Intelligent detection method and system for steel surface defect identification

Abstract

The invention discloses an intelligent detection method for steel surface defect identification, which comprises the following steps: S1, image acquisition: acquiring images in real time, setting trigger conditions according to requirements, shooting at fixed time or triggering by external signals, and capturing images at specified time; s2, image preprocessing: preprocessing the collected image, wherein the preprocessing comprises the steps of image zooming and color space conversion; s3, defect detection: inputting the preprocessed image into a target detection model for reasoning, and outputting a detection result including the category and bounding box coordinates of each target; and S4, result display and positioning: drawing a bounding box and a category label on the original image, and visualizing the detection result. The invention also discloses an intelligent detection system for steel surface defect identification. The method aims at solving the technical problems in the aspects of accuracy and efficiency in the steel surface defect detection process, and can be widely applied to the technical field of deep learning.

Description

Technical Field

[0001] The present invention relates to the field of deep learning technology, and in particular to an intelligent detection method and system for identifying surface defects of steel. Background Art

[0002] Steel is vital in modern industry. The equipment, processing parameters and raw material quality in its production process will affect the performance of the final product. Surface defects such as cracks and scratches will reduce its safety. The existing technologies mainly include traditional manual detection methods and eddy current detection technology.

[0003] Traditional manual inspection methods rely on the experience and skills of inspectors, usually through visual inspection or using handheld inspection equipment. This method is slow, inefficient, and prone to missed or false detection.

[0004] Eddy Current Testing (ECT) is a non-destructive testing technology based on the principle of electromagnetic induction. When an alternating current passes through the coil in the eddy current probe, an alternating magnetic field is generated. When it is close to a conductive material, this magnetic field will generate eddy currents inside the material. The intensity and distribution of eddy currents are affected by the electrical conductivity, magnetic permeability and geometry of the material. If there are defects in the material (such as cracks and holes), the characteristics of the eddy current will change, thereby affecting the electrical signal sensed by the probe. By processing and analyzing these signals, defects in the material can be identified. ECT has high sensitivity and can detect tiny defects on the surface of steel. It can make up for the problems of traditional manual detection methods to a certain extent and improve detection efficiency and quality.

[0005] Eddy current testing technology is a non-destructive testing method, which is widely used in the detection of metal materials. It is mainly used to detect surface and near-surface defects, such as cracks, inclusions, delamination, etc. When there are defects in the material, such as cracks or holes, the normal distribution of eddy currents will be destroyed, resulting in changes in the eddy current path, eddy current intensity and distribution. Eddy current testing technology has the characteristics of high sensitivity and rapid detection, and is currently widely used in industrial production processes. However, it has obvious disadvantages: First, the selection of detection frequency affects the detection effect. Generally speaking, high-frequency eddy currents can detect surface defects, and low-frequency eddy currents can detect deep defects. The selection of inspection frequency often depends on human experience, which is prone to errors in detection results; second, eddy current testing is easily limited by material thickness, shape and size. Too thick or too thin materials may affect the accuracy and stability of detection, and there may be missed detection or false detection of very small or very large defects. Summary of the invention

[0006] The purpose of the present invention is to overcome the shortcomings of the above-mentioned background technology and provide an intelligent detection method and system for steel surface defect identification, so as to solve the technical problems of accuracy and efficiency in the process of steel surface defect detection. By applying intelligent visual recognition technology, defects on the steel surface can be detected more accurately and quickly, and the detection efficiency and accuracy can be improved.

[0007] The present invention provides an intelligent detection method for steel surface defect identification, comprising the following steps: S1, image acquisition: real-time image acquisition, setting trigger conditions according to needs, timing photography or external signal triggering, and capturing images at a specified time; S2, image preprocessing: preprocessing the acquired image, including image scaling and color space conversion steps; S3, defect detection: inputting the preprocessed image into a target detection model for inference, and outputting detection results including the category and bounding box coordinates of each target; S4, result display and positioning: drawing bounding boxes and category labels on the original image to visualize the detection results.

[0008] In the above technical scheme, the specific process of step S3 is as follows: S31, target detection model construction: construct a model consisting of a backbone network, a neck network and a detection head; the backbone network introduces a deep separable convolutional network to extract features; the neck network adopts a C3 module and a bidirectional feature pyramid network to fuse features, wherein the C3 module filters background interference, and the bidirectional feature pyramid network enhances the expression ability of features at each scale; the detection head constructs the final target classification and bounding box regression; S32, target detection model training: input the preprocessed image data into the target detection model for training, and the target detection model training adopts a large-scale open source NEU surface defect detection data set; S33, target detection model reasoning: input the real-time collected image into the trained model, and the model calculates the prediction results of each grid unit including the target category, bounding box position and confidence. After non-maximum suppression, duplicate detection results are removed, the bounding box with the highest confidence is retained, and the category and bounding box coordinates of each detected target are output.

