Metal stamping plate stamping quality detection method, equipment and medium

Abstract

The invention provides a metal stamping plate stamping quality detection method and device and a medium, and relates to the technical field of metal processing.The method comprises the steps that a vibration characteristic value list corresponding to each vibration sensor is determined according to vibration signals detected by each vibration sensor in the stamping time period; performing frequency domain transformation processing on a plurality of vibration signals detected by each vibration sensor in the stamping time period to obtain a frequency spectrum characteristic value list corresponding to each vibration sensor; determining a first surface feature value list and a second surface feature value list according to the contour feature values of the upper / lower surface of the punching area of the to-be-detected punching plate; and according to each vibration characteristic value list, each frequency spectrum characteristic value list, the first surface characteristic value list and the second surface characteristic value list, the punching quality state of the punching area of the to-be-detected punching plate is determined, and whether cracks influencing the use quality can be generated in the punching work of the metal punching plate or not is analyzed.

Description

Background Art

[0002] The metal stamping die is used to stamp metal stamping sheets. The metal stamping die includes a punch, which is used to punch or stamp the metal stamping sheets. During the manufacturing process, the metal stamping sheets may have cracks inside or on the surface that are not recognizable to the naked eye due to manufacturing process accuracy problems. If such cracks exist in the punching area of the metal stamping sheet, then after the punch punches the metal stamping sheet, the cracks may cause unsatisfactory punching or fail to achieve standard operating results. Or, when the metal stamping sheet has low internal hardness due to manufacturing problems, when the punch punches the punching area, cracks may occur around the punching area of the metal stamping sheet due to hardness problems. Such cracks will affect the quality of the metal stamping sheet. Therefore, it is necessary to detect the quality of the metal stamping sheet during the stamping process. Summary of the invention

[0003] In view of the above technical problems, the technical solution adopted by the present invention is: According to one aspect of the present application, a method for detecting the stamping quality of a metal stamping sheet is provided, which is applied to a stamping quality detection system, wherein the stamping quality detection system is connected to a plurality of vibration sensors, which are arranged around a punching area of a stamping sheet to be detected, and the distance between each vibration sensor and the center point of the punching area of the stamping sheet to be detected is within a preset detection distance range; Among them, the metal stamping sheet stamping quality detection method includes the following steps: Step S100, in response to receiving a stamping detection signal of a stamping sheet to be detected, a list of vibration characteristic values corresponding to each vibration sensor is determined according to a number of vibration signals detected by each vibration sensor in a stamping time period; the starting time of the stamping time period is the time when the punching area of the stamping sheet to be detected is started to be punched; the ending time of the stamping time period is the time when the punching area of the stamping sheet to be detected is completed; Step S200, performing frequency domain transformation processing on a plurality of vibration signals detected by each vibration sensor during the stamping time period, so as to obtain a list of frequency spectrum characteristic values corresponding to each vibration sensor; Step S300, determining a first surface feature value list and a second surface feature value list respectively according to the contour feature values of the upper surface at the punching area of the stamped sheet to be detected and the contour feature values of the lower surface at the punching area of the stamped sheet to be detected; Step S400: Determine the stamping quality state of the punching area of the stamped sheet to be inspected according to each vibration eigenvalue list, each spectrum eigenvalue list, the first surface eigenvalue list and the second surface eigenvalue list.

[0004] In an exemplary embodiment of the present application, step S100 includes: Step S110, in response to receiving a stamping detection signal of a stamping sheet to be detected, obtaining a plurality of vibration signals detected by each vibration sensor during a stamping time period to obtain a plurality of vibration signal lists E1, E2,..., E g ,..., E h ; where g = 1, 2,..., h; h is the number of vibration sensors; E g is the vibration signal list corresponding to the g-th vibration sensor; E g =(E g1 , E g2 ,..., E gb ,..., E gc ); b = 1, 2,..., c; c is the number of detection time nodes included in the stamping time period; the time length between every two adjacent detection time nodes in the stamping time period is the same; E gb is the vibration signal detected by the g-th vibration sensor at the b-th detection time node in the stamping time period; Step S120, extracting the time series feature value corresponding to each vibration signal in E g through a preset time series feature extraction module to obtain a vibration feature value list F g =(F g1 , F g2 ,..., F gb ,..., F gc ); where F gb is the time series feature value extracted from E gb through a preset time series feature extraction module.

[0005] In an exemplary embodiment of the present application, step S200 includes: Step S210, performing a short-time Fourier transform on each vibration signal in the vibration signal list E g corresponding to the g-th vibration sensor to obtain a spectrum signal list G g =(G g1 , G g2 ,..., G gb ,..., G gc ); where G gb is the spectrum signal obtained by performing a short-time Fourier transform on E gb ; Step S220, extracting G gThe spectral eigenvalue corresponding to each spectral signal therein to obtain a list of spectral eigenvalues H corresponding to the g-th vibration sensor g =(H g1 ,H g2 ,...,H gb ,...,H gc ); where H gb is the spectral eigenvalue corresponding to G gb extracted by a preset spectral feature extraction module.

[0006] In an exemplary embodiment of the present application, step S300 includes: Step S310, obtaining the contour feature values of the upper surface at the punching area of the punching sheet to be detected to obtain a first surface feature value list M=(M1, M2,..., M d ,..., M e ); where d = 1, 2,..., e; e is the number of contour feature values of the upper surface at the punching area of the punching sheet to be detected; M d is the d-th contour feature value of the upper surface at the punching area of the punching sheet to be detected; Step S320, obtaining the contour feature values of the lower surface at the punching area of the punching sheet to be detected to obtain a second surface feature value list N=(N1, N2,..., N d ,..., N e ); where N d is the d-th contour feature value of the lower surface at the punching area of the punching sheet to be detected.

