Intelligent detection method for electronic device shell production mold

Abstract

The application relates to the technical field of intelligent detection, and particularly discloses an intelligent detection method for an electronic device shell production mold, which comprises the following steps: step S1: obtaining historical use data of the mold, setting a standard input period according to the historical use data, and dividing the period into a safe stage and a loss stage; step S2: if the current mold is in the safe stage, obtaining three-dimensional image data and sample image data of a shell finished product in real time; performing grid division on the image data, and calculating a flaw index; step S3: when the mold enters the loss stage, continuously obtaining the flaw index in real time, combining the previously calculated environmental flaw index, and obtaining a wear flaw index; the wear flaw index obtained through multiple measurements can generate a curve changing with time, which is used for evaluating the wear condition of the mold; real-time monitoring data is used for evaluating the mold state, so that whether the mold needs to be repaired or replaced can be accurately judged, and the production efficiency and product quality are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent detection, and particularly relates to an intelligent detection method for an electronic device shell production mold. BACKGROUND

[0002] The intelligent detection of the shell production mold is a comprehensive process involving multiple aspects to ensure the quality, precision and service life of the mold; including appearance detection, size detection, durability detection and service life detection.

[0003] In the existing electronic device shell production technology, the quality detection of the shell production mold usually depends on the defect condition of the finished product. However, in the actual production environment, the factors affecting the quality of the finished product are various, and the quality of the finished product is jointly affected by various factors, including raw material quality, production process parameters, operator skills and equipment state. Therefore, when performing quality detection, it cannot be arbitrarily considered that the quality problem of the finished product is caused by the quality problem of the mold, which will cause unnecessary waste of the mold cost. SUMMARY

[0004] The purpose of the present application is to provide an intelligent detection method for an electronic device shell production mold to solve the above technical problems.

[0005] The purpose of the present application can be achieved by the following technical solutions:

[0006] An intelligent detection method for an electronic device shell production mold, comprising the following steps:

[0007] Step S1: obtaining historical use data of the mold, the historical use data being the input period of each mold used in the past, the input period being the time period experienced by the mold from being put into use to being replaced; setting a standard input period according to the historical use data, and dividing the standard input period into a safe stage and a loss stage;

[0008] Step S2: recording the mold being put into use as a current mold; when the current mold is in the safe stage, real-time acquiring image data of the shell finished product, and acquiring sample image data of the shell finished product; the sample image data being image data of a shell finished product sample, and the image data being three-dimensional images of the shell finished product on each surface;

[0009] The three-dimensional images are grid divided to obtain a plurality of squares, and the three-dimensional images are placed in a three-dimensional coordinate system to acquire coordinates of center points of the squares; the center points in the same column are sequentially numbered as i, i∈[1, 2,..., n] and n being the total number of center points in the same column; the distance between each adjacent center point in the same column is obtained as |Pi-Pi+1|, i∈[1, 2,..., n-1] and n-1 being the total number of center points in the same column; the distance between each adjacent center point in the same row is obtained as |Pi-Pj|, i∈[1, 2,..., n] and j∈[1, 2,..., m] and n and m being the total number of center points in the same row and column respectively; the distance between each adjacent center point in the same plane is obtained as |Pi-Pj|, i∈[1, 2,..., n] and j∈[1, 2,..., m] and n and m being the total number of center points in the same row and column respectively; and the distance between each adjacent center point in the same space is obtained as |Pi-Pj|, i∈[1, 2,..., n] and j∈[1, 2,..., m] and n and m being the total number of center points in the same row and column respectively. i+1P i wherein P i represents the coordinate of the i-th center point;

[0010] According to the image data and sample image data, a flaw index is obtained:

[0011]

[0012] wherein P i ' represents the coordinate of the i-th center point on the same column in the sample image data, m is the total column number of the three-dimensional image grid division of one of the faces, k∈[1,m], N is the total number of three-dimensional images in the image data, x∈[1,N]; according to all the flaw indexes obtained in real time, an environmental flaw index Di 环 at the safe stage is obtained.

