of the object. The infrared camera may also generate numerical data of the temperature distribution corresponding to the generated infrared image along with the infrared image. In this case, the numerical data of the temperature distribution includes multiple positional data points in the infrared image, that is, multiple positional data points on the object's surface, and the temperature data of one pixel of the infrared image corresponding to each of the multiple positional data points. This numerical data of the temperature distribution can also be extracted from the infrared image. When the measuring device 3 is an infrared camera, the temperature distribution data that the measuring device 3 outputs to the controller 5 may include an infrared image of the surface of the press part P, and / or numerical data of the temperature distribution on the surface of the press part P. Furthermore, the measuring device 3 does not necessarily need to measure the entire surface area of ​​the press part P. In addition, the measuring device 3 may consist of two or more infrared cameras to extend the measurement area of ​​the surface of the press part P.

[0024] When the measuring device 3 is an infrared camera, the measuring device 3 is fixed in a position that allows it to image the surface of the press part P from a predetermined direction and at a predetermined angle at the timing of measurement (image capture). The predetermined direction and angle are determined by the type of press part P. In addition, the measuring device 3 is not limited to an infrared camera, but may be a measuring device equipped with multiple temperature sensors attached to the upper die 101u of the press working apparatus 100. The multiple temperature sensors are, for example, thermocouples. The multiple temperature sensors are mounted in an array on the inner surface of the upper die 101u to measure the surface temperature of the press part P immediately after press working and before the upper die 101u rises. In the following description, unless otherwise specified, the measuring device 3 is an infrared camera, and the temperature distribution data output by the measuring device 3 to the controller 5 is an infrared image of the surface of the press part P.

[0025] The controller 5 is configured as a computer equipped with a central processing unit (CPU), storage devices such as random access memory (RAM), read-only memory (ROM), hard disk drive (HDD), and solid state drive (SSD), and an input / output interface. When the controller 5 receives temperature distribution data of the surface of the press part P from the measuring device 3, it performs predetermined calculations related to detecting signs of defects that may occur in the press part P in the future.

[0026] The controller 5 includes a calculation unit 11 that performs predetermined calculations based on the measurement results of the measuring device 3, and a predictive detection unit 12 that detects signs of defects that may occur in future press parts P. The controller 5 may also include a control unit 13 that controls the notification device 7 and the press working device 100. The controller 5 may also include an analysis unit 14 that, when the predictive detection unit 12 detects a sign of a defect, stores information regarding at least the detected sign of the defect as a history and analyzes the stored history.

[0027] Furthermore, the notification device 7 is, for example, a human-machine interface (HMI) device. The notification device 7 receives command signals from the control unit 13 and provides notifications to the worker regarding the press work. The notifications from the notification device 7 may be visual or audible. The notification device 7 can provide notifications by both display and sound, or by either one of these methods. The notification device 7 is placed in a location that is easily visible to the worker.

[0028] As mentioned above, conventional defect detection devices detect defects that have already occurred in pressed parts, but they cannot detect precursors to defects that may occur in pressed parts produced in future press working. In other words, conventional defect detection devices cannot prevent defects that may occur in future pressed parts.

[0029] Therefore, the calculation unit 11 calculates a temperature change distribution, which is the difference between the surface temperature distribution of the pressed part P obtained in the current press working process and a reference temperature distribution, based on the measurement results from the measuring device 3, for each press working process. Furthermore, the predictive detection unit 12 stores the temperature change distribution calculated by the calculation unit 11 as temperature change data, and based on the multiple stored temperature change data, detects signs of defects that may occur in the pressed part P obtained in the upcoming press working process, that is, in future pressed parts P. In other words, the predictive detection unit 12 stores the temperature change distribution calculated by the calculation unit 11 as temperature change data, and by analyzing the multiple stored temperature change data, detects signs of defects that may occur in future pressed parts P.