[0007] In an exemplary embodiment of the present application, the contour feature values of the upper surface at the punching area of the punching sheet to be detected are determined according to the following steps: Step S301, placing the punching sheet to be detected on the transmission line so that the punching sheet to be detected moves on the transmission line; several upper surface detection mechanisms of the punching sheet are arranged above the transmission line, the upper surface detection mechanisms of the punching sheet are arranged in a column, and the arrangement direction of this column is perpendicular to the moving direction of the punching sheet to be detected on the transmission line. The distance between the contact end of each upper surface detection mechanism of the punching sheet and the upper surface of the transmission line is a preset thickness threshold, and the upper surface detection mechanism of the punching sheet is used to detect the pressure value given by the object passing through the contact end of the upper surface detection mechanism of the punching sheet; Step S302, obtaining several pressure values at the upper surface of the punching area of the punching sheet to be detected detected by each upper surface detection mechanism of the punching sheet during the detection time period to obtain an upper surface pressure value list set I=(I1, I2,..., I d ,..., I e); where e is the number of detection time nodes included in the detection time period; the time length between every two adjacent detection time nodes in the detection time period is the same; I d is the list of pressure values corresponding to the upper surface of the punched area of the to-be-detected stamping sheet at the d-th detection time node in the detection time period; I d =(I d1 , I d2 ,..., I df ,..., I dk ); f = 1, 2,..., k; k is the number of detection mechanisms for the upper surface of the stamping sheet; I df is the pressure value at the upper surface of the punched area of the to-be-detected stamping sheet detected by the f-th detection mechanism for the upper surface of the stamping sheet at the d-th detection time node in the detection time period; The start time of the detection time period is the moment when the punched area of the to-be-detected stamping sheet first passes through the contact end of any detection mechanism for the upper surface of the stamping sheet; the end time of the detection time period is the moment when the punched area of the to-be-detected stamping sheet completely passes through the detection mechanisms for the upper surface of the stamping sheet; Step S303, determine (∑ f=1 k I df ) / k as the d-th profile feature value M d of the upper surface at the punched area of the to-be-detected stamping sheet.

[0008] In an exemplary embodiment of the present application, each detection mechanism for the upper surface of the stamping sheet includes: a sheet contact member for contacting the upper surface of the to-be-detected stamping sheet; a pressure telescopic member connected to the sheet contact member for providing a telescopic space for the sheet contact member when the sheet contact member is externally squeezed; a pressure sensor connected to the pressure telescopic member for obtaining the extrusion force of the pressure telescopic member when the pressure telescopic member is squeezed.

[0009] In an exemplary embodiment of the present application, step S400 includes: Step S410, input F1,..., F g ,..., F h , H1,..., H g ,..., H h , M, N into a preset feature analysis model to obtain the stamping quality status identifier output by the feature analysis model; The feature analysis model is obtained by training the vibration feature values, spectrum feature values, pressure values on the upper surface, and pressure values on the lower surface during punching of the punched areas of several key stamping sheets; The key stamping sheet is the stamping sheet that has been stamped by a metal stamping die during a historical period.

[0010] In an exemplary embodiment of the present application, when the stamping quality status identifier output by the feature analysis model is the first identifier, it indicates that the stamping quality status at the punching area of the stamping sheet to be detected is in a normal state; When the stamping quality status identifier output by the feature analysis model is the second identifier, it indicates that there are hidden cracks in the stamping quality status at the punching area of the stamping sheet to be detected; When the stamping quality status identifier output by the feature analysis model is the third identifier, it indicates that there are obvious cracks in the stamping quality status at the punching area of the stamping sheet to be detected.

[0011] According to another aspect of the present application, there is provided a non-transitory computer-readable storage medium, in which at least one instruction or at least one program segment is stored, and the at least one instruction or the at least one program segment is loaded and executed by a processor to implement the foregoing method for detecting the stamping quality of metal stamping sheets.

[0012] According to still another aspect of the present application, there is provided an electronic device, including a processor and the foregoing non-transitory computer-readable storage medium.

[0013] The present invention has at least the following beneficial effects: The method for detecting the stamping quality of metal stamping sheets according to the present invention first determines a vibration characteristic value list corresponding to each vibration sensor according to a plurality of vibration signals detected by each vibration sensor during the stamping time period, and then performs frequency domain transformation processing on the plurality of vibration signals detected by each vibration sensor during the stamping time period to obtain a spectrum characteristic value list corresponding to each vibration sensor. According to the contour characteristic values of the upper surface and the lower surface at the punching area of the stamping sheet to be detected, a first surface characteristic value list and a second surface characteristic value list are respectively determined. Finally, according to each vibration characteristic value list, each spectrum characteristic value list, the first surface characteristic value list and the second surface characteristic value list, the stamping quality status at the punching area of the stamping sheet to be detected is determined. By obtaining a plurality of vibration characteristic values at the punching area of the stamping sheet to be detected during the punching operation, and combining the contour characteristic values of the upper and lower surfaces of the stamping sheet to be detected, the vibration states of the surface and the interior of the punching area of the stamping sheet to be detected are analyzed to determine whether cracks that affect the service quality will occur in the metal stamping sheet during the stamping operation. Description of the Drawings

[0014] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0015] Figure 1 It is a flowchart of the stamping quality detection method for the metal stamping sheet provided by the embodiment of the present invention; Figure 2 It is a schematic structural diagram of the upper surface detection mechanism of the stamping sheet provided by the embodiment of the present invention; In the figure: 1. Sheet contact member; 2. Pressure telescopic member; 3. Pressure sensor. Detailed implementation manners

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0017] The present application proposes a stamping quality detection method for metal stamping sheets, which is applied to a stamping quality detection system. The stamping quality detection system is connected with a plurality of vibration sensors. The plurality of vibration sensors are arranged around the punching area of the stamping sheet to be detected, and the distance between each vibration sensor and the center point of the punching area of the stamping sheet to be detected is within a preset detection distance range.