[0013] Step S3: when the current mold is at the wear stage, a flaw index Di 损 at this time is obtained in real time, and according to the environmental flaw index, a wear flaw index Wi=Di 损 -Di 环 is obtained; and according to the wear flaw index obtained each time, a curve F(t) of the wear flaw index changing with time is generated, t being the time stamp corresponding to each time when the wear flaw index is obtained.

[0014] The average slope K of the curve F(t) is obtained in real time, if Wi>0 and K>0, then the current mold is worn at this time, and the replacement time of the current mold is predicted according to the curve F(t).

[0015] As a further scheme of the present application, the setting process of the standard input cycle comprises:

[0016] The input cycles of each mold used in the past are obtained, and a set of input cycles Z={C1,C2,...,C num} is obtained, wherein C1 represents the input cycle of the first mold used in the past, num is the total number of the molds used in the past, and the standard input cycle C is obtained, wherein g∈[1,num].

[0017] As a further scheme of the present application, the division process of the standard input cycle comprises:

[0018] Obtaining the minimum value in the input cycle set Z, denoted as Min(Z); the time when the mold is put into use is denoted as the use time T0, then [T0, T0+Min(Z)-T'] is denoted as a safety stage, wherein T' is a preset time period threshold, and 0

[0019] As a further scheme of the present application: the three-dimensional image is obtained based on a laser scanning technology.

[0020] As a further scheme of the present application: the environmental flaw index is an average value of all flaw indexes obtained in real time.

[0021] As a further scheme of the present application: the obtaining process of the average slope K of the curve F(t) comprises:

[0022] M monitoring points are selected on the curve F(t), wherein M>=w, and w is the total number of flaw indexes obtained in the loss stage; the slopes of the M monitoring points on the curve F(t) are obtained, and an average value of the M slopes is obtained, denoted as the average slope K of the curve F(t).

[0023] As a further scheme of the present application: if Wi<=0 or K<=0, then the current mold has not appeared wear at this time.

[0024] As a further scheme of the present application: the process of predicting the replacement time of the current mold according to the curve F(t) comprises:

[0025] Setting a flaw index threshold DI, then obtaining a wear flaw index threshold WI=DI-Di 环 ; obtaining a time stamp corresponding to the entry of the current mold into the loss stage as t0, then obtaining a replacement time t'=t0+WI / K.

[0026] The present application has the following beneficial effects:

[0027] The present application can more accurately identify the wear or damage of the mold during use by acquiring three-dimensional image data of the shell product in real time and comparing it with the sample image data. This method can provide detailed flaw indexes, which helps to accurately assess the state of the mold. By dividing the use cycle of the mold into a safe stage and a wear stage and monitoring the mold state in real time in the wear stage, timely maintenance or replacement can be performed according to actual needs, thereby avoiding production quality problems caused by excessive wear of the mold and prolonging the service life of the mold. By monitoring the wear of the mold and generating a curve of the wear flaw index over time, enterprises can better predict the maintenance needs and replacement time of the mold, thereby reasonably arranging production plans and maintenance work and reducing production interruptions caused by mold failures. According to the environmental flaw index in the safe stage, the influence of environmental or external factors on the flaws of the shell product is stripped out, reducing misjudgment of the wear condition of the mold. By comparing the real-time acquired flaw index with the environmental flaw index, the influence of environmental or external factors on the flaws of the shell product can be stripped out. The specific method is to subtract the environmental flaw index from the real-time acquired flaw index to obtain the mold wear flaw index after stripping out the influence of environmental factors. According to the wear flaw index obtained each time, a curve of the wear flaw index over time is generated. This curve can intuitively show the trend of the wear of the mold during use, which helps enterprises more accurately determine the maintenance needs and replacement time of the mold. BRIEF DESCRIPTION OF DRAWINGS

[0028] The present application will be further described below in conjunction with the accompanying drawings.

[0029] Figure 1 is a flowchart of an intelligent detection method for an electronic device shell production mold according to the present application. DETAILED DESCRIPTION

[0030] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative labor fall within the scope of the present application.

