FFC cable AI defect detection method, system and equipment
By obtaining the real-time image information and machine learning model of the FFC cable, and determining the defect distribution data element, it solves the problem that FFC cable detection is difficult to achieve real-time monitoring on large-scale production lines, improves detection efficiency and consistency, and reduces labor costs.
Patent Information
- Application Number
- CN202411001282.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-25
- Publication Date
- 2024-11-05
- Estimated Expiration
- 2044-07-25
AI Technical Summary
FFC line defect detection is difficult to achieve real-time monitoring on large-scale production lines, and its recognition capability is limited, resulting in low detection efficiency, high labor costs and poor consistency.
By obtaining real-time image information of FFC cables, using the defect identification model obtained by machine learning, we determine the defect distribution data elements, understand the distribution of defects on the spatial and time scales, and thus improve the detection and recognition capabilities and consistency.
It improves the recognition ability and consistency of FFC cable detection, improves detection efficiency, and reduces labor costs.
Smart Images

Figure CN118533848B_ABST
Abstract
Description
Technical Field
[0001] The present application belongs to the technical field of FFC cable detection, and in particular, relates to a FFC cable AI defect detection method, system and device. Background Art
[0002] FFC cable, full name is Flexible Flat Cable, Chinese name is flexible flat cable, is a new type of data cable used for internal connection of electronic equipment. Compared with traditional round wire harness, FFC cable can be wired in narrow space due to its flat shape, which is very suitable for compact electronic products such as mobile phones, laptops, printers, LCD monitors and other internal connections, which can effectively save space.
[0003] Traditional FFC cable defect detection mainly relies on manual visual inspection and some basic physical inspection tools. The detection process lacks unified automated tool support, making it difficult to achieve real-time monitoring on large-scale production lines, and the recognition capability is limited, resulting in low detection efficiency, high labor costs, and poor consistency. Summary of the invention
[0004] The embodiments of the present application provide an FFC cable AI defect detection method, system and device, which can solve the problem that the FFC cable defect detection process is difficult to achieve real-time monitoring on a large-scale production line and has limited recognition capabilities, resulting in low detection efficiency, high labor costs and poor consistency.
[0005] In a first aspect, an embodiment of the present application provides an FFC cable AI defect detection method, comprising:
[0006] Acquire real-time image information of the FFC cable; wherein the real-time image information of the FFC cable is used to reflect the defect of the FFC cable;
[0007] Determine a first defect distribution data element of the FFC cable according to the real-time image information and the defect recognition model of the FFC cable; wherein the defect recognition model is a model obtained by machine learning, and the first defect distribution data element is used to reflect the defect distribution of the FFC cable on a spatial scale;
[0008] Based on the first defect distribution data element of the FFC cable, determining a defect data time node of each of the FFC cables; wherein the defect data time node is used to reflect defect detection time information of the FFC cable;
[0009] Determine a second defect distribution data element of the FFC cable according to the defect data time node of each of the FFC cables and the first defect distribution data element; wherein the second defect distribution data element is used to reflect the defect distribution of the FFC cable on a time scale;
[0010] Determine a defect detection result of the FFC cable according to the first defect distribution data element and the second defect distribution data element; wherein the defect detection result is used to reflect the overall defect status of a preset number of the FFC cables.
[0011] The above technical solutions in the embodiments of the present application have at least the following technical effects:
[0012] The FFC cable AI defect detection method provided in the embodiment of the present application obtains real-time image information of the FFC cable that reflects the defect situation, and determines the first defect distribution data element of the FFC cable based on the real-time image information of the FFC cable and the defect recognition model, so as to understand the defect distribution of the FFC cable on a spatial scale. Based on the first defect distribution data element of the FFC cable, the defect data time node of each FFC cable is determined to understand the defect detection time information of the FFC cable. According to the defect data time node of each FFC cable and the first defect distribution data element, the second defect distribution data element of the FFC cable is determined to understand the defect distribution of the FFC cable on a time scale. Based on the first defect distribution data element and the second defect distribution data element, the defect detection result of the FFC cable is determined to improve the detection and recognition capability and consistency, improve the detection efficiency, and reduce the labor cost.
[0013] In a second aspect, an embodiment of the present application provides an FFC cable AI defect detection system, comprising:
[0014] An acquisition unit, used to acquire real-time image information of the FFC cable; wherein the real-time image information of the FFC cable is used to reflect the defect of the FFC cable;
[0015] A spatial unit, used to determine a first defect distribution data element of the FFC cable according to the real-time image information and a defect recognition model of the FFC cable; wherein the defect recognition model is a model obtained by machine learning, and the first defect distribution data element is used to reflect the defect distribution of the FFC cable on a spatial scale;
[0016] A node unit, used to determine a defect data time node of each FFC cable based on the first defect distribution data element of the FFC cable; wherein the defect data time node is used to reflect defect detection time information of the FFC cable;
[0017] A time unit, used to determine a second defect distribution data element of the FFC cable according to the defect data time node of each of the FFC cables and the first defect distribution data element; wherein the second defect distribution data element is used to reflect the defect distribution of the FFC cable on a time scale;
[0018] A result unit is used to determine a defect detection result of the FFC cable according to the first defect distribution data element and the second defect distribution data element; wherein the defect detection result is used to reflect the overall defect situation of a preset number of the FFC cables.
[0019] In a third aspect, an embodiment of the present application provides an FFC cable AI defect detection device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method described in any one of the above aspects when executing the computer program.
[0020] In a fourth aspect, an embodiment of the present application provides a computer program product. When the computer program product is run on an FFC cable AI defect detection device, the FFC cable AI defect detection device executes the method of any one of the above aspects.
[0021] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant descriptions in the above aspects and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.
