Composite material detection system, control method thereof, equipment and medium

Abstract

The invention relates to the technical field of material detection, and discloses a composite material detection system, a control method and equipment thereof and a medium, and the system comprises a detector module, an X-ray source, a transverse adjustment mechanism, a longitudinal adjustment mechanism, a fine adjustment mechanism and a control unit. The detector module, the X-ray source, the transverse adjusting mechanism, the longitudinal adjusting mechanism and the fine adjustment mechanism are electrically connected with the control unit; a composite material layer to be detected is arranged between the detector module and the X-ray source, the X-ray source is connected with the fine adjustment mechanism, and the fine adjustment mechanism is used for adjusting the emitting position and the emitting angle of the X-ray source. According to the invention, the detection effect of the detector module can be ensured, the detection accuracy is improved, the real-time detection of the defects of the composite material in the automatic layering process is met, and the problems of insufficient adaptability and incapability of accurately identifying the defects in the prior art are solved.

Description

Background Art

[0002] With the increasing demand for lightweight and high-strength materials in high-performance structural fields such as aerospace, automobiles and energy, various types of composite materials such as carbon fiber have been widely used due to their excellent performance. However, during the automatic laying process of composite materials, composite materials often have internal defects such as pores, delamination, and fiber dislocation, which may affect the mechanical properties, structural stability and safety of the final product.

[0003] Although existing detection systems (such as ultrasonic detection, infrared detection, etc.) can detect the inside of composite materials, their detection performance is poor. During the automatic laying process, the number of layers of composite materials continues to accumulate, and due to its own complex structure, the existing detection system cannot accurately detect the changes in the composite material layers during the automatic laying process and its own complex structure, resulting in inaccurate detection results. Therefore, the existing detection system is not adaptable enough to the problems existing in the automatic laying process and cannot accurately identify defects. Summary of the invention

[0004] The present application provides a composite material detection system and a control method, device and medium thereof to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0006] According to one aspect of an embodiment of the present application, a composite material detection system is provided, the composite material detection system comprising: a detector module, an X-ray source, a lateral adjustment mechanism, a longitudinal adjustment mechanism, a fine adjustment mechanism and a control unit; the detector module, the X-ray source, the lateral adjustment mechanism, the longitudinal adjustment mechanism, and the fine adjustment mechanism are all electrically connected to the control unit; A composite material layer to be detected is arranged between the detector module and the X-ray source, the X-ray source is connected to the fine-tuning mechanism, and the fine-tuning mechanism is used to adjust the emission position and emission angle of the X-ray source; The fine adjustment mechanism is arranged on the transverse adjustment mechanism and is slidably connected to the transverse adjustment mechanism; the longitudinal adjustment mechanism includes a guide rail and a support frame, the transverse adjustment mechanism is fixed on the support frame and is vertically arranged with the support frame; the bottom of the support frame is arranged on the guide rail and is slidably connected with the guide rail; The plane position and the plane angle of the plane of the detector module are adjusted by the control unit, and the plane of the detector module is always kept perpendicular to the emission direction of the X-ray source; In the process of detecting the composite material layer, the emission position and emission angle of the X-ray source are continuously adjusted so that each area of ​​the composite material layer is transmitted by the X-ray source to form a transmission signal; and the transmission signal is detected by the detector module to form a transmission image signal, and the transmission image signal is sent to the control unit.

[0007] In one embodiment of the present application, based on the aforementioned scheme, the composite material detection system also includes a workbench, which includes a base, a first rotating shaft, a first rotatable telescopic rod, a driving mechanism and a second rotating shaft; the first rotating shaft is arranged on the base and is rotatably connected to the first rotatable telescopic rod; the first rotatable telescopic rod is respectively connected to the driving mechanism and the second rotating shaft, and the second rotating shaft is connected to the detector module.

[0008] In one embodiment of the present application, based on the aforementioned scheme, the detector module includes a support plate and a detection sensor, the detection sensor is fixed on the support plate, and the support plate is rotatably connected to the second rotating shaft; wherein the plane position and plane angle of the support plate are adjusted by the second rotating shaft; the first rotatable telescopic rod is driven to be telescoped and / or the first rotatable telescopic rod is rotated on the first rotating shaft by the driving mechanism to adjust the position and angle of the second rotating shaft, so that the plane of the detection sensor on the support plate remains perpendicular to the emission direction of the X-ray source.

[0009] In one embodiment of the present application, based on the aforementioned scheme, the lateral movement mechanism includes a lateral beam and a sliding unit, the lateral beam is fixed on the support frame and is vertically arranged with the support frame; the sliding unit is slidably connected to the lateral beam and fixedly connected to the fine-tuning mechanism.