[0009] In the above technical solution, in the step S31, the specific process of introducing the deep separable convolutional network to extract features in the backbone network is as follows: input feature map convolution operation: use N convolution kernels with a size of S×S and a depth of M to perform a convolution operation on the input feature map to obtain N H×W feature maps, and the parameter quantity of the convolution operation is: P1=S×S×M×N; deep separable convolutional network operation: use M convolution kernels with a size of S×S and a depth of 1 to perform a deep convolution operation on the input feature map. Convolution is performed point by point to obtain M H×W feature maps, and the parameter quantity is: P2 = S×S×1×M; then N convolution kernels of size 1×1 and depth M are used to perform point-by-point convolution on the output of the convolution operation of the input feature map to generate N H×W feature maps, and the parameter quantity is: P3 = 1×1×M×N. The total parameter quantity of the depthwise separable convolutional network operation is: P4 = S×S×1×M+1×1×M×N. The ratio of the parameter quantity of the depthwise separable convolutional network operation to that of the ordinary convolution is:

[0010]

[0011] In the above technical solution, in step S31, the specific working process of the C3 module in the neck network is as follows: the C3 module adopts a SiLU structure, including a main branch and an auxiliary branch, wherein the main branch includes a convolution model and a Bottleneck block model, and the auxiliary branch includes a convolution model. The output obtained by the auxiliary branch is connected with the result calculated by the main branch, and then the feature information is further integrated through a convolution model again. The three convolution models all perform a 1×1 convolution operation.

[0012] In the above technical solution, in step S31, the specific working process of the Bottleneck block model of the C3 module in the neck network is as follows: the Bottleneck block model includes two branches, wherein the first branch firstly reduces the number of channels of the feature map by half through a 1×1 convolution, and then extracts features through a 3×3 convolution and doubles the number of channels; the second branch performs a residual connection through a shortcut, adds the original input to the feature map after the convolution operation, and realizes feature fusion.

[0013] In the above technical solution, in step S31, the specific working process of the bidirectional feature pyramid network in the neck network is as follows: first, remove the input nodes with low contribution to feature fusion; second, the bidirectional feature pyramid network locates and identifies targets at various scales by introducing cross-scale connections from features at various scales; third, introduce a weighted feature fusion mechanism to fuse the features of each scale after connection, and the features at each level are assigned corresponding weights. These weights are automatically learned during the training process to ensure the best integrated features.

[0014] In the above technical solution, in step S32, when the target detection model trains the open source NEU surface defect detection dataset, the target detection model optimizes parameters by minimizing the loss function, and the loss function includes classification loss, bounding box regression loss and confidence loss.

[0015] The above technical solution also includes step S5, defect type warning: storing the detection results and sending warnings for defects that reach a threshold.

[0016] In the above technical solution, step S6, process control, is also included: the controller determines whether the image sensor reaches the moving threshold. If not, it continues the detection after moving the specified distance; if it reaches, it requests a reset instruction; if reset is selected, the new steel sample detection continues; if not reset is selected, the detection process ends.

[0017] The present invention also provides an intelligent detection system for steel surface defect identification, which has a computer program capable of executing the intelligent detection method for steel surface defect identification.

[0018] The intelligent detection method and system for steel surface defect identification of the present invention have the following features:

[0019] Beneficial effects:

[0020] (1) The core part of the present invention adopts machine vision technology, which performs automated detection through preset algorithms and models, and can maintain consistent detection standards under different detection conditions, ensuring the repeatability and reliability of each detection and reducing the interference of human factors.

[0021] (2) The present invention can capture rich information in the image, including color, shape, texture, etc., which can better identify and classify various types of defects and improve the accuracy of detection. In contrast, eddy current detection mainly relies on electromagnetic signals and is difficult to provide comprehensive defect characteristics.

[0022] (3) The data preprocessing step and defect detection step in the present invention can be flexibly adapted to the detection of products of different materials, shapes and sizes by adjusting algorithms and parameters; however, eddy current detection is limited by material thickness and shape and is difficult to adapt to diverse detection needs.