[0030] Specifically, the calculation unit 11 acquires an infrared image from the measuring device 3. Here, the reference temperature distribution is an infrared image having the same data size as the acquired infrared image, or an infrared image having the same data size as the acquired infrared image and having undergone predetermined image processing. The calculation unit 11 calculates (generates) a difference image between the acquired infrared image and the infrared image as the reference temperature distribution. This difference image is the temperature change amount distribution. The temperature change amount distribution includes the position data of the surface of the pressed part P and the temperature change amount data (numerical values ​​of temperature difference) corresponding to each of the multiple position data. The temperature change amount data is what the predictive detection unit 12 accumulates and analyzes. In the process of finding the temperature change amount distribution (temperature change amount data) calculated by the calculation unit 11, the inventors performed the analysis described below regarding the trend of changes over time in the temperature change amount data obtained through multiple press working operations.

[0031] Figure 4 is a schematic diagram showing the temperature change data for one batch when a defective pressed part occurs in a single batch during press working.

[0032] Figure 5 is a schematic diagram showing the temperature change data for one batch in a press working process when no defective press parts are produced in that batch.

[0033] Figures 4 and 5 are based on the following assumptions: The horizontal axis represents the number of shots in press working, and the vertical axis represents the temperature change (numerical value of temperature difference). The number of shots refers to the count value (number of presses) of the number of press parts P produced by the press working machine 100. The temperature change data is plotted for a lot of 400 shots. For ease of explanation, only a portion of the temperature change data corresponding to a specific area of ​​the surface of the press part P within one lot is plotted.

[0034] As shown in Figure 4, in lots where defects actually occurred in the pressed parts P, the frequency of the temperature change exceeding a predetermined threshold tended to increase from around the 200th shot. Then, a defect actually occurred in the pressed part P obtained from approximately the 260th press. On the other hand, as shown in Figure 5, in lots where no defects occurred in the pressed parts P, the temperature change tended to remain generally within a predetermined threshold throughout the press processing of one lot. From these analysis results, the inventors found that the increasing frequency of the temperature change exceeding a predetermined threshold indicates a precursor to defects that may occur in future pressed parts P. In other words, the inventors found that temperature change data can contain precursors to defects that may occur in future pressed parts P. Therefore, the precursor detection unit 12 can store temperature change data that may contain precursors to defects and detect precursors to defects that may occur in future pressed parts P based on the stored data of multiple temperature change data.

[0035] Furthermore, each temperature change in the temperature change distribution (the difference between each temperature) may be the temperature change for each pixel in the difference image, or multiple pixels may be treated as a single sub-region, and the temperature changes within the sub-region may be averaged to represent the temperature change for the sub-region. The number of pixels contained in one sub-region is determined, for example, by the type and / or material of the pressed part P.

[0036] Furthermore, the reference temperature distribution may be the surface temperature distribution (infrared image) of the pressed part P obtained from at least one press operation prior to the current press operation (the most recent press operation). By doing so, the effects of disturbances caused by, for example, changes in the room temperature inside the factory where the press operation is performed can be removed from the temperature change distribution, i.e., the temperature change data, which may contain precursors to defects that may occur in the pressed part P in the future.

[0037] The reference temperature distribution may be the average of the surface temperature distributions of the pressed part P obtained in at least two press operations immediately preceding the current press operation. Specifically, the reference temperature distribution is the image obtained by averaging two infrared images obtained in the two preceding press operations. Alternatively, the reference temperature distribution may be the average value obtained by statistically processing the surface temperature distributions of the pressed part P obtained in multiple press operations performed prior to the current press operation, plus the standard deviation. Furthermore, the reference temperature distribution may be the temperature distribution for each press operation in a lot in the case where no defects actually occurred. In this case, for example, the surface temperature distribution of the pressed part P obtained in the fifth press operation in a lot in the case where no defects occurred can be used as the reference temperature distribution for the surface temperature distribution of the pressed part P obtained in the fifth press operation in a lot in the case where no defects occurred.