[0010] In one embodiment of the present application, based on the aforementioned scheme, the fine-tuning mechanism includes a second rotatable telescopic rod, a hydraulic drive unit, a horizontal rotation joint, a vertical rotation joint, a vertical connecting shaft and a rotation connecting rod; the second rotatable telescopic rod is respectively connected to the sliding unit, the hydraulic drive unit and the horizontal rotation joint; the horizontal rotation joint is rotationally connected to the vertical connecting shaft, and the vertical connecting shaft is rotationally connected to the vertical rotation joint; the rotation connecting rod is rotationally connected to the vertical rotation joint and is connected to the X-ray source.

[0011] According to one aspect of the present application, a control method for a composite material detection system is provided. The method is executed in the above-mentioned control unit, and the method includes: When the plane of the detector module is perpendicular to the emission direction of the X-ray source, receiving the transmission image signal of the composite material layer collected by the detector module; determining abnormal information of the composite material layer according to the transmission image signal; Parameter adjustment information of the composite material laying equipment is determined according to the abnormal information, so that the composite material laying equipment adjusts laying parameters of the composite material layer according to the parameter adjustment information.

[0012] In one embodiment of the present application, based on the above solution, determining the abnormal information of the composite material layer according to the transmission image signal includes: Dividing the composite material layer into a grid area of ​​a preset format according to the transmission image signal, wherein the grid area includes a plurality of grids; For each grid, determine multiple prediction bounding boxes of the grid, obtain position parameters, confidence parameters and abnormal category probability parameters of each prediction bounding box based on a preset deep learning algorithm, and determine abnormal information of the grid according to each position parameter, confidence parameter and abnormal category probability parameter; The abnormal information of the composite material layer is determined according to the abnormal information of each of the grids.

[0013] In one embodiment of the present application, based on the above solution, determining the abnormal information of the grid according to each of the position parameters, the confidence parameters and the abnormal category probability parameters includes: Determining a target position parameter from each of the position parameters according to a preset positioning loss function; Determining a target confidence parameter from among the confidence parameters according to a preset confidence loss function; Determining a target abnormal category probability parameter from each of the abnormal category probability parameters according to a preset abnormal category loss function; The abnormal information of the grid is determined according to the target position parameter, the target confidence parameter and the target abnormal category probability parameter.

[0014] According to one aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. The computer program includes executable instructions. When the executable instructions are executed by a processor, the method described in the above embodiment is implemented.

[0015] According to one aspect of an embodiment of the present application, an electronic device is provided, comprising: one or more processors; and a memory for storing executable instructions of the processors, wherein when the executable instructions are executed by the one or more processors, the one or more processors implement the methods described in the above embodiments.

[0016] The beneficial effects of the present application are as follows: the control unit can control the lateral adjustment mechanism, the longitudinal adjustment mechanism and the fine adjustment mechanism to realize the omnidirectional movement of the X-ray source, so that the X-ray source can quickly reach the desired position, and the fine adjustment mechanism can quickly adjust the emission angle required by the X-ray source, and then form a matching relationship with the detector module, so that the rays emitted by the X-ray source can pass through the composite material layer, and then be detected by the detector module to form a transmission image signal, and the control unit can analyze the received transmission image signal to obtain whether there are defects in the composite material layer, as well as the type and position of the defects. In the process of continuous automatic laying of composite materials, the volume of the composite material layer will continue to increase due to the accumulation of the number of layers. At this time, the emission position and emission angle of the X-ray source can be adaptively adjusted by controlling the lateral adjustment mechanism, the longitudinal adjustment mechanism and the fine adjustment mechanism. At the same time, the detector module is controlled to always remain perpendicular to the emission direction of the X-ray source, to ensure the detection effect of the detector module, to improve the accuracy of detection, and to meet the real-time detection of defects in the composite material during the automatic laying process, solving the problem of insufficient adaptability and inability to accurately identify defects in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following is a brief description of the drawings required for use in the description of the embodiments. Obviously, the drawings described are only part of the embodiments of the present application, not all of the embodiments, and those skilled in the art can also obtain other design solutions and drawings based on these drawings without creative work.

[0018] Figure 1 The overall schematic diagram of a composite material detection system according to an embodiment of the present application is shown; Figure 2 This is a perspective view of a composite material detection system from a top view according to an embodiment of the present application; Figure 3 is a schematic diagram of a workbench and a detector module according to an embodiment of the present application; Figure 4 is an overall structural diagram of a fine-tuning mechanism according to an embodiment of the present application; Figure 5 A schematic diagram of the rotation direction of a horizontal rotation joint according to an embodiment of the present application; Figure 6 is a schematic diagram of the rotation direction of a vertical rotation joint according to an embodiment of the present application; Figure 7 is a diagram showing the connection relationship between the guide rail and the support frame according to an embodiment of the present application; Figure 8is a flow chart of a control method of a composite material detection system according to an embodiment of the present application; Fig. 9 It is a schematic diagram of the system structure of an electronic device according to an embodiment of the present application.

