A method for detecting the uniformity of a preform of an aeroengine fan blade

Abstract

The present invention relates to the technical field of three-dimensional braided composite material detection, and solves the technical problem that the traditional method cannot perform on-line detection of yarn uniformity during the weaving process of three-dimensional braided preforms. In particular, it relates to a method for detecting the uniformity of a preform of an aero-engine fan blade, including correcting the original image; extracting and fusing features to obtain fused features; decoupling the interlacing point detection task into two subtasks of center point prediction and size estimation; determining the position distribution of effective interlacing points within the effective detection area; and realizing accurate evaluation of the yarn uniformity of the preform. The present invention can accurately and efficiently complete the automatic detection of the yarn uniformity of the preform of an aero-engine fan blade, effectively solve engineering detection problems such as large scale span, high density and variable angles of yarn interlacing points, significantly improve the quality evaluation ability of the blade preform during the production process of the aviation industry, and meet the actual needs of high-standard production in the aviation industry.

Description

Technical Field

[0001] The present invention relates to the technical field of three-dimensional braided composite material detection, and particularly to a method for detecting the uniformity of a preform of an aero-engine fan blade. Background Art

[0002] As a core power component of an aircraft, the performance of an aero-engine directly determines the overall performance level and service life of the aircraft. Among the many core components of an aero-engine, the fan blade plays a crucial role. It not only directly determines the thrust output and operating efficiency of the engine, but also its reliability and durability are important foundations for ensuring flight safety. With the continuous improvement of the requirements for the overall performance and safety of engines in the modern aviation industry, traditional metal materials have gradually become difficult to meet the various requirements such as high thrust-to-weight ratio, long service life, and high reliability. Therefore, three-dimensional braided composite fan blades with excellent specific strength, specific stiffness, fatigue resistance, damage tolerance, and thermal stability have gradually become a research and application hotspot for aero-engine components.

[0003] However, the manufacturing process of three-dimensional braided composite fan blades is relatively complex. Especially in the weaving stage of the blade preform, the uniformity of the yarns is directly related to the overall mechanical properties, structural integrity of the composite material after the blade is formed, and its reliability under harsh working conditions. Current production practices show that factors such as design defects in the weaving process plan, unreasonable setting of weaving process parameters, and human operation errors can significantly affect the spatial distribution uniformity of the yarns, and then cause error accumulation in the blade forming stage, resulting in a reduction in the mechanical properties of the final product, weakening of the damage tolerance and impact resistance, and even directly shortening the service life of the blade. Thus, it can be seen that timely and accurately detecting and feedbacking the uniformity status of the yarns during the preform weaving process is of crucial significance for ensuring the overall quality of composite fan blades.

[0004] Currently, the on-line detection methods for the yarn uniformity of three-dimensional braided composite preforms in the aviation industry still face a series of severe challenges, which are mainly reflected in the following aspects: First, due to the tiny size, extremely high density, and complex arrangement of the yarn intersection points, traditional detection technologies are difficult to accurately identify and evaluate the yarn uniformity on an efficient and real-time industrial production line; Second, the traditional off-line manual sampling detection method has low efficiency and large randomness, and cannot provide timely and effective feedback on the production process, so it is difficult to achieve comprehensive coverage of the uniformity detection throughout the weaving cycle; In addition, the existing detection methods based on traditional image processing usually target two-dimensional simple fabric samples, and do not fully consider the actual situation of complex three-dimensional braided structures, high fabric density, and coexistence of multiple fiber bundle interweaving modes in actual industrial production, resulting in a significant decline in the reliability and accuracy of the existing technologies. Summary of the Invention

[0005] Aiming at the deficiencies of the prior art, the present invention provides a method for detecting the uniformity of an aeroengine fan blade preform, which solves the technical problem that the traditional method cannot perform on-line detection of yarn uniformity during the weaving process of a three-dimensional braided preform.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: A method for detecting the uniformity of an aeroengine fan blade preform, the method comprising the following steps:

[0007] S1. Obtain the original images collected in real time from the production line, and correct the intersection points of the carbon fiber horizontal and vertical yarns in the original images to a standard angle presented from a unified perspective through an image angle normalization module;

[0008] S2. Based on the global path and local path of the dual-path feature extraction network, perform feature extraction on the corrected original images respectively to obtain dual-path features;

[0009] S3. Through a dual-path feature fusion network adopting a cross-attention mechanism and a multi-scale self-attention mechanism, fuse the dual-path features to obtain fusion features;

[0010] S4. Input the fusion features into the context decoupled detection head module, decouple the intersection point detection task into two subtasks of center point prediction and size estimation, and obtain the center position of the intersection points located in the detection frame and the width and height of the detection frame;

[0011] S5. Define the threshold of the image edge region, delimit the effective detection region based on the detection frame and eliminate the incomplete intersection points existing on the image edge, and obtain the position distribution of the effective intersection points within the effective detection region;

[0012] S6. Calculate the evaluation index for evaluating the yarn distribution uniformity in the fan blade preform according to the position distribution of the effective intersection points to achieve accurate evaluation of the preform yarn uniformity.

[0013] Further, in step S1, the specific process includes the following steps:

[0014] S11. Using the ResNet50 network model as the basic feature extraction network, extract the initial feature map from the original image, and then use the feature pyramid network to generate multi-scale feature maps layer by layer to capture the visual features of the intersection points at different scales;

[0015] S12. Set rotation-sensitive anchor boxes according to the different sizes and inclination angles of the yarn intersection points , and the expression is:

[0016] ;

[0017] Wherein, is the center coordinate of the rotation-sensitive anchor box; is the width and height of the rotation-sensitive anchor box; is the rotation angle of the rotation-sensitive anchor box;

[0018] S13. Based on the rotation-sensitive anchor box Use the region proposal network head to generate rotation candidate regions and obtain the angle prediction value of the rotation multi-scale feature map , and through the ROIAlign operation, unify the multi-scale feature maps of different sizes into a feature map of a fixed size and containing intersection points;

[0019] S14. Formulate an abnormal angle filtering mechanism, and through the angle threshold filter out the abnormal angles in the angle prediction value , and the expression is:

[0020] ;

[0021] Among them, is the reserved angle prediction value; is the rotation intersection point feature map 's angle prediction value; is the predicted mean value of the rotation angle;

[0022] S15. After averaging the angle prediction value , obtain the corrected angle , and correct the original image through the rotation transformation matrix. The rotation transformation matrix is:

[0023] ;

[0024] Among them, represents the pixel coordinates of the intersection point in the original image; is the coordinate of the intersection point after the rotation transformation matrix.