[0018] The vibration sensors are arranged around the upper surface and / or the lower surface of the punching area (the area that needs to be punched) of the stamping sheet to be detected, and are used to detect the impact vibration signals of the punching area during the punching operation.

[0019] Among them, the stamping quality detection method for metal stamping sheets, as Figure 1 shown, includes the following steps: Step S100: In response to receiving the stamping detection signal of the stamping sheet to be detected, determine the vibration characteristic value list corresponding to each vibration sensor according to a plurality of vibration signals detected by each vibration sensor during the stamping time period; The starting moment of the stamping time period is the moment when the punching of the punching area of the stamping sheet to be detected starts; the ending moment of the stamping time period is the moment when the punching of the punching area of the stamping sheet to be detected is completed.

[0020] The stamping detection signal of the stamping sheet to be detected represents the start signal for stamping the stamping sheet to be detected.

[0021] Further, step S100 includes steps S110 - S120: Step S110, in response to receiving the stamping detection signal of the stamping sheet to be detected, obtain a number of vibration signals detected by each vibration sensor during the stamping time period to obtain a number of vibration signal lists E1, E2,..., E g ,..., E h ; where g = 1, 2,..., h; h is the number of vibration sensors; E g is the vibration signal list corresponding to the g-th vibration sensor; E g =(E g1 , E g2 ,..., E gb ,..., E gc ); b = 1, 2,..., c; c is the number of detection time nodes included in the stamping time period; the time length between every two adjacent detection time nodes in the stamping time period is the same; E gb is the vibration signal detected by the g-th vibration sensor at the b-th detection time node in the stamping time period; Step S120, extract the time series feature values corresponding to each vibration signal in E g through a preset time series feature extraction module to obtain the vibration feature value list F g =(F g1 , F g2 ,..., F gb ,..., F gc ); where F gb is the time series feature value extracted from E gb corresponding to through the preset time series feature extraction module.

[0022] The time series feature extraction module uses an existing module for extracting the features of time series signals.

[0023] Step S200, perform frequency domain transformation processing on the several vibration signals detected by each vibration sensor during the stamping time period to obtain the spectrum feature value list corresponding to each vibration sensor; Further, step S200 includes steps S210 - S220: Step S210, perform short-time Fourier transform on each vibration signal in the vibration signal list E g corresponding to the g-th vibration sensor to obtain the spectrum signal list G g =(Gg1 , G g2 ,..., G gb ,..., G gc ); where G gb is the spectral signal obtained by performing a short-time Fourier transform on E gb . The short-time Fourier transform is used to convert the vibration signal of the time-series signal into the spectral signal of the frequency-domain signal.

[0024] Step S220: Extract the spectral feature values corresponding to each spectral signal in G g to obtain the spectral feature value list H g = (H g1 , H g2 ,..., H gb ,..., H gc ) for the g-th vibration sensor; where H gb are the spectral feature values extracted from G gb .

[0025] The spectral feature extraction module uses an existing module for extracting the features of the frequency-domain signal.

[0026] Step S300: Determine the first surface feature value list and the second surface feature value list respectively according to the contour feature values of the upper surface and the lower surface of the punching area of the stamping sheet to be detected; The contour feature values of the upper / lower surface of the punching area can be the flatness feature values of the upper / lower surface, which are used to represent the surface flatness of the upper / lower surface of the punching area.

[0027] Furthermore, step S300 includes steps S310 - S320: Step S310: Obtain the contour feature values of the upper surface of the punching area of the stamping sheet to be detected to obtain the first surface feature value list M = (M1, M2,..., M d ,..., M e ); where d = 1, 2,..., e; e is the number of the contour feature values of the upper surface of the punching area of the stamping sheet to be detected; M d is the d-th contour feature value of the upper surface of the punching area of the stamping sheet to be detected; Step S320: Obtain the contour feature values of the lower surface of the punching area of the stamping sheet to be detected to obtain the second surface feature value list N = (N1, N2,..., N d ,..., N e ); where N dIt is the d-th contour feature value of the lower surface at the punching area of the stamping sheet to be detected.

[0028] Among them, the contour feature value of the upper surface at the punching area of the stamping sheet to be detected is determined according to steps S301 - S303: Step S301: Place the stamping sheet to be detected on the transmission line so that the stamping sheet to be detected moves on the transmission line; Above the transmission line, there are several upper surface detection mechanisms for the stamping sheet. The upper surface detection mechanisms for the stamping sheet are arranged in a column, and the setting direction of this column is perpendicular to the moving direction of the stamping sheet to be detected on the transmission line. The distance between the contact end of each upper surface detection mechanism for the stamping sheet and the upper surface of the transmission line is a preset thickness threshold. The upper surface detection mechanism for the stamping sheet is used to detect the pressure value given by the object passing through the contact end of this upper surface detection mechanism for the stamping sheet.