[0019] Reference numerals X-ray source 1, detector module 2, detection sensor 21, support plate 22, lateral adjustment mechanism 3, lateral beam 31, sliding unit 32, longitudinal adjustment mechanism 4, control unit 5, composite material layer 6, workbench 7, base 71, first rotating shaft 72, first rotatable telescopic rod 73, driving mechanism 74, second rotating shaft 75, fine-tuning mechanism 8, second rotatable telescopic rod 81, hydraulic driving unit 82, horizontal rotating joint 83, vertical rotating joint 84, vertical connecting shaft 85, rotating connecting rod 86. DETAILED DESCRIPTION

[0020] Example embodiments are now described more fully in conjunction with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this application will be more comprehensive and complete and fully convey the concept of the example embodiments to those skilled in the art.

[0021] In addition, described feature, structure or characteristic can be combined in one or more embodiments in any suitable manner. In the following description, many specific details are provided so as to provide a full understanding of the embodiments of the present application. However, it will be appreciated by those skilled in the art that the technical scheme of the present application can be put into practice without one or more of the specific details, or other methods, components, devices, steps, etc. can be adopted. In other cases, known methods, devices, realizations or operations are not shown or described in detail to avoid blurring the various aspects of the present application.

[0022] The block diagrams shown in the accompanying drawings are only functional entities and do not necessarily correspond to physically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or micro-control node devices.

[0023] The flowcharts shown in the accompanying drawings are only exemplary and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps can be decomposed, and some operations / steps can be combined or partially combined, so the actual execution order may change according to actual conditions.

[0024] It should be noted that the "multiple" mentioned in this article refers to two or more. "And / or" describes the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0025] The vortex vibration suppression system proposed in the embodiment of the present application is described in detail below: like Figure 1 As shown, Figure 1 The composite material detection system of the embodiment of the present application is an overall schematic diagram. The composite material detection system includes a detector module 2, an X-ray source 1, a lateral adjustment mechanism 3, a longitudinal adjustment mechanism 4, a fine adjustment mechanism 8 and a control unit 5; the detector module 2, the X-ray source 1, the lateral adjustment mechanism 3, the longitudinal adjustment mechanism 4, and the fine adjustment mechanism 8 are all electrically connected to the control unit 5; A composite material layer 6 to be detected is provided between the detector module 2 and the X-ray source 1, and the X-ray source 1 is connected to the fine-tuning mechanism 8, and the fine-tuning mechanism 8 is used to adjust the emission position and emission angle of the X-ray source 1; The fine adjustment mechanism 8 is arranged on the transverse adjustment mechanism 3 and is slidably connected to the transverse adjustment mechanism 3; the longitudinal adjustment mechanism 4 includes a guide rail and a support frame, the transverse adjustment mechanism 3 is fixed on the support frame and is vertically arranged with the support frame; the bottom of the support frame is arranged on the guide rail and is slidably connected with the guide rail; The plane position and plane angle of the plane of the detector module 2 are adjusted by the control unit 5, and the plane of the detector module 2 is always kept perpendicular to the emission direction of the X-ray source 1; In the process of detecting the composite material layer 6, the emission position and emission angle of the X-ray source 1 are continuously adjusted so that each area of ​​the composite material layer 6 is transmitted by the X-ray source 1 to form a transmission signal; and the detector module 2 detects the transmission signal to form a transmission image signal, and sends the transmission image signal to the control unit 5.

[0026] Specifically, Figure 2 As shown, Figure 2 That is, the perspective diagram of the composite material detection system from a top-down perspective. Figure 2 The Y-axis direction is the direction of the guide rail of the longitudinal adjustment mechanism 4, and the support frame can slide on the guide rail to realize the overall movement of the composite material detection system in the Y-axis direction. Then the fine adjustment mechanism 8 can realize the movement of the X-axis on the transverse adjustment mechanism 3. It should be noted that the plane formed by the X-axis and the Y-axis is a horizontal plane, or a plane parallel to the horizontal plane. Figure 7 This is a diagram of the connection relationship between the guide rail and the support frame.

[0027] Furthermore, after the X-ray source 1 can be adjusted along the X-axis and Y-axis directions of the horizontal plane, the position adjustment in the Z-axis (normal axis perpendicular to the horizontal plane) direction can be achieved through the fine-tuning mechanism 8. At the same time, the emission angle of the X-ray source 1 can be adjusted through the fine-tuning mechanism 8. The emission angle has two dimensions of adjustment. The first dimension is rotation along the horizontal plane, and the adjustable angle is 360°. The second dimension is rotation along the Z-axis direction. At this time, the angle can also be adjusted arbitrarily. Then the fine-tuning mechanism 8 can achieve all-round angle adjustment, and cooperate with the lateral adjustment mechanism 3, the longitudinal adjustment mechanism 4 and the fine-tuning mechanism 8 that can achieve position adjustment in the Z-axis direction to achieve arbitrary adjustment of the emission position and emission angle of the X-ray source 1.