[0025] Furthermore, a rotation angle regression branch is introduced in the region proposal network head, that is:

[0026] First, for each initial rotation-sensitive anchor box assign a series of discrete initial angles to cover the possible inclination angles of the braided texture;

[0027] Then, the region proposal network head regresses and predicts the angle offset of each rotation-sensitive anchor box through the convolutional features, and obtains the correction value of this rotation-sensitive anchor box relative to its initial angle. The finally predicted rotation angle of the rotation-sensitive anchor box is denoted as , and its calculation formula is:

[0028] ;

[0029] In the formula, is the initial angle of the rotation-sensitive anchor box ; is the angle increment output by the region proposal network head regression.

[0030] Furthermore, in step S2, the dual-path features include a global semantic feature used to characterize the overall spatial distribution and context semantic features of the intersection points, and a local spatial detail feature containing the detailed texture and local fine spatial information of the intersection points. The specific process includes the following steps:

[0031] S21. The global path adopts a global feature extraction architecture based on Vision Transformer, and captures the overall spatial distribution and context semantic features of the prefabricated body intersection points through the self-attention mechanism;

[0032] S22. The local path adopts a classical convolutional neural network structure, and effectively extracts the detailed texture and local fine spatial information of the intersection points through multi-layer convolutional operations;

[0033] S23. Define the feature outputs of the global path and the local path as and , that is:

[0034] ;

[0035] Among them, represents the mapping function for extracting global semantic features through Vision Transformer; represents the mapping function for extracting local spatial detail features through a classical convolutional neural network.

[0036] Furthermore, in step S3, the specific process includes the following steps:

[0037] S31. Use the cross-attention mechanism to take the global semantic feature output by the global path as the query, and the local spatial detail features output by the local path as the key and value respectively, to achieve deep interaction and fusion between the two path features to obtain the fusion feature , and the expression is:

[0038] ;

[0039] Among them, the query ; the key ; the value is the feature transformation matrix; is the learnable parameter; is the feature dimension;

[0040] S32. Use the multi-scale self-attention mechanism to perform weighted integration on the fused features at multiple scales respectively, capture the cross-scale dependence relationships between different scale intersection points, and obtain the comprehensive features The expression is as follows: , the expression is:

[0041] ;

[0042] Among them, represents the scale set; represents the attention weight coefficient corresponding to the scale ; represents the comprehensive feature after fusion by the multi-scale self-attention mechanism; represents the selected scale set; represents at the scale the fused feature obtained.

[0043] Furthermore, in step S4, the context decoupling detection head module includes a center point attention module, a size attention module, and an offset attention module. The specific process includes the following steps:

[0044] S41. The center point attention module converts the position prediction in the intersection point detection task into the center point heat map prediction, and optimizes the network training to output the center position of the intersection point through the loss function . The expression is:

[0045] ;

[0046] In the formula, is the predicted value of the network prediction heat map at the position (i, j); is the label value of the real heat map at the position (i, j); is the modulation factor of the focal loss; is the number of real intersection points in the image;

[0047] S42. The size attention module independently predicts the detection box size including the width and height of the center position of each intersection point, and uses the loss function to optimize the prediction error. The expression is:

[0048] ;

[0049] In the formula, and are the predicted width and height of the detection box of the i-th intersection point; and are the real width and height of the detection box of the i-th intersection point;

[0050] S43. The offset attention module predicts the slight offset of the actual center position of the intersection point relative to the center position of the predicted heat map and uses a loss function to reduce the position prediction error and further improve the refinement of intersection point localization. The loss function has the following expression:

[0051] ;

[0052] In the formula, and are the offsets of the center of the i-th intersection point predicted by the network relative to the grid; and are the corresponding true offsets; is the smooth absolute value loss function, which is a loss function used to measure the prediction offset error.

[0053] Furthermore, in step S5, the specific process includes the following steps:

[0054] S51. Define the threshold for the image edge region to accurately delimit the effective detection region and eliminate possible incomplete edge intersection points;

[0055] S52. In the set of all detected intersection points, identify and mark the incomplete intersection points located at the image edge, which are defined as follows:

[0056] ;

[0057] Among them, is the center point of the intersection point, and are the center coordinates; , , , respectively represent the preset left, right, upper, and lower boundary thresholds; is the horizontal coordinate of the i-th valid intersection point in the image; is the vertical coordinate of the i-th valid intersection point in the image;

[0058] S53. Calculate the average value of the right boundary of the incomplete intersection points located at the left edge in the detection box, denoted as the average boundary , that is:

[0059] ;

[0060] In the formula, is the number of intersection points at the left edge; is the right boundary abscissa position of the detection box of the -th incomplete intersection point at the left edge;

[0061] S54. According to the average boundary Establish an effective detection boundary standard, and all detection frames with the center points of all intersection points located on the left side of this boundary are removed, that is:

[0062] ;

[0063] In the formula, represents the set of effective intersection points; represents the j-th intersection point after boundary screening; are the abscissa and ordinate of the center of the intersection point;

[0064] S55. Process the edge regions including the upper, lower, and right boundaries in the image respectively according to the above standard, so as to obtain a set of effective detection points after removing the incomplete intersection points at the edges .

[0065] Furthermore, in step S54, the specific process of establishing the effective detection boundary standard includes the following steps:

[0066] S541. Statistically calculate the average abscissa of the right boundaries of all detection frames of incomplete intersection points located on the left edge of the image , which is used to determine the left boundary of the effective detection area, and the expression is:

[0067] ;

[0068] In the formula, is the abscissa value of the right boundary of the i-th detection frame of incomplete intersection points located on the left edge of the image; N is the total number of incomplete intersection points located on the left edge of the image;

[0069] S542. Taking the average abscissa as a benchmark, define the effective detection area of the left boundary of the image;

[0070] If the abscissa value of the center point of the intersection point , then it is considered that this intersection point is complete and effective; if the abscissa value of the center point of the intersection point , then it is considered that this intersection point is located in the edge area and belongs to an incomplete intersection point, and should be excluded from subsequent evaluations;

[0071] S543. Repeat steps S541 - S542, and process the right, upper, and lower edge regions of the image respectively to establish an effective detection boundary standard with four boundary directions.