[0023] Figure 1 It is a flowchart of an FFC cable AI defect detection method provided by an embodiment of the present application;
[0024] Figure 2 It is a flowchart of step S200 in the FFC cable AI defect detection method provided in one embodiment of the present application;
[0025] Figure 3 is a flow chart of step S210 of the FFC cable AI defect detection method provided by an embodiment of the present application;
[0026] Figure 4 It is a partial flow chart of the FFC cable AI defect detection method provided by one embodiment of the present application;
[0027] Figure 5 is a flowchart of step S220 of the FFC cable AI defect detection method provided by an embodiment of the present application;
[0028] Figure 6 is a flowchart diagram of step S223 of the FFC cable AI defect detection method provided by an embodiment of the present application;
[0029] Figure 7 is a flowchart of step S400 of the FFC cable AI defect detection method provided by an embodiment of the present application;
[0030] Figure 8 is a flow chart of step S500 of the FFC cable AI defect detection method provided by an embodiment of the present application;
[0031] Fig. 9 is a flowchart of step S520 of the FFC cable AI defect detection method provided by an embodiment of the present application;
[0032] Fig.10 It is a structural schematic diagram of an FFC cable AI defect detection system provided by an embodiment of the present application;
[0033] Fig.11 It is a structural schematic diagram of an FFC cable AI defect detection device provided in one embodiment of the present application. DETAILED DESCRIPTION
[0034] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.
[0035] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.
[0036] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.
[0037] As used in the specification of this application and the appended claims, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "if it is determined" or "if the described condition or event is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce the described condition or event is detected" or "in response to detecting the described condition or event" depending on the context.
[0038] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.
[0039] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.
[0040] Traditional FFC cable defect detection mainly relies on manual visual inspection and some basic physical inspection tools. The detection process lacks unified automated tool support, making it difficult to achieve real-time monitoring on large-scale production lines, and the recognition capability is limited, resulting in low detection efficiency, high labor costs, and poor consistency.
[0041] To solve the above problems, the embodiments of the present application provide an AI defect detection method, system and device for FFC cables. In this method, by obtaining real-time image information of the FFC cables used to reflect the defect situation, and based on the real-time image information and defect recognition model of the FFC cables, the first defect distribution data element of the FFC cables is determined to understand the defect distribution of the FFC cables on a spatial scale. Based on the first defect distribution data element of the FFC cables, the defect data time node of each FFC cable is determined to understand the defect detection time information of the FFC cables. According to the defect data time node of each FFC cable and the first defect distribution data element, the second defect distribution data element of the FFC cables is determined to understand the defect distribution of the FFC cables on a time scale. Based on the first defect distribution data element and the second defect distribution data element, the defect detection result of the FFC cables is determined to improve the detection and recognition capabilities and consistency, improve the detection efficiency and reduce labor costs.
[0042] The FFC cable AI defect detection method provided in the embodiment of the present application can be applied to an FFC cable AI defect detection device. At this time, the FFC cable AI defect detection device is the executor of the FFC cable AI defect detection method provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the FFC cable AI defect detection device.
[0043] For example, the FFC cable AI defect detection device can be a variety of intelligent detection devices. The FFC cable AI defect detection device can include, but is not limited to, image acquisition devices (cameras or other imaging devices), computing devices, display devices, etc. The computing devices can be desktop computers, smart large screens, smart TVs, handheld devices with wireless communication functions, computing devices, computers, laptop computers, etc.
[0044] In order to better understand the FFC cable AI defect detection method provided in the embodiment of the present application, the specific implementation process of the FFC cable AI defect detection method provided in the embodiment of the present application is exemplarily introduced below.
[0045] Figure 1 A schematic flow chart of an FFC cable AI defect detection method provided in an embodiment of the present application is shown. The FFC cable AI defect detection method includes:
[0046] S100, obtaining real-time image information of the FFC cable; wherein the real-time image information of the FFC cable is used to reflect the defect of the FFC cable.
[0047] It is understood that real-time images of FFC (flexible flat cable) cables can be obtained using high-resolution camera equipment or machine vision systems. These real-time FFC images are collected by sensors and initially analyzed by image processing software to ensure that the images are clear and free of interference. Camera equipment can be installed above the production line to capture images of FFC cables through continuous shooting. For example, industrial cameras can be used to scan FFC cables to ensure that high-quality image data can be obtained during high-speed movement, which is then transmitted and further processed and analyzed.
[0048] S200, determining a first defect distribution data element of the FFC cable based on real-time image information and a defect recognition model of the FFC cable; wherein the defect recognition model is a model obtained through machine learning, and the first defect distribution data element is used to reflect the defect distribution of the FFC cable on a spatial scale.
[0049] It can be understood that the first defect distribution data element can be determined based on the real-time image information and the defect recognition model. The defect recognition model is obtained by training through machine learning technology, and can effectively identify and classify different types of defects, such as fractures, scratches or contamination. The first defect distribution data element is a data set that reflects the defect distribution of the FFC cable on a spatial scale, determined by analyzing the real-time image information of the FFC cable and the output results of the defect recognition model. The first defect distribution data element is the basic data that constitutes the first defect distribution data element, and contains detailed defect information detected by a single FFC cable. The real-time image information can be input into the defect recognition model, and the model outputs specific information of each defect in the image, such as the type, location and severity of the defect, through techniques such as feature extraction and pattern matching. Then, the defect of the FFC cable is determined based on these output results, and the spatial relationship between various defects is calculated through a preset algorithm, and finally the first defect distribution data element is generated. For example, a convolutional neural network (CNN) can be used to process the image, extract image features, and identify the location and type of different defects through a trained model.