[0023] (4) The present invention can process a large number of images quickly and provide timely feedback of the detection results. Real-time detection determines that it is suitable for online detection on the production line. Eddy current detection usually requires a long preparation and adjustment time, especially in frequency selection and equipment calibration.

[0024] (5) Wide range of detection types: The present invention can detect six types of steel defects, including foreign matter inclusions, scratches, cracks, plaques, rolling oxidation and surface pitting, while eddy current detection is mainly applicable to specific defect types (such as cracks in conductive materials). BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 It is a functional schematic diagram of the intelligent detection method and system for steel surface defect identification of the present invention;

[0026] Figure 2 It is a schematic diagram of the overall process of the intelligent detection method for steel surface defect identification of the present invention;

[0027] Figure 3 It is a flow chart of step S4 of the intelligent detection method for steel surface defect identification of the present invention;

[0028] Figure 4 Schematic diagram of the workflow of each algorithm in step S41 of the intelligent detection method for steel surface defect identification of the present invention;

[0029] Figure 5 Schematic diagram of the topological structure of the C3 module in step S412 of the intelligent detection method for steel surface defect identification of the present invention;

[0030] Figure 6 Schematic diagram of the topological structure of the Bottleneck block in the C3 module of step S412 of the intelligent detection method for steel surface defect identification of the present invention;

[0031] Figure 7 It is a schematic diagram of the workflow of the bidirectional feature pyramid network in step S413 of the intelligent detection method for steel surface defect identification of the present invention;

[0032] Figure 8 Schematic diagram of six main defects on the surface of steel included in the large-scale open source NEU surface defect detection data set in step S42 of the intelligent detection method for steel surface defect identification of the present invention;

[0033] Fig. 9 It is a schematic diagram of the architecture of the intelligent detection system for steel surface defect identification according to the present invention;

[0034] Fig.10 Schematic diagram of the results of qualitative comparison between the intelligent detection method and system for steel surface defect identification and other deep learning detection algorithms. DETAILED DESCRIPTION

[0035] The present invention is further described in detail below in conjunction with the accompanying drawings and embodiments, but the embodiments should not be construed as limiting the present invention.

[0036] The detection technology based on intelligent machine vision (the method related to the present invention) uses image processing and computer vision algorithms to automatically detect defects on the surface of products. The basic principle is to capture the image of the object to be detected through a high-resolution camera, and then use image processing software to analyze the image. The intelligent algorithm unit (i.e., defect detection unit) identifies the location and type of defects through technologies such as feature extraction, image segmentation and pattern recognition.

[0037] The present invention requires the use of detection and analysis equipment, which mainly includes a data acquisition part and a system host part. The data acquisition part is mainly a camera (i.e., an image sensor) used to capture images of the steel surface; the system host part integrates data processing functions and intelligent algorithm functions. The data processing function pre-processes the collected images and detects the surface features of the steel, while the intelligent algorithm function is used to identify and analyze defects. This technical solution can improve detection accuracy and efficiency and reduce manpower input and costs.

[0038] 1. Technical functions (see Figure 1 )

[0039] Image sensor function: used to collect image information of the steel surface. The sensor module includes two types: RGB camera and depth camera.

[0040] Data processing function: Receive images collected by the sensor and perform cropping and filtering on the signals to extract useful information and reduce noise interference.

[0041] Intelligent algorithm function: An innovative target detection algorithm is used to analyze and process the collected data to identify and classify defects on the steel surface.

[0042] Display and alarm function: The test results are displayed on the human-machine interface, and the corresponding alarm mechanism is triggered according to the test results to remind the operator to carry out subsequent processing.

[0043] 2. Technical solution

[0044] See also Figure 2 The workflow of the intelligent detection method for steel surface defect identification of the present invention can be divided into the following steps:

[0045] S1. MCU initialization: Hardware preparation: Ensure that the camera module is installed correctly and connected to the computing platform. Configure the camera parameters, such as resolution, frame rate, exposure time, etc., to ensure the shooting quality.

[0046] S2, Image acquisition: Start the motor and start real-time image acquisition. Set the trigger conditions according to your needs. You can choose to take pictures at a fixed time or trigger with an external signal to capture images at a specified time.

[0047] S3, image preprocessing: preprocess the collected images to improve the effect of subsequent detection, including image scaling and color space conversion (from BGR to RGB).

[0048] S4, defect detection: The preprocessed image is input into the object detection model for inference. The model will output the detection results, including the category and bounding box coordinates of each object.

