Semiconductor rib and lead cut-off defect rapid detection method and equipment

Abstract

The present invention relates to the field of semiconductor rib cutting technology, and more specifically, to a method and device for rapid detection of semiconductor rib and pin cut-off defects. The scheme includes matching and setting a point light source, and converting it into parallel light of a preset direction through a convex lens; setting a visual collection sensor on the opposite side of the parallel light to form a visual sensing map; setting a loading method and a grabbing method track, and performing front and back detection and processing; obtaining information on the material to be detected at the current moment, and matching the corresponding shielding sheet; completing the replacement of the shielding sheet one by one, and quickly obtaining the corresponding visual sensing map, judging whether there is an abnormality and feeding back the abnormality type; for the equipment that feedbacks an abnormality, blowing it to a trash can through a blower. The scheme sets two rapid parallel light generation and information collection devices, combined with the feedback of rib and pin cut-off, pin offset or deformation, etc. generated after the optical fiber projection obtained by the sensor, if there is an abnormality, rapid detection is achieved.

Description

Technical Field

[0001] The present invention relates to the field of semiconductor rib cutting technology, and more specifically, to a method and device for quickly detecting semiconductor rib and pin cutting defects. Background Art

[0002] In the field of semiconductor rib cutting, research on rapid detection methods for rib and pin cutting defects is of great significance for improving production efficiency and product quality. By combining high-precision image recognition technology with machine learning algorithms, microscopic defects such as cracks, fragments or irregular fractures generated during the cutting process can be monitored and analyzed in real time. The implementation of this detection method can not only significantly reduce the missed detection rate and false positive rate caused by manual inspection, ensure the reliability of semiconductor components in subsequent packaging and applications, but also provide data support for process optimization and achieve precise control of cutting process parameters.

[0003] Prior to the technology of the present invention, the existing technology mainly relied on manual visual inspection and automatic inspection based on machine vision technology. The technical difficulty and key point lies in how to accurately and quickly identify and classify the cutting defects. Several major challenges include the diversity of defect morphology, the balance between detection speed and accuracy, and the need to adapt to the detection of different products. In terms of manual visual inspection, the operator uses tools such as microscopes or magnifying glasses to check the ribs and pins of semiconductor chips one by one. This method relies on the operator's experience and concentration, and has problems such as low efficiency, low accuracy, high cost, high labor intensity and inconsistent standards. It has been gradually replaced by automatic inspection technology. Automatic inspection technology based on machine vision has become the mainstream. The key lies in using image processing algorithms to analyze the collected chip images and identify the cutting defects of ribs and pins. This method improves the detection speed and accuracy, but there are still the following technical challenges: Diverse defect morphology: Various types of defects may occur in the chip production process, such as poor raw materials, foreign matter, scratches, Bump component defects, etc. These defects have different shapes and complex backgrounds, which brings challenges to accurate identification. Balance between detection speed and accuracy: Improving detection speed often comes at the expense of detection accuracy. How to achieve rapid detection while ensuring high accuracy is a major technical difficulty. Adaptability to different products: There are many types of semiconductor chips, and the structures and specifications of different products are different. The detection system needs to have good adaptability and flexibility to meet the detection needs of different products. Selection and optimization of image processing algorithms: How to select appropriate image processing algorithms (such as feature selection algorithms, pattern recognition and classification algorithms, etc.) and optimize them to meet the needs of high-speed and high-precision detection is the key in the implementation of the technology. Selection of light source and imaging technology: Different light sources and imaging technologies have a direct impact on the detection effect. Choosing suitable light sources and imaging technologies is crucial to improving the detection quality. In summary, for the rapid detection of semiconductor ribs and pin cut-off defects, the existing technical methods are mainly manual visual inspection and automatic inspection based on machine vision. The technical difficulties faced are the diversity of defect morphology, the balance between detection speed and accuracy, adaptation to the needs of different products, and the selection and optimization of image processing algorithms. Summary of the invention

[0004] In view of the above problems, the present invention proposes a method and device for rapid detection of semiconductor rib and pin cut defects. By setting up two fast parallel light generation and information collection devices, combined with the feedback generated by the sensor after optical fiber projection, rib and pin cut, pin offset or deformation, etc., if any abnormality occurs, rapid detection can be achieved.

[0005] According to a first aspect of an embodiment of the present invention, a method for rapid detection of semiconductor rib and lead cut-off defects is provided.

[0006] In one or more embodiments, preferably, the semiconductor rib and pin cut-off defect rapid detection method comprises:

[0007] Match the set point light source and transform it into parallel light in a preset direction through a convex lens;

[0008] A visual collection sensor is arranged on the opposite side of the parallel light to form a visual sensing map;

[0009] Set the feeding method and grabbing method track, and perform front and back side detection and processing;

[0010] Get the information of the sheet to be detected at the current moment and match the corresponding shielding sheet;

[0011] Replace the shielding sheets one by one and quickly obtain the corresponding visual sensing images to determine whether there is an abnormality and feedback the type of abnormality;

[0012] For devices with abnormal feedback, blow them into the trash bin using a blower.

[0013] In one or more embodiments, preferably, the matching and setting of the point light source and converting it into parallel light in a preset direction through a convex lens specifically includes:

[0014] Set a point light source above and on one side of the track respectively;

[0015] A convex lens is arranged between the point light source and the track to convert the point light source into parallel light.

[0016] In one or more embodiments, preferably, the step of arranging a visual collection sensor on the opposite side of the parallel light to form a visual sensing map specifically includes:

[0017] A panel-shaped optical signal sensor group is arranged at a position after the parallel light irradiation direction passes through the track;

[0018] The intensity of light received by the optical signal sensor will be converted into a voltage signal;

[0019] A visual sensing map is formed based on the voltage signal.