[0029] Step S302: Obtain several pressure values at the upper surface of the punching area of the stamping sheet to be detected detected by each upper surface detection mechanism for the stamping sheet during the detection time period, so as to obtain the upper surface pressure value list set I=(I1, I2,..., I d ,..., I e ); where e is the number of detection time nodes included in the detection time period; the time length between every two adjacent detection time nodes in the detection time period is the same; I d is the pressure value list corresponding to the d-th detection time node of the upper surface of the punching area of the stamping sheet to be detected during the detection time period; I d =(I d1 , I d2 ,..., I df ,..., I dk ); f = 1, 2,..., k; k is the number of upper surface detection mechanisms for the stamping sheet; I df is the pressure value at the upper surface of the punching area of the stamping sheet to be detected detected by the f-th upper surface detection mechanism for the stamping sheet at the d-th detection time node during the detection time period; The starting moment of the detection time period is the moment when the punching area of the stamping sheet to be detected first passes through the contact end of any upper surface detection mechanism for the stamping sheet; the ending moment of the detection time period is the moment when the punching area of the stamping sheet to be detected completely passes through the upper surface detection mechanism for the stamping sheet.

[0030] Step S303: Determine (∑ f=1 k I df ) / k as the d-th contour feature value M d of the upper surface at the punching area of the stamping sheet to be detected.

[0031] Correspondingly, a plurality of stamping plate lower surface detection mechanisms are also arranged below the stamping plate transmission line, and each stamping plate upper surface detection mechanism and each stamping plate lower surface detection mechanism are arranged one by one opposite to each other. The stamping plate upper surface detection mechanism is used to detect the pressure information of the upper surface of the stamping plate, and the stamping plate lower surface detection mechanism is used to detect the pressure information of the lower surface of the stamping plate. When the stamping plate needs to be detected, the stamping plate is placed on the transmission line. When the stamping plate passes through each stamping plate upper surface detection mechanism and each stamping plate lower surface detection mechanism, the stamping plate upper surface detection mechanism and the stamping plate lower surface detection mechanism are pressed. The surface detection mechanism will collect the pressure value of the area through which the stamped plate passes. A stamped plate lower surface detection mechanism is arranged below each stamped plate upper surface detection mechanism separated by a transmission line. The row composed of several stamped plate upper surface detection mechanisms is perpendicular to the transmission direction of the transmission line of the stamped plate (that is, it can be understood that the row composed of the stamped plate upper surface detection mechanisms is longitudinal, and the transmission direction of the stamped plate transmission line is transverse). The method for obtaining the contour feature value of the lower surface at the punching area of the stamped plate to be detected is the same as the method for obtaining the contour feature value of the upper surface at the punching area of the stamped plate to be detected, and will not be repeated here.

[0032] Further, if Figure 2 As shown, each stamping plate upper surface detection mechanism and each stamping plate lower surface detection mechanism include a plate contact piece 1, a pressure expansion piece 2 and a pressure sensor 3. The plate contact piece 1 is used to contact the upper surface / lower surface of the stamping plate to be detected. The pressure expansion piece 2 is connected to the plate contact piece 1 and is used to provide a retractable space for the plate contact piece 1 when the plate contact piece 1 is squeezed by external force. The pressure sensor 3 is connected to the pressure expansion piece 2 and is used to obtain the extrusion force of the pressure expansion piece 2 when the pressure expansion piece 2 is squeezed.

[0033] Specifically, the pressure expansion joint 2 can be a spring. In the initial state of the pressure expansion joint 2, the pressure value detected by the pressure sensor 3 is zero or a fixed initial value. When the stamped plate passes through the stamped plate upper surface detection mechanism, the plate contact piece 1 of the stamped plate upper surface detection mechanism will be squeezed by the upper surface of the stamped plate, and the plate contact piece 1 will move toward the inside of the stamped plate upper surface detection mechanism. During the movement of the plate contact piece 1, the pressure expansion joint 2 will be squeezed, and then the pressure sensor 3 will collect the pressure value transmitted by the pressure expansion joint 2.

[0034] When there is no punching sheet between the upper surface detection mechanism and the lower surface detection mechanism of the punching sheet in a relative position relationship, the distance between the contact ends of the sheet contact members 1 of the upper surface detection mechanism of the punching sheet and the contact ends of the sheet contact members 1 of the lower surface detection mechanism of the punching sheet is the preset thickness of the punching sheet, and the preset thickness cannot be greater than the thickness of the punching sheet to be detected.

[0035] Step S400: Determine the stamping quality state at the punching area of the punching sheet to be detected according to each vibration eigenvalue list, each frequency spectrum eigenvalue list, the first surface eigenvalue list, and the second surface eigenvalue list; Further, step S400 includes step S410: Step S410: Input F1,..., F g ,..., F h , H1,..., H g ,..., H h , M, N into a preset feature analysis model to obtain the stamping quality state identifier output by the feature analysis model; F1 is the vibration eigenvalue list corresponding to the first vibration sensor; F h is the vibration eigenvalue list corresponding to the hth vibration sensor; H1 is the frequency spectrum eigenvalue list corresponding to the first vibration sensor; H h is the frequency spectrum eigenvalue list corresponding to the hth vibration sensor; The feature analysis model is obtained by training the vibration eigenvalue, frequency spectrum eigenvalue, pressure value on the upper surface, and pressure value on the lower surface during punching of the punching area of several key punching sheets. The feature analysis model is a binary classification model, and its training method adopts the existing binary classification model training method, that is, several pressure values, eigenvalues corresponding to the punching area of each key punching sheet, and the stamping quality state identifier of the key punching sheet after punching the punching area of the key punching sheet are input into the binary classification model for multiple rounds of training, and finally the feature analysis model used in this application is obtained.

