Abnormality detection method, equipment and device, computer equipment and readable storage medium

Abstract

The invention relates to an anomaly detection method, equipment and device, computer equipment and a computer readable storage medium. The method comprises the following steps: acquiring a first position compensation value of a first detection point on a special-shaped edge of a detected device, performing compensation processing according to a preset detection position value and the first position compensation value to obtain a first detection position value of the first detection point, performing compensation processing according to a preset position difference value and the first detection position value to obtain a second detection position value, and determining the first detection position value of the first detection point according to the second detection position value. And according to the first detection position value and the second detection position value, carrying out abnormal value calculation on the detection points on the special-shaped edge to obtain an abnormal value of the special-shaped edge, and according to the abnormal value of the special-shaped edge and a preset abnormal threshold value, carrying out abnormal judgment on the detection points on the special-shaped edge. By adopting the method, the accuracy of arc-shaped edge position detection can be improved, and the accuracy of arc-shaped edge anomaly detection is further improved.

Description

Technical Field

[0001] The present application relates to the technical field of irregular graphic edge detection, and in particular to an anomaly detection method, device, apparatus, computer equipment and computer-readable storage medium. Background Art

[0002] With the rapid development of the automobile industry, the market has put forward higher requirements for the diversity of automobile design. Manufacturers must not only improve the endurance and power of automobiles, but also invest heavily in the research and development of appearance and interior design. In terms of the appearance design of automobile interior equipment, the design of automobile interior equipment uses arc lines to replace the traditional straight line design, making the interior of the car more beautiful, and the car screen has also derived many styles using arc line design.

[0003] In the production of automotive screens, COF binding and subsequent AOI particle inspection and appearance inspection are required. The inspection process mainly detects the explosion of the conductive particles of the COF in the binding area, and detects whether there are cracks, foreign matter, etc. in the conductive particles of the COF.

[0004] It is relatively convenient to perform COF testing on traditional rectangular screens. Even if multiple flip-chip films are tested on one side, the testing range is all in a straight line. For multi-side testing, the product can be quickly tested by rotating it by ±90°. However, the car screen with arc line design is not just straight lines, and each individual flip-chip film on the arc line needs to be individually calculated and compensated. Therefore, in the prior art, the COF testing process for arc lines is relatively complicated and requires a long testing time. Summary of the invention

[0005] Based on this, it is necessary to provide an abnormality detection method, equipment, device, computer equipment and readable storage medium that can simplify the process of COF detection of arc lines and retrieve detection time in response to the above technical problems.

[0006] In a first aspect, the present application provides an anomaly detection method, comprising:

[0007] Obtaining a first position compensation value of a first detection point on the irregular edge of the device under test; wherein the first detection point includes a detection point set on the irregular edge;

[0008] Perform compensation processing according to a preset detection position value and the first position compensation value to obtain a first detection position value of the first detection point;

[0009] Perform compensation processing according to a preset position difference and the first detected position value to obtain a second detected position value;

[0010] Calculate the outlier value of the detection point on the irregular edge according to the first detection position value and the second detection position value to obtain the irregular edge outlier value;

[0011] An abnormality judgment is performed on the detection point on the irregular edge according to the irregular edge abnormal value and a preset abnormal threshold.

[0012] In one embodiment, performing compensation processing according to a preset detection position value and the first position compensation value to obtain the first detection position value of the first detection point includes:

[0013] comparing the first position compensation value with a preset compensation value threshold;

[0014] When the first position compensation value is less than or equal to the compensation value threshold, the detected position value is compensated according to the first position compensation value to obtain the first detected position value.

[0015] In one embodiment, the step of performing compensation processing according to the preset detection position value and the position compensation value to obtain the first detection position value of the first detection point further includes:

[0016] When the first position compensation value is greater than the compensation value threshold, reacquiring a second position compensation value of the first detection point;

[0017] comparing the second position compensation value with the compensation value threshold until the second position compensation value is less than or equal to the compensation value threshold;

[0018] The detected position value is compensated according to the second position compensation value to obtain the first detected position value.

[0019] In one embodiment, after performing compensation processing according to the preset position difference and the first detected position value to obtain the second detected position value, the method further includes:

[0020] Scanning all detection points of the irregular edge; wherein the detection points include: the first detection point and a plurality of second detection points;

[0021] In the case that compensation is not completed for any of the detection points, compensation processing is performed on the detection point that is not completed.

[0022] In one embodiment, the abnormality judgment based on the abnormal value of the irregular edge and a preset abnormal threshold includes:

[0023] Comparing the abnormal value of the irregular edge with the abnormal threshold;

[0024] When the abnormal value of the special-shaped edge is less than or equal to the abnormal threshold, the target detection point is normal; wherein, the target detection point is the detection point currently being judged as abnormal.

