Product inspection method, apparatus, system, and medium

Abstract

The application provides a product detection method, device, system and medium. The method comprises: obtaining sanding processing data of a product; determining a sanding quality score of the product based on the sanding processing data; marking a three-dimensional model of the product based on the sanding quality score and the corresponding first preset mark; determining whether the sanding processing of the product is abnormal based on the sanding quality score; and identifying an abnormal area in the marked three-dimensional model based on the sanding processing of the product being abnormal. The above method can accurately detect whether the sanding processing of the product is abnormal, thereby ensuring the product detection efficiency.

Description

TECHNICAL FIELD

[0001] The present application belongs to the field of detection, and particularly relates to a product detection method, device, system and medium. BACKGROUND

[0002] In the field of sanding processing, in order to ensure the quality of products, it is an indispensable link to detect the abnormality of products after sanding processing.

[0003] However, the traditional method currently adopted depends on manual detection, and the manual detection method is easily affected by subjective factors (for example, experience and state) of the detection personnel, which is difficult to ensure the accuracy of detection and may also lead to missed detection, resulting in poor detection efficiency and further affecting the quality of products. SUMMARY

[0004] In view of the above, it is necessary to provide a product detection method, device, system and medium, which can solve the technical problem that poor detection efficiency affects the quality of products.

[0005] In one aspect, the present application provides a product detection method, which comprises: obtaining sanding processing data of a product, determining a sanding quality score of the product based on the sanding processing data, obtaining a corresponding first preset mark based on the sanding quality score, performing mark processing on a three-dimensional model of the product, determining whether the sanding processing of the product is abnormal based on the sanding quality score, and identifying an abnormal area in the three-dimensional model after mark processing based on the fact that the sanding processing of the product is abnormal.

[0006] In some embodiments of the present application, the method further comprises: obtaining specification data of the product, and constructing a three-dimensional model of the product according to the specification data.

[0007] In some embodiments of the present application, the sanding processing data comprises polishing force data corresponding to single sanding processing, the polishing force data is data generated when at least one sanding processing area in the product is processed, and the polishing force data comprises real polishing force and target polishing force corresponding to a plurality of time points. The method of determining the sanding quality score of the product based on the sanding processing data comprises: determining a real friction coefficient between the at least one sanding processing area and a grinding tool and a normal force applied by the grinding tool to the at least one sanding processing area at each time point based on the real polishing force corresponding to the plurality of time points, calculating real friction force at each time point according to the real friction coefficient and the normal force corresponding to each time point, calculating target friction force at each time point according to a standard friction coefficient and the target polishing force corresponding to each time point, and determining sanding quality scores corresponding to each time point according to the real friction force and the target friction force at each time point.

[0008] In some embodiments of the present application, the sanding process data includes polishing force data corresponding to multiple sanding processes of the product, the polishing force data corresponding to each sanding process is data generated when at least one sanding area in the product is processed, and the polishing force data corresponding to each sanding process includes real polishing forces and target polishing forces corresponding to multiple time points. The method for determining the sanding quality score of the product based on the sanding process data includes: determining real friction coefficients between the at least one sanding area and a polishing tool and normal forces applied by the polishing tool to the at least one sanding area at each time point based on the real polishing forces corresponding to the multiple time points; calculating real friction forces at each time point in each sanding process according to the real friction coefficients and the normal forces corresponding to the multiple time points in each sanding process; calculating target friction forces at each time point in each sanding process according to standard friction coefficients and target polishing forces corresponding to the multiple time points in each sanding process; determining initial quality scores corresponding to each time point in each sanding process according to the real friction forces and the target friction forces at each time point in each sanding process; and calculating sanding quality scores of each time point according to the multiple initial quality scores corresponding to each time point in the multiple sanding processes of the product.

[0009] In some embodiments of the present application, the method for determining the sanding quality score of the product based on the sanding process data further includes: counting the number of initial quality scores corresponding to each sanding process; determining whether the number of initial quality scores corresponding to each sanding process is different; if the number of initial quality scores corresponding to each sanding process is different, taking the number of initial quality scores corresponding to a single sanding process with the largest number as a target number value; and performing interpolation processing on initial quality scores other than the initial quality score corresponding to the target number value according to the target number value, so that the multiple sanding processes correspond to the same number of initial quality scores.

[0010] In some embodiments of the present application, the step of determining the real friction coefficient between the at least one sanding processing area and the grinding tool and the normal force applied by the grinding tool to the at least one sanding processing area at each time point based on the real grinding forces corresponding to the plurality of time points comprises: performing frequency domain transformation on the real grinding forces corresponding to the plurality of time points to obtain frequency spectrum data, determining the amplitude corresponding to each frequency within a preset frequency range in the frequency spectrum data, calculating the energy corresponding to each frequency according to the amplitude corresponding to each frequency, determining the real friction coefficient according to the energy corresponding to a plurality of frequencies within the preset frequency range, and filtering the real grinding forces corresponding to each time point to obtain the normal force corresponding to each time point.

[0011] In some embodiments of the present application, the method further comprises: determining a first curve constituted by the real grinding forces corresponding to each time point, and a second curve constituted by the target grinding forces corresponding to each time point, determining a first difference area and a second difference area corresponding to each sanding processing area constituted by the first curve and the second curve, wherein the first difference area is a region where the real grinding force at each time point during the sanding processing of the sanding processing area of the product is less than the corresponding target grinding force, and the second difference area is a region where the real grinding force at each time point during the sanding processing of the sanding processing area of the product is greater than the corresponding target grinding force, and visually marking the first difference area and the second difference area corresponding to each sanding processing area.

[0012] In some embodiments of the present application, the method further comprises: based on the first difference area and the second difference area corresponding to each sanding processing area of the product, calculating a first total area of all first difference areas and a second total area of all second difference areas of the product, calculating the area difference and the area sum between the first total area and the second total area, and visualizing the area difference and the area sum.

[0013] In some embodiments of the present application, the method further comprises: calculating a sanding quality index of the at least one sanding processing area according to the real grinding force and the target grinding force corresponding to the at least one sanding processing area, and / or the first difference area and the second difference area, generating a data table according to the sanding quality index, and marking an abnormal quality index in the data table with a second preset mark if the abnormal quality index is included in the sanding quality index of the data table.

[0014] In some embodiments of the present application, the marking processing of the three-dimensional model based on the first preset mark corresponding to the sanding quality score comprises: determining a visual area corresponding to the at least one sanding processing area in the three-dimensional model, and marking the visual area according to the first preset mark corresponding to the sanding quality score at each time point.

[0015] In some embodiments of the present application, the marking processing of the three-dimensional model based on the first preset mark corresponding to the sanding quality score comprises: determining a visual area corresponding to the at least one sanding processing area in the three-dimensional model, and marking the visual area according to the first preset mark corresponding to the sanding quality score at each time point.

[0016] In some embodiments of the present application, the method further comprises: determining a sanding force deviation between a real sanding force corresponding to the abnormal quality score and a target sanding force, and calculating a compensation value of the target sanding force corresponding to the abnormal quality score by using a preset model based on the sanding force deviation, so as to perform sanding processing on a next product.