[0038] Figure 6 is a schematic diagram showing a portion of the temperature change data that corresponds to at least a portion of the surface area of ​​a pressed part, which is analyzed by the predictive detection unit of the predictive detection device according to the embodiment of the present invention.

[0039] Note that the schematic diagram of the temperature change data (temperature change distribution) shown in Figure 6 is merely an example and may vary depending on the type, material, and reference temperature distribution of the pressed part P. Also, in Figure 6, for the sake of explanation, the temperature change distribution on the surface of the pressed part P is represented by isotherms. Furthermore, in Figure 6, the regions R1' to R3' shown by the isotherms are all different regions. The temperature differences ΔT1' in region R1', ΔT2' in region R2', and ΔT3' in region R3' satisfy the following relation (2). (Temperature difference ΔT1′)>(Temperature difference ΔT2′)>(Temperature difference ΔT3′) (2)

[0040] Furthermore, the predictive detection unit 12 may detect signs of defects that may occur in the press part P in the future based on a portion of the temperature change data from the accumulated temperature change data that corresponds to at least a portion of the surface area of ​​the press part P. By doing so, the predictive detection unit 12 reduces the data size of the temperature change data to be analyzed and excludes the remaining temperature change data that does not contribute to the detection of signs of defects, or whose contribution to the detection of signs of defects is low, from the analysis. As a result, the predictive detection unit 12 can improve the accuracy of predictive detection while reducing the computational load related to predictive detection. In the example in Figure 6, the predictive detection unit 12 detects signs of defects D that may occur in the press part P in the future based on a portion of the temperature change data that corresponds to at least a portion of the surface area A enclosed by a dashed line.

[0041] Note that region A shown in Figure 6 includes nine rectangular sub-regions. The size of region A is determined, for example, based on temperature change data for one batch in which defective press parts P actually occurred, as well as the location and size of the defects D.

[0042] Furthermore, at least a portion of the surface area of ​​the press part P that corresponds to a portion of the temperature change data analyzed by the predictive detection unit 12 may be a different location from the area on the surface of the press part P obtained by the upcoming press working where defect occurrence is predicted.

[0043] Specifically, on the surface of the pressed part P, locations where temperature change data that may indicate a defect exceeds a predetermined threshold do not necessarily coincide with locations where defect occurrence is predicted. Rather, analysis of examples where defective pressed parts P occurred in a single lot during press processing suggests that temperature change data exceeding a predetermined threshold may occur around locations where defect occurrence is predicted. Therefore, by analyzing temperature change data from locations on the surface of the pressed part P that are different from those where defect occurrence is predicted, the predictive detection unit 12 can detect defect precursors with greater accuracy. In the example in Figure 6, at least a portion of the surface region A of the pressed part P, corresponding to a portion of the temperature change data analyzed by the predictive detection unit 12, is set in a location different from the location where defect D as a crack is predicted to occur.

[0044] Furthermore, it is preferable that at least a portion of the surface area of ​​the press part P, which corresponds to a portion of the temperature change data used by the predictive detection unit 12 to detect signs of defects, is determined according to the type of press part P.

[0045] Specifically, the shape of the pressed part P changes depending on the type of pressed part P. The shape of the pressed part P is closely related to the location and size of defects that may occur in the pressed part P. In other words, the location and size of defects that may occur in the pressed part P can be inferred from the shape of the pressed part P. If the location and size of the defects can be inferred, then at least a portion of the surface of the pressed part P that should be considered in relation to the temperature change data can be determined. Therefore, the predictive detection unit 12 can accurately detect signs of defects even when the type of pressed part P changes.

[0046] Furthermore, at least a portion of the surface area of ​​the pressed part P may be determined based on, in addition to the type of pressed part P, at least one of the following: for example, the operating conditions of the press working apparatus 100, the thickness of the pressed part P, and the material of the pressed part P.