[0025] In a second aspect, the present application also provides an anomaly detection device, including:

[0026] A visual inspection system, used for acquiring an image of a device under test, and obtaining a first position compensation value of a first inspection point on the irregular edge based on the image; wherein the first inspection point includes an inspection point set on the irregular edge;

[0027] A detection platform is used to place the device under test and to communicate with the visual inspection system, obtain the first position compensation value, perform compensation processing according to a preset detection position value and the first position compensation value to obtain a first detection position value of the first detection point, perform compensation processing according to a preset position difference value and the first detection position value to obtain a second detection position value, calculate anomaly values ​​of the detection points on the irregular edge according to the first detection position value and the second detection position value to obtain an irregular edge anomaly value, and perform an abnormality judgment on the detection points on the irregular edge according to the irregular edge anomaly value and a preset abnormality threshold.

[0028] In one embodiment, the device under test includes a first device under test and a second device under test, and the detection platform includes:

[0029] A first detection platform, used for performing abnormality detection on a first non-irregular edge of the first device under test; wherein the non-irregular edge refers to an edge with a straight line;

[0030] A second detection platform, used for performing abnormality detection on a second non-special-shaped edge of the second device under test;

[0031] The third detection platform is used to detect the first irregular edge of the first device under test when the detection of the first non-irregular edge is completed, and is also used to detect the second irregular edge of the second device under test when the detection of the second non-irregular edge is completed.

[0032] In a third aspect, the present application also provides an abnormality detection device, comprising:

[0033] A compensation value acquisition module, used to acquire a first position compensation value of a first detection point on the irregular edge of the device under test; wherein the first detection point includes a detection point set on the irregular edge;

[0034] A first compensation module, used for performing compensation processing according to a preset detection position value and the first position compensation value to obtain a first detection position value of the first detection point;

[0035] A second compensation module, used for performing compensation processing according to a preset position difference value and the first detected position value to obtain a second detected position value;

[0036] an outlier value calculation module, configured to calculate an outlier value of a detection point on the irregular edge according to the first detection position value and the second detection position value, so as to obtain an outlier value of the irregular edge;

[0037] The abnormality judgment module is used to judge the abnormality of the detection point on the irregular edge according to the abnormal value of the irregular edge and a preset abnormal threshold.

[0038] In a fourth aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0039] Obtaining a first position compensation value of a first detection point on the irregular edge of the device under test; wherein the first detection point includes a detection point set on the irregular edge;

[0040] Perform compensation processing according to a preset detection position value and the first position compensation value to obtain a first detection position value of the first detection point;

[0041] Perform compensation processing according to a preset position difference and the first detected position value to obtain a second detected position value;

[0042] Calculate the outlier value of the detection point on the irregular edge according to the first detection position value and the second detection position value to obtain the irregular edge outlier value;

[0043] An abnormality judgment is performed on the detection point on the irregular edge according to the irregular edge abnormal value and a preset abnormal threshold.

[0044] In a fifth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0045] Obtaining a first position compensation value of a first detection point on the irregular edge of the device under test; wherein the first detection point includes a detection point set on the irregular edge;

[0046] Perform compensation processing according to a preset detection position value and the first position compensation value to obtain a first detection position value of the first detection point;

[0047] Perform compensation processing according to a preset position difference and the first detected position value to obtain a second detected position value;

[0048] Calculate the outlier value of the detection point on the irregular edge according to the first detection position value and the second detection position value to obtain the irregular edge outlier value;

[0049] An abnormality judgment is performed on the detection point on the irregular edge according to the irregular edge abnormal value and a preset abnormal threshold.

[0050] The above-mentioned abnormality detection method, equipment, device, computer equipment and readable storage medium obtain the compensation value of the first detection point set on the irregular edge of the device under test to obtain the first compensation value, compensate the position value of the first detection point according to the preset detection position value and the first position compensation value to obtain the first detection position value, compensate the position value of the second detection point according to the preset position difference and the first detection position value to obtain the second detection position value, calculate the abnormal value of the detection point on the irregular edge according to the first detection position value and the second detection position value to obtain the irregular edge abnormal value, compare the irregular edge abnormal value with the preset abnormal threshold value, and make an abnormal judgment on the irregular edge of the device under test according to the comparison result, which can improve the accuracy of arc edge position detection, and thus improve the accuracy of arc edge abnormality detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0052] FIG1 is a schematic diagram of a flow chart of an abnormality detection method in one embodiment;

[0053] FIG2 is a schematic diagram of a flow chart of step 102 in one embodiment;

[0054] FIG3 is a schematic diagram of a flow chart of step 102 in another embodiment;

[0055] FIG4 is a schematic diagram of a flow chart of an abnormality detection method in another embodiment;

[0056] FIG5 is a schematic diagram of a flow chart of step 105 in one embodiment;

[0057] FIG6 is a block diagram of a detection platform in one embodiment;

[0058] FIG7 is a schematic diagram of a detection process of a device under test in one embodiment;

[0059] FIG8 is a schematic diagram of a process for detecting a device under test in one embodiment;

[0060] FIG9 is a block diagram of an abnormality detection device in one embodiment;

[0061] FIG. 10 is a diagram showing the internal structure of a computer device in one embodiment.