[0017] In some embodiments of the present application, the sanding processing area is multiple, and the method further comprises: determining an index corresponding to each sanding processing area according to a processing sequence corresponding to the multiple sanding processing areas, and marking the visual area corresponding to the multiple sanding processing areas according to the processing sequence and the index corresponding to each sanding processing area.

[0018] In another aspect, the present application provides an electronic device, comprising: a memory storing at least one instruction; and a processor executing the at least one instruction to implement the product detection method.

[0019] In another aspect, the present application provides a product detection system, comprising: a sanding device for performing sanding processing on the product to generate the sanding processing data; and the electronic device for pushing processing data to the sanding device based on the abnormality in the sanding processing of the product.

[0020] In another aspect, the present application provides a computer readable storage medium, wherein at least one instruction is stored in the computer readable storage medium, and the at least one instruction is executed by a processor in an electronic device to implement the product detection method.

[0021] In the product inspection method provided in this embodiment, since the product specification data can reflect the product's size, shape, and structural characteristics, a three-dimensional model of the product can be accurately constructed based on the specification data. Since sanding data can reflect parameters such as the actual grinding force and target grinding force during the sanding process, the sanding quality score can be accurately determined, ensuring that the sanding quality score accurately reflects the sanding quality. By marking the three-dimensional model using the first preset mark corresponding to the sanding quality score, the sanding effect can be displayed intuitively. Because the sanding quality score accurately reflects the sanding quality, it can accurately detect whether there are any abnormalities in the sanding process of the product, thereby ensuring product inspection efficiency. When an abnormality is determined in the sanding process, the abnormal area is marked on the marked three-dimensional model, intuitively displaying the abnormal location, allowing the user to quickly locate the abnormality and make corresponding adjustments to the processing parameters or methods for subsequent products. Attached Figure Description

[0022] Figure 1 This is a schematic diagram of a product testing system provided in one embodiment of this application.

[0023] Figure 2 This is a flowchart of a product testing method provided in one embodiment of this application.

[0024] Figure 3 This is a schematic diagram of a three-dimensional model provided in an embodiment of this application.

[0025] Figure 4 This is a schematic diagram of the grinding force data provided in one embodiment of this application.

[0026] Figure 5 This is a schematic diagram of grinding force data provided in another embodiment of this application.

[0027] Figure 6 This is a schematic diagram of the projection area provided in one embodiment of this application.

[0028] Figure 7 This is a flowchart of a method for determining the actual coefficient of friction and normal force according to an embodiment of this application.

[0029] Figure 8 This is a flowchart of a product testing method provided in another embodiment of this application.

[0030] Figure 9 This is a schematic diagram of the first difference region and the second difference region provided in an embodiment of this application.

[0031] Figure 10 This is a schematic diagram of the area difference and area sum curves of each product after sanding, provided in one embodiment of this application.

[0032] Figure 11 is a flowchart of a product detection method provided by another embodiment of the present application.

[0033] Figure 12 is a schematic diagram of a data table provided by an embodiment of the present application.

[0034] Figure 13 is a structural diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0035] It should be noted that “at least one” in the present application means one or more, and “multiple” means two or more than two. “And / or” describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B can represent: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The terms “first”, “second”, “third”, “fourth” and the like (if any) in the specification and claims of the present application and the drawings are used to distinguish similar objects, and are not used to describe a specific order or sequence.

[0036] In the embodiments of the present application, the words “exemplary” or “for example” are used to mean serving as an example, instance, or illustration. Any embodiment or design presented as “exemplary” or “for example” in the embodiments of the present application should not be interpreted as being more preferred or advantageous than other embodiments or design solutions. Rather, the use of “exemplary” or “for example” is merely intended to present related concepts in a specific manner. The embodiments described below and the features in the embodiments can be combined with each other without conflict, if possible.

[0037] The embodiments of the present application provide a product detection method, device, system and medium. The product detection method can be applied to one or more electronic devices.

[0038] The electronic device and the sanding device can constitute a product detection system, for example, Figure 1 is a schematic diagram of a product detection system provided by an embodiment of the present application. The electronic device 10 can be a server, a computer, a tablet computer, an industrial computer, a mobile phone, etc. The server can be a single server, a server cluster or a cloud server, and the type of the electronic device is not limited in the present application.

[0039] In Figure 1 , the electronic device 10 can be connected with the sanding device 20 through a bus, Bluetooth (BT), wireless fidelity (Wi-Fi) or the like, and the connection mode is not limited in the present application.

[0040] The sanding device 20 can include a device such as a grinding tool and a motor. The motor is used to drive the grinding tool to rotate, and the grinding tool is used for sanding the product. The grinding tool can be a grinding wheel, a sand belt, a paper sanding sheet, etc. The type of grinding tool is not limited in the present application. The sanding device 20 can send sanding data to the electronic device 10 for the electronic device 10 to implement the product detection method provided in the embodiments of the present application.

[0041] If the sanding of the product is detected to be abnormal according to the received sanding data, the electronic device 10 can push the processing data to the sanding device or the terminal. The processing data can be a compensation value of the target polishing force of the sanding device for sanding the product. Through the processing data, the sanding process can be adjusted and optimized to ensure the sanding effect.

[0042] As shown in FIG. 1, it is a flowchart of a product detection method provided in an embodiment of the present application. The order of the steps in the flowchart can be adjusted according to actual requirements, and some steps can be omitted. The product detection method is applied to an electronic device, such as the electronic device 10 shown in FIG. 1. The product detection method includes the following steps: Figure 2 Figure 1

[0043] S11, obtaining specification data and sanding data of a product.

[0044] In some embodiments of the present application, the product can be any type of product, and the type of product is not limited in the present application. For example, the product can be a mobile phone shell, a watch shell, a sound box shell, a computer shell, a vehicle shell, etc.

[0045] In some embodiments of the present application, the specification data can be obtained by the electronic device 1 at the same time as obtaining the sanding data, or before or after obtaining the sanding data. The specification data of the product can include but is not limited to: size information, structure shape information, color information, material information. For example, if the product is a metal frame, the size information can include length, width, height, weight, etc., the structure shape information can include the shape of the edge (for example, a circular arc), the position of the keys such as the power key and the volume key, the position of the interfaces such as the charging port and the earphone hole, the color information can include the type of color (for example, orange) and the color change effect (for example, gradient, etc.).

[0046] In some embodiments of the present application, the electronic device can obtain the specification data of the product by various methods, and the method of obtaining the specification data is not limited in the present application. For example, the electronic device can obtain the specification data by scanning the product, measuring the product, and taking a picture, etc.

[0047] ​​In other embodiments, the electronic device can read text data and / or image data under a preset path as the specification data. The preset path can be customized.

[0048] The sanding processing data can correspond to a single sanding processing or multiple sanding processings. The sanding processing data can include polishing force data. For example, when the sanding processing data corresponds to multiple sanding processings, the sanding processing data can include polishing force data corresponding to each sanding processing.