[0072] Furthermore, in step S6, the specific process includes the following steps:

[0073] S61. Calculate the actual area of the effective detection area , the calculation formula is:

[0074] ;

[0075] In the formula, and are the boundary coordinates of the effective detection area in the image;

[0076] S62. Count the number of intersection points within the effective area , and use the number of intersection points per unit area as the evaluation index for yarn uniformity , accurately quantify and evaluate the weaving quality and uniformity of the fan blade preform, that is:

[0077] ;

[0078] If the yarn uniformity evaluation index is close to the reference value , and within the allowable error range, it is considered that the yarn distribution uniformity of the fan blade preform is good and meets the quality requirements;

[0079] If the yarn uniformity evaluation index is significantly lower than the reference value , it indicates that there are too few yarn intersection points per unit area, the yarn density may be small, and there may be sparse weaving or holes; conversely, if the yarn uniformity evaluation index is higher than the reference value , it means that the local yarn is crowded or repeated, indicating uneven weaving.

[0080] By means of the above technical solution, the present invention provides a method for detecting the uniformity of an aeroengine fan blade preform, which at least has the following beneficial effects:

[0081] 1. The present invention can accurately and efficiently complete the automatic detection of the yarn uniformity of the aeroengine fan blade preform, effectively solve the engineering detection problems such as large scale span, high density and variable angles of yarn intersection points, significantly improve the quality evaluation ability of the blade preform in the aeroindustry production process, and meet the actual needs of high-standard production in the aeroindustry.

[0082] 2. Through the design of multi-scale feature interaction fusion and context decoupling attention mechanism, the present invention realizes the accurate, efficient and automatic detection of the yarn uniformity of the aeroengine fan blade preform, significantly improves the quality evaluation and control level on the industrial production line, and meets the strict requirements of the aeroindustry for production quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0084] Figure 1 It is a flow chart of the method for detecting uniformity of a preform in the present invention;

[0085] Figure 2 This is a network structure diagram for preform uniformity detection in the present invention. DETAILED DESCRIPTION

[0086] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

[0087] In view of the series of severe challenges faced by the online detection method of yarn uniformity of three-dimensional woven composite preforms, how to achieve accurate and online detection of yarn uniformity during the weaving process of three-dimensional woven preforms of aircraft engine fan blades under the premise of high precision, high real-time performance and low interference has become a key technical problem that needs to be solved urgently.

[0088] An advanced online uniformity detection method is proposed, which has important theoretical significance and engineering application value for further improving the manufacturing quality and production efficiency of aircraft engine fan blade preforms and ensuring the overall performance stability and reliability of aircraft engines. Figure 1 - Figure 2 This embodiment proposes a uniformity detection method for aircraft engine fan blade preforms. Through the design of multi-scale feature interactive fusion and context decoupling attention mechanism, accurate, efficient and automated detection of the uniformity of the yarn of aircraft engine fan blade preforms is achieved, which significantly improves the quality assessment and control level on the industrial production line and meets the strict requirements of the aviation industry for production quality. The method includes the following steps:

[0089] S1. Obtain the original image collected in real time on the production line, and correct the interweaving points of the carbon fiber horizontal and vertical yarns in the original image to a standard angle presented at a uniform viewing angle through an image angle standardization module. In view of the fact that the original images of aircraft engine fan blade preforms collected in actual production environments usually have obvious angle differences, which affects the precise positioning and detection accuracy of the subsequent carbon fiber yarn interweaving points, this embodiment first proposes an image angle standardization module to uniformly correct the collected original images to a standard angle to ensure that the features of the interweaving points are presented at a uniform viewing angle, thereby improving the accuracy of subsequent feature detection. The specific process includes the following steps:

[0090] S11. Use the ResNet50 network model as the basic feature extraction network to extract the initial feature map from the original image, and then use the Feature Pyramid Network (FPN) to generate multi-scale feature maps layer by layer to capture the visual features of the intersection points at different scales;

[0091] S12. Set rotation-sensitive anchor boxes according to the different sizes and tilt angles of the yarn intersection points , and the expression is:

[0092] ;

[0093] Among them, is the center coordinate of the rotation-sensitive anchor box; is the width and height of the rotation-sensitive anchor box; is the rotation angle of the rotation-sensitive anchor box;

[0094] S13. Based on the rotation-sensitive anchor box use the Region Proposal Network head (RPN) to generate rotation candidate regions (ROIs) and obtain the angle prediction value of the rotation multi-scale feature map , and through the ROIAlign operation, unify the multi-scale feature maps of different sizes to a fixed size and the feature map containing the intersection points.

[0095] In this embodiment, a Region Proposal Network (RPN) based on rotation-sensitive anchor boxes is used to predict the rotation angle of the intersection point image. Specifically, a rotation angle regression branch is introduced into the Region Proposal Network head, that is:

[0096] First, a series of discrete initial angles, such as 0°, 5°, 10°, 15°, 20°, 25°, 30°, are assigned to each initial rotation-sensitive anchor box to cover the possible tilt angles of the weaving texture. These angles are all from actual observations. Generally, the tilt angles of the weaving texture on the surface of the preform of the aeroengine fan blade are within 30°.

[0097] Then, the Region Proposal Network head performs regression prediction on the angle offset of each rotation-sensitive anchor box through the convolutional features, and obtains the correction value of this rotation-sensitive anchor box relative to its initial angle. The finally predicted rotation angle of the rotation-sensitive anchor box is denoted as , and its calculation formula is:

[0098] ;

[0099] In the formula, is the initial angle of the rotation-sensitive anchor box ; is the angle increment output by the region proposal network head regression.

[0100] Finally, the trained region proposal network head can output the angle prediction value of each rotation candidate region for any input image .

[0101] S14. Establish an abnormal angle filtering mechanism. Through the angle threshold , eliminate the abnormal angles in the angle prediction value . The expression is:

[0102] ;

[0103] Among them, is the retained angle prediction value; is the angle prediction value of the rotation intersection feature map ; is the predicted mean value of the rotation angle.