[0062] Description of reference numerals:

[0063] A first testing platform 601, a second testing platform 602, and a third testing platform 603;

[0064] Compensation value acquisition module 901 , first compensation module 902 , second compensation module 903 , abnormal value calculation module 904 , abnormality judgment module 905 . DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0066] At present, the car screen with arc line design is not just straight lines, and each individual chip-on-film on the arc line needs to be individually calculated and compensated. In the existing technology, the process of COF detection of arc lines is relatively complicated and requires a long detection time.

[0067] Therefore, the present application provides an abnormality detection method, device, apparatus, computer device and readable storage medium that can simplify the process of COF detection of arc lines and retrieve the detection time.

[0068] In an exemplary embodiment, as shown in FIG1 , a method for detecting anomalies is provided, which is described by taking the method applied to an anomaly detection device as an example, and includes the following steps 101 to 105. Among them:

[0069] Step 101, obtaining a first position compensation value of a first detection point on a special-shaped edge of a device under test; wherein the first detection point includes a detection point set on the special-shaped edge.

[0070] Among them, an image of the device under test is captured by an abnormality detection device, and the irregular edge of the device under test is identified in the image. Several detection points are set on the irregular edge, including a first detection point. The first detection point can be any one of the several detection points. In addition, the first position compensation value includes a position compensation value of the position where the first detection point is located, and the position compensation value includes a compensation value between the position where the first detection point is located and a preset detection position.

[0071] Optionally, a position compensation value of a position where a first detection point set on the irregular edge is located is acquired to obtain a first position compensation value.

[0072] Step 102: Perform compensation processing according to a preset detection position value and a first position compensation value to obtain a first detection position value of a first detection point.

[0073] Among them, the preset detection position value includes the position value of the preset detection position, the position value includes the coordinate value set in a pre-established coordinate system, the coordinate system includes the Y-axis and the Q-axis, therefore, the detection position value includes the coordinate value on the Y-axis coordinate and the coordinate value on the Q-axis coordinate, and the first position compensation value includes the compensation value on the Y-axis coordinate and the compensation value on the Q-axis coordinate.

[0074] Optionally, the compensation value of the Y-axis coordinate in the first position compensation value is compensated on the Y-axis coordinate value of the detection position value, and the compensation value of the Q-axis coordinate in the first position compensation value is compensated on the Q-axis coordinate value of the detection position value to obtain the first detection position value of the current position of the first detection point.

[0075] Step 103: Perform compensation processing according to the preset position difference and the first detected position value to obtain a second detected position value.

[0076] Among them, the several detection points also include several second detection points in addition to the first detection point, the preset position difference includes the coordinate value difference between the position of the first detection point and the position of any second detection point, and the coordinate value difference includes the difference on the Y-axis coordinate and the difference on the Q-axis coordinate.

[0077] Optionally, the difference in Y-axis coordinates in the position difference is compensated on the Y-axis coordinate value of the first detection position value, and the difference in Q-axis coordinates in the position difference is compensated on the Q-axis coordinate value of the first detection position value to obtain the second detection position value at the current position of the second detection point.

[0078] Step 104 , calculating an outlier value of the detection point on the irregular edge according to the first detection position value and the second detection position value to obtain an irregular edge outlier value.

[0079] Among them, the outlier calculation is implemented based on the COF algorithm. By calculating the connectivity score between the detection point and other surrounding detection points, and judging whether the detection point is an anomaly based on the connectivity score, the outlier value of the heterogeneous edge can be expressed as the connectivity score.

[0080] Optionally, when compensation is completed for several second detection points, the first detection position value and several second detection position values ​​are input into a preset COF algorithm to calculate the outlier values ​​of all detection points on the irregular edge to obtain the irregular edge outlier value.

[0081] Step 105 , performing abnormality judgment on the detection points on the irregular edge according to the irregular edge abnormal value and the preset abnormal threshold.

[0082] The abnormal threshold includes a threshold used to determine whether a detection point is abnormal.

[0083] Optionally, anomaly judgment is performed on all detection points on the irregular edge according to an abnormality threshold and a number of irregular edge abnormal values.