[0031] Please refer to Figure 1 The present application is an intelligent detection method for an electronic device shell production mold, which includes the following steps:

[0032] Step S1: obtaining historical use data of the mold, the historical use data being an input cycle of each mold used in the past, the input cycle being a time period experienced by the mold from being put into use to being replaced; setting a standard input cycle according to the historical use data, and dividing the standard input cycle into a safe stage and a loss stage;

[0033] It can be understood that the input cycle data of each mold used in the past is collected, and the historical use data includes the entire time period from the beginning of use to the final replacement; through analysis and arrangement of the historical data, the service life of different molds and various problems that may occur in the use process can be understood; in the safe stage, the use state of the mold is relatively stable, and the wear degree is small, and the mold can continue to be used normally; in the loss stage, the wear degree of the mold gradually increases, and various faults and problems may occur, and maintenance or replacement is required; by dividing the standard input cycle into the two stages, the use condition of the mold can be better monitored, and potential problems can be discovered and handled in time;

[0034] As a preferred embodiment of the present application, the setting process of the standard input cycle includes:

[0035] Obtaining the input cycle of each mold used in the past to obtain an input cycle set Z={C1, C2,..., Cnum}, wherein C1 represents the input cycle of the first mold used in the past, num is the total number of the molds used in the past, and the standard input cycle C is obtained num Wherein g∈[1, num];

[0036] The dividing process of the standard input cycle includes:

[0037] Obtaining the minimum value in the input cycle set Z, denoted as Min(Z); the time when the mold is put into use is denoted as use time T0, then [T0, T0+Min(Z)-T'] is denoted as the safe stage, wherein T' is a preset time period threshold, and 0

[0038] It can be understood that by calculating the average value of the historical input cycle, a relatively accurate standard input cycle can be obtained, and the standard value can be used as a basis for predicting the service life of the mold; the minimum value Min(Z) represents the shortest service life among all the molds used in the past, and can be used as an important reference for judging whether the mold enters the loss stage; in the safe stage, the mold is in a relatively stable use state, and the wear degree is small; in the loss stage, the wear degree of the mold gradually increases, and various faults and problems may occur, and maintenance or replacement is required;​

[0039] Step S2: record the mold being put into use as a current mold; when the current mold is in the safety stage, acquire image data of the shell product in real time, and acquire sample image data of the shell product; the sample image data is image data of a shell product sample, and the image data is three-dimensional image data of the shell product on each surface;

[0040] The three-dimensional image is meshed to obtain a plurality of squares, and the three-dimensional image is placed in a three-dimensional coordinate system to obtain coordinates of the center points of the squares; the center points in the same column are sequentially numbered as i, i∈[1, 2,..., n] and n is the total number of center points in the same column; the distance between each adjacent center point in the same column is obtained as |P i+1 -P i |, wherein P i represents the coordinates of the i-th center point;

[0041] According to the image data and the sample image data, a flaw index is obtained as:

[0042]

[0043] wherein P i ' represents the coordinates of the i-th center point in the same column in the sample image data, m is the total number of columns after meshing of the three-dimensional image of one surface, k∈[1, m], N is the total number of three-dimensional images in the image data, and x∈[1, N]; according to all the flaw indexes acquired in real time, an environmental flaw index Di 环 at the safety stage is obtained.

[0044] It can be understood that when the mold being put into use is in the safety stage, the image data of the shell product is acquired in real time; the image data is three-dimensional image data of the shell product on each surface, and can comprehensively reflect the surface condition of the shell product; the sample image data represents the surface condition of the shell product in an ideal state.

[0045] It is worth noting that the three-dimensional image acquired in real time is meshed to divide it into a plurality of small squares, so that the image difference of each small area can be more conveniently compared; if there is a pit or other defect on the surface of the shell product, the area where the pit or other defect is located is recorded as a defect area, and the distance between the adjacent center points corresponding to the position of the defect area on the image data will be larger than that of the sample image data; therefore, the larger the flaw index is, the larger the flaw condition on the surface of the shell product is compared with the sample shell product.

[0046] As a preferred embodiment of the present application, the three-dimensional image is acquired based on a laser scanning technology.

[0047] It should be noted that the three-dimensional image is obtained based on a laser scanning technology, which uses a laser beam to scan the surface of an object with high precision to capture detailed geometric shapes and surface features of the object, and provides comprehensive three-dimensional data.