[0050] Exemplarily, the defect recognition model can be obtained through data collection, model selection, and model training. Data collection is the first step in model training. By acquiring a large number of FFC cable images, these images should include different types of defects, such as breaks, scratches, contamination, etc., as well as normal defect-free images. By manually annotating the defect location and type in each image, a labeled data set for training is generated. One or more candidate models are selected based on the characteristics of the task and existing experience. Commonly used models include convolutional neural networks (CNN), ResNet, VGG, Inception, etc. Design a suitable network architecture, determine the number of layers of the model, the number of neurons in each layer, the activation function, etc. The following is an example of defect recognition using a convolutional neural network (CNN):
[0051] 100,000 FFC cable images were collected from the camera on the production line, including various defect types and defect-free images. All images were annotated, rotated, flipped, and normalized to obtain 200,000 preprocessed images. ResNet50 was selected as the preliminary model architecture. The dataset was divided into training set, validation set, and test set in a ratio of 8:1:1. The model was trained using the cross entropy loss function and the Adam optimizer, and the initial learning rate was set to 0.001. The learning rate was adjusted according to the performance of the validation set after each epoch, and a total of 50 epochs were trained. The model performance was evaluated on the validation set, and the accuracy, precision, recall, and F1-score were 98%, 97%, 96%, and 96.5%. The L2 regularization and dropout methods were used to further optimize the model to prevent overfitting. The trained model was deployed to the production line for real-time defect detection.
[0052] In one possible implementation, see Figure 2 S200, determining a first defect distribution data element of the FFC cable according to the real-time image information and the defect recognition model of the FFC cable, including:
[0053] S210, determining a defect condition of the FFC cable according to the real-time image information of the FFC cable and a defect recognition model.
[0054] It can be understood that by inputting real-time image information into a pre-trained defect recognition model, the model will output information including defect type and location. The output information including defect type and location will be further processed to generate a comprehensive defect situation report. For example, during the production process, the real-time collected image is immediately input into the model, and the model quickly returns the recognition result, outputting which parts have defects, as well as the specific nature and location of these defects.
[0055] Optionally, see Figure 3 S210, determining the defect of the FFC cable according to the real-time image information and the defect recognition model, including:
[0056] S211, inputting the real-time image information of the FFC cable into the defect recognition model to obtain an output result of the defect recognition model.
[0057] It can be understood that real-time image information will be input into the trained defect recognition model. The defect recognition model performs operations such as feature extraction and pattern recognition on the image, and the output results include the type, location and severity of each defect. For example, when image information is input into the convolutional defect recognition model, the defect recognition model will identify the defects in the image and return an output result including the location and type of the defect.
[0058] S212, determining the defect status of the FFC cable according to the output result of the defect recognition model.
[0059] It is understood that the output of the defect recognition model can be analyzed by a preset algorithm to determine the specific situation of each defect. Based on the output, a detailed defect report is generated, including the type, location and severity of each defect. For example, a table or image markup is generated based on the model output to clearly display the specific information of each defect and quickly understand the defect distribution.
[0060] Optionally, the FFC cable AI defect detection method further includes:
[0061] S600, determining a quality inspection result of the FFC cable according to a defect condition of the FFC cable.
[0062] It can be understood that, according to the output results obtained from the defect recognition model, the output results include the type of defect (such as physical damage, insulation layer damage, etc.), location coordinates (precise location on the FFC cable), and preliminary severity score (which can be based on area size, degree of impact on circuit function, etc.). According to the application standards and quality requirements of the FFC cable, the tolerance threshold can be pre-set, such as the maximum number of defects allowed, the maximum acceptable defect size, and specific types of defects that are not allowed to appear, to determine the quality of a single FFC cable inspection. The quality inspection results of the FFC cable can be determined by, for example, using rule-based algorithms, statistical analysis methods, or data mining techniques to parse and classify the output data.
[0063] S700: When the quality inspection result of the FFC cable does not meet the preset quality requirements, a defect prompt message is triggered.
[0064] It can be understood that, by using a rule-based algorithm, if the severity of any defect exceeds the preset threshold, it is judged as unqualified; or by using a statistical analysis method, the total number of defects, average severity and other indicators are calculated and compared with the standard. A comprehensive judgment is made by combining all defect information and preset standards in a single test. If the number of defects is small, the distribution is sparse and does not seriously affect the function, it may be judged as qualified; conversely, if there are serious or concentrated defects, it is judged as unqualified. According to the quality test results of the analyzed FFC cable, if the test results are unqualified, the defect prompt information is triggered. The prompt information can be transmitted in a variety of ways. For example, by starting the sound and light alarm device, SMS, email or production management system to send notifications, interface prompts, etc. By effectively detecting and evaluating the quality of a single FFC cable, the defect prompt information is triggered in time when the test results are unqualified, ensuring quality control and timely response in the production process, and feedback to the production line for adjustment and optimization, while continuously iterating the defect recognition model to improve detection accuracy and efficiency.
[0065] S220, based on the defect condition of the FFC cable, obtaining first defect distribution data of the FFC cable; wherein the first defect distribution data is basic data constituting a first defect distribution data element.
[0066] It can be understood that the first defect distribution data of the FFC cable can be generated based on the determined defect situation. These data are displayed by analyzing the spatial distribution, type and density of each defect. First, the specific type and spatial position of each defect are determined, and then displayed on the preset defect space based on this information, and the spatial distance of all defects is calculated. Defect space refers to a multi-dimensional virtual space constructed in the process of detecting FFC cables to accurately describe and analyze the distribution of defects. In this space, each point or area represents a specific position on the FFC cable and its corresponding defect information. The defect space is mainly used to reflect the type, position, density and distribution of defects on the FFC cable, to help identify possible problems in the production process and to perform quality control and optimization. Each identified defect is marked in a two-dimensional coordinate system, and the distance between each defect is calculated to understand the concentrated distribution area and density distribution of the defects.
[0067] Optionally, see Figure 5 , S220, based on the defect condition of the FFC cable, obtaining first defect distribution data of the FFC cable, including:
[0068] S221, based on the defect condition of the FFC cable, determining the defect type and spatial position information of each defect of the FFC cable; wherein the spatial position information is used to reflect the spatial position of each defect of the FFC cable on the FFC cable.
[0069] It can be understood that the type and exact position on the FFC cable can be determined based on the specific information of each defect. The defect detection output includes the type of defect (such as physical damage, insulation layer damage, etc.), the position coordinates (the exact position on the FFC cable), and a table or image mark can be generated to clearly display the specific information of each defect. For example, the starting and ending positions of each defect on the cable, as well as its type, such as scratches or breaks, are recorded for subsequent defect distribution analysis. The spatial position information can be determined by the position coordinates through mapping or association algorithms, which is the specific mapping of the defect position coordinates in subsequent analysis.