[0084] In the above-mentioned abnormality detection method, a position compensation value of a first detection point set on the irregular edge is obtained to obtain a first position compensation value, the compensation value of the Y-axis coordinate in the first position compensation value is compensated on the Y-axis coordinate value of the detection position value, and the compensation value of the Q-axis coordinate in the first position compensation value is compensated on the Q-axis coordinate value of the detection position value to obtain a first detection position value of the current position of the first detection point, the difference of the Y-axis coordinate in the position difference is compensated on the Y-axis coordinate value of the first detection position value, and the difference of the Q-axis coordinate in the position difference is compensated on the Q-axis coordinate value of the first detection position value to obtain a second detection position value of the current position of the second detection point, and when compensation is completed for several second detection points, the first detection position value and several second detection position values ​​are input into a preset COF algorithm to calculate the abnormal values ​​of all detection points on the irregular edge to obtain the irregular edge abnormal value, and all detection points on the irregular edge are judged abnormally according to the abnormal threshold and several irregular edge abnormal values, so as to improve the accuracy of arc edge position detection, and thereby improve the accuracy of arc edge abnormality detection.

[0085] In an exemplary embodiment, as shown in FIG2 , step 102 includes steps 201 to 202. Among them:

[0086] Step 201: compare the first position compensation value with a preset compensation value threshold.

[0087] The compensation value threshold is used to determine whether the compensation value is normal. If the compensation value is normal, compensation is performed according to the compensation value.

[0088] Step 202: When the first position compensation value is less than or equal to the compensation value threshold, the detected position value is compensated according to the first position compensation value to obtain a first detected position value.

[0089] When the compensation value is less than or equal to the compensation value threshold, the compensation value is normal.

[0090] Optionally, the comparison result between the first position compensation value and the compensation value threshold indicates that the first position compensation value is less than or equal to the compensation value threshold, the compensation value of the Y-axis coordinate in the first position compensation value is compensated on the Y-axis coordinate value of the detected position value, and the compensation value of the Q-axis coordinate in the first position compensation value is compensated on the Q-axis coordinate value of the detected position value to obtain the first detected position value.

[0091] In this embodiment, by comparing the first position compensation value with a preset compensation value threshold, when the compensation value is greater than the compensation value threshold, the compensation value of the Y-axis coordinate in the first position compensation value is compensated on the Y-axis coordinate value of the detected position value, and the compensation value of the Q-axis coordinate in the first position compensation value is compensated on the Q-axis coordinate value of the detected position value, to obtain the first detected position value, which can judge the abnormal situation of the compensation value, improve the accuracy of the position compensation, and thereby improve the accuracy of the arc edge position detection.

[0092] In an exemplary embodiment, as shown in FIG3 , step 102 further includes steps 301 to 303. Among them:

[0093] Step 301: when the first position compensation value is greater than the compensation value threshold, reacquire the second position compensation value of the first detection point.

[0094] Wherein, when the compensation value is greater than the compensation value threshold, the compensation value is abnormal. When the compensation value is abnormal, the compensation value is acquired again.

[0095] Optionally, the comparison result between the first position compensation value and the compensation value threshold indicates that the first position compensation value is greater than the compensation value threshold, and the compensation value of the first detection point is reacquired to obtain the second compensation value.

[0096] Step 302: compare the second position compensation value with the compensation value threshold until the second position compensation value is less than or equal to the compensation value threshold.

[0097] Optionally, the second position compensation value is compared with the compensation value threshold. If the second position compensation value is still greater than the compensation value threshold, the second compensation value of the first detection point is reacquired until the second position compensation value is less than the compensation value threshold. The loop is stopped and the next step is performed.

[0098] Step 303: Compensate the detected position value according to the second position compensation value to obtain a first detected position value.

[0099] Optionally, when the second position compensation value is less than or equal to the compensation value threshold, the compensation value of the Y-axis coordinate in the second position compensation value is compensated on the Y-axis coordinate value of the detected position value, and the compensation value of the Q-axis coordinate in the second position compensation value is compensated on the Q-axis coordinate value of the detected position value to obtain the first detected position value.

[0100] In this embodiment, the comparison result between the first position compensation value and the compensation value threshold indicates that the first position compensation value is greater than the compensation value threshold, the compensation value of the first detection point is reacquired to obtain the second compensation value, and the second position compensation value is compared with the compensation value threshold. If the second position compensation value is still greater than the compensation value threshold, a loop of reacquiring the second compensation value is entered until the second position compensation value is less than the compensation value threshold, the loop is stopped, and the compensation value of the Y-axis coordinate in the second position compensation value is compensated on the Y-axis coordinate value of the detection position value, and the compensation value of the Q-axis coordinate in the second position compensation value is compensated on the Q-axis coordinate value of the detection position value to obtain the first detection position value. This can judge the abnormal situation of the compensation value, improve the accuracy of the position compensation, and thereby improve the accuracy of the arc edge position detection.

[0101] In an exemplary embodiment, as shown in FIG4 , after step 104, steps 401 to 402 are included. Among them:

[0102] Step 401, scanning all detection points of the irregular edge; wherein the detection points include: a first detection point and a plurality of second detection points.