[0048] Step S3: When the current mold is in the wear stage, the flaw index Di at this time is obtained in real time 损 , and the wear flaw index Wi is obtained according to the environment flaw index Di 损 -Di 环 ; and a curve F(t) of the wear flaw index changing with time is generated according to each obtained wear flaw index, t being a time stamp corresponding to each time when the wear flaw index is obtained;

[0049] The average slope K of the curve F(t) is obtained in real time, and if Wi>0 and K>0, the current mold is worn at this time, and the replacement time of the current mold is predicted according to the curve F(t);

[0050] It can be understood that the environment flaw index is a reference flaw index determined in the safe stage; the wear flaw index calculated represents the increase of the current wear degree of the mold relative to the safe stage; a curve F(t) of the wear flaw index changing with time is generated according to each obtained wear flaw index, and the curve can intuitively show the cumulative effect of the wear of the mold with time, helping to analyze the wear trend of the mold;

[0051] It should be noted that the average slope reflects the overall change rate of the wear flaw index with time; if Wi>0 and K>0, it is determined that the current mold is worn, and at this time, the increase of the flaw index and the upward trend of the curve jointly indicate the decline of the performance of the mold and the aggravation of the wear, which indicates that the current mold is experiencing wear and the wear speed is increasing; this is a clear signal that the state of the mold needs to be closely monitored and maintenance or replacement needs to be considered;

[0052] As a preferred embodiment of the present application, the process of obtaining the average slope K of the curve F(t) comprises:

[0053] M monitoring points are selected on the curve F(t), where M≥w, w being the total number of flaw indexes obtained in the wear stage; the slopes of the M monitoring points on the curve F(t) are obtained, and the average value of the M slopes is obtained, denoted as the average slope K of the curve F(t);

[0054] It can be understood that M monitoring points are selected on the curve F(t); M is a value greater than or equal to w, wherein w represents the total number of flaw indexes obtained in the wear stage; selecting enough monitoring points can ensure that the calculated average slope is more accurate and reliable; for the M monitoring points on the curve F(t), the slope of each point is calculated respectively; the slope is a quantity for measuring the inclination of the tangent line at a point on the curve, which can be solved by mathematical methods (such as differentiation); the sum of the slope values of all monitoring points is divided by the total number of monitoring points M, and the result is the average slope K of the curve F(t); if K is positive, it indicates that the curve shows an upward trend, that is, the wear flaw index of the mold increases with time, indicating that the mold is gradually wearing out;

[0055] As a preferred embodiment of the present application, if Wi≤0 or K≤0, the current mold has not yet appeared wear at this time;

[0056] It can be understood that when the calculated wear flaw index Wi≤0, it means that the flaw index of the current mold has not increased compared with the reference environment flaw index, indicating that the performance of the mold remains stable or improves, and no obvious wear has appeared; the average slope K of the curve F(t) reflects the change trend of the wear flaw index with time; if K≤0, it indicates that the curve F(t) shows a non-upward trend, that is, the wear condition of the mold has not deteriorated, which also indicates that the current mold has not yet appeared wear that needs attention;

[0057] As a preferred embodiment of the present application, the process of predicting the replacement time of the current mold according to the curve F(t) comprises:

[0058] Set a flaw index threshold DI, and then obtain a wear flaw index threshold WI=DI-Di 环 ; set the time stamp corresponding to the entry of the current mold into the wear stage as t0, and then obtain the replacement time t′=t0+WI / K;

[0059] It can be understood that a flaw index threshold DI needs to be set, which is a predefined value for judging whether the mold has reached the degree of replacement, and the setting of DI is based on the performance requirements of the mold, the production quality standards and the analysis of historical data; the wear flaw index threshold represents the wear degree of the mold from the safe stage to the critical state of replacement;

[0060] It is worth noting that WI / K is the time increment required to reach the threshold value according to the current wear rate.

[0061] The above has been described in detail one embodiment of the present application, but the content is only the preferred embodiment of the present application, cannot be considered for limiting the scope of the present application. Any equivalent changes and improvements made in the scope of the present application, should still belong to the scope of the present application.