[0049] The polishing force data is data generated when sanding processing is performed on at least one sanding processing region of the product. The polishing force data includes real polishing force and target polishing force corresponding to multiple time points. The real polishing force is a polishing force value applied to the product by a grinding tool of the sanding device in the actual sanding process, and the grinding tool can be a grinding wheel or the like. The target polishing force is a polishing force value expected to be applied to the product, and the target polishing force can be a polishing force value sent to the sanding device or set on the sanding device before sanding processing.

[0050] The sanding processing region can be one or more. In order to ensure the quality of sanding processing, the product can be divided into multiple sanding processing regions, so that sanding processing of the product can be performed regionally. For example, if the product is a metal frame, the straight edge, the round corner, or a feature region thereof can be sanding processed alternately. For example, the metal frame can be divided into multiple sanding processing regions, for example, the metal frame can be divided into 9 sanding processing regions, and the positions of the 9 sanding processing regions can refer to the positions of the visualization regions of the three-dimensional model as shown in the following Figure 3

[0051] The above examples of specification data and sanding processing data are only examples, and in actual applications, they are not limited thereto. For example, the sanding processing data can also include the rotating speed of the motor in the sanding device and the feed, etc.

[0052] In some embodiments of the present application, the electronic device is in communication connection with the sanding device, and the electronic device can receive data generated when the product is sanding processed by the sanding device, and use the received data as the sanding processing data.

[0053] S12, constructing a three-dimensional model of the product according to the specification data.

[0054] In some embodiments of the present application, the electronic device can construct a three-dimensional model of the product based on the specification data by using a modeling algorithm.

[0055] ​The three-dimensional model can include a visual area corresponding to each sanding processing area. The modeling algorithm includes but is not limited to a constraint-based parametric feature modeling method and a pattern surface modeling method. The modeling method for the three-dimensional model can be implemented by using related technologies, and the embodiments of the present application do not limit this.

[0056] In other embodiments of the present application, when the sanding processing area is multiple, the electronic device can determine an index corresponding to each sanding processing area according to a processing sequence corresponding to the multiple sanding processing areas, and mark the visual area corresponding to the multiple sanding processing areas according to the processing sequence and the index corresponding to each sanding processing area.

[0057] For example, if the product is a metal frame, a three-dimensional model of the metal frame can be constructed according to the specification data of the metal frame. As shown in Figure 3 FIG. 1 is a schematic diagram of a three-dimensional model provided by an embodiment of the present application. Figure 3 The three-dimensional model shown in FIG. 1 is a three-dimensional model of a metal frame. Figure 3 The three-dimensional model in FIG. 1 includes visual areas corresponding to 9 sanding processing areas in the product. The position of each visual area can refer to the index 0, 1, 2, 3, …, 8 in Figure 3 FIG. 1.

[0058] In this embodiment, by modeling the three-dimensional model of the product, and marking the corresponding visual area in the three-dimensional model according to the processing sequence of the sanding processing area and the index corresponding to the sanding processing area, the digital twin of the product and the processing process can be obtained.

[0059] S13, determining the sanding quality score of the product based on the sanding processing data.

[0060] In some embodiments of the present application, the sanding processing performed on each sanding processing area can be single or multiple. The polishing force data in the sanding processing data can be in the form of a signal. For example, based on the above embodiment, if the product includes 9 sanding processing areas, the sanding processing number of each sanding processing area is 5, as shown in Figure 4 FIG. 2 is a schematic diagram of polishing force data provided by an embodiment of the present application. As shown in Figure 5 FIG. 3 is a schematic diagram of polishing force data provided by another embodiment of the present application.

[0061] Figure 4 The polishing force data shown in FIG. 2 corresponds to single sanding processing, Figure 5 The polishing force data shown in FIG. 3 corresponds to multiple sanding processing. Figure 4 The polishing force data shown in FIG. 2 indicates a signal segment corresponding to each sanding processing area. The signal segment corresponding to each sanding processing area can refer to Figure 4The signal ranges corresponding to areas 0, 1...8 are indicated in the diagram. When performing a sanding process on the product, this can be based on... Figure 3 The indexes of the visualized areas correspond to the order in which the nine sanding areas are sanded sequentially. The processing paths for these nine sanding areas form a closed loop (cycle). Therefore... Figure 5 The signal segments corresponding to circles 1, 2...5 represent the grinding force data obtained from one sanding process on the product. The signal segments corresponding to circles 1, 2...5 can be used as a reference. Figure 5 The signal is divided using dashed lines. Figure 4 and Figure 5 In the diagram, the horizontal axis represents a point in time, and the vertical axis represents the grinding force data. Figure 4 and Figure 5 The polishing force data shown can be the actual polishing force.

[0062] In other embodiments of this application, the electronic device can detect grinding force data. When the detected change value between consecutive grinding force data is greater than or equal to a first configured value, the electronic device can identify the consecutive grinding force data in the grinding force data. The first configured value can be customized, and this application does not limit it. For example, the electronic device can use rectangles, circles, or other methods to mark the corresponding consecutive grinding force data that are greater than or equal to the first configured value in the grinding force data.

[0063] In some embodiments of this application, if the sanding data includes grinding force data corresponding to a single sanding operation, step S13 includes:

[0064] S131a: Based on the actual grinding force corresponding to the plurality of time points, determine the actual coefficient of friction between the at least one sanding area and the abrasive and the positive force applied by the abrasive to the at least one sanding area at each time point.

[0065] S132a: Calculate the actual friction force at each time point based on the actual friction coefficient and the positive force corresponding to each time point.

[0066] S133a: Calculate the target friction force at each time point based on the standard friction coefficient and the target grinding force corresponding to each time point.

[0067] S134a: Determine the sanding quality score corresponding to each time point based on the actual friction force and target friction force at each time point.

[0068] The method for determining the real friction coefficient and the corresponding normal force at each time point will be described in detail below. For example, the electronic device can determine the product of the real friction coefficient and the corresponding normal force at each time point as the real friction force at each time point, or the electronic device can determine the product of the first preset weight, the real friction coefficient and the corresponding normal force at each time point as the real friction force at each time point. The first preset weight can be customized, and the present application does not limit this.

[0069] The standard friction coefficient can be customized or determined by the production data of the abrasive tool. The electronic device can determine the product of the standard friction coefficient and the target polishing force corresponding to each time point as the target friction force at each time point, or the electronic device can determine the product of the second preset weight, the standard friction coefficient and the target polishing force corresponding to each time point as the target friction force at each time point. The second preset weight can be customized, and the present application does not limit this.

[0070] Each time point has a corresponding sanding quality score, and the electronic device can determine the difference or weighted difference between the real friction force and the target friction force at each time point as the sanding quality score corresponding to each time point.

[0071] In the present embodiment, the difference or weighted difference between the real friction force and the target friction force at each time point can reflect the gap between the sanding processing effect and the expected effect, so that the difference or weighted difference between the real friction force and the target friction force at each time point is determined as the sanding quality score corresponding to each time point, so that the sanding quality score can accurately reflect the sanding processing quality, and the quantification of the sanding processing quality is realized.