[0104] In this embodiment, the angle threshold is used to determine the magnitude of the abnormal value in the predicted angle. In this embodiment, the angle threshold is set to 5° (equivalent to about 0.087 radians). That is to say, when the absolute value of the difference between the angle prediction value of a certain feature map rotation and the predicted mean value exceeds 5°, it is considered to deviate from the normal range, and this prediction is regarded as abnormal and eliminated. This value is based on the observed yarn weaving inclination fluctuation range in actual production. As the default value, 5° can well balance the strictness of abnormal elimination and the sensitivity of retaining normal changes through experiments.

[0105] S15. After averaging the angle prediction value , obtain the corrected angle . Correct the original image through the rotation transformation matrix. The rotation transformation matrix is:

[0106] ;

[0107] Among them, represents the pixel coordinates of the intersection point in the original image, that is, before the correction rotation, the position coordinates of this point in the original image; is the coordinate of the intersection point after the rotation transformation matrix.

[0108] In order to horizontally align the yarn interweaving texture in the image, after rotating the original image around the origin to the correction angle , the position of this point will move to the new coordinate . Through this transformation, the original image can be rotated as a whole by the correction angle , thus rotating the originally inclined yarn texture to a unified angle. Through the above method, this embodiment completes the angular normalization correction process of the original image, and the achieved technical effects include:

[0109] Weaving texture alignment: By calculating the correction angle of the rotation-sensitive anchor box set and rotating and correcting the image, this step rotates the randomly oriented carbon fiber yarn interweaving texture to a unified perspective, making the overall arrangement direction of the yarn interweaving points in the image consistent, and eliminating the inclination difference caused by different shooting and acquisition angles.

[0110] Abnormal angle elimination: An abnormal angle filtering mechanism is introduced during the rotation correction process to eliminate outliers that deviate too much from the average angle, avoiding the interference of extremely few abnormal rotation detection values on the correction result, and improving the stability and accuracy of the rotation correction.

[0111] Improve the subsequent detection accuracy: After the above unified angle correction, the spatial distribution law of the interweaving points in the image is more unified, providing a standardized input for the feature extraction network. This directly improves the reliability of the subsequent interweaving point detection algorithm, eliminates the problem of inconsistent feature distribution caused by different image rotation angles, and reduces the difficulty of interweaving point detection.

[0112] Generally speaking, through the angle normalization process, the yarn interweaving texture is aligned in the image, significantly reducing the impact of the inclination diversity of the interweaving points on the detection, and improving the accuracy and consistency of feature extraction and interweaving point detection.

[0113] S2. Based on the global path and local path of the dual-path feature extraction network, feature extraction is respectively performed on the corrected original image to obtain dual-path features. The dual-path features include global semantic features used to represent the overall spatial distribution and context semantic features of the interweaving points, and local spatial detail features containing the detailed texture and local fine spatial information of the interweaving points. After the original image undergoes angle normalization, the spatial features of the interweaving points of the carbon fiber horizontal and vertical yarns become more regular and unified, but there are still problems such as large scale differences and dense distributions. To accurately capture the rich detailed features of the interweaving points in the corrected image, this embodiment constructs a multi-scale dual-path feature extraction module to respectively extract the global semantic features and local spatial detail features of the original image, providing sufficient feature support for subsequent fine interweaving point detection. The specific process includes the following steps:

[0114] S21. The global path adopts a global feature extraction architecture (ViT) based on Vision Transformer, and captures the overall spatial distribution and context semantic features of the preform interweaving points through the self-attention mechanism;

[0115] S22, the local path adopts the classic convolutional neural network (CNN) structure, which effectively extracts the detailed texture and local fine spatial information of the interweaving points through multi-layer convolution operations, solving the detection problem of large scale changes of interweaving points;

[0116] S23, define the feature outputs of the global path and the local path respectively and ,Right now:

[0117] ;

[0118] in, Represents the mapping function of extracting global semantic features through visual Transformer, and its output It mainly includes the overall spatial distribution and contextual information of the intersection points; Represents the mapping function of extracting local spatial detail features through the classic convolutional neural network, and its output It mainly contains the detailed texture and local fine spatial information of each interlaced point. Using this representation method, the functions and outputs of the two different feature extraction branches can be clearly distinguished, thereby providing complementary information for subsequent feature fusion.

[0119] In this embodiment, the dual-path feature extraction network adopts a dual-branch design in architecture: on the one hand, the global feature extraction architecture (ViT) based on visual Transformer is used to realize global semantic feature extraction, which can capture the long-distance dependency and overall arrangement of the preform interweaving points; on the other hand, the classic convolutional neural network (CNN) structure is used to deeply extract local detail information to obtain the texture features of each interweaving point. The combination of the two can take into account both the global and the local, solving the problem that the traditional single path is difficult to take into account.

[0120] By introducing multi-scale feature extraction and feature pyramid structure in the local path, the network can adapt to the feature changes caused by scale differences at the intersection points, thus reflecting multi-scale enhancement. The outputs of the dual paths not only exist independently, but also achieve deep fusion through cross-attention in the subsequent process, so that global semantics and local details can complement each other to improve detection accuracy, thus reflecting cross-scale information fusion.

[0121] Therefore, compared with the existing scheme that only uses a single path feature extraction or a simple parallel two-branch scheme, the present invention combines Transformer and CNN and optimizes parameters and structures according to the characteristics of yarn interlacing points. It has the advantages of multi-scale enhancement and cross-scale information fusion, which significantly improves the accuracy, robustness and adaptability of detection, thus having obvious technical innovation.

[0122] S3. By using a dual-path feature fusion network with a cross-attention mechanism and a multi-scale self-attention mechanism to fuse the dual-path features, the robustness of the intersection point features is significantly improved. The specific process includes the following steps:

[0123] S31. Use the cross-attention mechanism to take the global semantic features output by the global path as the query, and the local spatial detail features output by the local path as the key and value respectively, to achieve deep interaction and fusion between the two path features and obtain the fused features , and the expression is:

[0124] ;

[0125] Among them, the query ; the key ; the value is the feature transformation matrix; is the learnable parameter; is the feature dimension;

[0126] S32. To further improve the representation ability of the fused features for intersection points at different scales, use the multi-scale self-attention mechanism to weighted integrate the fused features at multiple scales respectively, capture the cross-scale dependence relationship between intersection points at different scales, and obtain the comprehensive features , and the expression is:

[0127] ;

[0128] Among them, represents the scale set; represents the attention weight coefficient corresponding to the scale , which is learned and used to adjust the contribution of features at different scales in the final fused representation; represents the comprehensive features after being fused by the multi-scale self-attention mechanism; represents the selected scale set, for example, the index set of different downsampling ratios or feature layer levels; represents the fused features obtained at the scale , and the superscript is used to indicate that this feature corresponds to the th scale.