[0103] A number of detection points are pre-set on the irregular edge, and the detection point for performing the first detection is defined as the first detection point, and the other detection points are defined as the second detection point.

[0104] Optionally, the first detection point and the plurality of second detection points on the current irregular edge are scanned respectively to detect whether the first detection point and the plurality of second detection points have all completed compensation. Among them, the detection points that do not need to be compensated can be classified as having completed compensation.

[0105] Step 402: When compensation is not completed for any detection point, compensation processing is performed on the detection point for which compensation is not completed.

[0106] Optionally, if the first detection point has not completed compensation, step 101 and step 102 are executed to complete compensation for the first detection point. If any second detection point among several second detection points has not completed compensation, step 103 is executed until several second detection points have completed compensation.

[0107] In this embodiment, the first detection point and several second detection points on the current irregular edge are scanned respectively. When the first detection point has not completed compensation, steps 101 and 102 are executed to complete the compensation of the first detection point. When any one of the several second detection points has not completed compensation, step 103 is executed to complete the compensation of the current second detection point until the several second detection points have completed compensation. The compensation status of the detection points can be judged, the accuracy of the compensation is improved, and the accuracy of the arc edge position detection is further improved.

[0108] In an exemplary embodiment, as shown in FIG5 , step 105 includes steps 501 to 502, wherein:

[0109] Step 501, compare the abnormal value of the irregular edge with the abnormal threshold.

[0110] Optionally, the outlier values ​​of the irregular edges corresponding to several detection points are compared with the outlier thresholds respectively.

[0111] Step 502: When the abnormal value of the special-shaped edge is less than the abnormal threshold, the target detection point is normal; wherein the target detection point is the detection point currently being judged as abnormal.

[0112] The target detection point represents the detection point corresponding to the abnormal value of the special-shaped edge currently used for abnormality judgment.

[0113] Optionally, when the irregular edge anomaly value corresponding to the first detection point is less than the abnormal threshold, the first detection point is normal; when the irregular edge anomaly value corresponding to the first detection point is greater than the abnormal threshold, the first detection point is abnormal; when the irregular edge anomaly value corresponding to the current second detection point is less than the abnormal threshold, the current second detection point is normal; when the irregular edge anomaly value corresponding to the current second detection point is greater than the abnormal threshold, the current second detection point is abnormal.

[0114] In this embodiment, by comparing the irregular edge anomaly values ​​corresponding to several detection points with the abnormal threshold values ​​respectively, when the irregular edge anomaly value corresponding to the target detection point is less than the abnormal threshold value, the target detection point is normal; when the irregular edge anomaly value corresponding to the target detection point is greater than the abnormal threshold value, the target detection point is abnormal. This can determine whether several detection points on the irregular edge are normal, thereby improving the accuracy of irregular edge detection.

[0115] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0116] Based on the same inventive concept, the embodiment of the present application also provides an anomaly detection device for implementing the anomaly detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more anomaly detection device embodiments provided below can refer to the limitations on the anomaly detection method above, and will not be repeated here.

[0117] In an exemplary embodiment, as shown in FIG6 , an abnormality detection device is provided, including a visual detection system and a detection platform, wherein:

[0118] The visual inspection system is used to obtain an image of the device under test and obtain a first position compensation value of a first inspection point on the irregular edge based on the image; wherein the first inspection point includes an inspection point set on the irregular edge.

[0119] Among them, the visual inspection system is not drawn in Figure 6. The visual inspection system includes a camera and a sliding device, etc. The camera is used to photograph the device under test, and the sliding device is used to slide the camera to a preset shooting point.

[0120] The detection platform is used to place the device under test and to communicate with the visual detection system to obtain a first position compensation value, perform compensation processing according to a preset detection position value and the first position compensation value to obtain a first detection position value of the first detection point, perform compensation processing according to a preset position difference value and the first detection position value to obtain a second detection position value, calculate anomaly values ​​of the detection points on the irregular edge according to the first detection position value and the second detection position value to obtain an abnormal value of the irregular edge, and perform abnormality judgment on the detection points on the irregular edge according to the abnormal value of the irregular edge and a preset abnormal threshold.

[0121] Among them, only three inspection platforms are drawn in FIG6 , and each inspection platform is equipped with a visual inspection system.