[0072] In other embodiments of the present application, if the sanding processing data includes polishing force data corresponding to multiple sanding processes, S13 determines the sanding quality score of the product based on the sanding processing data, which includes:

[0073] S131b, based on the real polishing force corresponding to the plurality of time points, determines the real friction coefficient between the at least one sanding processing area and the abrasive tool in each sanding process and the normal force applied by the abrasive tool to the at least one sanding processing area at each time point.

[0074] S132b, according to the real friction coefficient and the normal force corresponding to each time point in each sanding process, calculates the real friction force at each time point in each sanding process.

[0075] S133b, calculating the target friction force of each time point in each sanding process according to the standard friction coefficient and the target polishing force corresponding to the time point.

[0076] S134b, determining the initial quality score corresponding to each time point in each sanding process according to the real friction force and the target friction force of the time point.

[0077] S135b, calculating the sanding quality score of each time point according to the plurality of initial quality scores corresponding to each time point in the plurality of sanding processes.

[0078] The determination method of the initial quality score corresponding to each time point can refer to the description of the determination method of the sanding quality score corresponding to each time point, which will not be repeated here.

[0079] For example, the electronic device can determine the average or weighted average of the plurality of initial quality scores corresponding to each time point in the plurality of sanding processes as the sanding quality score of the time point.

[0080] In this embodiment, the average or weighted average of the plurality of initial quality scores corresponding to each time point in the plurality of sanding processes can reflect the overall situation of the sanding effect, so by determining the average or weighted average of the plurality of initial quality scores corresponding to each time point in the plurality of sanding processes as the sanding quality score of the time point, the reliability of the sanding quality score can be ensured.

[0081] Considering that the lengths of the real polishing force data and the target polishing force data may be different due to differences in sampling frequency, sampling duration, etc., the number of initial quality scores of a sanding process in the plurality of sanding processes may be different, which may cause the sanding quality score to be inaccurate. In order to align the number of initial quality scores between the plurality of sanding processes of one product, in some embodiments of the present application, step S13 determines the sanding quality score of the product based on the sanding process data further includes:

[0082] S1341b, counting the number of initial quality scores corresponding to each sanding process.

[0083] Specifically, if the sanding process of one product is 5 circles, the number of initial quality scores of all time points of all sanding areas when each circle of sanding process is performed on the product is counted.

[0084] S1342b, determining whether the number of initial quality scores corresponding to each sanding process is different.

[0085] Specifically, the electronic device determines whether the number of initial quality scores formed by each of the 5 sanding processes is the same.

[0086] In S1343b, if the number of initial quality scores formed by each sanding process is not the same, the number of initial quality scores corresponding to the sanding process with the largest number of initial quality scores is taken as the target number value.

[0087] Specifically, in the 5 sanding processes, the number of initial quality scores formed by one or two sanding processes is different from the number of initial quality scores formed by the other sanding processes. At this time, it is determined which sanding process among the 5 sanding processes has the largest number of initial quality scores. The number of initial quality scores formed by the sanding process with the largest number of initial quality scores is taken as the target number value.

[0088] In S1344b, according to the target number value, interpolation is performed on the initial quality scores other than the initial quality score corresponding to the target number value, so that the same number of initial quality scores is formed by the multiple sanding processes.

[0089] Specifically, the electronic device performs interpolation on the initial quality scores formed by the sanding process that does not reach the target number value.

[0090] The electronic device can perform interpolation by various methods, and the method of interpolation is not limited in the present application.

[0091] For example, the electronic device can calculate an interpolation coefficient by using an interpolation algorithm based on the initial quality score corresponding to each sanding process and the target number value, predict the missing initial quality score according to the interpolation coefficient, associate the predicted initial quality score with the corresponding time point, so that the number of the other initial quality scores matches the target number value, so that the same number of initial quality scores is formed by each sanding process. The interpolation algorithm includes but is not limited to linear interpolation algorithm, spline interpolation algorithm, nearest neighbor interpolation algorithm and polynomial interpolation algorithm. The prediction method of the missing initial quality score can refer to related technologies.

[0092] In the present embodiment, according to the target number value, the electronic device can perform interpolation on the initial quality scores other than the initial quality score corresponding to the target number value, so that the same number of initial quality scores is formed by the multiple sanding processes, thereby ensuring the accuracy of the sanding quality score.

[0093] In other embodiments of the present application, the electronic device can interpolate / zoom the real polishing force data or the target polishing force data, so that the length of the real polishing force data matches the length of the target polishing force data, so that the same number of initial quality scores is formed by the multiple sanding processes.

[0094] The interpolation / scaling of the real polishing force data or the target polishing force data can refer to the description of the method of interpolating the other initial quality scores, which will not be repeated herein.

[0095] S14, based on the sanding quality score, a corresponding first preset mark is obtained, and the three-dimensional model is marked.

[0096] In some embodiments of the present application, the first preset mark can be a visual element such as color, text, icon, or combination. For example, each sanding quality score can have a corresponding color, and the colors corresponding to different sanding quality scores can be different.

[0097] In some embodiments of the present application, the electronic device performs marking processing on the three-dimensional model based on the first preset mark corresponding to the sanding quality score, which includes: determining a visual area corresponding to the at least one sanding area in the three-dimensional model, and marking the visual area according to the first preset mark corresponding to the sanding quality score at each time point.

[0098] In the three-dimensional model as shown in Figure 3 In each visual area, different shades of color correspond to different sanding quality scores. For example, the larger the sanding quality score, the darker or lighter the corresponding color in the visual area.

[0099] In this embodiment, the first preset mark such as color is used to mark the corresponding visual area in the three-dimensional model, which can realize the visualization of the sanding effect.

[0100] S15, based on the sanding quality score, it is determined whether the sanding of the product is abnormal.

[0101] In some embodiments of the present application, the electronic device can determine whether the sanding of the product is abnormal based on the comparison between the sanding quality score and the preset threshold range. The preset threshold range can be customized, which is not limited in the present application.

[0102] For example, when the number of sanding quality scores outside the preset threshold range is greater than or equal to a preset number, the electronic device can determine that the sanding of the product is abnormal, and when the number of sanding quality scores outside the preset threshold range is less than the preset number, the electronic device can determine that the sanding of the product is normal. The preset number can be customized, which is not limited in the present application. For example, the preset number can be 1, 2, or 3.

[0103] In the embodiment, since the sanding processing data can reflect the real polishing force, the target polishing force and other parameters in the sanding process, the sanding quality score can be accurately determined through the sanding processing data. Since the sanding quality score can accurately reflect the sanding processing quality, whether the sanding processing of the product is abnormal can be accurately detected through the sanding quality score, so that the product detection efficiency can be ensured.

[0104] S16, identifying an abnormal area in the three-dimensional model after the marking treatment based on that the sanding processing of the product is abnormal.