[0047] Furthermore, it is preferable that the predictive detection unit 12 detects a potential defect in the press-formed part P obtained from the upcoming press-formation when, within a predetermined number of press-formation cycles, the number of temperature change data exceeding a predetermined threshold among multiple temperature change data exceeds a predetermined number. By doing so, the predictive detection unit 12 can accurately detect potential defects with reproducibility.

[0048] Furthermore, it is preferable that the predetermined threshold, predetermined number of press working cycles, and predetermined number are determined according to at least the type of press part P or at least the material of the press part P.

[0049] Specifically, the type and material of the pressed part P are closely related to the temperature distribution on the surface of the pressed part P immediately after pressing and to the defects that may occur in the pressed part P. Therefore, by setting predetermined thresholds, predetermined number of pressing operations, and predetermined numbers—parameters necessary for determining whether to detect a defect precursor—according to the differences in the type and material of the pressed part P, the defect precursor detection unit 12 can detect defect precursors with greater accuracy.

[0050] Furthermore, it is preferable that the control unit 13 of the controller 5 stops the press operation of the press working apparatus 100 when the predictive detection unit 12 detects a precursor to a defect, or causes the notification device 7 to notify the notification device 7 of predetermined information, such as information prompting the cooling of the mold 101 or information regarding the precursor to a defect.

[0051] Specifically, by stopping the press operation of the press working machine 100, the mold 101 can be cooled, and the operator can inspect the mold 101. In addition, by having the notification device 7 notify the operator of information prompting the cooling of the mold 101 or information regarding signs of defects, the operator can activate the cooling device of the press working machine 100 to cool the mold 101, or temporarily strengthen the inspection system for the press working machine 100 and the pressed parts P. As a result, the control unit 13 can enable the press working machine 100 and the operator to take appropriate measures to prevent defects from occurring in the pressed parts P.

[0052] Furthermore, the press working apparatus 100 may be equipped with a notification device (not shown), and the control unit 13 may cause the notification device of the press working apparatus 100 to notify information prompting the cooling of the mold 101, or information regarding signs of defects.

[0053] Furthermore, it is preferable that the analysis unit 14 of the controller 5 links the management number of the mold 101 with the number of detected signs of defects that may occur in future press parts P, and when the number of signs of defects detected in the same mold 101 within a predetermined period exceeds a certain number, the control unit 13 notifies the notification device 7 of information regarding the repair of the same mold 101.

[0054] Specifically, the number of times a defect precursor is detected within a predetermined period in the same mold 101 can serve as an indicator for repairing the mold 101. Therefore, the analysis unit 14 analyzes the number of defect precursors detected within a predetermined period in the same mold 101 at a timely interval, and if the number of defect precursors exceeds a certain number, it prompts the operator to repair the mold 101 in which the number of defect precursors has exceeded that number. In other words, the analysis unit 14 enables the maintenance of the mold 101 and, consequently, the quality control of the press-formed parts P at a high level.

[0055] The predetermined period is, for example, one day, one week, or one month. The management number for mold 101 is a unique number that can identify each of the multiple molds 101. Alternatively, the analysis unit 14 may analyze the trend of the times when signs of defects are detected within the predetermined period. By doing so, if the analysis results of the analysis unit 14 reveal a tendency for the times when signs of defects are detected to be concentrated in specific time periods, such as early morning, after breaks, and late at night, it becomes possible to, for example, increase the number of workers assigned to these specific time periods, or to check the environment inside the factory where press working is performed during these specific time periods, and whether or not the settings of the press working machine 100 have been changed.

[0056] Figure 7 is a flowchart showing the operation of the predictive detection device according to an embodiment of the present invention.

[0057] Now, referring to Figure 7, the process (predictive detection method) executed by the controller 5 of the predictive detection device 1 according to this embodiment, as described above, will be explained. The flowchart in Figure 7 consists of steps S1 to S4. For the sake of explanation, as a premise, the measuring device 3 measures the temperature distribution on the surface of each press part P obtained after each press working and outputs the temperature distribution data obtained from the measurement to the controller 5.