[0028] Furthermore, in the process of detecting the composite material layer 6, as the composite materials in the composite material layer 6 are continuously laid, the volume and structure of the composite material layer 6 are also constantly changing. At this time, the emission position and emission angle of the X-ray source 1 are continuously adjusted so that the emission direction of the X-ray source 1 is always perpendicular to the plane of the detector module 2. At the same time, by adjusting the emission position of the X-ray source 1, a suitable distance is maintained between the X-ray source 1 and the composite material layer 6, ensuring the good transmission effect of the X-ray source 1 on the composite material layer. As a result, the transmission image signal collected by the detector module 2 has high accuracy, and parameters such as resolution and clarity also meet good performance parameter requirements.

[0029] In one embodiment of the present application, the composite material detection system also includes a workbench 7, which includes a base 71, a first rotating shaft 72, a first rotatable telescopic rod 73, a driving mechanism 74 and a second rotating shaft 75; the first rotating shaft 72 is arranged on the base 71 and is rotatably connected to the first rotatable telescopic rod 73; the first rotatable telescopic rod 73 is respectively connected to the driving mechanism 74 and the second rotating shaft 75, and the second rotating shaft 75 is connected to the detector module 2.

[0030] Specifically, the schematic diagram of the workbench 7 and the detector module 2 can be as follows: Figure 3As shown, the first rotating shaft 72 is arranged on the base 71, and the first rotating shaft 72 can be slidably connected with the base 71, that is, the first rotating shaft 72 can adjust the position of the detector module 2 by sliding on the upper surface of the base 71. The first rotatable telescopic rod 73 can rotate around the first rotating shaft 72 and around the second rotating shaft 75, and the second rotating shaft 75 is connected to the detector module 2; at this time, the length of the first rotatable telescopic rod 73 can be extended and retracted by the driving mechanism 74, so as to adjust the position of the second rotating shaft 75, that is, to adjust the position of the detector module 2. When the detector module 2 is far away from the composite material layer 6, it can be driven to extend the first rotatable telescopic rod 73 to get closer to the composite material layer 6, so that the transmission image signal received by the detector module 2 is more accurate and has a better effect. The driving mechanism 74 can be specifically a driving compression cylinder.

[0031] In one embodiment of the present application, the detector module 2 includes a support plate 22 and a detection sensor 21, the detection sensor 21 is fixed on the support plate 22, and the support plate 22 is rotatably connected to the second rotating shaft 75; wherein the plane position and plane angle of the support plate 22 are adjusted by the second rotating shaft 75; the first rotatable telescopic rod 73 is driven to be telescoped and / or the first rotatable telescopic rod 73 is rotated on the first rotating shaft 72 by the driving mechanism 74 to adjust the position and angle of the second rotating shaft 75, so that the plane of the detection sensor 21 on the support plate 22 remains perpendicular to the emission direction of the X-ray source 1.

[0032] Specifically, the detection sensor 21 is fixed to the support plate 22, and the support plate 22 is rotatably connected to the second rotating shaft 75, so the position of the detection sensor 21 can be adjusted by rotating the second rotating shaft 75 and adjusting the extension and contraction of the first rotatable telescopic rod 73. The plane position of the support plate 22 needs to maintain an appropriate distance from the composite material layer 6, which should not be too far or too close, and the plane angle of the support plate 22 (that is, the plane angle of the detector) needs to be parallel to the composite material layer 6, so that the detection effect reaches a good state. Therefore, the plane position and plane angle of the support plate 22 are adjusted through the second rotating shaft 75, and the first rotatable telescopic rod 73 is driven to extend and contract through the driving mechanism 74 and / or the first rotatable telescopic rod 73 is rotated on the first rotating shaft 72 to adjust the position and angle of the second rotating shaft 75, so that the plane of the detection sensor 21 on the support plate 22 is perpendicular to the emission direction of the X-ray source 1.

[0033] In one embodiment of the present application, the transverse movement mechanism includes a transverse beam 31 and a sliding unit 32, the transverse beam 31 is fixed on the support frame and is vertically arranged with the support frame; the sliding unit 32 is slidably connected to the transverse beam 31 and is fixedly connected to the fine-tuning mechanism 8.