[0020] In one or more embodiments, preferably, the setting of the feeding mode and the grabbing mode track, and the front and back side detection and processing specifically include:

[0021] Use double magazines to rotate and load materials, and put the magazines filled with materials into the magazine placement position;

[0022] The equipment does not need to be stopped when changing the magazine. After the magazine filled with sheets rotates to the loading position, the motor lifts the sheets up to the gripper material picking position and waits for the materials to be grabbed.

[0023] The material is picked up by a vacuum nozzle. The material is sucked first and then grabbed. If the material is not picked up stably, a vacuum alarm will be given and the machine will stop.

[0024] The feeding track uses image detection to determine the front and back of the material. If the front and back are wrong, the material is quickly grabbed by a vacuum nozzle and the front and back are replaced.

[0025] In one or more embodiments, preferably, the obtaining information of the sheet to be detected at the current moment and matching the corresponding shielding sheet specifically includes:

[0026] Obtain the information of the material to be inspected at the current moment, obtain the projection of the corresponding rib piece and pin after normal removal, the longitudinal projection of the pin, and the transverse projection of the pin, where the projected area is black and the unprojected area is white;

[0027] The projection of the tendon and the pin after normal removal is inverted, and the white part is set to be transparent to match the corresponding preset first shielding sheet;

[0028] The longitudinal projection of the pin is inverted, and the white part is set to be transparent to match the corresponding preset second shielding sheet;

[0029] The lateral projection of the pin is inverted, and the white portion is set to be transparent to match the corresponding preset third shielding sheet.

[0030] In one or more embodiments, preferably, the replacing of the shielding sheets one by one and quickly obtaining the corresponding visual sensing images to determine whether there is an abnormality and feedback the type of abnormality specifically include:

[0031] Setting a preset first shielding sheet, a second shielding sheet and a third shielding sheet, and reading a visual sensing image at a corresponding moment;

[0032] Calculating a first light intensity ratio using a first calculation formula;

[0033] Calculating the projection ratio using a second calculation formula according to the proportion of the transparent portion in the first shielding sheet;

[0034] Determine whether the relationship between the first light intensity ratio and the projection ratio satisfies a third calculation formula, and if so, it is considered that there is a risk of not being cut off;

[0035] Calculating the second light intensity ratio using a fourth calculation formula;

[0036] Calculate the projection ratio using a fifth calculation formula according to the proportion of the transparent portion in the second shielding sheet;

[0037] Determine whether the relationship between the second light intensity ratio and the projection ratio satisfies a sixth calculation formula, and if so, it is considered that there is a risk of pin deviation;

[0038] Calculate the third light intensity ratio using the seventh calculation formula;

[0039] Calculate the projection ratio using the eighth calculation formula according to the proportion of the transparent portion in the third shielding sheet;

[0040] Determine whether the relationship between the third light intensity ratio and the projection ratio satisfies a ninth calculation formula, and if so, it is considered that there is a bending risk;

[0041] taking the non-cut-off risk, the pin deviation risk and the bending risk as feedback abnormality types;

[0042] The first calculation formula is:

[0043] G1=AVG1÷ZZ1

[0044] Wherein, G1 is the first light intensity ratio, AVG1 is the average voltage formed in the visual sensing image, and ZZ1 is the overall light intensity of the projection area of ​​the first shielding sheet without accessories;

[0045] The second calculation formula is:

[0046] T1=L1÷M1

[0047] Wherein, T1 is the projection ratio, L1 is the transparent portion area, and M1 is the total area of ​​the projection region of the first shielding sheet;

[0048] The third calculation formula is:

[0049] G1>1.2×T1

[0050] The fourth calculation formula is:

[0051] G2=AVG2÷ZZ2

[0052] Wherein, G2 is the second light intensity ratio, AVG2 is the average voltage formed in the visual sensing map corresponding to the second shielding sheet, and ZZ2 is the overall light intensity of the projection area of ​​the second shielding sheet without accessories;

[0053] The fifth calculation formula is:

[0054] T2=L2÷M2

[0055] Wherein, T2 is the projection ratio, L2 is the transparent portion area corresponding to the second shielding sheet, and M2 is the total area of ​​the projection region of the second shielding sheet;

[0056] The sixth calculation formula is:

[0057] G2>1.2×T2

[0058] The seventh calculation formula is:

[0059] G3=AVG1÷ZZ3

[0060] Wherein, G3 is the third light intensity ratio, AVG3 is the average voltage formed in the visual sensing map corresponding to the third shielding sheet, and ZZ3 is the overall light intensity of the projection area of ​​the third shielding sheet without accessories;

[0061] The eighth calculation formula is:

[0062] T3=L3÷M3

[0063] Wherein, T3 is the projection ratio corresponding to the third shielding sheet, L3 is the transparent portion area corresponding to the third shielding sheet, and M3 is the total area of ​​the projection region of the third shielding sheet;

[0064] The ninth calculation formula is:

[0065] G3>1.2×T3

[0066] In one or more embodiments, preferably, the device with abnormal feedback is blown to a trash bin by a blower, specifically including:

[0067] Mark the devices with abnormal feedback;

[0068] The tagged equipment will be automatically blown out to the trash bin when it reaches the blower.

[0069] According to a second aspect of an embodiment of the present invention, a rapid detection device for semiconductor rib and lead cut-off defects is provided.