[0036] Among them, the position layout of the vibration sensors for obtaining the vibration eigenvalues during punching of the punching area of several key punching sheets is the same as the position layout of the vibration sensors for obtaining the vibration eigenvalues during punching of the punching area of the punching sheet to be detected.

[0037] The key punching sheet is a punching sheet that has been punched by a metal stamping die during a historical period (including punching sheets with the punch in a normal state and punching sheets with the punch in an abnormal state).

[0038] When the stamping quality state identifier output by the feature analysis model is the first identifier, it indicates that the stamping quality state at the punching area of the punching sheet to be detected is in a normal state; The stamping quality state being in the normal state means that there are no hidden cracks and visible cracks in the punched area of the stamping sheet to be detected after stamping is completed.

[0039] When the stamping quality state identifier output by the feature analysis model is the second identifier, it indicates that the stamping quality state in the punched area of the stamping sheet to be detected is that there are hidden cracks. The stamping quality state being with hidden cracks means that there are hidden cracks in the punched area of the stamping sheet to be detected after stamping is completed (i.e., there are cracks inside the stamping sheet to be detected).

[0040] When the stamping quality state identifier output by the feature analysis model is the third identifier, it indicates that the stamping quality state in the punched area of the stamping sheet to be detected is that there are visible cracks.

[0041] The stamping quality state being with visible cracks means that there are visible cracks in the punched area of the stamping sheet to be detected after stamping is completed (i.e., there are cracks on the surface of the stamping sheet to be detected).

[0042] On the other hand, before step S100, the present application further includes a method for predicting the quality state of the punch of a metal stamping die, which is used to predict the quality state of the punch after punching the punched area. The specific steps are as follows: In response to receiving the surface detection signal of the stamping sheet to be detected (the surface detection signal of the stamping sheet to be detected means the signal indicating the start of the surface detection of the stamping sheet to be detected), obtain the pressure values collected by the pressure sensors of the surface detection mechanism on each stamping sheet within the target time period to obtain the first pressure value list set A = (A1, A2,..., A i ,..., A j ); where i = 1, 2,..., j; j is the number of surface detection mechanisms on the stamping sheet; A i is the pressure value list corresponding to the i-th surface detection mechanism on the stamping sheet; A i =(A i1 , A i2 ,..., A im ,..., A in ); m = 1, 2,..., n; n is the number of acquisition time nodes included in the target time period; the time length between every two adjacent acquisition time nodes within the target time period is the same; A im is the pressure value collected by the pressure sensor of the i-th surface detection mechanism on the stamping sheet at the m-th acquisition time node within the target time period; Obtain the pressure values collected by the pressure sensors of the lower surface detection mechanism on each stamping sheet within the target time period to obtain the second pressure value list set B = (B1, B2,..., Bi ,..., B j ); where B i is the list of pressure values corresponding to the lower surface detection mechanism of the i-th stamping sheet; B i = (B i1 , B i2 ,..., B im ,..., B in ); B im is the pressure value collected by the pressure sensor of the lower surface detection mechanism of the i-th stamping sheet at the m-th acquisition time node in the target time period; Traverse the first set of pressure value lists A. If A im is not within the preset standard pressure value range, then determine A im as the first key pressure value; Traverse the second set of pressure value lists B. If B im is not within the preset standard pressure value range, then determine B im as the second key pressure value; If the detected pressure value is not within the preset standard pressure value range, it means that there is a protrusion or depression on the surface of the acquisition area of the stamping sheet to be detected corresponding to this pressure value, then determine it as the key pressure value for subsequent processing; Determine the detection area corresponding to each first key pressure value on the stamping sheet to be detected as the first detection area (the detection area corresponding to the first key pressure value on the stamping sheet to be detected is the area corresponding to the stamping sheet to be detected where this first key pressure value is collected); Determine the detection area corresponding to each second key pressure value on the stamping sheet to be detected as the second detection area; Obtain the distance between every two first detection areas to obtain the first detection area distance list C = (C 12 ,..., C pq ,..., C r-1,r ); where p = 1, 2,..., r; q = 1, 2,..., r; and p ≠ q; r is the number of first detection areas; C pq is the distance between the p-th first detection area and the q-th first detection area; Obtain the distance between every two second detection areas to obtain the second detection area distance list D = (D 12 ,..., D st ,..., D u-1,u ); where s = 1, 2,..., u; t = 1, 2,..., u; and s ≠ t; u is the number of second detection areas; D st is the distance between the s-th second detection area and the t-th second detection area; Traverse the first detection area distance list C. If C pq is less than a preset distance threshold, then determine the p-th first detection area and the q-th first detection area as the same detection area group; Traverse the second detection area distance list D. If D st is less than a preset distance threshold, then determine the s-th second detection area and the t-th second detection area as the same detection area group; Determine the area enclosed by several detection areas within the same detection area group as a target detection area (the target detection area on the stamping sheet to be detected is the area with relatively low surface flatness determined); Traverse each target detection area. If any target detection area has an overlapping part with the punching area of the stamping sheet to be detected, then determine this target detection area as a key detection area (if the target detection area has an overlapping part with the punching area (the area that needs to be punched) of the stamping sheet to be detected, it means that there is also an uneven area at the punching area, then determine it as a key detection area, and analyze the characteristic values of the key detection area to predict the quality state when the punch punches the punching area (the higher the flatness of the punching area, the smaller the damage to the punch)); Obtain the key detection area image corresponding to the key detection area of the stamping sheet to be detected (the key detection area image is an image taken of the key detection area); Extract features from the key detection area image to obtain several key detection area characteristic values (the method of extracting features from the image uses existing image feature extraction methods); Input several key detection area characteristic values, several first key pressure values of the key detection area, and several second key pressure values of the key detection area into a preset analysis model to obtain the status identifier output by the analysis model; Among them, the analysis model is obtained by training the pressure values on the upper surface, the pressure values on the lower surface, and the characteristic values of the image of the punching areas of several key stamping sheets. The analysis model is a binary classification model, and its training method uses the existing binary classification model training method, that is, input several pressure values, characteristic values corresponding to the punching area of each key stamping sheet, and the quality status identifier of the punch after punching the punching area of this key stamping sheet into the binary classification model for multiple rounds of training, and finally obtain the analysis model used in this application.