[0070] S222, based on the defect types and spatial position information of all defects of the FFC cable, the defect types and spatial position information are displayed on a preset defect space, and the spatial distances of all defects in the defect space are calculated; wherein the defect space is used to reflect the spatial structure of the FFC cable.
[0071] It can be understood that all defect information can be mapped to a preset defect space (which can be a two-dimensional or three-dimensional space), and the spatial distance between each defect can be calculated to understand the aggregation and distribution of defects. Defect space refers to a multi-dimensional virtual space constructed in the process of detecting FFC cables to accurately describe and analyze the distribution of defects. For example, the defect information is displayed on the expansion diagram of the cable, and the distance between each two defects is calculated.
[0072] S223, obtaining first defect distribution data of the FFC cable according to the spatial distances of all defects in the defect space.
[0073] It can be understood that the distribution of each defect in the defect space can be analyzed by a preset algorithm, and the distance between defects can be calculated to analyze the area where defects are concentrated, determine the location and range of the high-incidence area of defects, and generate the first defect distribution data. The first defect distribution data refers to a comprehensive data set that systematically describes the defect distribution of the FFC cable on a spatial scale by analyzing the real-time image information of the FFC cable and combining the output results of the defect recognition model.
[0074] For example, see Figure 6 , S223, obtaining first defect distribution data of the FFC cable according to the spatial distances of all defects in the defect space, including:
[0075] S2231, dividing the defect space into a plurality of sub-defect spaces according to the spatial distances of all defects in the defect space, and calculating the number of defects in each sub-defect space.
[0076] It can be understood that the defect space can be divided into multiple sub-areas, and the number of defects in each sub-area can be counted to analyze the defect distribution in more detail. It can be a dynamic method based on a clustering algorithm or a dynamic grid method. Taking K-means clustering as an example, the number of clusters can be dynamically determined. A suitable K value (i.e., the number of sub-defect spaces) can be preliminarily estimated based on experience or through methods such as the Elbow Method, and the K value can be continuously adjusted in multiple iterations until a suitable division effect is achieved. K initial cluster centers can be obtained according to the preset K value. These initial cluster centers should be located around the defect point or selected according to the defined heuristic method. According to the spatial distance of all defects in the defect space, each defect point is assigned to the subspace (cluster) where the nearest cluster center is located. The new center of each subspace (cluster) is calculated, which is usually the coordinate mean of all points in the subspace. The K value is iterated until the cluster center no longer changes significantly or the preset maximum number of iterations is reached. Density-based clustering algorithms such as DBSCAN (Density-Based Spatial Clustering of Applications with Noise) can also be used. DBSCAN does not pre-specify the number of clusters (subspaces), but automatically discovers high-density areas based on the neighborhood density of data points to form clusters, while identifying noise points in low-density areas. This method is very suitable for data sets with uneven distribution and complex structures.
[0077] Exemplarily, the DBSCAN algorithm first defines the neighborhood radius (eps), that is, sets a distance threshold to define the "proximity" relationship between data points. A minimum number of points (MinPts) is determined to specify the minimum number of points in the domain required to constitute a core object. Based on the spatial distance of each defect, each defect is traversed. If a defect's ε-neighborhood contains at least MinPts points, it is marked as a core point; for any data point X, its ε-neighborhood refers to the set of all other data points whose distance from X does not exceed ε. For example, if the distance between sample point A and sample point B is less than ε, then sample A is in the ε-neighborhood of sample B. If there are less than MinPts points, it is marked as a boundary point; if it is neither a core point nor a boundary point, it is marked as a noise point. Starting from any unvisited core point, all points in its ε-neighborhood are used as starting points, and other core points in the neighborhood are recursively searched to form a cluster. This process is repeated until all core points are visited. The DBSCAN algorithm automatically discovers the clustering structure based on the provided eps and MinPts parameters each time it runs, without the need to pre-specify the number of clusters. Therefore, the iterative process is more about adjusting parameters rather than directly increasing or decreasing the clustering results.
[0078] S2232, based on the result of calculating the number of defects in each sub-defect space, taking the sub-defect space with the largest number of defects as the first sub-defect space.
[0079] It can be understood that according to the result of dividing the defect space into multiple sub-defect spaces, the sub-area with the largest number of defects is found as the first sub-defect space that is focused on. A 10 cm area with the largest number of defects is found in the statistical results and marked as the first sub-defect space.
[0080] S2233, determining a unit space defect density of the first sub-defect space according to the number of defects in the first sub-defect space, and using the unit space defect density as first defect distribution data of the FFC cable.
[0081] It can be understood that the defect density in the first sub-defect space can be calculated by a preset algorithm (defect density = number of defects / unit area), and the value of the defect density is used as a key indicator of the first defect distribution data. For example, if there are 20 defects in the first sub-defect space, and the length and width of the area are both 10 cm, then the defect density per unit space is 0.2 defects / 1 square centimeter.
[0082] S230 , determining a first defect distribution data element of the FFC cable according to the first defect distribution data of the FFC cable.
[0083] It is understandable that when the number of continuously detected FFC cables reaches a preset value, the first defect distribution data of these cables can be collected to form a comprehensive first defect distribution data element. In this way, a certain period of time or a certain number of FFC cables can be evaluated as a whole to find potential systemic problems. For example, in a production cycle, the defect data of 50 FFC cables detected are integrated to form a comprehensive data to better analyze and guide subsequent production improvements and quality control.
[0084] Optionally, S230, determining a first defect distribution data element of the FFC cable according to the first defect distribution data of the FFC cable, includes:
[0085] S231, when the number of continuously detected FFC cables reaches a preset number, a set of first defect distribution data of the FFC cables is established according to the first defect distribution data of the preset number of FFC cables, and the set of first defect distribution data of the FFC cables is used as a first defect distribution data element.