[0122] In the above-mentioned abnormality detection equipment, after the visual inspection system detects that the device under test moves to the photographing point, it photographs the device under test to obtain an image of the device under test, and analyzes the image through the control system to obtain a first position compensation value of the first inspection point on the irregular edge, and the inspection platform obtains the first position compensation value transmitted by the visual inspection system, compensates the compensation value of the Y-axis coordinate in the first position compensation value on the Y-axis coordinate value of the inspection position value, and compensates the compensation value of the Q-axis coordinate in the first position compensation value on the Q-axis coordinate value of the inspection position value, to obtain the first inspection position value of the current position of the first inspection point, and compensates the compensation value of the Y-axis coordinate in the Y-axis coordinate value of the first inspection position value. The difference in Y-axis coordinates in the position difference is compensated at the Q-axis coordinate value of the first detection position value, and the second detection position value of the current position of the second detection point is obtained. When several second detection points have completed compensation, the first detection position value and several second detection position values ​​are input into the preset COF algorithm to calculate the abnormal values ​​of all detection points on the irregular edge, and the irregular edge abnormal value is obtained. According to the abnormal threshold and several irregular edge abnormal values, all detection points on the irregular edge are respectively judged as abnormal, which can improve the accuracy of arc edge position detection, and then improve the accuracy of arc edge abnormality detection.

[0123] In an exemplary embodiment, as shown in FIG6 , the device under test includes a first device under test and a second device under test, and the detection platform includes: a first detection platform 601 , a second detection platform 602 and a third detection platform 603 , wherein:

[0124] The first detection platform 601 is used to perform abnormality detection on a first non-irregular edge of a first device under test; wherein the non-irregular edge refers to an edge with straight lines.

[0125] The first non-irregular edge of the first device under test includes all non-irregular edges that need to be detected and are arranged on the first device under test.

[0126] Optionally, the first detection platform 601 is used to perform abnormality detection on detection points set on the first non-special-shaped edge of the first device under test.

[0127] The second detection platform 602 is used to perform abnormality detection on the second non-special-shaped edge of the second device under test.

[0128] The second non-irregular edge of the second device under test includes all non-irregular edges that need to be detected and are arranged on the second device under test.

[0129] Optionally, the second detection platform 602 performs abnormality detection on detection points arranged on the second non-special-shaped edge of the second device under test.

[0130] The third inspection platform 603 is used to inspect the first irregular edge of the first device under test when the inspection of the first non-irregular edge is completed, and is also used to inspect the second irregular edge of the second device under test when the inspection of the second non-irregular edge is completed.

[0131] The first non-irregular edge of the first device under test includes all non-irregular edges that need to be detected and are arranged on the first device under test. The first non-irregular edge of the first device under test includes all non-irregular edges that need to be detected and are arranged on the first device under test.

[0132] Optionally, when the first non-irregular edge detection is completed, the third detection platform 603 performs abnormality detection on the detection points set on the first irregular edge of the first device under test, or, when the second non-irregular edge detection is completed, the third detection platform 603 performs abnormality detection on the detection points set on the second irregular edge of the second device under test.

[0133] In this embodiment, the first detection platform 601 is used to perform abnormal detection on the detection points set on the first non-irregular edge of the first device under test, and the second detection platform 602 is used to perform abnormal detection on the detection points set on the second non-irregular edge of the second device under test. When the detection of the first non-irregular edge is completed, the third detection platform 603 is used to perform abnormal detection on the detection points set on the first irregular edge of the first device under test, or when the detection of the second non-irregular edge is completed, the third detection platform 603 is used to perform abnormal detection on the detection points set on the second irregular edge of the second device under test. This can improve the accuracy of the abnormality detection of the irregular edge, and can also improve the detection efficiency of the device under test by using the three detection platforms.

[0134] In an exemplary embodiment, the abnormality detection device also includes a loading robot and an unloading robot. The loading robot is used to place the device under test at the detection position of the detection platform, and the unloading robot is used to unload the device under test when the abnormality detection of the device under test is completed.

[0135] After the first inspection platform 601 or the second inspection platform 602 completes the abnormality detection, the first device under test or the second device under test is placed at the inspection position of the third inspection platform 603 by the loading robot.

[0136] In an exemplary embodiment, as shown in FIG7 , the panel 1 of the device under test is placed horizontally against the edge of the first detection platform 6016 by a loading robot. When the device under test is detected for abnormalities, the camera 4 scans the long side of the device under test along the dotted line until the line scan range 2 in FIG7 is scanned, where the long side represents a non-irregular side. After the long side detection of the device under test is completed, the panel 1 of the device under test is placed horizontally against the edge of the third detection platform 603 by a loading robot. The third detection platform 603 is rotated around the center of the circle 7 by an angle Q1 to rotate the first inspection point of the device under test to the detection position 3. At this time, the position of the first inspection point is perpendicular to the line scan range 2 of the camera 4.