[0049] The defect detection step, i.e. the intelligent algorithm function, is the core content of the present invention, which is equipped with a new improved YOLOv9 network. The construction principle and process of this step are introduced below. Figure 3 :

[0050] S41. Target detection model construction: The model mainly consists of three parts: backbone network (Backbone), neck network (Neck) and detection head (Head). The backbone network Backbone is responsible for feature extraction, using a deep separable convolutional network based on the YOLOv9 structure; the neck network Neck is used for feature fusion, in which the C3 module and the bidirectional feature pyramid network are added to filter background interference and enhance the expression ability of features of different scales respectively; the detection head Head is responsible for the final target classification and bounding box regression.

[0051] The algorithm embedded in step S41 is as follows. Figure 4 :

[0052] S411. Introducing the deep separable convolutional (DWConv) network into the backbone network structure reduces redundant feature information, reduces the number of parameters of the target detection model, and speeds up the inference speed of the target detection model.

[0053] In one or more embodiments,

[0054] Use N convolution kernels of size S×S and depth M to perform convolution operation on the input feature map to obtain N feature maps of H×W. The number of parameters in this process is: P1 = S×S×M×N.

[0055] The process of depth-wise separable convolution (DWConv): First, the input feature map is deep convolved through M convolution kernels of size S×S and depth 1 to obtain M H×W feature maps, and the parameter amount is: P2 = S×S×1×M; then N convolution kernels of size 1×1 and depth M are used to perform point-by-point convolution on the output of the previous step to generate N H×W feature maps, and the parameter amount is: P3 = 1×1×M×N. The total parameter amount of DWConv is: P4 = S×S×1×M+1×1×M×N, and the ratio of the parameter amount of DWConv and ordinary convolution is:

[0056]

[0057] In formula ①, the ratio of P4 to P1 is much less than 1, which means that using DWConv can significantly reduce the complexity of the model, reduce the computational cost, and improve the detection speed of the model.

[0058] S412. The C3 module is introduced into the neck network structure, which helps to filter background interference, allowing the object detection model to focus more on the target area of ​​interest, retaining key details in the image and producing clearer and more accurate output.

[0059] As an innovative component based on deep learning architecture, the structure of the C3 module includes three convolutional modules and n Bottleneck modules. The specific composition is as follows:

[0060] The main branch contains a Conv block and a Bottleneck block, and the auxiliary branch contains only one Conv block. The output is connected with the result of the main branch, and then further integrated with feature information through another Conv block. The Conv blocks here all perform 1×1 convolution operations. In addition, the C3 module uses SiLU (Sigmoid-like Unit) instead of the traditional LeakyReLU. The topology of the C3 module is as follows: Figure 5 shown.

[0061] The following is a detailed explanation of the Bottleneck block in the C3 module. The Bottleneck block also contains two branches. The first branch first halves the number of channels of the feature map through 1×1 convolution, then extracts features through 3×3 convolution and doubles the number of channels. The second branch performs residual connection through shortcut, adds the original input to the feature map after convolution operation, and realizes feature fusion. The topological structure of the Bottleneck block is as follows: Figure 6 shown.

[0062] S413, in the neck network structure based on YOLOv9, a bidirectional feature pyramid network (BiFPN) is introduced. By enhancing the target detection model's recognition of the geometric shape of the target in the image and its understanding of the scene environment, the target detection model can more accurately identify the edge and shape of the target, reducing missed detections and false alarms. For details, see Figure 7 :

[0063] The design of BiFPN is different from the existing spatial pyramid structure in that: first, some input nodes with low contribution to feature fusion are removed, such as Figure 7The P3 and P7 nodes shown. This improvement not only improves the efficiency of feature fusion, but also reduces network parameters and computational load. Secondly, by introducing cross-scale connections, BiFPN is able to fuse features from different scales, thereby accurately locating and identifying targets at different scales. In the feature fusion process, a weighted feature fusion mechanism is introduced, and features at different levels are assigned different weights, which are automatically learned during the training process to ensure the optimal integration of features.

[0064] S42. Target detection model training: Input the prepared data set into the target detection model for training. The large-scale open source NEU surface defect database (NEU-DET) is used for model training.

[0065] NEU-DET includes six main defects on the surface of steel, including inclusions (In), scratches (Sc), cracks (Cr), patches (Pa), rolled-in scale (Rs) and pitted surface (Ps). Figure 8 shown.

[0066] During the NEU-DET training process, the target detection model optimizes parameters by minimizing the loss function, which includes classification loss, bounding box regression loss, and confidence loss.