[0086] It can be understood that when the number of continuously inspected FFC cables reaches a preset value, the first defect distribution data sets of these cables are collected to form a comprehensive first defect distribution data element. After the preset number of first defect distribution data are collected, a data table or database is established to store and process these data to obtain a data set constructed by the first defect distribution data. For example, in a production cycle, 100 FFC cables are continuously inspected, and the defect data of these cables are integrated into a data set for subsequent analysis of the overall defect distribution.
[0087] S300, determining a defect data time node of each FFC cable based on a first defect distribution data element of the FFC cable; wherein the defect data time node is used to reflect defect detection time information of the FFC cable.
[0088] It can be understood that the defect data time node of each FFC cable can be determined based on the first defect distribution data element, and the defect data time node of each FFC cable reflects the specific time when each FFC cable detects a defect. This can be achieved by recording the timestamp of each detection in the image processing system. For example, when a new FFC cable is detected to have a defect, the current time is automatically recorded, and the time is associated with the defect data to generate a time node log.
[0089] S400, determining a second defect distribution data element of the FFC cable according to the defect data time node of each FFC cable and the first defect distribution data element; wherein the second defect distribution data element is used to reflect the defect distribution of the FFC cable on a time scale.
[0090] It can be understood that the first defect distribution data element is combined with each defect data time node, and multiple time sub-segments are displayed and divided through a preset time axis to analyze the changes in defects in each time sub-segment. By comparing the maximum and minimum defect distribution data in each time sub-segment, the second defect distribution data of the time sub-segment is determined, and the second defect distribution data element is constructed to identify the time pattern of defects in the production process. For example, the defect data is divided by hours, the change in the number of defects per hour is analyzed, and the time period in which problems may occur in the production process is found. The second defect distribution data is the basic data that constitutes the second defect distribution data, which contains detailed information on the defect distribution of the FFC cable in a specific time period. The second defect distribution data is a data set determined based on the defect data time node of each FFC cable and the first defect distribution data element to describe the defect distribution of the FFC cable on a time scale, and is used to analyze and reflect the defect changes of the FFC cable in different time periods.
[0091] In one possible implementation, see Figure 7S400, determining a second defect distribution data element of the FFC cable according to the defect data time node of each FFC cable and the first defect distribution data element, including:
[0092] S410, according to the defect data time node of each FFC cable and the first defect distribution data element, the first defect distribution data element is displayed on a preset time axis according to the defect data time node, and the preset time axis is divided into multiple time sub-segments according to a preset time distance; wherein the time distance is used to reflect the detection time difference of the FFC cable.
[0093] It can be understood that the first defect distribution data element can be displayed on the time axis according to the time node, and the time sub-segments can be divided according to the preset time distance. The preset time axis refers to a reference axis or timeline predefined in the time dimension, which is used to analyze and record the changes of events or data over time. The time series analysis method can be used to ensure the rationality and effectiveness of the time sub-segment division. For example, a 24-hour day is divided into 24 time periods, and the defect distribution data within one hour is analyzed in each time period.
[0094] S420, based on all the first defect distribution data in the first defect distribution data element and multiple time sub-segments, determine the difference between the maximum first defect distribution data and the minimum first defect distribution data of each time sub-segment, and use the difference between the maximum first defect distribution data and the minimum first defect distribution data as the second defect distribution data of the time sub-segment; wherein the second defect distribution data is used to reflect the characteristics of the defect situation in the time sub-segment changing over time.
[0095] It can be understood that the first defect distribution data in each time sub-segment can be compared, the maximum and minimum first defect distribution data can be found, and the difference between them can be calculated as the second defect distribution data of the time sub-segment. This data reflects the fluctuation of the defect distribution in the time sub-segment. For example, in a time sub-segment of one hour, the difference between the maximum first defect distribution data and the minimum first defect distribution data is found as the fluctuation data of the hour, and the second defect distribution data of the time sub-segment is obtained. The difference between the maximum first defect distribution data and the minimum first defect distribution data reflects the change of defect data between the FFC cable with the largest defect density and the FFC cable with the smallest defect density in the time period, reflecting the characteristics of the defect situation changing over time in the time sub-segment.
[0096] S430, determining a second defect distribution data element of the FFC cable on a preset time axis based on the second defect distribution data of each time sub-segment.
[0097] It can be understood that the overall second defect distribution data element is generated based on the second defect distribution data of each time sub-segment. The second defect distribution data element reflects the defect distribution on the entire time axis and can help analyze the time variation pattern in the production process. For example, the second defect distribution data of all time sub-segments within 24 hours are integrated to generate a comprehensive data set, that is, the second defect distribution data element is obtained to determine the overall fluctuation of the defect distribution within a day.
[0098] S500, determining a defect detection result of the FFC cable according to the first defect distribution data element and the second defect distribution data element; wherein the defect detection result is used to reflect the overall defect status of a preset number of FFC cables.
[0099] It can be understood that the defect detection result of the FFC cable can be determined based on the first defect distribution data element and the second defect distribution data element. The defect detection result comprehensively considers the defect distribution in both spatial and temporal dimensions to provide a comprehensive defect assessment. The spatial and temporal defect components can be calculated separately, and then the overall defect assessment value can be calculated based on these components. For example, by analyzing the defect data at different locations and time periods on the production line, an estimated score and a comprehensive report are generated to show which areas and time periods have a higher defect incidence rate, and an overall defect detection rating is obtained.
[0100] In one possible implementation, see Figure 8 S500, determining a defect detection result of the FFC cable according to the first defect distribution data element and the second defect distribution data element, including:
[0101] S510, based on the first defect distribution data element and the second defect distribution data element, determine the spatial defect component and the temporal defect component of the FFC cable; wherein the spatial defect component is used to reflect the defect assessment data of the spatial scale of the FFC cable, and the temporal defect component is used to reflect the defect assessment data of the temporal scale of the FFC cable.