[0137] In an exemplary embodiment, taking the detection of one non-irregular edge and two irregular edges of a device under test as an example, as shown in FIG8 , the loading robot places the first device under test and the second device under test on the first detection platform 601 and the second detection platform 602, respectively, and performs abnormal detection on the long edges of the first device under test and the second device under test through the first detection platform 601 and the second detection platform 602, respectively. After the first device under test on the first detection platform 601 is detected to be normal, the first device under test is transported to the third detection platform 603 by the loading robot. After the second device under test on the second detection platform 602 is detected to be normal, the second device under test is transported to the third detection platform 603 by the loading robot. The third detection platform 603 moves the device under test to the shooting area, triggers visual photography through the visual detection system, and obtains the first position compensation value of the first inspection point. It determines whether the first compensation value exceeds the limit according to the compensation value threshold. If it exceeds the limit, a pop-up window will be displayed to remind you to reshoot. If the first compensation value is normal, the third detection platform 603 performs position compensation to correct the position of the first inspection point and obtain the first detection position value. In addition, the third detection performs compensation processing according to the preset position difference and the first detection position value to correct the positions of several second inspection points and obtain the second detection position value. When the correction of the first detection point and several second detection points is completed, it rotates to the detection position of the first detection point on the special-shaped edge for scanning to determine whether the detection of all detection points has been completed. When all detection points are completed, the third detection platform 603 moves the value transfer position to transfer the device under test and ends the detection process.

[0138] This application calculates the COF detection position of the irregular edge and accurately quantifies the detection position, making the COF detection position of the irregular edge accurate and efficient. In addition, through the optimization of the three-platform detection strategy, it is concluded that the strategy of double-platform detection of non-irregular edges and one-platform detection of irregular edges is better than the independent detection of three platforms, and the single-chip production time is improved by 2.68s. In addition, logically, by increasing the preset compensation value, the equipment debugging efficiency is improved.

[0139] Based on the same inventive concept, the embodiment of the present application also provides an anomaly detection device for implementing the anomaly detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the anomaly detection device embodiment provided below can refer to the limitations of the anomaly detection method above, and will not be repeated here.

[0140] In an exemplary embodiment, as shown in FIG9 , an abnormality detection device is provided, including: a compensation value acquisition module 901, a first compensation module 902, a second compensation module 903, an abnormality calculation module 904 and an abnormality judgment module 905, wherein:

[0141] The compensation value acquisition module 901 is used to acquire a first position compensation value of a first detection point on the irregular edge of the device under test; wherein the first detection point includes a detection point set on the irregular edge.

[0142] The first compensation module 902 is used to perform compensation processing according to a preset detection position value and the first position compensation value to obtain a first detection position value of the first detection point.

[0143] The second compensation module 903 is used to perform compensation processing according to a preset position difference value and the first detected position value to obtain a second detected position value.

[0144] The outlier value calculation module 904 is used to calculate the outlier value of the detection point on the irregular edge according to the first detection position value and the second detection position value to obtain the irregular edge outlier value.

[0145] The abnormality judgment module 905 is used to perform abnormality judgment on the detection points on the irregular edge according to the irregular edge abnormal value and a preset abnormal threshold.

[0146] Each module in the above-mentioned abnormality detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0147] In an exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG10. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an abnormality detection method is implemented.

[0148] Those skilled in the art will understand that the structure shown in FIG. 10 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0149] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the following steps are implemented:

[0150] Step 101, obtaining a first position compensation value of a first detection point on a special-shaped edge of a device under test; wherein the first detection point includes a detection point set on the special-shaped edge.

[0151] Step 102: Perform compensation processing according to a preset detection position value and a first position compensation value to obtain a first detection position value of a first detection point.

[0152] Step 103: Perform compensation processing according to the preset position difference and the first detected position value to obtain a second detected position value.

[0153] Step 104 , calculating an outlier value of the detection point on the irregular edge according to the first detection position value and the second detection position value to obtain an irregular edge outlier value.

[0154] Step 105 , performing abnormality judgment on the detection points on the irregular edge according to the irregular edge abnormal value and the preset abnormal threshold.

[0155] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0156] Step 101, obtaining a first position compensation value of a first detection point on a special-shaped edge of a device under test; wherein the first detection point includes a detection point set on the special-shaped edge.

[0157] Step 102: Perform compensation processing according to a preset detection position value and a first position compensation value to obtain a first detection position value of a first detection point.

[0158] Step 103: Perform compensation processing according to the preset position difference and the first detected position value to obtain a second detected position value.

[0159] Step 104 , calculating an outlier value of the detection point on the irregular edge according to the first detection position value and the second detection position value to obtain an irregular edge outlier value.

[0160] Step 105 , performing abnormality judgment on the detection points on the irregular edge according to the irregular edge abnormal value and the preset abnormal threshold.

[0161] In one embodiment, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the following steps:

[0162] Step 101, obtaining a first position compensation value of a first detection point on a special-shaped edge of a device under test; wherein the first detection point includes a detection point set on the special-shaped edge.

[0163] Step 102: Perform compensation processing according to a preset detection position value and a first position compensation value to obtain a first detection position value of a first detection point.