[0034] Specifically, the transverse beam 31 is fixed on the support frame, wherein the support frame and the transverse beam 31 can be arranged perpendicular to each other, so that the position of the X-ray source 1 can be adjusted in two directions of the horizontal plane, namely, the horizontal direction and the vertical direction. The sliding unit 32 is slidably connected to the transverse beam 31, that is, the fine-tuning mechanism 8 can be fixed on the sliding unit 32, and the emission position of the X-ray source 1 can be adjusted by connecting the sliding unit 32 to the transverse beam 31.

[0035] In one embodiment of the present application, the fine-tuning mechanism 8 includes a second rotatable telescopic rod 81, a hydraulic drive unit 82, a horizontal rotation joint 83, a vertical rotation joint 84, a vertical connecting shaft 85 and a rotation connecting rod 86; the second rotatable telescopic rod 81 is respectively connected to the sliding unit 32, the hydraulic drive unit 82 and the horizontal rotation joint 83; the horizontal rotation joint 83 is rotationally connected to the vertical connecting shaft 85, and the vertical connecting shaft 85 is rotationally connected to the vertical rotation joint 84; the rotation connecting rod 86 is rotationally connected to the vertical rotation joint 84 and is connected to the X-ray source 1.

[0036] Specifically, refer to Figure 4 As shown, Figure 4 is the overall structure diagram of the fine-tuning mechanism 8, wherein the rotation direction diagram of the horizontal rotation joint 83 is as shown in FIG. Figure 5 As shown, the schematic diagram of the vertical rotation joint 84 is as shown Figure 6 As shown, the rotation direction of the horizontal rotation joint 83 and the rotation direction of the vertical rotation joint 84 are in two different planes, so that the rotation direction of the X-ray source 1 can achieve full rotation, that is, the emission angle of the X-ray source 1 can be adjusted in all directions, which greatly improves the adjustability of the emission angle of the X-ray source 1. The height of the horizontal rotation joint 83 can also be adjusted by driving the second rotatable telescopic rod 81 through the hydraulic drive unit 82. The height change of the horizontal rotation joint 83 will inevitably lead to the height change of the vertical rotation joint 84, thereby adjusting the height of the X-ray source 1.

[0037] In summary, the composite material detection system proposed in the embodiment of the present application can realize the position adjustment in the large direction through the lateral adjustment mechanism 3 and the longitudinal adjustment mechanism 4, and can realize the position adjustment of a large amplitude. The emission position and emission handover of the X-ray source 1 can be adjusted slightly through the fine adjustment mechanism 8. In this way, the X-ray source 1 can quickly reach the required position to transmit the composite material layer 6, and the transmission of the X-ray source 1 is synchronously coordinated through the workbench 7 under the detector module 2. The transmission image signal detected is excellent, so the control unit 5 can analyze the transmission image signal with good effect and identify the defect parameters existing in the composite material layer 6, such as the location of the defect and the category of the defect (such as delamination, bubbles, fiber dislocation), etc. The composite material detection system can automatically adjust the ray energy and emission angle emitted by the X-ray source 1 according to the material thickness and the number of layers, ensure uniform penetration of each layer of composite material, and obtain high-quality layered imaging. Through the deep learning algorithm built into the control unit 5, the control unit 5 can automatically identify various defects such as delamination, pores, fiber dislocation, etc. of carbon fiber composite materials, and classify and record them in real time to generate accurate information such as defect location, shape, size, etc. The system can work in conjunction with laying equipment for composite materials, automatically adjusting laying pressure, speed and other parameters according to the severity of defects, reducing the occurrence of subsequent defects and ensuring the overall quality of automatic laying of composite materials.

[0038] According to one aspect of an embodiment of the present application, a control method for a composite material detection system is provided. The method is executed in a control unit of the composite material detection system. Figure 8 The flowchart of the control method of the composite material detection system proposed in the embodiment of the present application includes steps S1-S3, which are described in detail as follows: In step S1 , when the plane of the detector module is perpendicular to the emission direction of the X-ray source, a transmission image signal of the composite material layer collected by the detector module is received.

[0039] Specifically, only when the plane of the detector module is perpendicular to the emission direction of the X-ray source, that is, after the emission position and emission angle of the X-ray source are adjusted through the various mechanisms of the composite material detection system, the X-ray source is turned on to transmit the composite material layer. At this time, the detector module can detect or collect the transmission image signal of the composite material layer.

[0040] In step S2, abnormal information of the composite material layer is determined according to the transmission image signal.

[0041] In one embodiment of the present application, determining the abnormal information of the composite material layer according to the transmission image signal includes: Dividing the composite material layer into a grid area of ​​a preset format according to the transmission image signal, wherein the grid area includes a plurality of grids; For each grid, determine multiple prediction bounding boxes of the grid, obtain position parameters, confidence parameters and abnormal category probability parameters of each prediction bounding box based on a preset deep learning algorithm, and determine abnormal information of the grid according to each position parameter, confidence parameter and abnormal category probability parameter; The abnormal information of the composite material layer is determined according to the abnormal information of each of the grids.

