Foreign matter monitoring method and device for automobile stamping die and automatic stamping production equipment

Abstract

The invention relates to a foreign matter monitoring method and device for an automobile stamping die and automatic stamping production equipment. The foreign matter monitoring method for the automobile stamping die comprises the steps that a die area image before a plate enters the die is obtained; segmenting the image by adopting a moving window mechanism to obtain a current mold small area image; meanwhile, a foreign matter image classification model and a foreign matter recognition model are adopted to classify and recognize the current mold small area image, and the classification result and the foreign matter confidence coefficient of the current mold small area image are obtained; then judging whether the classification result of the current small area image of the die and the confidence coefficient of the foreign matter meet a foreign matter condition or not: if not, conveying the plate material to the die for stamping, and conveying the stamped plate material to the next process; and if yes, early warning is conducted, and the mold is cleaned. According to the foreign matter monitoring method for the automobile stamping die, the false detection rate of the foreign matter is remarkably reduced, and the foreign matter recognition accuracy is improved.

Description

Technical Field

[0001] The invention relates to the field of automobile manufacturing, and in particular to a foreign matter monitoring method and device for automobile stamping dies and automatic stamping production equipment. Background Art

[0002] In the automobile manufacturing process, automobile production relies on four core processes: stamping, welding, painting and assembly. Among them, the stamping process is the initial forming process of the automobile, which is used to process sheet metal into large-sized metal parts such as the body and chassis. The stamping process uses high pressure to shape the metal sheet through the mold, that is, the mold is combined with the stamping machine, and the metal sheet is squeezed on the mold by the stamping machine to shape the metal sheet into the shape in the mold, obtain automobile parts, and transport the automobile parts to the next process.

[0003] The stamping process usually includes multiple forming operations, each of which gradually shapes the metal sheet into the desired shape. Therefore, when the structure of the mold is more complex or the material is deformed during the stamping process, scraps, waste or residual materials may be generated. Based on this, general processing workshops will use waste recycling mechanisms such as automatic conveyor belts, waste slides or high wind devices to recycle scraps or waste during the stamping process.

[0004] However, when the shape of scraps, waste or residual materials is irregular, or due to external factors such as vibration, improper operation, or even other unknown objects falling, they may be retained inside the mold, and because of their own irregular shape or structure, it is difficult to remove them by gravity or airflow, and eventually form foreign objects in the mold. These foreign objects may hinder the normal movement of the sheet in the mold, causing scratches, indentations or irregular deformation of the sheet, thus affecting the quality of the final product; in addition, foreign objects that remain for a long time may also cause wear on the mold surface, resulting in cracks or breaks in the mold, which in turn causes the production line to stop, seriously affecting production efficiency.

[0005] Based on this, the existing target detection model is used to monitor the stamping die in real time. Once foreign objects are found, an early warning is issued and the production line is suspended for on-site personnel to clean up. However, due to the large size of the die used in the automobile stamping process, the image input to the target detection model presents the characteristics of "large field of view, small target", which may cause the target detection model to mistakenly misjudge irrelevant details or noise as foreign objects, thereby triggering false alarms and causing unnecessary production line suspensions, seriously affecting production efficiency. Therefore, in the existing technology, it is difficult to accurately monitor foreign objects in the die in the automobile stamping process. Summary of the invention

[0006] Based on this, the object of the present invention is to provide a foreign matter monitoring method for an automobile stamping die.

[0007] A method for monitoring foreign matter in an automobile stamping die comprises the following steps:

[0008] S1: Acquire the image of the mold area before the sheet enters the mold;

[0009] S2: Use a moving window mechanism to segment the current mold area image to obtain the current mold small area image;

[0010] S3A: using a foreign body image classification model to classify the current small area image of the mold, and obtaining a classification result of the current small area image of the mold;

[0011] S3B: A foreign body recognition model is used to perform fine recognition on the current small area image of the mold to obtain the foreign body confidence of the current small area image of the mold;

[0012] S4: Determine whether the classification result and foreign body confidence of the current small area image of the mold meet a foreign body condition: if not, execute step S5A; if yes, execute step S5B;

[0013] S5A: Determine whether the current mold small area image is the last small area image: if not, execute step S2 to select the next small area image; if yes, execute step S6;

[0014] S5B: issuing an early warning according to the foreign body confidence of the current area image, and cleaning the mold; wherein, after the mold is cleaned through the step S5B, executing step S6, and continuing the stamping operation;

[0015] S6: conveying the sheet material to the mold for stamping, and conveying the stamped sheet material to the next process; wherein, after the sheet material is stamped through step S6, if the current mold is in an empty state, execute step S1.

[0016] Compared with the prior art, the foreign body monitoring method for automobile stamping dies described in the present invention divides the mold area into small areas through a moving window mechanism, which can effectively avoid missing small foreign bodies due to the presence of small targets in a large field of view and reduce the problem of false detection caused by environmental interference; at the same time, the coordinated work of the foreign body image classification model and the foreign body recognition model is adopted to ensure higher detection accuracy and minimize the risk of false detection and missed detection, thereby improving the production efficiency of automobile stamping and the safety of mold use on the basis of ensuring high accuracy of foreign body recognition.