[0164] Step 103: Perform compensation processing according to the preset position difference and the first detected position value to obtain a second detected position value.

[0165] Step 104 , calculating an outlier value of the detection point on the irregular edge according to the first detection position value and the second detection position value to obtain an irregular edge outlier value.

[0166] Step 105 , performing abnormality judgment on the detection points on the irregular edge according to the irregular edge abnormal value and the preset abnormal threshold.

[0167] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0168] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0169] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0170] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. An anomaly detection method, characterized in that: The method comprises: Obtaining a first position compensation value of a first detection point on the irregular edge of the device under test; wherein the first detection point includes a detection point set on the irregular edge; Perform compensation processing according to a preset detection position value and the first position compensation value to obtain a first detection position value of the first detection point; Perform compensation processing according to a preset position difference and the first detected position value to obtain a second detected position value; Calculate the outlier value of the detection point on the irregular edge according to the first detection position value and the second detection position value to obtain the irregular edge outlier value; An abnormality judgment is performed on the detection point on the irregular edge according to the irregular edge abnormal value and a preset abnormal threshold.

2. The method according to claim 1, characterized in that The performing compensation processing according to the preset detection position value and the first position compensation value to obtain the first detection position value of the first detection point includes: comparing the first position compensation value with a preset compensation value threshold; When the first position compensation value is less than or equal to the compensation value threshold, the detected position value is compensated according to the first position compensation value to obtain the first detected position value.

3. The method according to claim 2, characterized in that The performing compensation processing according to the preset detection position value and the position compensation value to obtain the first detection position value of the first detection point also includes: When the first position compensation value is greater than the compensation value threshold, reacquiring a second position compensation value of the first detection point; comparing the second position compensation value with the compensation value threshold until the second position compensation value is less than or equal to the compensation value threshold; The detected position value is compensated according to the second position compensation value to obtain the first detected position value.

4. The method according to claim 1, characterized in that: After performing compensation processing according to the preset position difference and the first detected position value to obtain the second detected position value, the method further includes: Scanning all detection points of the irregular edge; wherein the detection points include: the first detection point and a plurality of second detection points; In the case that compensation is not completed for any of the detection points, compensation processing is performed on the detection point that is not completed.

5. The method according to claim 1, characterized in that: The step of performing abnormality judgment on the detection point on the irregular edge according to the irregular edge abnormal value and a preset abnormal threshold comprises: Comparing the abnormal value of the irregular edge with the abnormal threshold; When the abnormal value of the special-shaped edge is less than or equal to the abnormal threshold, the target detection point is normal; wherein, the target detection point is the detection point currently being judged as abnormal.

6. An abnormality detection device, characterized in that: The device comprises: A visual inspection system, used for acquiring an image of a device under test, and obtaining a first position compensation value of a first inspection point on the irregular edge based on the image; wherein the first inspection point includes an inspection point set on the irregular edge; A detection platform is used to place the device under test and to communicate with the visual inspection system, obtain the first position compensation value, perform compensation processing according to a preset detection position value and the first position compensation value to obtain a first detection position value of the first detection point, perform compensation processing according to a preset position difference value and the first detection position value to obtain a second detection position value, calculate anomaly values ​​of the detection points on the irregular edge according to the first detection position value and the second detection position value to obtain an irregular edge anomaly value, and perform an abnormality judgment on the detection points on the irregular edge according to the irregular edge anomaly value and a preset abnormality threshold.

7. The device according to claim 6, characterized in that The device under test includes a first device under test and a second device under test, and the detection platform includes: A first detection platform, used for performing abnormality detection on a first non-irregular edge of the first device under test; wherein the non-irregular edge refers to an edge with a straight line; A second detection platform, used for performing abnormality detection on a second non-special-shaped edge of the second device under test; The third detection platform is used to detect the first irregular edge of the first device under test when the detection of the first non-irregular edge is completed, and is also used to detect the second irregular edge of the second device under test when the detection of the second non-irregular edge is completed.

8. An abnormality detection device, characterized in that: The device comprises: A compensation value acquisition module, used to acquire a first position compensation value of a first detection point on the irregular edge of the device under test; wherein the first detection point includes a detection point set on the irregular edge; A first compensation module, used for performing compensation processing according to a preset detection position value and the first position compensation value to obtain a first detection position value of the first detection point; A second compensation module, used for performing compensation processing according to a preset position difference value and the first detected position value to obtain a second detected position value; an outlier value calculation module, configured to calculate an outlier value of a detection point on the irregular edge according to the first detection position value and the second detection position value, so as to obtain an outlier value of the irregular edge; The abnormality judgment module is used to judge the abnormality of the detection point on the irregular edge according to the abnormal value of the irregular edge and a preset abnormal threshold.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images