[0105] In some embodiments of the present application, S16, identifying an abnormal area in the three-dimensional model after the marking treatment based on that the sanding processing of the product is abnormal, comprises:

[0106] S161, projecting the marked visual area to a preset plane to obtain a projection area.

[0107] S162, determining that the sanding quality score beyond the preset threshold range is an abnormal quality score.

[0108] S163, determining the abnormal area in the projection area and / or the marked visual area according to the abnormal quality score, and framing the abnormal area in the projection area and / or the marked visual area.

[0109] The preset plane can be a two-dimensional plane. In the actual sanding process, the processing position in each sanding processing area of the product has a corresponding time point, so the projection area and / or the marked visual area corresponding to each sanding processing area has a corresponding time point, and the abnormal area can be an area formed by the processing position corresponding to the time point corresponding to the multiple abnormal quality scores in the projection area and / or the marked visual area.

[0110] As shown in Figure 6 , the above embodiment is taken, and if the three-dimensional model comprises nine visual areas, it is a schematic diagram of the projection area provided by an embodiment of the present application. The projection area corresponding to each visual area of the nine visual areas can refer to the area 0, area 1, …, area 8 marked in Figure 6 , the color mark of each projection area matches the color mark of the corresponding visual area, and the shape of each projection area is a rectangle. Figure 6 In the projection area, two abnormal areas are framed.

[0111] In some embodiments of the present application, if the sanding processing of the product is multiple times, the sanding quality score corresponding to each sanding processing can be calculated according to the sanding processing data corresponding to each sanding processing, and the visual area can be marked according to the sanding quality score calculated each time, so when the sanding processing of the product is multiple times, multiple diagrams likeFigure 6 The visualization area and the projection area constitute a region map. For example, when the number of sanding processes of the product is 5, 5 region maps as shown in FIG. 6 can be obtained. Figure 6 The visualization area and the projection area constitute a region map.

[0112] Considering that the projection area is a two-dimensional expansion map of the visualization area, the projection area is more intuitive than the visualization area, and therefore in this embodiment, the abnormal area is framed from the projection area, so that the user can locate the abnormality more quickly and accurately. When it is determined that the sanding process of the product is abnormal, the abnormal position can be intuitively displayed by framing the abnormal area on the three-dimensional model after the marking process, so as to facilitate the user to quickly locate the abnormality.

[0113] In other embodiments of the present application, the product detection method further comprises:

[0114] S17, the polishing force deviation between the real polishing force corresponding to the abnormal quality score and the target polishing force can be determined by using the preset model.

[0115] S18, based on the polishing force deviation, a compensation value of the target polishing force corresponding to the abnormal quality score is calculated by using the preset model, and the compensation value is used for sanding the next product.

[0116] The polishing force deviation can be the difference between the real polishing force and the corresponding target polishing force. The preset model can be a proportional-integral-derivative (PID) controller. The method of calculating the compensation value by using the PID control algorithm can refer to the construction method of the transfer function in the related art.

[0117] In this embodiment, the compensation value of the target polishing force is calculated by the polishing force deviation between the real polishing force and the target polishing force, which can feedback adjust the sanding process of the sanding equipment, so as to improve the sanding effect.

[0118] In the product detection method provided in the embodiment, the specification data of the product can reflect the size, shape, structure and other characteristics of the product, and therefore the three-dimensional model of the product can be accurately constructed according to the specification data. The sanding processing data can reflect the real polishing force, target polishing force and other parameters in the sanding process, and therefore the sanding quality score can be accurately determined through the sanding processing data, so that the sanding quality score can accurately reflect the sanding processing quality. The three-dimensional model is marked by using the first preset mark corresponding to the sanding quality score, and the sanding effect can be intuitively displayed. Since the sanding quality score can accurately reflect the sanding processing quality, the sanding processing of the product can be accurately detected through the sanding quality score, so as to ensure the product detection efficiency. When it is determined that the sanding processing of the product is abnormal, the abnormal area is marked on the three-dimensional model after the marking, and the abnormal position can be intuitively displayed, so as to facilitate the user to quickly locate the abnormality.

[0119] As shown in Figure 7 FIG. 1 is a flowchart of a method for determining a real friction coefficient and a forward force according to an embodiment of the present application. S131b includes the following steps:

[0120] S1311, performing frequency domain transformation on the real polishing force corresponding to the plurality of time points to obtain frequency spectrum data.

[0121] In some embodiments of the present application, the electronic device can use various methods to perform frequency domain transformation on the polishing force data. For example, the electronic device can perform Fourier transformation on the real polishing force corresponding to the plurality of time points to obtain frequency spectrum data.

[0122] S1312, determining the amplitude value corresponding to each frequency in the preset frequency range in the frequency spectrum data.

[0123] In some embodiments of the present application, the preset frequency range can be customized, and the present application does not limit this.

[0124] S1313, calculating the energy corresponding to each frequency according to the amplitude value corresponding to each frequency.

[0125] The electronic device can square the amplitude value corresponding to each frequency as the energy corresponding to each frequency.

[0126] S1314, determining the real friction coefficient according to the energy corresponding to the plurality of frequencies in the preset frequency range.

[0127] In some embodiments of the present application, the preset frequency range can be customized, and the present application does not limit this.

[0128] It is considered that, compared with low-frequency rotation of the motor and the abrasive tool in the sanding device and the like, high-frequency rotation or vibration of the motor and the abrasive tool has a greater impact on sanding processing, and therefore, compared with low-frequency components in the frequency spectrum data, high-frequency components in the frequency spectrum data have a greater impact on sanding processing. In order to select components having a greater impact on sanding processing from the frequency spectrum data, the preset frequency range can be set to be higher.

[0129] In some embodiments of the present application, the electronic device can take the mean or weighted mean of the energy corresponding to all frequencies in the preset frequency range as the real friction coefficient.

[0130] In the present embodiment, by setting the preset frequency range to be higher and taking the mean or weighted mean of the energy corresponding to all frequencies in the preset frequency range as the real friction coefficient, the real friction coefficient can reflect the impact of high-frequency rotation or vibration of the motor and the abrasive tool on sanding processing, thereby ensuring the reliability of the real friction coefficient.

[0131] S1315, filtering the real polishing force corresponding to each time point to obtain a forward force corresponding to each time point.

[0132] In some embodiments of the present application, the filtering of the real polishing force can be low-frequency filtering. The electronic device can perform low-frequency filtering on the real polishing force of each time point to obtain a low-frequency component of the real polishing force, and the electronic device can take the low-frequency component as the forward force.

[0133] It is considered that, compared with high-frequency components, low-frequency components can better reflect the contact state and contact force between the abrasive tool and the product during sanding, and the like. Therefore, in the present embodiment, the real polishing force is filtered by low-frequency filtering, which can remove noise, high-frequency vibration / rotation, cumulative error and the like, thereby ensuring the accuracy of the forward force.

[0134] As shown in FIG. 13, it is a flow chart of a product detection method provided by another embodiment of the present application. The product detection method further includes: Figure 8

[0135] S21, determining a first curve composed of the real polishing force corresponding to each time point, and a second curve composed of the target polishing force corresponding to each time point.