[0129] In this embodiment, by weighted summing the fused features at all scales, a comprehensive feature that combines the information of each scale is finally obtained , so as to better capture the details and global semantics of the intersection points at different scales. By introducing a fusion scheme that combines the cross-attention mechanism and the multi-scale self-attention mechanism. Its specific innovation is reflected in:

[0130] First, using the cross-attention mechanism (with global features as queries and local features as keys and values), the deep interaction of dual-path features is achieved, which enables the global information to actively guide the weighted extraction of local details and generate more discriminative fusion features.

[0131] Secondly, on this basis, by performing self-attention calculations on the fusion features at different scales and then weighted summing using learnable scale weights, cross-scale dependencies are captured, making the entire detection method still stable when facing changes in the sizes of preform intersection points.

[0132] This fusion method is more accurate and robust than traditional simple feature splicing or element-wise addition methods, and this structure is proposed for the first time in the yarn uniformity detection of aero-engine fan blade preforms (which can be extended to three-dimensional braided / woven preforms), thus demonstrating obvious innovation.

[0133] S4. Input the comprehensive features into the context decoupled detection head module, decouple the intersection point detection task into two subtasks of center point prediction and size estimation, and obtain the center position of the intersection point in the detection box and the width and height of the detection box. The context decoupled detection head module designed in this embodiment consists of a center point attention module, a size attention module, and an offset attention module. The specific process includes the following steps:

[0134] S41. The center point attention module converts the position prediction in the intersection point detection task into the prediction of the center point heat map, and optimizes the network training through the loss function to output the center position of the intersection point, so as to effectively improve the accuracy of center point prediction and reduce the missed detection of small-scale targets. In this embodiment, by adopting the center point heat map prediction method, the problem of insufficient detection accuracy of traditional position regression methods for small targets (preform intersection points) is solved. The specific process includes:

[0135] Generate the output heat map of the true center point: For the true center position of each intersection point, generate a two-dimensional Gaussian distribution on the output heat map to make the response value of the output heat map at the true center position the highest, that is, the target value , and the rest of the area decays according to the distance from the center. The expression is:

[0136] ;

[0137] In the formula, is the true center coordinate position of the intersection point; is the standard deviation parameter that controls the size of the Gaussian response region, usually determined according to the size of the intersection point.

[0138] Output of the network prediction heatmap:

[0139] The network outputs a prediction heatmap with the same size as the input image , and the predicted value at each position in the heatmap represents the probability or confidence that there is an intersection center at that position;

[0140] Loss function for optimizing heatmap prediction:

[0141] To optimize the network's prediction of the heatmap, a focal loss function is adopted to effectively alleviate the problem of imbalance between positive and negative samples. Its definition is:

[0142] ;

[0143] In the formula, is the predicted value of the network prediction heatmap at the position (i,j); is the label value of the true heatmap at the position (i,j); is the modulation factor of the focal loss, usually set to 2; is the number of true intersection points in the image, used to normalize the loss.

[0144] During the training process, by minimizing the optimization function , the output heatmap has a response value close to 1 at the center of the true intersection point, and a response value close to 0 in the background area;

[0145] In the inference stage, by performing local maximum detection (peak detection) on the output heatmap , the rough center position of each intersection point is determined, and then the center point position is sub-pixel corrected by combining offset prediction to obtain the final accurate center point position of the intersection point.

[0146] S42. Size attention module, independently predicting the detection box size including width and height for the center position of each intersection point, and using the loss function to optimize the prediction error, effectively ensuring the accuracy and stability of the detection box size prediction. Since the loss function is more robust to outliers and can avoid excessive loss caused by individual abnormal samples, thus ensuring the stability of training.

[0147] Among them, in this embodiment, a special size attention module is used to predict the detection box size of each intersection point. For the center position of each intersection point, the network outputs two values in parallel on the same feature map, namely the predicted width and the predicted height. During training, using the width and height of the true detection box of the intersection point as the supervision annotation, the loss function is used for regression optimization, and the expression is:

[0148] ;

[0149] In the formula, is the number of true intersection points in the image; and are the predicted width and height of the i-th intersection detection box; and are the true width and height of the i-th intersection detection box.

[0150] In this embodiment, by minimizing this loss, the network is driven to output accurate size predictions. After training, the size attention module learns to give relatively accurate size estimates in pixels. In the inference stage, the and output by the network are directly read for the center points detected in each heatmap as the sizes of the detection boxes. In this way, through the cooperation of the center point heatmap and size regression, the center and size of the positioning box are determined for each intersection point. The independent size prediction branch can avoid interference with the center positioning task and improve the independent optimization effect of the two tasks, thus making the size prediction more accurate and stable.

[0151] S43. Offset attention module, predicts the slight offset of the actual center position of the intersection point relative to the center position of the predicted heatmap, and uses the loss function to reduce the position prediction error and further improve the refinement of intersection point positioning. The expression of the loss function is:

[0152] ;

[0153] In the formula, is the number of true intersection points in the image; and are the offsets of the center of the i-th intersection point predicted by the network relative to the grid; and are the corresponding true offsets; is the smooth absolute value loss function, which is a loss function used to measure the predicted offset error.

[0154] When this loss is minimized, it means that the prediction of the intersection point center is very close to the true position. In this embodiment is defined as: 0.5e when |e| < 1 2 , and |e| - 0.5 when |e| ≥ 1. This piecewise function gives a quadratic penalty when the error is small, thereby improving the accuracy; and gives a linear penalty when the error is large, thereby ensuring stability.