[0070] In one or more embodiments, preferably, the semiconductor rib and pin cut-off defect rapid detection device comprises:

[0071] A parallel light generation module is used to match the set point light source and convert it into parallel light in a preset direction through a convex lens;

[0072] The collection and processing module is used to set a visual collection sensor on the opposite side of the parallel light to form a visual sensing map;

[0073] Mechanical gripper and track module, used to set the feeding method, gripping method track, and perform front and back side detection and processing;

[0074] The device information matching module is used to obtain the information of the material to be detected at the current moment and match the corresponding shielding piece;

[0075] The visual analysis module is used to replace the shielding sheets one by one and quickly obtain the corresponding visual sensing images to determine whether there is an abnormality and feedback the type of abnormality;

[0076] The trash bin setting module is used to blow the devices with abnormal feedback to the trash bin through a blower.

[0077] According to a third aspect of an embodiment of the present invention, there is provided a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method as described in any one of the first aspect of the embodiment of the present invention is implemented.

[0078] According to a fourth aspect of an embodiment of the present invention, there is provided an electronic device, comprising a memory and a processor, wherein the memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement any one of the methods described in the first aspect of the embodiment of the present invention.

[0079] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0080] In the solution of the present invention, by setting up two fast parallel light generation and information collection devices, the speed is extremely fast and it is easy to quantify and execute.

[0081] In the solution of the present invention, different types of abnormalities can be effectively distinguished by using the feedback ribs and pin cuts, pin offsets or deformations etc. generated after the optical fiber projection obtained in combination with the sensor.

[0082] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings.

[0083] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0085] Figure 1 The present invention is a flowchart of a method for rapidly detecting semiconductor rib and lead cut-off defects according to an embodiment of the present invention.

[0086] Figure 2 The present invention is a flowchart of matching and setting a point light source in a method for rapid detection of semiconductor rib and lead cut-off defects in one embodiment of the present invention, and converting the light into parallel light of a preset direction through a convex lens.

[0087] Figure 3 It is a flow chart of a method for quickly detecting semiconductor rib and pin cut-off defects in one embodiment of the present invention, in which a visual collection sensor is set on the opposite side of parallel light to form a visual sensing image.

[0088] Figure 4 It is a flow chart of setting the feeding mode and the grabbing mode track, and performing front and back side detection and processing in a method for rapid detection of semiconductor rib and pin cut-off defects in one embodiment of the present invention.

[0089] Figure 5 It is a flow chart of obtaining information of a material sheet to be inspected at the current moment and matching a corresponding shielding sheet in a method for rapid detection of semiconductor rib and pin cut-off defects according to an embodiment of the present invention.

[0090] Figure 6 It is a flowchart of a method for quickly detecting semiconductor rib and pin cut-off defects in an embodiment of the present invention, which completes the replacement of shielding sheets one by one, quickly obtains corresponding visual sensing images, determines whether there is an abnormality, and feeds back the type of abnormality.

[0091] Figure 7 This is a flow chart of a method for quickly detecting semiconductor rib and pin cut-off defects in an embodiment of the present invention, in which a device with abnormal feedback is blown to a trash bin by a blower.

[0092] Figure 8 It is a structural diagram of a semiconductor rib and lead cut-off defect rapid detection device according to an embodiment of the present invention.

[0093] Fig. 9 is a structural diagram of an electronic device in one embodiment of the present invention;

[0094] Fig.10 It is a schematic diagram of the first, second and third shielding sheets in the present invention. DETAILED DESCRIPTION

[0095] In some of the processes described in the specification and claims of the present invention and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0096] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0097] In the field of semiconductor rib cutting, research on rapid detection methods for rib and pin cutting defects is of great significance for improving production efficiency and product quality. By combining high-precision image recognition technology with machine learning algorithms, microscopic defects such as cracks, fragments or irregular fractures generated during the cutting process can be monitored and analyzed in real time. The implementation of this detection method can not only significantly reduce the missed detection rate and false positive rate caused by manual inspection, ensure the reliability of semiconductor components in subsequent packaging and applications, but also provide data support for process optimization and achieve precise control of cutting process parameters.

[0098] Prior to the technology of the present invention, the existing technology mainly relied on manual visual inspection and automatic inspection based on machine vision technology. The technical difficulty and key point lies in how to accurately and quickly identify and classify the cutting defects. Several major challenges include the diversity of defect morphology, the balance between detection speed and accuracy, and the need to adapt to the detection of different products. In terms of manual visual inspection, the operator uses tools such as microscopes or magnifying glasses to check the ribs and pins of semiconductor chips one by one. This method relies on the operator's experience and concentration, and has problems such as low efficiency, low accuracy, high cost, high labor intensity and inconsistent standards. It has been gradually replaced by automatic inspection technology. Automatic inspection technology based on machine vision has become the mainstream. The key lies in using image processing algorithms to analyze the collected chip images and identify the cutting defects of ribs and pins. This method improves the detection speed and accuracy, but there are still the following technical challenges: Diverse defect morphology: Various types of defects may occur in the chip production process, such as poor raw materials, foreign matter, scratches, Bump component defects, etc. These defects have different shapes and complex backgrounds, which brings challenges to accurate identification. Balance between detection speed and accuracy: Improving detection speed often comes at the expense of detection accuracy. How to achieve rapid detection while ensuring high accuracy is a major technical difficulty. Adaptability to different products: There are many types of semiconductor chips, and the structures and specifications of different products are different. The detection system needs to have good adaptability and flexibility to meet the detection needs of different products. Selection and optimization of image processing algorithms: How to select appropriate image processing algorithms (such as feature selection algorithms, pattern recognition and classification algorithms, etc.) and optimize them to meet the needs of high-speed and high-precision detection is the key in the implementation of the technology. Selection of light source and imaging technology: Different light sources and imaging technologies have a direct impact on the detection effect. Choosing suitable light sources and imaging technologies is crucial to improving the detection quality. In summary, for the rapid detection of semiconductor ribs and pin cut-off defects, the existing technical methods are mainly manual visual inspection and automatic inspection based on machine vision. The technical difficulties faced are the diversity of defect morphology, the balance between detection speed and accuracy, adaptation to the needs of different products, and the selection and optimization of image processing algorithms.