[0136] ​In some embodiments of this application, since each sanding cycle has a corresponding actual sanding force and target sanding force at each time point, the first curve and the second curve can have the same starting point and ending point. The first curve and the second curve can share a coordinate axis so that users can intuitively compare the first curve and the second curve.

[0137] S22, determine the first difference zone and the second difference zone corresponding to each sanding processing area formed by the first curve and the second curve.

[0138] In some embodiments of this application, the first difference zone is where the actual grinding force at each time point during the sanding process of a single product is less than the corresponding target grinding force, and the second difference zone is where the actual grinding force at each time point during the sanding process of a single product is greater than the corresponding target grinding force. S23, the first difference zone and the second difference zone corresponding to each of the sanding processes are visually identified.

[0139] For example, such as Figure 9 The diagram shown is a schematic representation of the first and second difference regions of nine sanding areas after one round of sanding, according to an embodiment of this application. Figure 9 In the diagram, the horizontal axis represents a point in time, and the vertical axis represents the actual grinding force and the target grinding force. Figure 9 In the diagram, the pink curve represents the first curve, and the blue curve represents the second curve. The first difference area of ​​each sanding area of ​​the product is marked as the pink area, and the second difference area of ​​each sanding area of ​​the product can be marked as the green area. Figure 9 The first and second difference areas shown in the image are for illustrative purposes only. The type of visual label can be customized as needed; for example, the first difference area could be labeled in blue, and the second difference area in red.

[0140] In this embodiment, both the first difference region and the second difference region can reflect the difference between the actual polishing force and the corresponding target polishing force.

[0141] Another embodiment of the product testing method in this application further includes:

[0142] S24, based on the first difference area and the second difference area corresponding to each of the sanding processing areas of the product, calculate the first total area of ​​all first difference areas and the second total area of ​​all second difference areas.

[0143] Specifically, if the product sanding process is only one circle, the first total area is calculated by summing up the first difference values of each sanding area after the sanding process of this circle, and the second total area is calculated by summing up the second difference values of each sanding area. If the product sanding process is more than one circle, after the first total area and the second total area of each circle are calculated, the first total area and the second total area of each circle are further summed up to obtain the first total area and the second total area of the overall sanding process of each product.

[0144] S25, calculate the area difference and the area sum between the first total area and the second total area to visualize the area difference and the area sum of each product.

[0145] Figure 10 is a curve diagram provided by an embodiment of the present application to show the area difference and the area sum of each product after sanding. In actual sanding process, the sanding equipment can process multiple products in parallel, so the sanding data of multiple products can be obtained. Based on the detection of the sanding data of multiple products, the area sum and the area difference corresponding to each of the multiple products can be obtained, as shown in Figure 10 The electronic device can generate a third curve (blue curve) according to the area sum corresponding to multiple products and a fourth curve (red curve) according to the area difference corresponding to multiple products, thereby realizing the visualization of the area sum (total_area) and the area difference (area_difference). The third curve and the fourth curve can share the coordinate axis, so that the user can intuitively compare the third curve and the fourth curve. The horizontal axis in the coordinate axis can represent the number or serial number of the product, and the vertical axis can represent the specific numerical value of the area sum and the area difference. The green line represents the reference baseline of the area sum and the area difference of multiple products.

[0146] In this embodiment, the first difference area and the second difference area can reflect the gap between the actual polishing force and the corresponding target polishing force. By calculating the first total area of all first difference areas and the second total area of all second difference areas, and the area difference and the area sum between the first total area and the second total area, the gap between the actual sanding effect and the expected sanding effect can be quantified, so as to facilitate the user to optimize the sanding parameters.

[0147] In other embodiments of the present application, when the difference between the area sum of the third curve and the corresponding area difference of the fourth curve is greater than the second configuration value, the electronic device can identify the area sum from the third curve and the area difference from the fourth curve. For example, the electronic device can identify the area sum and the area difference from the third curve and the fourth curve by using a rectangular frame, a circle, etc. For example, refer to Figure 10 the circle represented by the dashed line in the figure.

[0148] As Figure 11 shown, it is a flow chart of a product detection method provided by another embodiment of the present application. The product detection method further comprises:

[0149] S31, calculating a sanding quality index of the at least one sanding processing area according to the real polishing force and the target polishing force corresponding to the at least one sanding processing area, and / or the first difference area and the second difference area.

[0150] For example, the electronic device can take the standard deviation between the real polishing force and the corresponding target polishing force of any sanding processing area as the sanding quality index of the sanding processing area.

[0151] For example, the electronic device can determine the real polishing force greater than the corresponding target polishing force in the real polishing force of any sanding processing area, and count the sum of all real polishing forces greater than the corresponding target polishing force as the sanding quality index of the sanding processing area.

[0152] For example, the electronic device can determine all real polishing forces less than the corresponding target polishing force in the real polishing force of any sanding processing area, and count the sum of all real polishing forces less than the corresponding target polishing force as the sanding quality index of the sanding processing area.

[0153] For example, the electronic device can take the weighted sum of the area of the determined first difference area and the area of the determined second difference area in the corresponding first difference area and second difference area of any one or more sanding processing areas as the sanding quality index of the sanding processing area. Wherein, the first difference area and the second difference area can refer to the description of step S22 above.

[0154] For example, the electronic device can take the weighted difference of the area of the determined first difference area and the area of the determined second difference area in the corresponding first difference area and second difference area of any one or more sanding processing areas as the sanding quality index of the sanding processing area.

[0155] The above examples of sanding quality indexes are only examples, and in actual applications, they are not limited thereto.

[0156] In this embodiment, the real polishing force and the target polishing force corresponding to the sanding processing area, and / or the first difference area and the second difference area, can determine multiple sanding quality indexes of the sanding processing area, so as to determine whether the sanding processing quality is abnormal in multiple dimensions.

[0157] S32, generating a data table according to the sanding quality index.

[0158] In some embodiments of this application, if the sanding processing area is a single area, the electronic device can generate a data table based on the same type of sanding quality index of the sanding processing area in each sanding process. When there are multiple types of sanding quality indexes, multiple data tables can be obtained. If there are multiple sanding processing areas, the electronic device can generate a data table based on the same type of sanding quality index of multiple sanding processing areas in each sanding process. When there are multiple types of sanding quality indexes, multiple data tables can be obtained.

[0159] S33, if the sanding quality index in the data table includes abnormal quality indexes that are greater than the preset value, the abnormal quality indexes are marked in the data table using the second preset mark.

[0160] The preset values ​​can be customized, and this application does not impose any restrictions on this. When there are multiple data tables, each data table corresponding to a type of sanding quality index can have corresponding preset values, and all data in that data table can be judged uniformly based on the preset values.

[0161] This application does not limit the type of the second preset mark. For example, the second preset mark can be a color such as red or blue, or a shape such as a dotted circle or a square.