[0042] Specifically, the transmission image signal may be a single picture detected by the detector module, and the transmission image signal corresponds to the transmission image of the composite material layer. Therefore, the composite material layer in the transmission image may be divided into grid areas of a preset format, wherein the preset format may be specifically an S×S grid area, S may be any positive integer, and the grid area includes multiple grids, each grid corresponding to a specific area of ​​the composite material layer, and each grid is responsible for predicting the target in a specific area.

[0043] The preset deep learning algorithm can be specifically a convolutional neural network based on YOLOv11, which extracts features from the obtained transmission image signal and marks the defect type. Each grid predicts multiple bounding boxes. , each bounding box includes three parameters: location parameter, confidence parameter and abnormal category probability parameter, where the location parameter includes: center coordinates ,width ,high The confidence parameter is YOLOv11 predicts the class probability distribution for each bounding box. The abnormal class probability parameter is , The probability distributions of different defect categories (delamination, pores, fiber dislocation, cracks) are respectively corresponded. For each bounding box prediction, it can be expressed as:

[0044] in, are the bounding box center coordinates, is the width of the bounding box, is the height of the bounding box, is the confidence parameter, The locations and categories of multiple bounding boxes are predicted for each mesh, corresponding to the probability distribution of different defect categories (delamination, pores, fiber dislocation, cracks).

[0045] In one embodiment of the present application, determining the abnormal information of the grid according to each of the position parameters, the confidence parameters, and the abnormal category probability parameters includes: Determining a target position parameter from each of the position parameters according to a preset positioning loss function; Determining a target confidence parameter from among the confidence parameters according to a preset confidence loss function; Determining a target abnormal category probability parameter from each of the abnormal category probability parameters according to a preset abnormal category loss function; The abnormal information of the grid is determined according to the target position parameter, the target confidence parameter and the target abnormal category probability parameter.

[0046] Specifically, a target bounding box is generated through regression analysis for each grid (the abnormal information of the grid can be generated based on the target bounding box), and the coordinate information of the defect area and the defect category of the area can be obtained through the abnormal information of the grid.

[0047] The loss function of YOLOv11 consists of multiple parts, mainly including positioning loss, confidence loss and classification loss. The specific loss function form is:

[0048] in It is the positioning loss of the bounding box, which measures the gap between the predicted bounding box and the true bounding box, and is usually calculated using the mean square error (MSE). The target position parameters in the grid with the largest predicted probability, that is, the closest to the true bounding box, can be determined.

[0049] is the confidence loss, which measures the gap between the predicted confidence parameters and the true confidence parameters of each bounding box. The target confidence parameter with the largest predicted probability in the grid, that is, the one closest to the true confidence parameter, can be determined.

[0050] is the classification loss, which measures the gap between the category prediction and the true category, and usually uses the cross entropy loss function. The probability parameter of the target anomaly category with the largest predicted probability in the grid, that is, the one closest to the true category, can be determined.

[0051] Furthermore, the target position parameter, the target confidence parameter and the target abnormal category probability parameter constitute the abnormal information of the grid, so that the position coordinates of the defect and the defect category, shape, size and other information can be known, so as to adjust the parameters of the automatic layer laying equipment in a targeted manner to avoid the occurrence of these defects. The abnormal information of the composite material layer is composed of the abnormal information of each grid. If a grid has no defects, the abnormal information of the grid will not be generated.

[0052] Furthermore, in the initial training stage of the deep learning algorithm, in terms of the processing of the data set, a large amount of image data of carbon fiber composite materials was collected in advance. These images include different types of defects, such as cracks, bubbles, delamination, etc. Each image is manually annotated to determine the location and type of defects. The images in the data set are preprocessed, standardized to a uniform size, and data enhancement operations are performed to improve the generalization ability of the model. Data enhancement operations include but are not limited to image rotation, translation, cropping, brightness adjustment, etc. These operations help improve the detection performance of the model under different viewing angles and lighting conditions.

[0053] The YOLOv11 model is trained using annotated datasets. During the training process, the model learns the features of each part of the image and predicts the location and category of defects based on these features. After training, the YOLOv11 model can perform real-time detection of new composite images, identify defects, and output defect location parameters and abnormal category probability parameters (i.e., abnormal information of the grid). This algorithm is suitable for real-time defect monitoring on carbon fiber composite production lines and can reduce the error and missed detection rate of manual detection.

[0054] In step S3, parameter adjustment information of the composite material laying equipment is determined according to the abnormal information, so that the composite material laying equipment adjusts laying parameters of the composite material layer according to the parameter adjustment information.