[0102] It can be understood that the spatial defect component of the FFC cable can be calculated by the first defect distribution data element, and the temporal defect component of the FFC cable can be calculated by the second defect distribution data element. The spatial defect component reflects the overall evaluation level of defects in the spatial dimension, and the temporal defect component reflects the overall evaluation level of defects in the temporal dimension. The quality index of the overall spatial defect component and the temporal defect component can be calculated by weighted average method or machine model method.
[0103] For example, the weighted average method can assign a weight to each sub-region , the weight can be set according to the importance or area of the sub-region (the first sub-defect space of each FFC cable). Usually, the weight can be set as the relative proportion of the area of all sub-regions, that is:
[0104]
[0105] in, is the area of the subregion, is the total number of sub-regions, is the sum of all subspace areas. Similarly, the temporal defect component can also be calculated using a similar formula. According to the weighted average method, the defect density of each sub-area is weighted averaged to obtain the overall spatial defect evaluation value. This overall spatial defect evaluation value is used to replace the defect density of the inspection batch. The calculation formula for the overall spatial defect component S is:
[0106]
[0107] in, Represents the value of the i-th first defect distribution data, and pre-builds a scoring table to map different spatial defect components corresponding to different S values to quality indices according to the specific value of S. For example:
[0108] 0-1 defect / cm² corresponds to 100 points
[0109] 1-2 defects / cm², corresponding to 80 points
[0110] 2-3 defects / cm², corresponding to 60 points
[0111] 3-4 defects / cm², corresponding to 40 points
[0112] 4-5 defects / cm², corresponding to 20 points
[0113] 5 defects / cm² corresponds to 0 points
[0114] According to this table, you can directly look up the corresponding score, so as to systematically evaluate the spatial defect distribution of FFC cables and accurately determine their quality inspection results. Similarly, for the quality index of the time defect component, the same algorithm can be used to weight the change data of different time sub-segments to obtain the average value, and finally obtain the quality index of the time defect component.
[0115] The machine learning method can use the defect density and evaluation level of all sub-areas as features for the data set of the machine learning model. Use machine learning algorithms such as regression analysis, decision trees, neural networks, etc. for training to predict the quality index of defect components. Evaluate the prediction ability and accuracy of the model and select the most suitable model for quality index prediction. Use the trained model to predict new data and obtain the overall spatial defect component and temporal defect component quality index.
[0116] S520, determining a defect detection result of the FFC cable according to a spatial defect component and a temporal defect component of the FFC cable.
[0117] It can be understood that the spatial defect component and the temporal defect component are integrated to generate the overall defect detection result. The defect detection result reflects the defect distribution of the FFC cable in the two dimensions of space and time. For example, the defect components in the two dimensions of space and time are weighted and integrated to generate a comprehensive defect evaluation value, and the defect evaluation value is mapped to an evaluation level as the final detection result.
[0118] Optionally, see Fig. 9 S520, determining a defect detection result of the FFC cable according to a spatial defect component and a temporal defect component of the FFC cable, including:
[0119] S521, determining a defect evaluation value of the FFC cable according to a spatial defect component and a temporal defect component of the FFC cable.
[0120] It can be understood that the comprehensive defect evaluation value of the FFC cable can be calculated based on the spatial defect component and the temporal defect component. This evaluation value can be used to compare the quality of different batches of FFC cables and guide production improvements. For example, through the weighted average method, the spatial and temporal defect components are combined into a comprehensive evaluation value, namely the defect evaluation value, as a key indicator of the quality of the FFC cable. The spatial defect component S and the temporal defect component T are weighted and synthesized to obtain a comprehensive defect evaluation value Q. Then there is a formula Q=α*S+β*T, where α and β are the preset weight coefficients of the spatial and temporal defect components, and the sum of these two coefficients is 1 (i.e., α+β=1).
[0121] S522, determining a defect detection result of the FFC cable based on the defect evaluation value of the FFC cable.
[0122] Exemplarily, based on the comprehensive defect evaluation value, an evaluation level can be mapped as the final defect detection result. The defect detection result can be used to determine whether the FFC cable is qualified and provide improvement suggestions. For example, a quality standard is set according to the comprehensive evaluation value Q. If the evaluation value is lower than 60, the FFC cable is judged to be unqualified and a corresponding quality report is generated; if the evaluation value is 60-80, the FFC cable is judged to be qualified; if the evaluation value is 81-90, the FFC cable is judged to be good; if the evaluation value is 90-100, the FFC cable is judged to be excellent. Finally, through the intelligent recognition and analysis process, the defect recognition ability of the FFC cable is improved, the detection efficiency is improved, the labor cost is reduced, and the detection uniformity is increased.
[0123] Corresponding to the FFC cable AI defect detection method of the above embodiment, the embodiment of the present application further provides an FFC cable AI defect detection system, and each unit of the system can implement each step of the FFC cable AI defect detection method. Fig.10 The structural block diagram of the FFC cable AI defect detection system provided in the embodiment of the present application is shown. For the convenience of explanation, only the parts related to the embodiment of the present application are shown.
[0124] Reference Fig.10 , the FFC cable AI defect detection system includes:
[0125] An acquisition unit, used to acquire real-time image information of the FFC cable; wherein the real-time image information of the FFC cable is used to reflect the defect of the FFC cable;
[0126] A spatial unit, used to determine a first defect distribution data element of the FFC cable according to the real-time image information and a defect recognition model of the FFC cable; wherein the defect recognition model is a model obtained by machine learning, and the first defect distribution data element is used to reflect the defect distribution of the FFC cable on a spatial scale;
[0127] A node unit, used to determine a defect data time node of each FFC cable based on the first defect distribution data element of the FFC cable; wherein the defect data time node is used to reflect defect detection time information of the FFC cable;
[0128] A time unit, used to determine a second defect distribution data element of the FFC cable according to the defect data time node of each of the FFC cables and the first defect distribution data element; wherein the second defect distribution data element is used to reflect the defect distribution of the FFC cable on a time scale;
[0129] A result unit is used to determine a defect detection result of the FFC cable according to the first defect distribution data element and the second defect distribution data element; wherein the defect detection result is used to reflect the overall defect situation of a preset number of the FFC cables.