[0058] As shown in Figure 7, first, in step S1, the controller 5 acquires temperature distribution data from the surface of the pressed part P.

[0059] In step S2, following step S1, the controller 5 calculates the temperature change distribution, which is the difference between the surface temperature distribution of the pressed part P obtained in this press operation and a reference temperature distribution.

[0060] In step S3, following step S2, the controller 5 stores the temperature change distribution calculated in step S2 as temperature change data, and based on the stored temperature change data, determines whether or not it has detected any signs of defects that may occur in the press-formed part P obtained from the upcoming press-forming process. If signs of defects are detected (YES in step S3), the process proceeds to step S4. If signs of defects are not detected (NO in step S3), the process returns to step S1 and performs the operations of steps S1 and S2.

[0061] In step S3, the controller 5 determines that it has detected a precursor to a defect that may occur in the future press part P if, among the multiple accumulated temperature change data, the number of temperature change data exceeding a predetermined threshold exceeds a predetermined number within a predetermined number of press operations after the occurrence of temperature change data exceeding a predetermined threshold begins.

[0062] In step S4, following the YES response in step S3, the controller 5 either stops the press operation (pressing) of the press working apparatus 100, or issues a predetermined notification via the notification device 7. The predetermined notification includes, for example, information prompting the cooling of the mold 101 or information regarding potential defects that may occur in future pressed parts P.

[0063] After executing the process in step S4, controller 5 terminates this series of processes.

[0064] As described above, the predictive detection device 1 according to this embodiment includes a calculation unit 11 that calculates a temperature change distribution, which is the difference between the temperature distribution on the surface of the pressed part P obtained in the current press working process and a reference temperature distribution, based on the measurement results from the measuring device 3, for each press working process, and a predictive detection unit 12 that stores the temperature change distribution as temperature change data and detects signs of defects that may occur in the pressed part P in the future based on the stored temperature change data. Furthermore, the predictive detection method according to this embodiment includes an acquisition step of acquiring the temperature distribution on the surface of each pressed part P obtained in each press working process, a calculation step of calculating a temperature change distribution, which is the difference between the temperature distribution on the surface of the pressed part P obtained in the current press working process and a reference temperature distribution, for each press working process, and a predictive detection step of storing the temperature change distribution as temperature change data and detecting signs of defects that may occur in the pressed part P in the future based on the stored temperature change data. The temperature change distribution, that is, the temperature change data, contains signs of defects that may occur in the pressed part P in the future. Therefore, the predictive detection device 1 and predictive detection method can detect signs of defects that may occur in future press-formed parts P based on multiple accumulated temperature change data. Furthermore, when signs of defects are detected, the predictive detection device 1 and predictive detection method can prevent the occurrence of defects in press-formed parts P by prompting the press-formed machine 100 and / or the operator to take appropriate action.

[0065] Furthermore, in the predictive detection device 1 according to this embodiment, the reference temperature distribution used to calculate the temperature change distribution is the surface temperature distribution of the pressed part P obtained in at least one press working operation prior to the current press working operation. Therefore, the predictive detection device 1 can remove the influence of disturbances such as changes in room temperature in the factory where the press working is being performed from the temperature change data, which may contain precursors to defects that may occur in the pressed part P in the future. In other words, the predictive detection device 1 can accurately detect precursors to defects that may occur in the pressed part P in the future based on a plurality of temperature change data from which the influence of disturbances has been removed.