[0162] like Figure 12 The diagram shown is a schematic diagram of a data table provided in an embodiment of this application. Figure 12 The data table shown includes sanding quality indicators for nine sanding areas under five sanding processes. Figure 12 In this context, the sanding index corresponding to each sanding area can be the weighted sum of the areas within that sanding area. Each sanding area has a corresponding weighted sum of its area during each sanding process. Figure 12 The weighted sum area marked in red is an abnormal weighted sum area.

[0163] In this embodiment, abnormal quality indicators are marked using a second preset marker such as color, enabling users to quickly locate abnormal quality indicators.

[0164] like Figure 13 The diagram shown is a structural diagram of an electronic device provided in an embodiment of this application. Figure 13 As shown, the electronic device 10 may include a communication module 101, a memory 102, a processor 103, an input / output (I / O) interface 104, and a bus 105. The processor 103 is coupled to the communication module 101, the memory 102, and the input / output interface 104 via the bus 105.

[0165] The communication module 101 can include a wired communication module and / or a wireless communication module. The wired communication module can provide one or more of the following wired communication solutions: universal serial bus (USB), Controller Area Network (CAN) bus, etc. The wireless communication module can provide one or more of the following wireless communication solutions: wireless fidelity, Bluetooth, mobile communication network, frequency modulation (FM), near field communication (NFC), infrared technology (IR), etc.

[0166] The memory 102 can include one or more random access memories (RAMs) and one or more non-volatile memories (NVMs). The random access memory can be directly readable and writable by the processor 103, can be used to store executable programs (e.g., machine instructions) of programs that are running or other programs, and can also be used to store data of users and applications, etc. The random access memory can include static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), etc.

[0167] The non-volatile memory can also store executable programs and store data of users and applications, etc., which can be loaded in advance into the random access memory for direct reading and writing by the processor 103. The non-volatile memory can include a magnetic disk storage device, a flash memory.

[0168] The memory 102 is configured to store one or more computer programs. The one or more computer programs are configured to be executed by the processor 103. The one or more computer programs include a plurality of instructions, which when executed by the processor 103, can implement the product detection method executed on the electronic device 10.

[0169] In other embodiments, as Figure 13The electronic device 10 shown also includes an external memory interface for connecting an external memory, to extend the storage capability of the electronic device 10.

[0170] The processor 103 can include one or more processing units, for example: the processor 103 can include an application processor (AP), a modem processor, a graphics processing unit (GPU), an image signal processor (ISP), a controller, a video codec, a digital signal processor (DSP), and / or a neural-network processing unit (NPU), etc. Among them, different processing units can be independent devices, or can be integrated in one or more processors.

[0171] The processor 103 provides computing and control capabilities, for example, the processor 103 is used to execute the computer program stored in the memory 102 to implement the product detection method described above.

[0172] The input / output interface 104 is used to provide a channel for user input or output, for example, the input / output interface 104 can be used to connect various input / output devices, such as a mouse, a keyboard, a touch device, a display screen, etc., so that the user can enter information, or make the information visualized.

[0173] The bus 105 is used to provide a communication channel between the communication module 101, the memory 102, the processor 103, and the input / output interface 104 in the electronic device 10.

[0174] It can be understood that the structure shown in the embodiments of the present application does not constitute a specific limitation on the electronic device 10. In other embodiments of the present application, the electronic device 10 can include more or fewer components than the illustration, or combine certain components, or split certain components, or different component arrangements. The components shown can be implemented in hardware, software, or a combination of software and hardware.

[0175] The embodiments of the present application also provide a computer readable storage medium, the computer readable storage medium stores a computer program, the computer program includes program instructions, and the method implemented when the program instructions are executed can refer to the method in each of the embodiments of the present application.

[0176] The computer readable storage medium can be an internal storage of the electronic device, such as a hard disk or a memory of the electronic device. The computer readable storage medium can also be an external storage of the electronic device, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, and the like.

[0177] In some embodiments, the computer readable storage medium can include a program storage area and a data storage area. The program storage area can store an operating system, an application required by at least one function, and the like. The data storage area can store data created according to use of the electronic device, and the like.

[0178] It can be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the electronic device. In other embodiments of the present application, the electronic device can include more or fewer components than those illustrated, or combine certain components, or split certain components, or different arrangement of components. The illustrated components can be implemented in hardware, software, or a combination of software and hardware.

[0179] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the modules is only a logical function division. Actual implementation can have another division manner.

[0180] The modules described as separate components can or can not be physically separated, and the components displayed as modules can or can not be physical units, i.e., they can be located in one place, or distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments.

[0181] In addition, the functional modules in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software functional modules.

[0182] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and therefore all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any additional reference signs in the claims should not be considered as limiting the claims involved.

[0183] Furthermore, the term "comprising" does not exclude other elements or steps, and the singular does not exclude the plural and vice-versa, unless the context clearly requires these exclusions. The application can be implemented by means of both soft- and hardware, the elements being either specific integrated circuits (application specific ICs) or parts of software units (e.g. code means) arranged to perform the various functionalities.

[0184] Finally, it should be noted that the above- described embodiments illustrate rather than limit the application, since various modifications and changes can be made thereto by those skilled in the art without departing from the broader spirit and scope of the application as set forth in the appended claims.

Claims

1. A product inspection method characterized by, The method comprises: acquiring sanding processing data of a product; determining a sanding quality score of the product based on the sanding processing data; based on the sanding quality score, acquiring a corresponding first preset mark, and performing mark processing on a three-dimensional model of the product; determining whether the sanding processing of the product is abnormal based on the sanding quality score; based on the sanding processing of the product being abnormal, identifying an abnormal area in the three-dimensional model after the mark processing; the sanding processing data comprises polishing force data corresponding to single sanding processing, the polishing force data is data generated when at least one sanding processing area in the product is processed, the polishing force data comprises real polishing force and target polishing force corresponding to a plurality of time points, and the determination of the sanding quality score of the product based on the sanding processing data comprises: determining a real friction coefficient between the at least one sanding processing area and a grinding tool and a normal force applied by the grinding tool to the at least one sanding processing area at each time point based on the real polishing force corresponding to the plurality of time points, calculating real friction force at each time point according to the real friction coefficient and the normal force corresponding to each time point, calculating target friction force at each time point according to a standard friction coefficient and the target polishing force corresponding to each time point, and determining a sanding quality score corresponding to each time point according to the real friction force and the target friction force at each time point; or the sanding processing data comprises polishing force data corresponding to multiple sanding processing of the product, the polishing force data corresponding to each sanding processing is data generated when at least one sanding processing area in the product is processed, the polishing force data corresponding to each sanding processing comprises real polishing force and target polishing force corresponding to a plurality of time points, and the determination of the sanding quality score of the product based on the sanding processing data comprises: determining a real friction coefficient between the at least one sanding processing area and a grinding tool in each sanding processing and a normal force applied by the grinding tool to the at least one sanding processing area at each time point based on the real polishing force corresponding to the plurality of time points, calculating real friction force at each time point in each sanding processing according to the real friction coefficient and the normal force corresponding to each time point in each sanding processing, calculating target friction force at each time point in each sanding processing according to a standard friction coefficient and the target polishing force corresponding to each time point in each sanding processing, determining an initial quality score corresponding to each time point in each sanding processing according to the real friction force and the target friction force at each time point in each sanding processing, and calculating a sanding quality score of each time point according to a plurality of initial quality scores corresponding to each time point in multiple sanding processing of the product.