[0043] The key stamping sheet is a stamping sheet that has been stamped by a metal stamping die during a historical period (including stamping sheets with the quality status of the punch being normal and stamping sheets with the quality status of the punch being abnormal).

[0044] When the status identifier output by the analysis model is the first identifier, it indicates that when the metal stamping die punches the punching area of the stamping sheet to be detected, the quality status of the punch of the metal stamping die is in a normal state; When the status identifier output by the analysis model is the second identifier, it indicates that when the metal stamping die punches the punching area of the stamping sheet to be detected, the quality status of the punch of the metal stamping die is in an abnormal state.

[0045] The abnormal quality status of the punch is characterized as a usage state where if the punch punches the punching area, it may cause damage.

[0046] Among them, the length of the target time period is determined according to the length of the stamping sheet to be detected and the transmission speed of the stamping sheet to be detected. Specifically, the method for determining the length of the target time period is: obtain the length a of the stamping sheet to be detected; obtain the transmission speed v of the transmission line of the stamping sheet to be detected; determine the length of the target time period as a / v.

[0047] Among them, the method for determining the standard pressure value range is: determine several stamping sheets with normal punch quality status after the metal stamping die punches the punching area during the historical period as historical stamping sheets; obtain several historical pressure values detected by the upper surface detection mechanism of each historical stamping sheet for the punching area and several historical pressure values detected by the lower surface detection mechanism of each historical stamping sheet for the punching area; determine the difference between the mean of several historical pressure values and the standard deviation of several historical pressure values as the lower limit of the standard pressure value range, and determine the sum of the mean of several historical pressure values and the standard deviation of several historical pressure values as the upper limit of the standard pressure value range.

[0048] The normal quality status of the punch means that after punching the stamping sheet, the punch has less damage or no damage. The standard pressure value range is determined according to several pressure values on the upper surface / lower surface of the determined several historical stamping sheets, and it is characterized that the pressure values within the standard pressure value range are the pressure values of the areas with higher surface flatness.

[0049] Taking the first detection area as an example, if the distance between two first detection areas (which can be the distance between the nearest boundaries of the two first detection areas or the distance between the center points of the two first detection areas) is less than the distance threshold, it means that the distance between the two first detection areas is relatively close, and the corresponding concave and convex parts may affect each other. Therefore, these two first detection areas are determined as the same detection area group. Correspondingly, if the distance between two first detection areas is not less than the distance threshold, it means that the distance between the two first detection areas is relatively far, and the influence of the corresponding concave and convex parts on each other is small, and they can be regarded as isolated areas, so no division of the detection area group is performed (the principle of dividing the detection area group of the second detection area is the same as that of the first detection area and will not be elaborated here).

[0050] For the metal stamping sheet stamping quality detection method of the present invention, first, according to a plurality of vibration signals detected by each vibration sensor during the stamping period, a vibration eigenvalue list corresponding to each vibration sensor is determined. Then, the frequency domain transformation processing is respectively performed on the plurality of vibration signals detected by each vibration sensor during the stamping period to obtain a spectral eigenvalue list corresponding to each vibration sensor. According to the contour eigenvalue of the upper surface at the punching area of the stamping sheet to be detected and the contour eigenvalue of the lower surface at the punching area of the stamping sheet to be detected, a first surface eigenvalue list and a second surface eigenvalue list are respectively determined. Finally, according to each vibration eigenvalue list, each spectral eigenvalue list, the first surface eigenvalue list and the second surface eigenvalue list, the stamping quality state at the punching area of the stamping sheet to be detected is determined to analyze whether cracks that affect the use quality will occur in the metal stamping sheet during the stamping work.

[0051] The embodiment of the present invention also provides a computer program product, which includes program code. When the program product runs on an electronic device, the program code is used to cause the electronic device to execute the steps in the method according to various exemplary embodiments of the present invention described above in this specification.

[0052] In addition, although the steps of the method in the present disclosure are described in a specific order in the drawings, this does not require or imply that these steps must be executed in that specific order, or that all the steps shown must be executed to achieve the desired result. Additionally or alternatively, some steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc.

[0053] From the description of the above embodiments, those skilled in the art can easily understand that the exemplary embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (such as a personal computer, a server, a mobile terminal, or a network device, etc.) to execute the method according to the embodiments of the present disclosure.