[0155] In this embodiment, by optimizing the loss function , it is ensured that the offsets and It highly coincides with the true value, enabling the positioning accuracy of the center of the intersection point to reach the sub-pixel level. In the above method proposed in this embodiment:

[0156] First, the detection task is decoupled into two sub-tasks: center positioning and size estimation. Each sub-task is processed by a dedicated module, reducing the task complexity and avoiding the instability that may be caused by directly regressing the entire bounding box. The center point attention module effectively improves the detection rate of dense small targets (intersection points) and significantly reduces the missed detection rate; the size attention module independently predicts and optimizes with a loss function to ensure the accuracy of the size of the detection box and avoid the problem of abnormal size caused by positioning deviation; the offset attention module further refines the center position, controlling the positioning error within the sub-pixel range.

[0157] Second, the introduction of the attention mechanism (center point attention, size attention, offset attention) means that the network allocates focus resources in these three branches, thus improving the prediction quality of key elements (position, size).

[0158] Third, through reasonable loss function design, the training process is more stable, correct predictions with high confidence are strengthened, and incorrect predictions with low confidence are suppressed.

[0159] The method of the present invention reduces false detection and missed detection, and is especially more accurate in positioning small-size intersection points; in terms of evaluation indicators, both the average false detection rate and the missed detection rate are significantly reduced. Therefore, the design of the context decoupled detection head module significantly improves the accuracy, stability and robustness of intersection point detection, providing reliable data support for subsequent uniformity evaluation.

[0160] S5. Define the threshold of the image edge region, delimit the effective detection region based on the detection box, and eliminate the incomplete intersection points existing on the image edge to obtain the position distribution of effective intersection points within the effective detection region. During the detection and positioning process of intersection points, due to the limitation of the imaging field of view, the intersection points located at the image boundary are often incomplete, and these incomplete intersection points may bring errors to the subsequent yarn uniformity calculation, affecting the accuracy and stability of the detection results. Therefore, this embodiment proposes an edge intersection point removal module to effectively exclude the incomplete intersection points at the image edge, significantly improving the accuracy and reliability of uniformity evaluation. In step S5, the specific process includes the following steps:

[0161] S51. According to the production practice experience and the boundary characteristics of intersection point detection, define the threshold of the image edge region for accurately delimiting the effective detection region and eliminating the possible incomplete edge intersection points. The threshold of the image edge region is used to delimit the reliable detection region in the image and exclude the regions where the intersection points are incomplete due to insufficient imaging field of view. The specific method is as follows:

[0162] According to the average detection box size of the intersection points in the preform image, let the average width of the intersection point detection box be and the average height be . Taking and as the reference, define the left and right edge thresholds and of the image, as well as the upper and lower edge thresholds and , that is:

[0163] ;

[0164] where and are the total width and height of the image respectively.

[0165] Any intersection point center located at , , or is regarded as an incomplete point and must be excluded. This method uses the average size of the detection box as a reference, which can better reflect the possible defect problems in the edge area of the image, so that the subsequent uniformity evaluation is only carried out in the complete area.

[0166] S52. In all the detected intersection point sets , identify and mark the incomplete intersection points located at the image edge, which are defined as follows:

[0167] ;

[0168] where is the center point of the intersection point, and is the center coordinate; , , , represent the preset left, right, upper, and lower boundary thresholds respectively; is the horizontal coordinate of the i-th valid intersection point in the image; is the vertical coordinate of the i-th valid intersection point in the image;

[0169] S53. Calculate the average value of the right boundaries of the incomplete intersection points located at the left edge in the detection box, denoted as the average boundary , that is:

[0170] ;

[0171] In the formula, represents the right boundary position of the detection box of the incomplete intersection points at the left edge, and the superscript Indicates taking the average value, i.e., average; is the number of left edge intersection points; is the abscissa position of the right boundary of the right boundary of the j-th left edge incomplete intersection point detection box;

[0172] S54. According to the average boundary Establish an effective detection boundary standard, and all detection boxes with the center points of intersection points located on the left side of this boundary are removed, that is:

[0173] ;

[0174] In the formula, represents the set of effective intersection points, that is, the set of the centers of the remaining intersection points after removing the edge incomplete points. All the points in this set are located within the effective detection area of the image and are the point set finally used for uniformity evaluation; represents the j-th intersection point after boundary screening; are the abscissa and ordinate of the center of the intersection point, used to determine whether the position of the point is on the left or right side of a certain threshold;

[0175] In step S54, "j" represents the points used for screening in the set of all intersection points, emphasizing that this set has been processed through the previous steps before differentiation to avoid symbol confusion and highlight the independence and clarity of the screening process.

[0176] Specifically, the specific process of establishing the effective detection boundary standard includes the following steps:

[0177] S541. Statistically calculate the average value of the abscissa of the right boundary of all detection boxes of the left edge incomplete intersection points in the image , used to determine the left boundary of the effective detection area, and the expression is:

[0178] ;

[0179] In the formula, is the abscissa value of the right boundary of the i-th incomplete intersection point detection box located on the left edge of the image; N is the total number of incomplete intersection points located on the left edge of the image;

[0180] S542. Based on the average abscissa value , define the effective detection area of the left boundary of the image;

[0181] If the abscissa value of the center point of the intersection point , then it is considered that this intersection point is complete and effective; if the abscissa value of the center point of the intersection point , it is considered that the intersection point is located in the edge area and belongs to an incomplete intersection point, which should be excluded from subsequent evaluations; the expression is:

[0182] ;

[0183] S543. Repeat steps S541 - S542 to process the right, upper, and lower edge areas of the image respectively, so as to establish an effective detection boundary standard with four boundary directions, and finally determine the set of intersection points in the overall effective detection area. Through this method, the interference of incomplete intersection points located at the image edge to the uniformity evaluation can be effectively excluded, improving the evaluation accuracy and reliability.

[0184] S55. Process the other edge areas of the image (i.e., the remaining upper, lower, and right boundaries) according to the above standards, so as to obtain a set of effective detection points after removing the incomplete intersection points at the edges , the expression is:

[0185] ;

[0186] In this embodiment, the processing of the left edge in steps S53 - S54 is also applied to the other edge areas of the image, that is, the remaining upper, lower, and right boundaries. In other words, for each edge, the following process is "repeated": find the incomplete points of the edge, calculate the average boundary, establish the threshold standard, and remove the invalid points of the edge. Step S55 precisely illustrates that the upper edge, lower edge, and right edge are processed through a similar method to ensure that all incomplete intersection points at the four boundaries are excluded. Finally, a set of effective detection points after processing all edges is obtained .