[0099] In an embodiment of the present invention, a method and device for rapid detection of semiconductor rib and pin cut defects are provided. The solution is to set up two rapid parallel light generation and information collection devices, and combine the feedback of rib and pin cut, pin offset or deformation generated by the sensor after the optical fiber projection, so as to achieve rapid detection if there is an abnormality.

[0100] According to a first aspect of an embodiment of the present invention, a method for rapid detection of semiconductor rib and lead cut-off defects is provided.

[0101] Figure 1The present invention is a flowchart of a method for rapidly detecting semiconductor rib and lead cut-off defects according to an embodiment of the present invention.

[0102] In one or more embodiments, preferably, the semiconductor rib and pin cut-off defect rapid detection method comprises:

[0103] S101, matching and setting a point light source, and converting it into parallel light in a preset direction through a convex lens;

[0104] S102, setting a visual collection sensor on the opposite side of the parallel light to form a visual sensing map;

[0105] S103, setting the feeding mode and grabbing mode track, and performing front and back side detection and processing;

[0106] S104, obtaining information of the sheet to be detected at the current moment, and matching the corresponding shielding sheet;

[0107] S105, complete the replacement of the shielding sheets one by one, and quickly obtain the corresponding visual sensing image, determine whether there is an abnormality and feedback the abnormality type;

[0108] S106. For devices with abnormal feedback, blow them into a trash bin using a blower.

[0109] In the embodiment of the present invention, by setting up two fast parallel light generation and information collection devices, combined with the feedback ribs and pin cuts, pin offset or deformation, etc. generated after the optical fiber projection obtained by the sensor, if there is an abnormality, rapid detection is achieved, and finally fast and accurate status feedback is completed.

[0110] Figure 2 The present invention is a flowchart of matching and setting a point light source in a method for rapid detection of semiconductor rib and lead cut-off defects in one embodiment of the present invention, and converting the light into parallel light of a preset direction through a convex lens.

[0111] like Figure 2 As shown, in one or more embodiments, preferably, the matching and setting of the point light source and converting it into parallel light in a preset direction through a convex lens specifically includes:

[0112] S201, setting a point light source above and on one side of the track respectively;

[0113] S202, setting a convex lens between the point light source and the track to convert the point light source into parallel light.

[0114] In the embodiment of the present invention, first, a point light source is set above and on one side of the track. These point light sources convert light into parallel light in a preset direction through a specially made convex lens. The configuration of the convex lens is used to ensure that the light emitted from the point light source can be effectively converted into parallel light, so as to provide uniform and stable lighting conditions for subsequent image acquisition.

[0115] Figure 2 It is a flow chart of a method for quickly detecting semiconductor rib and pin cut-off defects in one embodiment of the present invention, in which a visual collection sensor is set on the opposite side of parallel light to form a visual sensing image.

[0116] like Figure 3 As shown, in one or more embodiments, preferably, the obtaining of information of the sheet to be detected at the current moment and matching the corresponding shielding sheet specifically includes:

[0117] S301, arranging a panel-shaped optical signal sensor group at a position after the parallel light irradiates through the track;

[0118] S302, the intensity of light received by the optical signal sensor is converted into a voltage signal;

[0119] S303: forming a visual sensing image according to the voltage signal.

[0120] In an embodiment of the present invention, a panel-shaped optical signal sensor group is arranged at a position after the direction of parallel light irradiation passes through the track. This sensor group is arranged on the directly opposite side of the parallel light to optimize the receiving efficiency of the optical signal. Each unit of the panel-shaped optical signal sensor group has the function of converting the received light intensity into a voltage signal. In this way, when the parallel light passes through or is reflected from the semiconductor device, different light intensities will produce corresponding voltage changes on the sensor group. According to the voltage signal generated by the sensor group, a visual sensing map can be constructed. This map is essentially a voltage value map that reflects the light intensity distribution, which corresponds to the physical state of the semiconductor rib and the pin cut off. That is, the cut-off defect will cause abnormal reflection or blocking of light, and then present a voltage pattern that is significantly different from the normal area on the visual sensing map.

[0121] Figure 4 It is a flow chart of setting the feeding mode and the grabbing mode track, and performing front and back side detection and processing in a method for rapid detection of semiconductor rib and pin cut-off defects in one embodiment of the present invention.

[0122] like Figure 4 As shown, in one or more embodiments, preferably, the replacement of the shielding sheets is completed one by one, and the corresponding visual sensing images are quickly obtained to determine whether there is an abnormality and feedback the abnormality type, specifically including:

[0123] S401, using double magazines for rotating loading, placing a magazine filled with material pieces into a magazine placement position;

[0124] S402: When changing the magazine, the equipment does not need to stop. After the magazine filled with sheets rotates to the loading position, the motor lifts the sheets up to the gripper material taking position and waits for the materials to be grabbed.

[0125] S403, using vacuum suction nozzle to grab the material, the material is sucked first and then grabbed. If the material is not sucked stably, there will be a vacuum alarm prompt and the machine will stop;

[0126] S404: The front and back of the sheet are judged by image detection at the feeding track. If the front and back are wrong, the sheet is quickly grabbed by a vacuum nozzle and the front and back are replaced.