[0055] Specifically, the control unit can also exchange data with the composite material laying equipment, and the abnormal information of the composite material layer generated by the control unit can be sent to the main control unit of the composite material laying equipment, so that the main control unit of the composite material laying equipment can automatically adjust the laying parameters (such as pressure, laying speed) of the composite material laying equipment according to the abnormal information of the composite material layer to reduce the probability of defects in subsequent layers.

[0056] As another aspect, the present application further provides a computer-readable storage medium on which a program product capable of implementing the method provided above in this specification is stored. In some possible implementations, various aspects of the present application may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary implementations of the present application described in the above "Embodiment Method" section of this specification.

[0057] According to the program product for implementing the above method in the embodiment of the present application, it can adopt a portable compact disk read-only memory (CD-ROM) and include program code, and can be run on a terminal device, such as a personal computer. However, the program product of the present application is not limited thereto. In this document, a readable storage medium can be any tangible medium containing or storing a program, which can be used by or in combination with an instruction execution system, an apparatus or a device.

[0058] The program product may use any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared or semiconductor system, device or device, or any combination of the above. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection with one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0059] Computer readable signal media may include a data signal propagated in baseband as part of a carrier wave, wherein readable program code is carried. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Readable signal media may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0060] The program code embodied on the readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the foregoing.

[0061] Program code for performing the operations of the present application may be written in any combination of one or more programming languages, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device, partially on the remote computing device, or entirely on the remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., using an Internet service provider to connect through the Internet).

[0062] As another aspect, the present application also provides an electronic device capable of implementing the above method.

[0063] Those skilled in the art will appreciate that various aspects of the present application may be implemented as a system, method or program product. Therefore, various aspects of the present application may be specifically implemented in the following forms, that is, a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or a combination of hardware and software, which may be collectively referred to as "circuit", "module" or "system" herein.

[0064] Refer to the following Figure 7 The electronic device 400 according to this embodiment of the present application is described. Figure 7 The electronic device 400 shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0065] like Figure 7 As shown, the electronic device 400 is in the form of a general computing device. The components of the electronic device 400 may include but are not limited to: at least one processing unit 410, at least one storage unit 420, and a bus 430 connecting different system components (including the storage unit 420 and the processing unit 410).

[0066] The storage unit stores program codes, which can be executed by the processing unit 410, so that the processing unit 410 executes the steps described in the above “Example Method” section of this specification according to various exemplary implementations of the present application.

[0067] The storage unit 420 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 421 and / or a cache memory unit 422 , and may further include a read-only memory unit (ROM) 423 .

[0068] The storage unit 420 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0069] Bus 430 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller node, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0070] The electronic device 400 may also communicate with one or more external devices 1200 (e.g., keyboards, pointing devices, Bluetooth devices, etc.), may also communicate with one or more devices that enable a user to interact with the electronic device 400, and / or communicate with any device that enables the electronic device 400 to communicate with one or more other computing devices (e.g., routers, modems, etc.). Such communication may be performed via an input / output (I / O) interface 450. In addition, the electronic device 400 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 460. As shown, the network adapter 460 communicates with other modules of the electronic device 400 via a bus 430. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 400, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0071] Through the description of the above implementation methods, it is easy for those skilled in the art to understand that the example implementation methods described here can be implemented by software, or by combining software with necessary hardware. Therefore, the technical solution according to the implementation method of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, a terminal device or a network device, etc.) to execute the method according to the implementation method of the present application.

[0072] In addition, the above-mentioned figures are only schematic illustrations of the processes included in the method according to the exemplary embodiment of the present application, and are not intended to be limiting. It is easy to understand that the processes shown in the above-mentioned figures do not indicate or limit the time sequence of these processes. In addition, it is also easy to understand that these processes can be performed synchronously or asynchronously in multiple modules.

[0073] It should be understood that the present application is not limited to the precise structures that have been described above and shown in the drawings, and that various modifications and changes may be performed without departing from the scope thereof. The scope of the present application is limited only by the appended claims.