[0187] Through the above - mentioned edge intersection point removal steps, the calculation deviation of the yarn uniformity index caused by incomplete edge intersection points can be effectively avoided, improving the accuracy of the uniformity evaluation result and ensuring the industrial reliability and practical application value of the detection result.

[0188] S6. Calculate the evaluation index for evaluating the yarn distribution uniformity in the fan blade preform according to the position distribution of effective intersection points , realizing the accurate evaluation of the yarn uniformity of the preform. The specific process includes the following steps:

[0189] S61. According to the position distribution of the effective intersection points located in the effective detection area after step S5 processing, calculate the actual area of the effective detection area , providing an accurate spatial calculation basis for the uniformity evaluation;

[0190] After the edge processing in step S5, the boundary coordinates of the effective detection area in the image are determined. Determine the boundary coordinates of the effective detection area in the image, that is: and , where (left boundary), (right boundary), (upper boundary), (lower boundary), and these boundaries together enclose a rectangular area, which is the effective detection area. The actual area The calculation formula is:

[0191] ;

[0192] The actual area is the area of the region in the image that is truly used for uniformity calculation after removing the incomplete intersection points at the edges.

[0193] S62. Count the number of intersection points in the effective area after edge processing , and use the number of intersection points per unit area as the evaluation index for yarn uniformity , accurately quantify and evaluate the weaving quality and uniformity of the fan blade preform, that is:

[0194] ;

[0195] In this embodiment, the yarn uniformity evaluation index can provide reference for process designers and production quality inspectors. Compare the yarn uniformity evaluation index calculated in actual production with the design value of each preform component to check whether the number of intersection points per unit area is too high or too low to determine the uniformity.

[0196] During evaluation, compare the calculated yarn uniformity evaluation index with the expected ideal uniformity value or the value of the product at the design stage to judge the uniformity of the preform yarn distribution. The evaluation basis usually comes from design or empirical standards: for example, according to the process requirements of the preform, the ideal number of intersection points per unit area is .

[0197] If the yarn uniformity evaluation index is close to the reference value , and within the allowable error range (the empirical value according to the on-site process requirements is generally 0.2%), it is considered that the yarn distribution uniformity of the fan blade preform is good and meets the quality requirements. At this time, the conclusion can be given: the weaving quality of the preform is reliable, and the yarn density in each area is balanced.

[0198] If the yarn uniformity evaluation index is significantly lower than the reference value , it indicates that there are too few yarn interlacing points per unit area, and the yarn density may be on the low side, resulting in sparse or leaky weaving; conversely, if the yarn uniformity evaluation index is much higher than the reference value , it may also mean that the local yarns are crowded or repeated, indicating uneven weaving. Therefore, the real-time calculation of uniformity will provide real-time uniformity information reference for the on-site production department and production personnel.

[0199] Those of ordinary skill in the art can understand that all or part of the steps in the methods of the above embodiments can be completed by instructing relevant hardware through a program. Therefore, this application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, this application can be in the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0200] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. For the same or similar parts among the embodiments, reference can be made to each other. For the above embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and reference can be made to the partial description of the method embodiments for the relevant parts.

[0201] The above embodiments have introduced the present invention in detail. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A method for detecting uniformity of an aircraft engine fan blade preform, characterized in that: The method comprises the following steps: S1. Acquire the original image collected in real time from the production line, and correct the interweaving points of the carbon fiber horizontal and vertical yarns in the original image to a standard angle presented at a uniform viewing angle through an image angle standardization module; S2, based on the global path and the local path of the dual-path feature extraction network, extract features from the corrected original image to obtain dual-path features; S3, fusing dual-path features to obtain fused features through a dual-path feature fusion network using a cross-attention mechanism and a multi-scale self-attention mechanism; S4, input the fused features into the context decoupling detection head module, decouple the interweaving point detection task into two subtasks: center point prediction and size estimation, and obtain the center position of the interweaving point in the detection frame and the width and height of the detection frame; S5, defining an image edge region threshold, demarcating an effective detection region based on a detection frame and removing incomplete interlaced points existing at the edge of the image, and obtaining a position distribution of effective interlaced points within the effective detection region; S6. Calculate the evaluation index for evaluating the uniformity of yarn distribution in the fan blade preform based on the effective interlacing point position distribution , achieving accurate evaluation of preform yarn uniformity.

2. The uniformity detection method according to claim 1, characterized in that: In step S1, the specific process includes the following steps: S11. Using the ResNet50 network model as the basic feature extraction network, the initial feature map is extracted from the original image, and then the feature pyramid network is used to generate multi-scale feature maps layer by layer to capture the visual features of interweaving points at different scales. S12. Setting a rotation sensitive anchor frame according to different sizes and tilt angles of the yarn interlacing points , the expression is: ； in, is the center coordinate of the rotation-sensitive anchor box; is the width and height of the rotation-sensitive anchor box; is the rotation angle of the rotation-sensitive anchor box; S13, based on rotation-sensitive anchor box Use the region proposal network head to generate the rotation candidate region and obtain the angle prediction value of the rotation multi-scale feature map , and unify the multi-scale feature maps of different sizes into a feature map of fixed size containing interlaced points through ROIAlign operation; S14. Develop an abnormal angle filtering mechanism, through the angle threshold Angle prediction value The abnormal angles in are eliminated, and the expression is: ； in, is the predicted angle value that has been retained; is the rotation interlaced point feature map The angle prediction value of is the predicted mean of the rotation angle; S15, angle prediction value The correction angle is obtained by averaging , the original image is corrected by the rotation transformation matrix, and the rotation transformation matrix is: ； in, represents the pixel coordinates of the interlaced points in the original image; is the coordinate of the interlaced point after the rotation transformation matrix.

3. The uniformity detection method according to claim 2, characterized in that: The rotation angle regression branch is introduced into the region proposal network head, namely: First, for each initial rotation-sensitive anchor box A series of discrete initial angles are assigned to cover possible weave texture tilt angles; Then, the region proposal network head uses convolutional features to represent each rotation-sensitive anchor box. The angle offset is used for regression prediction to obtain the rotation-sensitive anchor frame The correction value relative to its initial angle , rotation sensitive anchor box The final predicted rotation angle is recorded as , and its calculation formula is: ； In the formula, is a rotation-sensitive anchor box The initial angle of is the angle increment of the regression output of the region proposal network head.