[0130] It should be noted that the information interaction, execution process, etc. between the above-mentioned systems / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.
[0131] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit module can exist physically separately, or two or more unit modules can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.
[0132] The present application also provides an FFC cable AI defect detection device. Fig.11 This is a schematic diagram of the structure of an FFC cable AI defect detection device provided in one embodiment of the present application. Fig.11 As shown, the FFC cable AI defect detection device 6 of this embodiment includes: at least one processor 60 ( Fig.11 Only one is shown), at least one memory 61 ( Fig.11 Only one is shown in the figure) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the FFC cable AI defect detection device 6 implements the steps in any of the above-mentioned FFC cable AI defect detection method embodiments, or the FFC cable AI defect detection device 6 implements the functions of each unit in the above-mentioned system embodiments.
[0133] Exemplarily, the computer program 62 may be divided into one or more units, which are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 62 in the FFC cable AI defect detection device 6.
[0134] The FFC cable AI defect detection device can be a variety of intelligent detection devices. The FFC cable AI defect detection device can include, but is not limited to, an image acquisition device (camera or other imaging device), a computing device, a display device, etc. The computing device of the FFC cable AI defect detection device can include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that Fig.11 It is only an example of the FFC cable AI defect detection device 6 and does not constitute a limitation of the FFC cable AI defect detection device 6. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, buses, etc.
[0135] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.
[0136] In some embodiments, the memory 61 may be an internal storage unit of the FFC cable AI defect detection device 6, such as a hard disk or memory of the FFC cable AI defect detection device 6. In other embodiments, the memory 61 may also be an external storage device of the FFC cable AI defect detection device 6, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the FFC cable AI defect detection device 6. Further, the memory 61 may also include both the internal storage unit of the FFC cable AI defect detection device 6 and an external storage device. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 61 may also be used to temporarily store data that has been output or is to be output.
[0137] An embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.
[0138] An embodiment of the present application provides a computer program product. When the computer program product runs on an FFC cable AI defect detection device, the FFC cable AI defect detection device implements the steps in any of the above method embodiments.
[0139] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the FFC cable AI defect detection device, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, RandomAccess Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.
[0140] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0141] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.
[0142] In the embodiments provided in the present application, it should be understood that the disclosed FFC cable AI defect detection system / FFC cable AI defect detection device and method can be implemented in other ways. For example, the FFC cable AI defect detection system / FFC cable AI defect detection device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.
[0143] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0144] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.
Claims
1. A FFC cable AI defect detection method, characterized in that: include: Acquire real-time image information of the FFC cable; wherein the real-time image information of the FFC cable is used to reflect the defect of the FFC cable; Determine a first defect distribution data element of the FFC cable according to the real-time image information and the defect recognition model of the FFC cable; wherein the defect recognition model is a model obtained by machine learning, and the first defect distribution data element is used to reflect the defect distribution of the FFC cable on a spatial scale; Based on the first defect distribution data element of the FFC cable, determining a defect data time node of each of the FFC cables; wherein the defect data time node is used to reflect defect detection time information of the FFC cable; Determine a second defect distribution data element of the FFC cable according to the defect data time node of each of the FFC cables and the first defect distribution data element; wherein the second defect distribution data element is used to reflect the defect distribution of the FFC cable on a time scale; Determine a defect detection result of the FFC cable according to the first defect distribution data element and the second defect distribution data element; wherein the defect detection result is used to reflect the overall defect status of a preset number of the FFC cables; The determining, based on the real-time image information and the defect recognition model of the FFC cable, a first defect distribution data element of the FFC cable comprises: Determine the defect of the FFC cable according to the real-time image information and the defect recognition model of the FFC cable; Based on the defect condition of the FFC cable, first defect distribution data of the FFC cable is obtained; wherein the first defect distribution data is basic data constituting a first defect distribution data element; Determining a first defect distribution data element of the FFC cable according to the first defect distribution data of the FFC cable; The obtaining first defect distribution data of the FFC cable based on the defect condition of the FFC cable comprises: Based on the defect condition of the FFC cable, determine the defect type and spatial position information of each defect of the FFC cable; wherein the spatial position information is used to reflect the spatial position of each defect of the FFC cable on the FFC cable; According to the defect types and the spatial position information of all defects of the FFC cable, the defect types and the spatial position information are displayed on a preset defect space, and the spatial distances of all defects in the defect space are calculated; wherein the defect space is used to reflect the spatial structure of the FFC cable; Obtaining first defect distribution data of the FFC cable according to the spatial distances of all defects in the defect space; The obtaining first defect distribution data of the FFC cable according to the spatial distances of all defects in the defect space includes: Dividing the defect space into a plurality of sub-defect spaces according to the spatial distances of all defects in the defect space, and calculating the number of defects in each of the sub-defect spaces; Based on the result of calculating the number of defects in each of the sub-defect spaces, taking the sub-defect space with the largest number of defects as the first sub-defect space; Determine a unit space defect density of the first sub-defect space according to the number of defects in the first sub-defect space, and use the unit space defect density as first defect distribution data of the FFC cable; The determining, according to the first defect distribution data of the FFC cable, a first defect distribution data element of the FFC cable comprises: When the number of the FFC cables continuously detected reaches a preset number, a set of the first defect distribution data of the FFC cables is established according to the preset number of the first defect distribution data of the FFC cables, and the set of the first defect distribution data of the FFC cables is used as a first defect distribution data element; The determining, according to the defect data time node of each FFC cable and the first defect distribution data element, the second defect distribution data element of the FFC cable comprises: According to the defect data time node of each FFC cable and the first defect distribution data element, the first defect distribution data element is displayed on a preset time axis according to the defect data time node, and the preset time axis is divided into a plurality of time sub-segments according to a preset time distance; wherein the time distance is used to reflect the detection time difference of the FFC cable; Determine the difference between the maximum first defect distribution data and the minimum first defect distribution data of each time sub-segment according to all the first defect distribution data in the first defect distribution data element and the multiple time sub-segments, and use the difference between the maximum first defect distribution data and the minimum first defect distribution data as the second defect distribution data of the time sub-segment; wherein the second defect distribution data is used to reflect the characteristics of the defect situation in the time sub-segment changing with time; Based on the second defect distribution data of each of the time sub-segments, a second defect distribution data element of the FFC cable on the preset time axis is determined.