[0067] S43, object detection model reasoning: The new image collected by the camera module is input into the trained object detection model. The object detection model will calculate the prediction results of each grid cell, including the category, bounding box position and confidence of the target. After non-maximum suppression (NMS), duplicate detection results are removed and the bounding box with the highest confidence is retained. Finally, the category and bounding box coordinates of each detected target are output.

[0068] S5. Result display and positioning: Draw bounding boxes and category labels on the original image to intuitively visualize the detection results.

[0069] S6. Defect type warning: This link will store the detection results and send a warning when the defect threshold (length × width) is reached. The system will track further analysis and processing results.

[0070] S7, process control: MCU determines whether the camera module has reached the moving threshold. If not, it moves the specified distance and continues the detection. If it has reached, it requests a reset instruction. If reset is selected, the new steel sample detection will continue; if not, the process ends.

[0071] See also Fig. 9 The intelligent detection system for steel surface defect identification of the present invention comprises the following parts:

[0072] Controller initialization unit: Hardware preparation ensures that the camera module is installed correctly and connected to the computing platform. Configure the camera parameters, such as resolution, frame rate, exposure time, etc., to ensure the shooting quality;

[0073] Image acquisition unit: real-time image acquisition, set trigger conditions according to needs, take photos at regular intervals or trigger with external signals, and capture images at specified times;

[0074] Image preprocessing unit: preprocesses the collected images, including image scaling and color space conversion steps;

[0075] Defect detection unit: inputs the preprocessed image into the object detection model for inference, and outputs the detection results including the category and bounding box coordinates of each object;

[0076] Result display and positioning unit: draw bounding boxes and category labels on the original image to visualize the detection results;

[0077] Defect type warning unit: stores the test results and sends warnings for defects that reach the threshold;

[0078] Process control unit: The controller determines whether the image sensor reaches the moving threshold. If not, it moves the specified distance and continues the detection. If it reaches, it requests a reset instruction. If reset is selected, the new steel sample detection continues. If not reset is selected, the detection process ends.

[0079] 3. Comparative effect of the technical solution of the present invention and other defect detection algorithms

[0080] With the development of computer vision, there are many defect detection technologies based on deep learning. Different neural networks have different advantages and are suitable for images in different fields and with different characteristics. During the research and development of the present invention, comparative experiments were carried out on a variety of existing schemes. The existing methods can also achieve the task of steel surface defect detection to a certain extent, but they still have different shortcomings. For example, some models have too many parameters and too slow inference time, which are not suitable for deployment in embedded devices; some models have too high a missed detection rate or false alarm rate for a certain type of defect; some models have poor feature extraction capabilities for depth maps, etc. The following table is the experimental results obtained after quantitative comparison of various defect detection algorithms. At the same time, the results of qualitative comparison of the present invention with other deep learning detection algorithms can be found in Fig.10 .

[0081] Quantitative comparison results of different defect detection algorithms

[0082]

[0083] 4. Terminology

[0084] MCU——Microcontroller Unit, micro control unit.

[0085] YOLO——You Only Look Once, a deep learning target detection framework.

[0086] BGR, RGB - the three channels of color images, B stands for Blue, G stands for Green, and R stands for Red.

[0087] Precision: Accuracy P,

[0088] AP: Average Precision,

[0089] mAP: mean Average Precision,

[0090] Among them, T p Indicates the number of defect targets detected correctly; F p Indicates the number of defect targets that are falsely detected; F N The number of missed defect targets; n represents the number of defect categories; AP(i) is the average precision representing the i-th target class.

[0091] FPS: (Frames Per Second) indicates the number of image frames displayed per second. An index greater than 35FPS can meet real-time requirements.

[0092] GFLOPs: (Giga Floating-point Operations Per Second, 1 billion floating-point operations per second), often used as a GPU performance parameter to measure algorithm / model complexity.

[0093] Parameters: parameter quantity.

[0094] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

[0095] The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in this field.

Claims

1. An intelligent detection method for steel surface defect identification, characterized in that: The steps include: S1. Image acquisition: real-time image acquisition, set trigger conditions according to needs, take photos at regular intervals or trigger with external signals, and capture images at specified times; S2, image preprocessing: preprocessing the collected images, including image scaling and color space conversion steps; S3, defect detection: the preprocessed image is input into the object detection model for inference, and the detection results including the category and bounding box coordinates of each object are output; S4. Result display and positioning: Draw bounding boxes and category labels on the original image to visualize the detection results.