2. The product inspection method of claim 1, wherein Further comprising: acquiring specification data of the product; constructing a three-dimensional model of the product according to the specification data.

3. The product inspection method of claim 1, wherein If the sanding data includes polishing force data corresponding to multiple sanding processes of the product, the determining of the sanding quality score of the product based on the sanding data further includes: counting the number of initial quality scores corresponding to each sanding process; determining whether the number of initial quality scores corresponding to each sanding process is different; if the number of initial quality scores corresponding to each sanding process is different, taking the number of initial quality scores corresponding to single sanding process with the largest number as a target number value; performing interpolation processing on initial quality scores other than the initial quality score corresponding to the target number value according to the target number value, so that the multiple sanding processes correspond to the same number of initial quality scores.

4. The product inspection method according to any one of claims 1 to 3, characterized by, The step of determining the real friction coefficient between the at least one sanding area and the grinding tool and the normal force applied by the grinding tool to the at least one sanding area at each time point based on the real polishing force corresponding to the multiple time points includes: performing frequency domain transformation on the real polishing force corresponding to the multiple time points to obtain frequency spectrum data; determining the amplitude value corresponding to each frequency within a preset frequency range in the frequency spectrum data; calculating the energy corresponding to each frequency according to the amplitude value corresponding to each frequency; determining the real friction coefficient according to the energy corresponding to multiple frequencies within the preset frequency range; performing filtering processing on the real polishing force corresponding to each time point to obtain the normal force corresponding to each time point.

5. The product inspection method according to any one of claims 1 to 3, characterized by, The method further includes: determining a first curve composed of the real polishing force corresponding to each time point, and a second curve composed of target polishing force corresponding to each time point; determining a first difference area and a second difference area corresponding to each sanding area composed of the first curve and the second curve, wherein the first difference area is the area where the real polishing force at each time point is less than the corresponding target polishing force when the sanding area of the product is processed, and the second difference area is the area where the real polishing force at each time point is greater than the corresponding target polishing force when the sanding area of the product is processed; visually identifying the first difference area and the second difference area corresponding to each sanding area.

6. The product inspection method of claim 5, wherein The method further includes: based on the first difference area and the second difference area corresponding to each sanding area of the product, calculating a first total area of all first difference areas and a second total area of all second difference areas of the product; calculating the area difference and the area sum between the first total area and the second total area to visualize the area difference and the area sum.

7. The product inspection method of claim 5, wherein The method further includes: calculating the sanding quality index of the at least one sanding area according to the real polishing force and the target polishing force corresponding to the at least one sanding area, and / or the first difference area and the second difference area; generating a data table according to the sanding quality index; if the sanding quality index in the data table includes an abnormal quality index greater than a preset value, marking the abnormal quality index in the data table with a second preset marker.

8. The product inspection method according to any one of claims 1 to 3, characterized by, The marking processing on the three-dimensional model based on the first preset mark corresponding to the sanding quality score comprises: determining a visual area corresponding to the at least one sanding processing area in the three-dimensional model; marking the visual area according to the first preset mark corresponding to the sanding quality score at each time point.

9. The product inspection method of claim 7, wherein, The method further comprises: determining a sanding quality score corresponding to the abnormal area in the three-dimensional model after the marking processing based on the existence of the abnormality in the sanding processing of the product comprises: projecting the marked visual area to a preset plane to obtain a projection area; determining that the sanding quality score outside the preset threshold range is an abnormal quality score; determining the abnormal area in the projection area and / or the marked visual area according to the abnormal quality score; 10. The product inspection method of claim 9, wherein framing the abnormal area in the projection area and / or the marked visual area. The method further comprises: determining a sanding quality score corresponding to the abnormal area in the three-dimensional model after the marking processing based on the existence of the abnormality in the sanding processing of the product comprises:

11. The product inspection method of claim 8, wherein determining a sanding quality score corresponding to the abnormal area in the three-dimensional model after the marking processing based on the existence of the abnormality in the sanding processing of the product comprises: projecting the marked visual area to a preset plane to obtain a projection area; determining that the sanding quality score outside the preset threshold range is an abnormal quality score; 12. An electronic device, comprising: determining the abnormal area in the projection area and / or the marked visual area according to the abnormal quality score; framing the abnormal area in the projection area and / or the marked visual area. The method further comprises:

13. A product inspection system, characterized by determining a sanding quality score corresponding to the abnormal area in the three-dimensional model after the marking processing based on the existence of the abnormality in the sanding processing of the product comprises: determining a sanding quality score corresponding to the abnormal area in the three-dimensional model after the marking processing based on the existence of the abnormality in the sanding processing of the product comprises: projecting the marked visual area to a preset plane to obtain a projection area; 14. A computer-readable storage medium, characterized in that: determining that the sanding quality score outside the preset threshold range is an abnormal quality score; determining the abnormal area in the projection area and / or the marked visual area according to the abnormal quality score; framing the abnormal area in the projection area and / or the marked visual area. The method further comprises: determining a sanding quality score corresponding to the abnormal area in the three-dimensional model after the marking processing based on the existence of the abnormality in the sanding processing of the product comprises: determining a sanding quality score corresponding to the abnormal area in the three-dimensional model after the marking processing based on the existence of the abnormality in the sanding processing of the product comprises: projecting the marked visual area to a preset plane to obtain a projection area; determining that the sanding quality score outside the preset threshold range is an abnormal quality score; determining the abnormal area in the projection area and / or the marked visual area according to the abnormal quality score; framing the abnormal area in the projection area and / or the marked visual area. The method further comprises: determining a sanding quality score corresponding to the abnormal area in the three-dimensional model after the marking processing based on the existence of the abnormality in the sanding processing of the product comprises: determining a sanding quality score corresponding to the abnormal area in the three-dimensional model after the marking processing based on the existence of the abnormality in the sanding processing of the product comprises: projecting the marked visual area to a preset plane to obtain a projection area; determining that the sanding quality score outside the preset threshold range is an abnormal quality score; determining the abnormal area in the projection area and / or the marked visual area according to the abnormal quality score; framing the abnormal area in the projection area and / or the marked visual area. The electronic device comprises: a memory storing at least one instruction; and a processor executing the at least one instruction to implement the product detection method according to any one of claims 1 to 11. The electronic device comprises: a sanding device for sanding the product to generate the sanding processing data; the electronic device according to claim 12, configured to push the processing data to the sanding device based on the existence of the abnormality in the sanding processing of the product. The computer readable storage medium stores at least one instruction, which is executed by the processor in the electronic device to implement the product detection method according to any one of claims 1 to 11.

Images