[0054] In an exemplary embodiment of the present disclosure, there is also provided an electronic device capable of implementing the above method.

[0055] Those skilled in the art can understand that various aspects of the present invention can be implemented as a system, a method, or a program product. Therefore, various aspects of the present invention can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuitry", "module", or "system" here.

[0056] The electronic device according to this embodiment of the present invention. The electronic device is only an example and should not impose any limitations on the functions and usage scopes of the embodiments of the present invention.

[0057] The electronic device is presented in the form of a general-purpose computing device. The components of the electronic device may include, but are not limited to: the above at least one processor, the above at least one storage, and a bus connecting different system components (including the storage and the processor).

[0058] Wherein, the storage stores program codes, and the program codes can be executed by the processor, so that the processor executes the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of this specification.

[0059] The storage may include a readable medium in the form of a volatile storage, such as a random access memory (RAM) and / or a cache memory, and may further include a read-only memory (ROM).

[0060] The storage may further include a program / utility having a set (at least one) of program modules, and such program modules include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. The implementation of a network environment may be included in each or some combination of these examples.

[0061] The bus can represent one or more of several types of bus architectures, including a memory bus or a memory controller, a peripheral bus, an accelerated graphics port, a processor, or a local bus using any of the various bus architectures.

[0062] The electronic device can also communicate with one or more external devices (such as a keyboard, a pointing device, a Bluetooth device, etc.), can also communicate with one or more devices that enable a user to interact with the electronic device, and / or can communicate with any device that enables the electronic device to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication can be carried out through an input / output (I / O) interface. Moreover, the electronic device can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter.

[0063] In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium, on which a program product capable of implementing the above methods in this specification is stored. In some possible implementation manners, various aspects of the present invention can also be implemented in the form of a program product, which includes program code. When the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above "Exemplary Method" section of this specification.

[0064] The program product can adopt any combination of one or more readable media. The readable media can be a readable signal medium or a readable storage medium. The readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0065] The computer-readable signal medium can include a data signal propagated in a baseband or as a part of a carrier wave, in which the readable program code is carried. Such a propagated data signal can take various forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable signal medium can also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program used by or in combination with an instruction execution system, apparatus, or device.

[0066] The program code contained on a readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0067] The program code for performing the operations of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, executed as a stand-alone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device can be connected to the user's computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or, alternatively, can be connected to an external computing device (e.g., by using an Internet service provider to connect through the Internet).

[0068] Furthermore, the above-mentioned drawings are only schematic illustrations of the processes included in the method according to the exemplary embodiments of the present invention, and are not for limiting purposes. It is easily understood that the processes shown in the above-mentioned drawings do not indicate or limit the chronological order of these processes. Additionally, it is also easily understood that these processes can be executed synchronously or asynchronously, for example, in multiple modules.

[0069] It should be noted that although several modules or units of devices for action execution are mentioned in the above detailed description, such a division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more of the above-mentioned modules or units can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0070] As described above, the above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims

1. A method for detecting the stamping quality of a metal stamping sheet, characterized in that, Applied to a stamping quality detection system, the stamping quality detection system is connected with a plurality of vibration sensors, and the plurality of vibration sensors are arranged around the punching area of the stamping plate to be detected, and the distance between each vibration sensor and the center point of the punching area of the stamping plate to be detected is within a preset detection distance range; Among them, the method for detecting the stamping quality of the metal stamping plate includes the following steps: Step S100: In response to receiving the stamping detection signal of the stamping plate to be detected, determine the vibration characteristic value list corresponding to each vibration sensor according to a plurality of vibration signals detected by each vibration sensor during the stamping time period; the starting moment of the stamping time period is the moment when punching starts for the punching area of the stamping plate to be detected; the ending moment of the stamping time period is the moment when punching of the punching area of the stamping plate to be detected is completed; Step S200: Perform frequency domain transformation processing on a plurality of vibration signals detected by each vibration sensor during the stamping time period to obtain the spectral characteristic value list corresponding to each vibration sensor; Step S300: Determine the first surface characteristic value list and the second surface characteristic value list respectively according to the contour characteristic value of the upper surface at the punching area of the stamping plate to be detected and the contour characteristic value of the lower surface at the punching area of the stamping plate to be detected; Step S400: Determine the stamping quality state at the punching area of the stamping plate to be detected according to each vibration characteristic value list, each spectral characteristic value list, the first surface characteristic value list and the second surface characteristic value list.

2. The method according to claim 1, wherein The step S100 includes: Step S110, in response to receiving a stamping detection signal of a stamping sheet to be detected, obtain a number of vibration signals detected by each of the vibration sensors during a stamping time period, so as to obtain a number of vibration signal lists E1, E2,..., E g ,..., E h ; where g = 1, 2,..., h; h is the number of the vibration sensors; E g is the vibration signal list corresponding to the g-th vibration sensor; E g =(E g1 ,E g2 ,...,E gb ,...,E gc ); b = 1, 2, ..., c; c is the number of detection time nodes included in the stamping time period; the time length between every two adjacent detection time nodes in the stamping time period is the same; E gb is the vibration signal detected by the g-th vibration sensor at the b-th detection time node in the stamping time period; Step S120: Extract the temporal feature values corresponding to each vibration signal in E g by means of a preset temporal feature extraction module, so as to obtain a vibration feature value list F g =(F g1 , F g2 ,..., F gb ,..., F gc ); where F gb is the temporal feature value corresponding to E gb extracted by the preset temporal feature extraction module.