[0127] In an embodiment of the present invention, the system adopts a dual-clip rotation mechanism for loading, in which two clips are loaded with undetected sheets. The clips are placed in a special clip placement position. When the sheets in one clip are about to run out, the other clip that is full of sheets can be rotated to the lifting position to ensure that the equipment does not need to be shut down when changing clips, and maintain continuous production. After reaching the loading position, the motor is triggered to lift the sheet, accurately deliver it to the gripper material picking position and wait for grabbing. This process ensures that the sheet can rise smoothly into place and be ready to be grabbed through precise control. The system uses a vacuum nozzle to grab the sheet. Before sucking the sheet, the system first checks whether it is successfully adsorbed. If the sheet is not absorbed stably or slips, the system will immediately activate the vacuum alarm prompt and shut down to prevent damage to the sheet or cause a larger production accident. At the feeding track, the system uses an image detection device to determine whether the direction of the sheet is correct. If the front and back sides of the blank are detected to be wrong, the system will respond quickly by adjusting the operating procedures of the vacuum nozzle, grabbing the wrong blank, and replacing the front and back sides to ensure that each blank can enter the next inspection process in the correct direction. The above-mentioned loading, grabbing and front and back inspection operations are tightly integrated into the entire rapid inspection system to ensure a high-efficiency and high-precision inspection process. Each link is precisely designed and adjusted to meet the dual requirements of accuracy and speed in the semiconductor industry.

[0128] Figure 5 It is a flow chart of obtaining information of a material sheet to be inspected at the current moment and matching a corresponding shielding sheet in a method for rapid detection of semiconductor rib and pin cut-off defects according to an embodiment of the present invention.

[0129] like Figure 5 As shown, in one or more embodiments, preferably, the device with abnormal feedback is blown to the trash bin by a blower, specifically including:

[0130] S501, obtaining information of the material to be inspected at the current moment, obtaining the projection of the corresponding rib piece and the pin after normal removal, the longitudinal projection of the pin, and the transverse projection of the pin, wherein the projected area is black and the unprojected area is white;

[0131] S502, inverting the projection of the rib sheet and the lead after normal removal, and setting the white part to be transparent to match the corresponding preset first shielding sheet;

[0132] S503, inverting the longitudinal projection of the pin, and setting the white part to be transparent to match the corresponding preset second shielding sheet;

[0133] S504: invert the lateral projection of the pin, and set the white part to be transparent to match the corresponding preset third shielding sheet.

[0134] In an embodiment of the present invention, first, the information of the sheet to be inspected at the current moment is obtained. This information includes the projection of the rib sheet and the pin after normal removal, the longitudinal projection of the pin, and the transverse projection of the pin. In these projections, the projection area appears black, while the unprojected area is white. This step is the basis for ensuring the subsequent matching of the shielding sheet. The system performs an inversion operation on the projection of the rib sheet and the pin after normal removal, that is, black and white inversion, and changes the original black projection area to white, and the white area to black. After performing this conversion, the system sets the white part to transparent and matches the corresponding preset first shielding sheet. The purpose of this is to block the normal projection area during the detection process, leaving only the possible defective area for further detection. The system performs an inversion operation on the longitudinal projection of the pin, and sets the processed white part to transparent, and then matches the corresponding preset second shielding sheet. This step is intended to block the normal longitudinal projection area of ​​the pin, so as to focus on abnormal changes. For the transverse projection of the pin, the system also performs an inversion and makes the white part transparent, matching the corresponding preset third shielding sheet. This operation ensures that only those abnormal projection areas that do not conform to the standard situation will be detected. By matching the three shielding sheets mentioned above, the system can accurately shield the normal projection area and only retain those potential defect areas for further optical inspection. This method greatly improves the accuracy and efficiency of inspection because it eliminates the interference of normal features on defect identification. Specifically, the schematic diagrams of the first, second and third shielding sheets are shown in Fig.10 shown.

[0135] Figure 6 It is a flowchart of a method for quickly detecting semiconductor rib and pin cut-off defects in an embodiment of the present invention, which completes the replacement of shielding sheets one by one, quickly obtains corresponding visual sensing images, determines whether there is an abnormality, and feeds back the type of abnormality.

[0136] like Figure 6As shown, in one or more embodiments, preferably, the canvas 1 specifically includes:

[0137] S601, setting a preset first shielding sheet, a second shielding sheet, and a third shielding sheet, and reading a visual sensing image at a corresponding moment;

[0138] S602, calculating a first light intensity ratio using a first calculation formula; and calculating a projection ratio using a second calculation formula according to a proportion of a transparent portion in the first shielding sheet;

[0139] S603, determining whether the relationship between the first light intensity ratio and the projection ratio satisfies a third calculation formula, and if so, it is considered that there is a risk of not being cut off;

[0140] S604, calculating the second light intensity ratio by using the fourth calculation formula; and calculating the projection ratio by using the fifth calculation formula according to the proportion of the transparent portion in the second shielding sheet;

[0141] S605, determining whether the relationship between the second light intensity ratio and the projection ratio satisfies a sixth calculation formula, and if so, it is considered that there is a risk of pin deviation;

[0142] S606, calculating the third light intensity ratio by using the seventh calculation formula; and calculating the projection ratio by using the eighth calculation formula according to the proportion of the transparent portion in the third shielding sheet;

[0143] S607, determining whether the relationship between the third light intensity ratio and the projection ratio satisfies a ninth calculation formula, and if so, it is considered that there is a bending risk;

[0144] S608, taking the uncut risk, the pin deviation risk and the bending risk as feedback abnormality types;

[0145] The first calculation formula is:

[0146] G1=AVG1÷ZZ1

[0147] Wherein, G1 is the first light intensity ratio, AVG1 is the average voltage formed in the visual sensing image, and ZZ1 is the overall light intensity of the projection area of ​​the first shielding sheet without accessories;

[0148] The second calculation formula is:

[0149] T1=L1÷M1

[0150] Wherein, T1 is the projection ratio, L1 is the transparent portion area, and M1 is the total area of ​​the projection region of the first shielding sheet;

[0151] The third calculation formula is:

[0152] G1>1.2×T1

[0153] The fourth calculation formula is:

[0154] G2=AVG2÷ZZ2

[0155] Wherein, G2 is the second light intensity ratio, AVG2 is the average voltage formed in the visual sensing map corresponding to the second shielding sheet, and ZZ2 is the overall light intensity of the projection area of ​​the second shielding sheet without accessories;

[0156] The fifth calculation formula is:

[0157] T2=L2÷M2

[0158] Wherein, T2 is the projection ratio, L2 is the transparent portion area corresponding to the second shielding sheet, and M2 is the total area of ​​the projection region of the second shielding sheet;

[0159] The sixth calculation formula is:

[0160] G2>1.2×T2

[0161] The seventh calculation formula is:

[0162] G3=AVG1÷ZZ3

[0163] Wherein, G3 is the third light intensity ratio, AVG3 is the average voltage formed in the visual sensing map corresponding to the third shielding sheet, and ZZ3 is the overall light intensity of the projection area of ​​the third shielding sheet without accessories;

[0164] The eighth calculation formula is:

[0165] T3=L3÷M3

[0166] Wherein, T3 is the projection ratio corresponding to the third shielding sheet, L3 is the transparent portion area corresponding to the third shielding sheet, and M3 is the total area of ​​the projection region of the third shielding sheet;

[0167] The ninth calculation formula is:

[0168] G3>1.2×T3

[0169] In an embodiment of the present invention, a first shielding sheet, a second shielding sheet and a third shielding sheet are preset, and the visual sensing images at the corresponding moments are read. These visual sensing images correspond to different detection items, such as the projection of the ribs and pins after normal removal, the longitudinal projection of the pins and the lateral projection of the pins. The first light intensity ratio (G1) is calculated using the first calculation formula. This ratio is based on the ratio of the voltage average (AVG1) formed in the visual sensing image to the total light intensity (ZZ1) of the projection area of ​​the first shielding sheet without accessories. Then, according to the proportion of the transparent part in the first shielding sheet, the projection ratio (T1) is calculated using the second calculation formula. It is determined whether the relationship between the first light intensity ratio (G1) and the projection ratio (T1) satisfies the third calculation formula (G1>1.2×T1). If it does, it is considered that there is a risk of not being cut off, that is, the ribs may not be completely cut off. The second light intensity ratio (G2) is calculated using the fourth calculation formula. This ratio is based on the ratio of the voltage average (AVG2) formed in the visual sensing map corresponding to the second shielding sheet to the total light intensity (ZZ2) of the projection area of ​​the second shielding sheet without accessories. Then, according to the proportion of the transparent part in the second shielding sheet, the projection ratio (T2) is calculated using the fifth calculation formula. It is determined whether the relationship between the second light intensity ratio (G2) and the projection ratio (T2) satisfies the sixth calculation formula (G2>1.2×T2). If it does, it is considered that there is a risk of pin offset, that is, the pin may be misaligned or shifted. The third light intensity ratio (G3) is calculated using the seventh calculation formula. This ratio is based on the ratio of the voltage average (AVG3) formed in the visual sensing map corresponding to the third shielding sheet to the total light intensity (ZZ3) of the projection area of ​​the third shielding sheet without accessories. Then, according to the proportion of the transparent part in the third shielding sheet, the projection ratio (T3) is calculated using the eighth calculation formula. Determine whether the relationship between the third light intensity ratio (G3) and the projection ratio (T3) satisfies the ninth calculation formula (G3>1.2×T3). If satisfied, it is considered that there is a bending risk, that is, the pin may be bent or deformed. The risk of not cutting off, the risk of pin offset and the risk of bending are used as the abnormality types for feedback. This information is used for further quality assessment and control processes to optimize production quality and efficiency. Through the above steps, this embodiment demonstrates a sophisticated method to identify and process semiconductor rib and pin cutting defects, ensuring the accuracy and reliability of the detection process.

[0170] Figure 7 This is a flow chart of a method for quickly detecting semiconductor rib and pin cut-off defects in an embodiment of the present invention, in which a device with abnormal feedback is blown to a trash bin by a blower.

[0171] like Figure 7 As shown, in one or more embodiments, preferably, the canvas 1 specifically includes:

[0172] S701, marking the device with abnormal feedback;

[0173] S702: The marked equipment is automatically blown out to the trash bin when it reaches the blower.

[0174] In an embodiment of the present invention, during the rapid detection process, the system marks the equipment identified as having a cut-off defect. This step is implemented by automated software to ensure that all equipment with problems detected can be accurately recorded and tracked. In order to achieve separation processing, the marked equipment will then enter the sorting stage. When these equipment reach the blower position, the system will automatically trigger the blower to blow the marked equipment out to the trash can. This process utilizes the weight of the equipment and the principle of air flow to ensure that the marked equipment can be accurately sorted out and transferred to the trash can, thereby completing the automatic elimination of defective products; a trash can is set up to collect equipment identified as defective by the system. In order to maintain the continuous operation of the system and avoid problems caused by overfilling the trash can, the system monitors the filling level of the trash can and reminds the operator to clean it up when appropriate. In addition, the design of the trash can takes into account the factors of easy cleaning and preventing equipment accumulation, ensuring the hygiene and safety of the processing process. The system records all marked and processed equipment information, including defect type, processing time and other data. These data are crucial for the quality management of the production line and subsequent process optimization, and can help engineers and managers analyze the causes of defects and take corresponding improvement measures to reduce future production defects.

[0175] According to a second aspect of an embodiment of the present invention, a rapid detection device for semiconductor rib and lead cut-off defects is provided.

[0176] Figure 8 It is a structural diagram of a semiconductor rib and lead cut-off defect rapid detection device according to an embodiment of the present invention.