Claims

1. An intelligent detection method for an electronic device shell production mold, characterized in that, The method comprises the following steps: Step S1: obtaining historical use data of the mold, the historical use data being an input cycle of each mold that has been used in the past, the input cycle being a time period experienced by the mold from being put into use to being replaced; setting a standard input cycle according to the historical use data, and dividing the standard input cycle into a safe stage and a loss stage; Step S2: recording a mold being put into use as a current mold; when the current mold is in the safe stage, obtaining image data of a shell product in real time, and obtaining sample image data of a shell product; the sample image data being image data of a shell product sample, and the image data being three-dimensional images of a shell product on each surface; The three-dimensional image is meshed to obtain a plurality of squares, and the three-dimensional image is placed in a three-dimensional coordinate system to obtain coordinates of center points of the squares; the center points in the same column are sequentially numbered as i, i∈[1, 2,..., n] and n is the total number of the center points in the same column; and a distance |P i+1 -P i | between each adjacent center point in the same column is obtained, wherein P i represents the coordinates of the i th center point. According to the image data and the sample image data, a flaw index is obtained: ； wherein P i represents the coordinate of the i-th center point on the same column in the sample image data, m is the total column number of the three-dimensional image grid division of one face, k∈[1, m], N is the total number of three-dimensional images in the image data, x∈[1, N]; According to the real-time acquisition of all the flaw indexes, the environmental flaw index Di of the safety stage is obtained 环 ; Step S3: Real-time acquisition of the flaw index Di at this time when the current mold is in the wear stage 损 And according to the environmental flaw index, the wear flaw index Wi=Di is obtained 损 -Di 环 And according to each obtained wear flaw index, a wear flaw index curve F(t) changing with time is generated, t is the time stamp corresponding to each acquisition of the wear flaw index; Real-time acquisition of the average slope K of the curve F(t), if Wi>0 and K>0, the current mold is worn at this time, and the replacement time of the current mold is predicted according to the curve F(t); The process of predicting the replacement time of the current mold according to the curve F(t) comprises: Setting a flaw index threshold value DI, a wear flaw index threshold value WI = DI - Di is obtained 环 ; The time stamp corresponding to the current mold entering the loss stage is recorded as t0, and the replacement time t' = t0+WI / K is obtained. 2.The intelligent detection method of an electronic device shell production mold according to claim 1, characterized in that, In step S1, the setting process of the standard input cycle comprises: The input cycle of each mold used in the past is acquired to obtain an input cycle set Z = {C1, C2,..., Cnum}, where C1 represents the input cycle of the first mold used in the past, num is the total number of molds used in the past, and the standard input cycle num is obtained, where g ∈ [1, num]. is obtained, where g ∈ [1, num]. 3.The intelligent detection method of an electronic device shell production mold according to claim 2, characterized in that, In step S1, the dividing process of the standard input cycle comprises: The minimum value in the input cycle set Z is obtained and recorded as Min(Z); the time when the mold is put into use is recorded as the use time T0, then [T0, T0+Min(Z)-T'] is recorded as the safe stage, wherein T' is a preset time period threshold, and 0 4.The intelligent detection method of an electronic device shell production mold according to claim 1, characterized in that, In step S2, the three-dimensional images are obtained based on laser scanning technology. 5.The intelligent detection method of an electronic device shell production mold according to claim 1, characterized in that, In step S2, the environmental flaw index is the average value of all flaw indexes obtained in real time. 6.The intelligent detection method of an electronic device shell production mold according to claim 1, wherein, In step S3, the process of obtaining the average slope K of the curve F(t) comprises: M monitoring points are selected on the curve F(t), wherein M≥w, and w is the total number of flaw indexes obtained in the loss stage; the slopes of the M monitoring points on the curve F(t) are obtained, and the average value of the M slopes is obtained and recorded as the average slope K of the curve F(t). 7.The intelligent detection method of an electronic device shell production mold according to claim 1, characterized in that, In step S3, if Wi≤0 or K≤0, the current mold has not yet appeared worn at this time.

Images