[0066] Furthermore, the predictive detection device 1 according to this embodiment includes a predictive detection unit 12 that detects signs of defects that may occur in the press part P in the future, based on a portion of the temperature change data corresponding to at least a portion of the surface area of ​​the press part P. The remaining portion of the temperature change data may not contribute to the detection of defect signs, or may have a low contribution to the detection of defect signs. In this case, by excluding such remaining temperature change data from the analysis target and reducing the data size of the temperature change data to be analyzed, the predictive detection device 1 can improve the accuracy of defect sign detection while reducing the computational load related to defect sign detection.

[0067] Furthermore, in the predictive maintenance device 1 according to this embodiment, at least a portion of the surface of the press part P corresponding to a portion of the temperature change data analyzed by the predictive maintenance unit 12 is a different location from the location where defects are predicted to occur on the surface of the press part P in the future. The location where defects are predicted to occur on the surface of the press part P in the future does not necessarily coincide with the location on the surface of the press part P where the temperature change data that may contain signs of defects exceeds a predetermined threshold. Rather, it is assumed that the temperature change data will exceed the predetermined threshold around the location where defects are predicted to occur. Therefore, by analyzing the temperature change data of a location on the surface of the press part P that is different from the location where defects are predicted to occur, the predictive maintenance device 1 can detect signs of defects that may occur on the press part P in the future with greater accuracy.

[0068] Furthermore, in the predictive maintenance device 1 according to this embodiment, at least a portion of the surface area of ​​the press part P that corresponds to a portion of the temperature change data used by the predictive maintenance unit 12 to detect signs of defects is determined according to the type of press part P. The location and size of defects that may occur in the press part P can be estimated from the shape of the press part P, which is closely related to the type of press part P. This makes it possible to determine at least a portion of the surface area of ​​the press part P that is of interest with respect to the temperature change data. Therefore, even if the type of press part P changes, the predictive maintenance device 1 can accurately detect signs of defects that may occur in the press part P in the future.

[0069] Furthermore, the predictive detection device 1 according to this embodiment includes a predictive detection unit 12 that determines that a precursor to a defect that may occur in a future pressed part P has been detected when, among a plurality of temperature change amount data, the number of temperature change amount data exceeding a predetermined threshold exceeds a predetermined number within a predetermined number of press working cycles after a temperature change amount data exceeding a predetermined threshold data starts to occur. Therefore, by specifically setting a predetermined threshold, a predetermined number of press working cycles, and a predetermined number, the predictive detection device 1 can accurately and reproducibly detect precursors to defects that may occur in a future pressed part P based on a plurality of accumulated temperature change amount data.

[0070] Furthermore, in the predictive mark detection device 1 according to this embodiment, predetermined thresholds, predetermined number of press operations, and predetermined number related to multiple temperature change data are determined according to at least the type of press part P or at least the material of the press part P. The predetermined thresholds, predetermined number of press operations, and predetermined number, which are parameters set to determine the detection of a defect precursor, are closely related to the type of press part P or the material of the press part P. Therefore, by determining the values ​​of these parameters according to the differences in the type of press part P and the material of the press part P, the predictive mark detection device 1 can more accurately detect a defect precursor that may occur in the press part P in the future.

[0071] Furthermore, the predictive detection device 1 according to this embodiment includes a control unit 13 that, when the predictive detection unit 12 detects a precursor to a defect that may occur in the press part P in the future, stops the press operation of the press working apparatus 100, or notifies the notification device 7 of information prompting the cooling of the mold 101 or information regarding the precursor to a defect. The control unit 13 enables the implementation of appropriate measures to prevent the occurrence of a defect in the press part P before the defect actually occurs. Therefore, the predictive detection device 1 can prevent the occurrence of defects in the press part P.

[0072] Furthermore, the predictive maintenance device 1 according to this embodiment includes an analysis unit 14 that links the management number of the mold 101 with the number of detected precursors of defects that may occur in future press parts P, and when the number of defect precursors detected in the same mold 101 within a predetermined period exceeds a certain number, it notifies the notification device 7 via the control unit 13 of information regarding the repair of the same mold 101. As a result, the predictive maintenance device 1 can achieve a high level of maintenance for the mold 101 and quality control for the press parts P.