[0177] In one or more embodiments, preferably, the semiconductor rib and pin cut-off defect rapid detection device comprises:

[0178] A parallel light generation module 801 is used to match a set point light source and convert it into parallel light in a preset direction through a convex lens;

[0179] The collection and processing module 802 is used to set a visual collection sensor on the opposite side of the parallel light to form a visual sensing map;

[0180] Mechanical gripper and track module 803, used to set the feeding mode, gripping mode track, and perform front and back side detection and processing;

[0181] The device information matching module 804 is used to obtain the information of the material to be detected at the current moment and match the corresponding shielding piece;

[0182] The visual analysis module 805 is used to replace the shielding sheets one by one, and quickly obtain the corresponding visual sensing map, determine whether there is an abnormality and feedback the abnormality type;

[0183] The trash bin setting module 806 is used to blow the devices with abnormal feedback to the trash bin through a blower.

[0184] In the embodiment of the present invention, a system suitable for different structures is realized through a series of modular designs. The system can achieve closed-loop, reliable and efficient execution through collection, analysis and control.

[0185] According to a third aspect of an embodiment of the present invention, there is provided a computer-readable storage medium on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method as described in any one of the first aspect of the embodiment of the present invention is implemented.

[0186] According to a fourth aspect of an embodiment of the present invention, an electronic device is provided. Fig. 9 It is a structural diagram of an electronic device in one embodiment of the present invention. Fig. 9 The electronic device shown is a general semiconductor rib and pin cut-off defect rapid detection device. Fig. 9 The electronic device 900 includes one or more (only one is shown in the figure) processors 902, a memory 904 and a wireless module 906 coupled to each other. The memory 904 stores a program that can execute the content of the above-mentioned embodiment, and the processor 902 can execute the program stored in the memory 904.

[0187] Among them, the processor 902 may include one or more processing cores. The processor 902 uses various interfaces and lines to connect various parts of the entire electronic device 900, and executes various functions and processes data of the electronic device 900 by running or executing instructions, programs, code sets or instruction sets stored in the memory 904, and calling data stored in the memory 904. Optionally, the processor 902 can be implemented in at least one hardware form of digital signal processing (DSP), field programmable gate array (FPGA), and programmable logic array (PLA). The processor 902 can integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. Among them, the CPU mainly processes the operating system, user interface, and target application program; the GPU is responsible for rendering and drawing display content; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 902, but implemented separately through a communication chip.

[0188] The memory 904 may include a random access memory (RAM) or a read-only memory (ROM). The memory 904 may be used to store instructions, programs, codes, code sets or instruction sets. The memory 904 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a touch function, a sound playback function, an image playback function, etc.), instructions for implementing the following various method embodiments, etc. The data storage area may also store data (such as the aforementioned text document) created by the electronic device 900 during use, etc.

[0189] The wireless module 906 is used to receive and send electromagnetic waves, realize the mutual conversion between electromagnetic waves and electrical signals, and thus communicate with a communication network or other equipment, for example, communicate with a base station based on a mobile communication protocol. The wireless module 906 may include various existing circuit elements for performing these functions, for example, an antenna, a radio frequency transceiver, a digital signal processor, an encryption / decryption chip, a user identity module (SIM) card, a memory, etc. The wireless module 906 may communicate with various networks such as the Internet, an intranet, a wireless network, or communicate with other electronic devices through a wireless network. The above-mentioned wireless network may include a cellular telephone network, a wireless local area network, or a metropolitan area network. The above-mentioned wireless network may use various communication standards, protocols, and technologies, including but not limited to WLAN protocols and Bluetooth protocols, and may even include those protocols that have not yet been developed.

[0190] The technical solution provided by the embodiments of the present invention may have the following beneficial effects:

[0191] In the solution of the present invention, by setting up two fast parallel light generation and information collection devices, the speed is extremely fast and it is easy to quantify and execute.

[0192] In the solution of the present invention, different types of abnormalities can be effectively distinguished by using the feedback ribs and pin cuts, pin offsets or deformations etc. generated after the optical fiber projection obtained in combination with the sensor.

[0193] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) containing computer-usable program code.

[0194] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0195] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0196] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0197] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for rapid detection of semiconductor rib and lead cut-off defects, characterized in that: The method includes: Match the set point light source and transform it into parallel light in a preset direction through a convex lens; A visual collection sensor is arranged on the opposite side of the parallel light to form a visual sensing map; Set the feeding method and grabbing method track, and perform front and back side detection and processing; Get the information of the sheet to be detected at the current moment and match the corresponding shielding sheet; Replace the shielding sheets one by one and quickly obtain the corresponding visual sensing images to determine whether there is an abnormality and feedback the type of abnormality; For equipment with abnormal feedback, blow it to the trash bin through a blower; The obtaining of information of the sheet to be detected at the current moment and matching the corresponding shielding sheet specifically includes: Obtain the information of the material to be inspected at the current moment, obtain the projection of the corresponding rib piece and pin after normal removal, the longitudinal projection of the pin, and the transverse projection of the pin, where the projected area is black and the unprojected area is white; The projection of the tendon and the pin after normal removal is inverted, and the white part is set to be transparent to match the corresponding preset first shielding sheet; The longitudinal projection of the pin is inverted, and the white part is set to be transparent to match the corresponding preset second shielding sheet; The lateral projection of the pin is inverted, and the white portion is set to be transparent to match the corresponding preset third shielding sheet.

2. The semiconductor rib and lead cut-off defect rapid detection method according to claim 1, characterized in that: The matching and setting of the point light source and converting it into parallel light in a preset direction through a convex lens specifically includes: Set a point light source above and on one side of the track; A convex lens is arranged between the point light source and the track to convert the point light source into parallel light.