3. The method according to claim 2, wherein The step S200 includes: Step S210: Perform short-time Fourier transform on each vibration signal in the vibration signal list E corresponding to the g-th vibration sensor g to obtain a spectrum signal list G corresponding to the g-th vibration sensor g =(G g1 ,G g2 ,...,G gb ,...,G gc ); where G gb is the spectrum signal obtained by performing short-time Fourier transform on E gb . Step S220: Extract the spectral feature values corresponding to each spectral signal in G g by means of a preset spectral feature extraction module, so as to obtain a list H g =(H g1 , H g2 ,..., H gb ,..., H gc ) of the spectral feature values corresponding to the g-th vibration sensor; where H gb is the spectral feature value corresponding to G gb extracted by means of the preset spectral feature extraction module.

4. The method according to claim 3, characterized in that, The step S300 includes: Step S310: Obtain the contour feature values of the upper surface at the punching area of the to-be-detected stamping sheet to obtain the first surface feature value list M = (M1, M2,..., M d ,..., M e ); where d = 1, 2,..., e; e is the number of contour feature values of the upper surface at the punching area of the to-be-detected stamping sheet; M d is the d-th contour feature value of the upper surface at the punching area of the to-be-detected stamping sheet; Step S320: Obtain the contour feature values of the lower surface at the punching area of the to-be-detected stamping sheet to obtain the second surface feature value list N = (N1, N2,..., N d ,..., N e ); where N d is the d-th contour feature value of the lower surface at the punching area of the to-be-detected stamping sheet.

5. The method according to claim 4, characterized in that, The contour characteristic value of the upper surface at the punching area of the stamping plate to be detected is determined according to the following steps: Step S301: Place the stamping plate to be detected on the transmission line so that the stamping plate to be detected moves on the transmission line; a plurality of upper surface detection mechanisms of the stamping plate are arranged above the transmission line, the upper surface detection mechanisms of the stamping plate are arranged in a row, and the arrangement direction of this row is perpendicular to the moving direction of the stamping plate to be detected on the transmission line. The distance between the contact end of each upper surface detection mechanism of the stamping plate and the upper surface of the transmission line is a preset thickness threshold, and the upper surface detection mechanism of the stamping plate is used to detect the pressure value given by the object passing through the contact end of the upper surface detection mechanism of the stamping plate; Step S302, obtain a plurality of pressure values at the upper surface of the punching area of the to-be-detected stamping sheet detected by each upper surface detection mechanism of the stamping sheets during the detection time period, so as to obtain the upper surface pressure value list set I = (I1, I2,..., I d ,..., I e ); where e is the number of detection time nodes included in the detection time period; the time length between every two adjacent detection time nodes in the detection time period is the same; I d is the pressure value list corresponding to the d-th detection time node of the upper surface of the punching area of the to-be-detected stamping sheet during the detection time period; I d =(I d1 ,I d2 ,...,I df ,...,I dk ); f = 1, 2, ..., k; k is the number of the upper surface detection mechanisms of the stamping sheet; I df is the pressure value at the upper surface of the punched area of the stamping sheet to be detected detected by the f-th upper surface detection mechanism of the stamping sheet at the d-th detection time node during the detection time period; The starting moment of the detection time period is the moment when the punching area of the stamping plate to be detected first passes through the contact end of any upper surface detection mechanism of the stamping plate; the ending moment of the detection time period is the moment when the punching area of the stamping plate to be detected completely passes through the upper surface detection mechanism of the stamping plate; Step S303, determine (∑ f=1 k I df ) / k as the d-th contour feature value M of the upper surface at the punching area of the to-be-detected stamping sheet d .

6. The method according to claim 5, characterized in that, Each upper surface detection mechanism of the stamping plate includes: A plate contact member for contacting the upper surface of the stamping plate to be detected; A pressure telescopic member, connected to the plate contact member, for providing a telescopic space for the plate contact member when the plate contact member is externally squeezed; A pressure sensor, connected to the pressure telescopic member, for obtaining the extrusion force of the pressure telescopic member when the pressure telescopic member is squeezed.

7. The method according to claim 6, characterized in that, The step S400 includes: Step S410: Input F1,..., F g ,..., F h , H1,..., H g ,..., H h , M, and N into a preset feature analysis model to obtain a stamping quality status identifier output by the feature analysis model; The feature analysis model is obtained by training the vibration eigenvalue, frequency spectrum eigenvalue, pressure value on the upper surface, and pressure value on the lower surface during punching of the punching areas of several key stamping plates; The key stamping plates are the stamping plates that have been stamped by a metal stamping die during a historical period.

8. The method according to claim 7, wherein When the stamping quality status identifier output by the feature analysis model is the first identifier, it indicates that the stamping quality status at the punching area of the to-be-detected stamping plate is in a normal state; When the stamping quality status identifier output by the feature analysis model is the second identifier, it indicates that the stamping quality status at the punching area of the to-be-detected stamping plate has hidden cracks; When the stamping quality status identifier output by the feature analysis model is the third identifier, it indicates that the stamping quality status at the punching area of the to-be-detected stamping plate has obvious cracks.

9. A non-transitory computer-readable storage medium, characterized in that, At least one instruction or at least one program is stored in the storage medium, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the method according to any one of claims 1-8.

10. An electronic device, characterized in that, It includes a processor and the non-transitory computer-readable storage medium described in claim 9.

Images