[0073] Therefore, according to the predictive detection device 1 and predictive detection method of this embodiment, it is possible to detect signs of defects that may occur in the press-formed part P in the future, in order to prevent defects from occurring in the press-formed part P.

[0074] While several embodiments of the present invention have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents. [Explanation of Symbols]

[0075] 1... Predictive detection device, 3... Measurement device, 5... Controller, 7... Notification device, 11... Calculation unit, 12... Predictive detection unit, 13... Control unit, 14... Analysis unit, 100... Pressing device, 101... Mold, 101u... Upper mold, 101b... Lower mold, 102... Upper part, 103... Lower part, D... Defect, P... Pressed part, A, R1, R2, R3, R1', R2', R3'... Area.

Claims

1. A measuring device measures the surface temperature distribution of each pressed part obtained after each press working process. Based on the measurement results from the measuring device, a calculation unit calculates a temperature change distribution, which is the difference between the temperature distribution on the surface of the pressed part obtained in the current press working process and a reference temperature distribution, for each press working process. A predictive detection device comprising: a calculation unit that stores the temperature change distribution calculated by the calculation unit as temperature change data, and a predictive detection unit that detects signs of defects that may occur in the press-formed part obtained by the press-formed part to be performed based on a plurality of the stored temperature change data.

2. The predictive mark detection device according to claim 1, wherein the reference temperature distribution is the temperature distribution of the surface of the pressed part obtained in at least one press operation prior to the current press operation.

3. The predictive detection device according to claim 1, wherein the predictive detection unit detects the precursor of the defect based on a portion of the temperature change data corresponding to at least a portion of the surface area of ​​the press part from among the respective temperature change data.

4. The predictive mark detection device according to claim 3, wherein at least a portion of the surface of the press part is a different location from the location where the defect is expected to occur on the surface of the press part obtained by the press work to be performed.

5. The predictive mark detection device according to claim 3, wherein at least a portion of the surface of the pressed part is determined according to the type of pressed part.

6. The predictive mark detection device according to claim 1, wherein the predictive mark detection unit determines that it has detected a predictive mark of a defect that may occur in the press part obtained by the upcoming press work when, among the plurality of temperature change amount data, the number of temperature change amount data exceeding a predetermined threshold exceeds a predetermined number within a predetermined number of press work cycles after the occurrence of temperature change amount data exceeding a predetermined threshold.

7. The predictive mark detection device according to claim 6, wherein the predetermined threshold, the predetermined number of press workings, and the predetermined number are determined at least according to the type of press part or at least the material of the press part.

8. A notification device that notifies predetermined information, The system comprises the aforementioned notification device, a press working apparatus having a mold and performing press working using the mold, and a control unit for controlling the press working apparatus. The predictive detection device according to claim 1, wherein the control unit stops the press operation of the press working apparatus or causes the notification device to notify the notification device of information prompting the cooling of the mold or information regarding the predictive defect when the predictive detection unit detects the predictive defect.

9. It is equipped with an analysis unit that performs a predetermined analysis, The predictive mark detection device according to claim 8, wherein the analysis unit links the management number of the mold with the number of detected precursors of the defect, and when the number of detected precursors of the defect in the same mold within a predetermined period exceeds a certain number, the control unit causes the notification device to notify the notification device of information regarding the repair of the same mold.

10. A process to acquire the surface temperature distribution of each pressed part obtained after each press working, A calculation step is performed for each press working operation to calculate the temperature change distribution, which is the difference between the temperature distribution on the surface of the press part obtained in the current press working operation and a reference temperature distribution. A method for detecting defects, comprising: a step of accumulating the temperature change distribution calculated in the calculation step as temperature change data, and a step of detecting signs of defects that may occur in the press-formed part obtained in the press-formed part to be performed, based on a plurality of the accumulated temperature change data.

Images