3. The semiconductor rib and lead cut-off defect rapid detection method according to claim 1, characterized in that: The method of arranging a visual collection sensor on the opposite side of the parallel light to form a visual sensing map specifically includes: A panel-shaped optical signal sensor group is arranged at a position after the parallel light irradiation direction passes through the track; The intensity of light received by the optical signal sensor will be converted into a voltage signal; A visual sensing map is formed based on the voltage signal.

4. The semiconductor rib and lead cut-off defect rapid detection method according to claim 1, characterized in that: The setting of the feeding mode and the grabbing mode track, and the front and back side detection and processing specifically include: Use double magazines to rotate and load materials, and put the magazines filled with materials into the magazine placement position; The equipment does not need to be stopped when changing the magazine. After the magazine filled with sheets rotates to the loading position, the motor lifts the sheets up to the gripper material picking position and waits for the materials to be grabbed. The material is picked up by a vacuum nozzle. The material is sucked first and then grabbed. If the material is not picked up stably, a vacuum alarm will be given and the machine will stop. The feeding track uses image detection to determine the front and back of the material. If the front and back are wrong, the material is quickly grabbed by a vacuum nozzle and the front and back are replaced.

5. The semiconductor rib and lead cut-off defect rapid detection method according to claim 1, characterized in that: The process of replacing the shielding sheets one by one and quickly obtaining the corresponding visual sensing images, determining whether there is an abnormality and feeding back the abnormality type specifically includes: Setting a preset first shielding sheet, a second shielding sheet and a third shielding sheet, and reading a visual sensing image at a corresponding moment; Calculating a first light intensity ratio using a first calculation formula; Calculating the projection ratio using a second calculation formula according to the proportion of the transparent portion in the first shielding sheet; Determine whether the relationship between the first light intensity ratio and the projection ratio satisfies a third calculation formula, and if so, it is considered that there is a risk of not being cut off; Calculating the second light intensity ratio using a fourth calculation formula; Calculate the projection ratio using a fifth calculation formula according to the proportion of the transparent portion in the second shielding sheet; Determine whether the relationship between the second light intensity ratio and the projection ratio satisfies a sixth calculation formula, and if so, it is considered that there is a risk of pin deviation; Calculate the third light intensity ratio using the seventh calculation formula; Calculate the projection ratio using the eighth calculation formula according to the proportion of the transparent portion in the third shielding sheet; Determine whether the relationship between the third light intensity ratio and the projection ratio satisfies a ninth calculation formula, and if so, it is considered that there is a bending risk; taking the non-cut-off risk, the pin deviation risk and the bending risk as feedback abnormality types; The first calculation formula is: G1=AVG1÷ZZ1 Wherein, G1 is the first light intensity ratio, AVG1 is the average voltage formed in the visual sensing image, and ZZ1 is the overall light intensity of the projection area of ​​the first shielding sheet without accessories; The second calculation formula is: T1=L1÷M1 Wherein, T1 is the projection ratio, L1 is the transparent portion area, and M1 is the total area of ​​the projection region of the first shielding sheet; The third calculation formula is: G1>1.2×T1 The fourth calculation formula is: G2=AVG2÷ZZ2 Wherein, G2 is the second light intensity ratio, AVG2 is the average voltage formed in the visual sensing map corresponding to the second shielding sheet, and ZZ2 is the overall light intensity of the projection area of ​​the second shielding sheet without accessories; The fifth calculation formula is: T2=L2÷M2 Wherein, T2 is the projection ratio, L2 is the transparent portion area corresponding to the second shielding sheet, and M2 is the total area of ​​the projection region of the second shielding sheet; The sixth calculation formula is: G2>1.2×T2 The seventh calculation formula is: G3=AVG1÷ZZ3 Among them, G3 is the third light intensity ratio, AVG3 is the average voltage formed in the visual sensing map corresponding to the third shielding sheet, and ZZ3 is the overall total light intensity of the projection area of ​​the third shielding sheet without accessories; The eighth calculation formula is: T3=L3÷M3 Wherein, T3 is the projection ratio corresponding to the third shielding sheet, L3 is the transparent portion area corresponding to the third shielding sheet, and M3 is the total area of ​​the projection region of the third shielding sheet; The ninth calculation formula is: G3>1.2×T3.

6. The semiconductor rib and lead cut-off defect rapid detection method according to claim 1, characterized in that: The equipment with abnormal feedback is blown to the trash bin by a blower, specifically including: Mark the devices with abnormal feedback; The tagged equipment will be automatically blown out to the trash bin when it reaches the blower.

7. Rapid detection equipment for semiconductor rib and pin cut-off defects, characterized in that: The device is used to implement the method according to any one of claims 1 to 6, and the device comprises: A parallel light generation module is used to match the set point light source and convert it into parallel light in a preset direction through a convex lens; The collection and processing module is used to set a visual collection sensor on the opposite side of the parallel light to form a visual sensing map; Mechanical gripper and track module, used to set the feeding method, gripping method track, and perform front and back side detection and processing; The device information matching module is used to obtain the information of the material to be detected at the current moment and match the corresponding shielding piece; The visual analysis module is used to replace the shielding sheets one by one and quickly obtain the corresponding visual sensing images to determine whether there is an abnormality and feedback the type of abnormality; The trash bin setting module is used to blow the devices with abnormal feedback to the trash bin through a blower.

8. A computer-readable storage medium storing computer program instructions, characterized in that: The computer program instructions implement the method according to any one of claims 1 to 6 when executed by a processor.

9. An electronic device, comprising a memory and a processor, characterized in that: The memory is used to store one or more computer program instructions, wherein the one or more computer program instructions are executed by the processor to implement the method according to any one of claims 1-6.

Images