Claims

1. A composite material detection system, characterized in that: The composite material detection system comprises: a detector module, an X-ray source, a lateral adjustment mechanism, a longitudinal adjustment mechanism, a fine adjustment mechanism and a control unit; the detector module, the X-ray source, the lateral adjustment mechanism, the longitudinal adjustment mechanism and the fine adjustment mechanism are all electrically connected to the control unit; A composite material layer to be detected is arranged between the detector module and the X-ray source, the X-ray source is connected to the fine-tuning mechanism, and the fine-tuning mechanism is used to adjust the emission position and emission angle of the X-ray source; The fine adjustment mechanism is arranged on the transverse adjustment mechanism and is slidably connected to the transverse adjustment mechanism; the longitudinal adjustment mechanism includes a guide rail and a support frame, the transverse adjustment mechanism is fixed on the support frame and is vertically arranged with the support frame; the bottom of the support frame is arranged on the guide rail and is slidably connected with the guide rail; The plane position and the plane angle of the plane of the detector module are adjusted by the control unit, and the plane of the detector module is always kept perpendicular to the emission direction of the X-ray source; In the process of detecting the composite material layer, the emission position and emission angle of the X-ray source are continuously adjusted so that each area of ​​the composite material layer is transmitted by the X-ray source to form a transmission signal; and the transmission signal is detected by the detector module to form a transmission image signal, and the transmission image signal is sent to the control unit.

2. The composite material detection system according to claim 1, characterized in that: The composite material detection system also includes a workbench, which includes a base, a first rotating shaft, a first rotatable telescopic rod, a driving mechanism and a second rotating shaft; the first rotating shaft is arranged on the base and is rotatably connected to the first rotatable telescopic rod; the first rotatable telescopic rod is respectively connected to the driving mechanism and the second rotating shaft, and the second rotating shaft is connected to the detector module.

3. The composite material detection system according to claim 2, characterized in that: The detector module includes a support plate and a detection sensor, wherein the detection sensor is fixed on the support plate, and the support plate is rotatably connected to the second rotating shaft; wherein the plane position and plane angle of the support plate are adjusted by the second rotating shaft; the first rotatable telescopic rod is driven to be telescopically extended and / or the first rotatable telescopic rod is rotated on the first rotating shaft by the driving mechanism to adjust the position and angle of the second rotating shaft, so that the plane of the detection sensor on the support plate remains perpendicular to the emission direction of the X-ray source.

4. The composite material detection system according to claim 1, characterized in that: The transverse movement mechanism includes a transverse beam and a sliding unit. The transverse beam is fixed on the support frame and is vertically arranged with the support frame. The sliding unit is slidably connected with the transverse beam and is fixedly connected with the fine-tuning mechanism.

5. The composite material detection system according to claim 4, characterized in that: The fine-tuning mechanism includes a second rotatable telescopic rod, a hydraulic drive unit, a horizontal rotation joint, a vertical rotation joint, a vertical connecting shaft and a rotation connecting rod; the second rotatable telescopic rod is respectively connected to the sliding unit, the hydraulic drive unit and the horizontal rotation joint; the horizontal rotation joint is rotationally connected to the vertical connecting shaft, and the vertical connecting shaft is rotationally connected to the vertical rotation joint; the rotation connecting rod is rotationally connected to the vertical rotation joint and is connected to the X-ray source.

6. A control method for a composite material detection system, characterized in that: The method is executed by a control unit according to any one of claims 1 to 5, and the method comprises: When the plane of the detector module is perpendicular to the emission direction of the X-ray source, receiving the transmission image signal of the composite material layer collected by the detector module; determining abnormal information of the composite material layer according to the transmission image signal; Parameter adjustment information of the composite material laying equipment is determined according to the abnormal information, so that the composite material laying equipment adjusts laying parameters of the composite material layer according to the parameter adjustment information.

7. The control method according to claim 6, characterized in that: The determining the abnormal information of the composite material layer according to the transmission image signal comprises: Dividing the composite material layer into a grid area of ​​a preset format according to the transmission image signal, wherein the grid area includes a plurality of grids; For each grid, determine multiple prediction bounding boxes of the grid, obtain position parameters, confidence parameters and abnormal category probability parameters of each prediction bounding box based on a preset deep learning algorithm, and determine abnormal information of the grid according to each position parameter, confidence parameter and abnormal category probability parameter; The abnormal information of the composite material layer is determined according to the abnormal information of each of the grids.

8. The control method according to claim 7, characterized in that: The determining the abnormal information of the grid according to each of the position parameters, the confidence parameters and the abnormal category probability parameters includes: Determining a target position parameter from each of the position parameters according to a preset positioning loss function; Determining a target confidence parameter from among the confidence parameters according to a preset confidence loss function; Determining a target abnormal category probability parameter from each of the abnormal category probability parameters according to a preset abnormal category loss function; The abnormal information of the grid is determined according to the target position parameter, the target confidence parameter and the target abnormal category probability parameter.

9. A computer-readable storage medium, characterized in that: At least one program code is stored in the computer-readable storage medium, and the at least one program code is loaded and executed by the processor to implement the operations performed by the method according to any one of claims 6 to 8.

10. An electronic device, characterized in that: The electronic device includes one or more processors and one or more memories, wherein the one or more memories store at least one program code, and the at least one program code is loaded and executed by the one or more processors to implement the operations performed by the method according to any one of claims 6 to 8.

Images