2. The intelligent detection method for steel surface defect identification according to claim 1 is characterized in that: The specific process of step S3 is as follows: S31, target detection model construction: construct a model consisting of a backbone network, a neck network and a detection head; the backbone network introduces a deep separable convolutional network to extract features; the neck network uses a C3 module and a bidirectional feature pyramid network to fuse features, wherein the C3 module filters background interference and the bidirectional feature pyramid network enhances the expression ability of features at each scale; the detection head constructs the final target classification and bounding box regression; S32, target detection model training: input the preprocessed image data into the target detection model for training. The target detection model training uses the large-scale open source NEU surface defect detection dataset; S33, target detection model reasoning: The real-time collected images are input into the trained model. The model calculates the prediction results of each grid unit, including the target category, bounding box position and confidence. After non-maximum suppression, duplicate detection results are removed, the bounding box with the highest confidence is retained, and the category and bounding box coordinates of each detected target are output.

3. The intelligent detection method for steel surface defect identification according to claim 2 is characterized in that: In step S31, the specific process of introducing the deep separable convolutional network into the backbone network to extract features is as follows: Convolution operation of input feature map: Use N convolution kernels of size S×S and depth M to perform convolution operation on the input feature map to obtain N H×W feature maps. The parameter quantity of this convolution operation is: P1=S×S×M×N; Depthwise separable convolutional network operation: Through M convolution kernels of size S×S and depth 1, the input feature map is deep convolved to obtain M H×W feature maps. The parameter quantity is: P2=S×S×1×M; then N convolution kernels of size 1×1 and depth M are used to perform point-by-point convolution on the output of the convolution operation of the input feature map to generate N H×W feature maps. The parameter quantity is: P3=1×1×M×N, then the total parameter quantity of the depthwise separable convolutional network operation is: P4=S×S×1×M+1×1×M×N, and the ratio of the parameter quantity of the depthwise separable convolutional network operation to that of the ordinary convolution is:

4. The intelligent detection method for steel surface defect identification according to claim 3 is characterized in that: In step S31, the specific working process of the C3 module in the neck network is as follows: The C3 module adopts a SiLU structure, which includes a main branch and an auxiliary branch. The main branch includes a convolution model and a Bottleneck block model, and the auxiliary branch includes a convolution model. The output of the auxiliary branch is connected with the result calculated by the main branch, and then the feature information is further integrated through a convolution model. The three convolution models all perform 1×1 convolution operations.

5. The intelligent detection method for steel surface defect identification according to claim 4 is characterized in that: In step S31, the specific working process of the Bottleneck block model of the C3 module in the neck network is as follows: The Bottleneck block model contains two branches. The first branch first halves the number of channels of the feature map through a 1×1 convolution, then extracts features through a 3×3 convolution and doubles the number of channels. The second branch performs a residual connection through a shortcut, adds the original input to the feature map after the convolution operation, and realizes feature fusion.

6. The intelligent detection method for steel surface defect identification according to claim 5 is characterized in that: In step S31, the specific working process of the bidirectional feature pyramid network in the neck network is as follows: First, remove the input nodes that have low contribution to feature fusion; Secondly, the bidirectional feature pyramid network locates and recognizes objects at various scales by introducing cross-scale connections between features from various scales; Third, a weighted feature fusion mechanism is introduced to fuse the features of each scale after connection. The features at each level are assigned corresponding weights, and these weights are automatically learned during the training process to ensure the best integrated features.

7. The intelligent detection method for steel surface defect identification according to claim 6, characterized in that: In step S32, when the target detection model trains the open source NEU surface defect detection dataset, the target detection model optimizes parameters by minimizing a loss function, where the loss function includes classification loss, bounding box regression loss, and confidence loss.

8. The intelligent detection method for steel surface defect identification according to claim 7, characterized in that: The method also includes step S5, defect type warning: storing the detection results and sending warnings for defects that reach a threshold.

9. The intelligent detection method for steel surface defect identification according to claim 8, characterized in that: It also includes step S6, process control: the controller determines whether the image sensor reaches the movement threshold. If not, it moves a specified distance and continues the detection; if it reaches, it requests a reset instruction; if reset is selected, the new steel sample detection continues; if not reset is selected, the detection process ends.

10. An intelligent detection system for steel surface defect identification, having a computer program, characterized in that: The computer program can execute the intelligent detection method for steel surface defect identification as described in any one of claims 1 to 9.

Images