4. The uniformity detection method according to claim 1, characterized in that: In step S2, the dual-path features include global semantic features for characterizing the overall spatial distribution and contextual semantic features of the interweaving points, and local spatial detail features including detail textures of the interweaving points and local fine spatial information. The specific process includes the following steps: S21, the global path adopts a global feature extraction architecture based on visual Transformer, and captures the overall spatial distribution and contextual semantic features of the preform interweaving points through the self-attention mechanism; S22, the local path adopts the classic convolutional neural network structure, and effectively extracts the detailed texture and local fine spatial information of the interweaving points through multi-layer convolution operations; S23, define the feature outputs of the global path and the local path respectively and ,Right now: ； in, Represents the mapping function of extracting global semantic features through visual Transformer; Represents the mapping function of extracting local spatial detail features through a classic convolutional neural network.

5. The uniformity detection method according to claim 1, characterized in that: In step S3, the specific process includes the following steps: S31. Use the cross-attention mechanism to take the global semantic features output by the global path as the query, and the local spatial detail features output by the local path as the key and value respectively, to achieve deep interactive fusion between the two path features to obtain the fused features. , the expression is: ； Among them, query ;key ;value is the feature transformation matrix; is a learnable parameter; is the feature dimension; S32, using the multi-scale self-attention mechanism to fusion features at multiple scales Perform weighted integration to capture the cross-scale dependencies between intertwined points of different scales to obtain comprehensive features , the expression is: ； in, represents a set of scales; Indicates the corresponding scale The attention weight coefficient under ; Represents the comprehensive features after fusion of multi-scale self-attention mechanism; represents the selected scale set; Indicated in scale The fusion features obtained below.

6. The uniformity detection method according to claim 1, characterized in that: In step S4, the context decoupling detection head module includes a center point attention module, a size attention module and an offset attention module. The specific process includes the following steps: S41, center point attention module, converts the position prediction in the intersection point detection task into the center point heat map prediction through the loss function Optimize the center position of the network training output interlacing point, the expression is: ； In the formula, Predict the predicted value of the heat map at position (i, j) for the network; is the label value of the real heat map at position (i, j); is the modulation factor of focus loss; is the number of real interlaced points in the image; S42, size attention module, independently predicts the detection box size including width and height of each intersection center position, and uses the loss function Optimize the prediction error, the expression is: ； In the formula, and is the predicted width and height of the i-th intersection point detection box; and is the actual width and height of the i-th intersection point detection box; S43, offset attention module, predicts the slight offset of the actual center position of the interweaving point relative to the predicted center position of the heat map, and uses the loss function Reduce the position prediction error and further improve the precision of the intersection point positioning. The loss function The expression is: ； In the formula, and is the offset of the center of the i-th interlaced point predicted by the network relative to the grid; and is the corresponding true offset; It is a smoothed absolute value loss function, which is a loss function used to measure the prediction offset error.

7. The uniformity detection method according to claim 1, characterized in that: In step S5, the specific process includes the following steps: S51, defining an image edge region threshold to accurately define an effective detection region and remove possible incomplete edge interlacing points; S52, a set of all detected interweaving points In the above example, the incomplete interlaced points at the edge of the image are identified and marked, which are defined as follows: ； in, is the center point of the interlaced points, and is the center coordinate; , , , Respectively represent the preset left, right, upper and lower boundary thresholds; is the horizontal coordinate of the i-th valid interlacing point in the image; is the vertical coordinate of the i-th valid interlacing point in the image; S53, calculating the average value of the right boundary of the incomplete interweaving point at the left edge of the detection frame, and recording it as the average boundary ,Right now: ； In the formula, is the number of interlacing points on the left edge; For the The horizontal coordinate position of the right boundary of the left edge incomplete interweaving point detection frame; S54, according to the average boundary The effective detection boundary standard is established, and the detection boxes whose center points of all interlaced points are located on the left side of the boundary are removed, that is: ； In the formula, represents the set of valid interleaving points; represents the jth interlaced point after boundary screening; are the abscissa and ordinate of the center of the interlacing point; S55: Process the edge regions including the upper, lower and right borders of the image according to the above standards, so as to obtain a set of valid detection points after removing the incomplete interlaced points at the edges. .

8. The uniformity detection method according to claim 7, characterized in that: In step S54, the specific process of establishing the effective detection boundary standard includes the following steps: S541, counting the average value of the horizontal coordinates of the right borders of all incomplete interlaced point detection boxes located at the left edge of the image , used to determine the left boundary of the effective detection area, the expression is: ； In the formula, is the right boundary abscissa value of the i-th incomplete interlaced point detection frame located at the left edge of the image; N is the total number of incomplete interlaced points located at the left edge of the image; S542, average value of horizontal axis As a benchmark, define the effective detection area on the left edge of the image; If the horizontal coordinate value of the center point of the intersection point , then the intersection point is considered complete and valid; if the horizontal coordinate value of the center point of the intersection point is , then the intersection is considered to be located in the edge area and is an incomplete intersection, and should be excluded from subsequent evaluation; S543, repeating steps S541-S542, processing the right, upper and lower edge regions of the image respectively, to establish an effective detection boundary standard with four boundary directions.

9. The uniformity detection method according to claim 1, characterized in that: In step S6, the specific process includes the following steps: S61. Calculate the actual area of ​​the effective detection area , the calculation formula is: ； In the formula, , is the boundary coordinate of the effective detection area in the image; S62. Count the number of intersection points in the effective area The number of interlacing points per unit area is used as the evaluation index of yarn uniformity. , accurately and quantitatively evaluate the weaving quality and uniformity of fan blade preforms, namely: ； If the yarn uniformity evaluation index Close to reference value , and it is within the allowable error range, then it is considered that the yarn distribution uniformity of the fan blade preform is good and meets the quality requirements; If the yarn uniformity evaluation index Significantly lower than the reference value , indicating that there are too few yarn interlacing points per unit area, the yarn density may be too small, and there are sparse weaving or holes; on the contrary, if the yarn uniformity evaluation index Higher than reference value , meaning localized yarn crowding or duplication, indicating uneven weaving.

Images