2. The FFC cable AI defect detection method according to claim 1, characterized in that: Determining the defect of the FFC cable according to the real-time image information and the defect recognition model of the FFC cable includes: Inputting the real-time image information of the FFC cable into the defect recognition model to obtain an output result of the defect recognition model; Determine the defect status of the FFC cable according to the output result of the defect recognition model.
3. The FFC cable AI defect detection method according to claim 2, characterized in that: The method further comprises: Determining a quality inspection result of the FFC cable according to the defect condition of the FFC cable; When the quality inspection result of the FFC cable does not meet the preset quality requirements, defect prompt information is triggered.
4. The FFC cable AI defect detection method according to claim 1, characterized in that: The step of determining the defect detection result of the FFC cable according to the first defect distribution data element and the second defect distribution data element includes: Based on the first defect distribution data element and the second defect distribution data element, determining a spatial defect component and a temporal defect component of the FFC cable; wherein the spatial defect component is used to reflect the defect evaluation data of the spatial scale of the FFC cable, and the temporal defect component is used to reflect the defect evaluation data of the temporal scale of the FFC cable; A defect detection result of the FFC cable is determined according to the spatial defect component and the temporal defect component of the FFC cable.
5. The FFC cable AI defect detection method according to claim 4, characterized in that: The step of determining a defect detection result of the FFC cable according to the spatial defect component and the temporal defect component of the FFC cable comprises: Determining a defect evaluation value of the FFC cable according to the spatial defect component and the temporal defect component of the FFC cable; Based on the defect evaluation value of the FFC cable, a defect detection result of the FFC cable is determined.
6. An FFC cable AI defect detection system, characterized in that: include: An acquisition unit, used for acquiring real-time image information of the FFC cable; wherein the real-time image information of the FFC cable is used to reflect the defect of the FFC cable; A spatial unit, used to determine a first defect distribution data element of the FFC cable according to the real-time image information and a defect recognition model of the FFC cable; wherein the defect recognition model is a model obtained by machine learning, and the first defect distribution data element is used to reflect the defect distribution of the FFC cable on a spatial scale; A node unit, used to determine a defect data time node of each FFC cable based on the first defect distribution data element of the FFC cable; wherein the defect data time node is used to reflect defect detection time information of the FFC cable; A time unit, used to determine a second defect distribution data element of the FFC cable according to the defect data time node of each of the FFC cables and the first defect distribution data element; wherein the second defect distribution data element is used to reflect the defect distribution of the FFC cable on a time scale; A result unit, used to determine a defect detection result of the FFC cable according to the first defect distribution data element and the second defect distribution data element; wherein the defect detection result is used to reflect the overall defect situation of a preset number of the FFC cables; Wherein, the space unit is also used for: Determine the defect of the FFC cable according to the real-time image information and the defect recognition model of the FFC cable; Based on the defect condition of the FFC cable, first defect distribution data of the FFC cable is obtained; wherein the first defect distribution data is basic data constituting a first defect distribution data element; Determining a first defect distribution data element of the FFC cable according to the first defect distribution data of the FFC cable; The obtaining first defect distribution data of the FFC cable based on the defect condition of the FFC cable comprises: Based on the defect condition of the FFC cable, determine the defect type and spatial position information of each defect of the FFC cable; wherein the spatial position information is used to reflect the spatial position of each defect of the FFC cable on the FFC cable; According to the defect types and the spatial position information of all defects of the FFC cable, the defect types and the spatial position information are displayed on a preset defect space, and the spatial distances of all defects in the defect space are calculated; wherein the defect space is used to reflect the spatial structure of the FFC cable; Obtaining first defect distribution data of the FFC cable according to the spatial distances of all defects in the defect space; The obtaining first defect distribution data of the FFC cable according to the spatial distances of all defects in the defect space includes: Dividing the defect space into a plurality of sub-defect spaces according to the spatial distances of all defects in the defect space, and calculating the number of defects in each of the sub-defect spaces; Based on the result of calculating the number of defects in each of the sub-defect spaces, taking the sub-defect space with the largest number of defects as the first sub-defect space; Determine a unit space defect density of the first sub-defect space according to the number of defects in the first sub-defect space, and use the unit space defect density as first defect distribution data of the FFC cable; The determining, according to the first defect distribution data of the FFC cable, a first defect distribution data element of the FFC cable comprises: When the number of the FFC cables continuously detected reaches a preset number, a set of the first defect distribution data of the FFC cables is established according to the preset number of the first defect distribution data of the FFC cables, and the set of the first defect distribution data of the FFC cables is used as a first defect distribution data element; The time unit is also used for: According to the defect data time node of each FFC cable and the first defect distribution data element, the first defect distribution data element is displayed on a preset time axis according to the defect data time node, and the preset time axis is divided into a plurality of time sub-segments according to a preset time distance; wherein the time distance is used to reflect the detection time difference of the FFC cable; Determine the difference between the maximum first defect distribution data and the minimum first defect distribution data of each time sub-segment according to all the first defect distribution data in the first defect distribution data element and the multiple time sub-segments, and use the difference between the maximum first defect distribution data and the minimum first defect distribution data as the second defect distribution data of the time sub-segment; wherein the second defect distribution data is used to reflect the characteristics of the defect situation in the time sub-segment changing with time; Based on the second defect distribution data of each of the time sub-segments, a second defect distribution data element of the FFC cable on the preset time axis is determined.
7. An FFC cable AI defect detection device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 5 is implemented.