[0017] Further, the foreign body image classification model includes a feature extraction module and a foreign body image classification module;

[0018] The specific calculation of the feature extraction module is expressed as follows:

[0019] Fi =Pool(ReLU(Conv 3×3 (F i-1 )))

[0020] F 1 =Pool(ReLU(Conv 3×3 (I small )))

[0021] In the formula, F i Represents the features of the small area image of the mold at layer i; F i-1 Represents the output of the previous layer; I small The small area image of the mold extracted from the current window; Conv 3×3 ReLU represents the convolution layer with a convolution kernel of 3×3; ReLU represents the activation function; Pool represents the pooling layer;

[0022] The specific calculation of the foreign body image classification module is as follows:

[0023] P result =σ(H n )

[0024] Where P result is the classification result of the current small area image of the mold, that is, the probability value of whether the foreign matter exists; σ is the sigmoid function; H n It is represented as the output of the nth fully connected layer, and its specific calculation is as follows:

[0025] H n =ReLU(FC n (H n-1 )))H 1 =ReLU(FC 1 (F i ))

[0026] In the formula, H n Represents the output of the nth fully connected layer, whose nth fully connected layer FC n The number of neurons n The specific calculation is expressed as:

[0027]

[0028] Where n∈[2, N], the calculation of N is expressed as:

[0029]

[0030] Among them, neuron 1 is the number of neurons in the first fully connected layer.

[0031] The present invention uses hierarchical convolution and pooling operations in the feature extraction module to effectively extract detailed features, namely local features, in the small area image of the mold, thereby improving the ability to identify foreign objects under complex scenes or environmental interference; at the same time, the number of neurons in the fully connected layer in the foreign object image classification module is gradually reduced to ensure that the model can more accurately judge the foreign object situation in the small area image of the mold, aiming to reduce the problems of false detection and missed detection; accordingly, the present invention combines the feature extraction module and the foreign object classification module to more accurately perform foreign object detection to adapt to more complex working conditions, thereby reducing the false alarm rate and missed detection rate of foreign object detection, thereby improving the efficiency and safety of the entire automobile stamping production line.

[0032] Further, the foreign body recognition model includes a backbone network, a neck network and a head network;

[0033] The backbone network is used to perform multi-level feature extraction on the input small area image of the mold and output feature maps of several scales;

[0034] Among them, the specific calculation of preliminary feature extraction is expressed as follows:

[0035] Feature 1 =Focus(I small )

[0036] In the formula, the Focus module is used to slice the input image to obtain the initial feature map Feature 1 ;

[0037] For the feature extraction of the i-th level, the specific calculation is expressed as:

[0038] Feature i =C3(CONV(Feature i-1 ) 2 ), i∈[2,n-1]

[0039] In the formula, CONV represents the convolution module, and its specific structure is:

[0040] SILU(BN(Conv2d(F x )))

[0041] In the formula, F x is the input image, Conv2d is the two-dimensional convolution, BN is the batch normalization and SILU is the activation function;

[0042] C3 represents the residual block, and its specific structure is:

[0043] CONV(Concat(Add(CONV(F x ) 3 ,CONV(Fx )), CONV(F x ) 2 ))

[0044] In the formula, Add means element-by-element addition, and Concat means concatenation operation;

[0045] The specific representation of feature extraction at the final level is as follows:

[0046] Feature n =C3(SPP(CONV(Feature i-1 )))

[0047] In the formula, Feature n Represents the feature map of the final scale; SPP is spatial pyramid pooling;

[0048] The neck network is used to perform feature fusion on feature maps of several scales to obtain fused feature maps of several scales, which are specifically expressed as follows:

[0049] F fusion ={FPN({Feature i |i∈[2,n]})}

[0050] In the formula, F fusion Represents a fusion feature atlas of several scales; FPN is a feature pyramid;

[0051] The head network is used to predict the fused feature maps of several scales, generate several prediction frames, and filter the several prediction frames using non-maximum suppression to obtain the foreign body confidence of the current small area image of the mold.

[0052] The present invention introduces a residual block of element-by-element addition and splicing operations to ensure that the model can effectively fuse feature information at multiple scales, thereby improving the perception of mold image details; at the same time, the model can maintain a high detection accuracy and reduce the occurrence of missed detection and false detection when there is noise or detail loss in the image of a small area of ​​the mold.

[0053] In one embodiment, the foreign matter condition is specifically expressed as follows:

[0054] The specific expression of the foreign matter condition is as follows:

[0055]

[0056] Wherein, isExist represents the judgment result of whether there is a foreign object in the current mold small area image. When isExist indicates that there is no foreign object, step S5A is executed; when isExist indicates that there is a foreign object, step S5B is executed; resultis the classification result of the current small area image of the mold; P target is the foreign body confidence of the current small area image of the mold; max is the maximum confidence threshold.

[0057] The present invention uses static fusion conditions to ensure that the system can accurately judge foreign objects based on a fixed maximum execution threshold, thereby avoiding false detections and ensuring the simplicity, stability and efficiency of system decisions, aiming to reduce the risk of production stagnation in a high-speed production environment and ensure efficient and safe operation of the production line.

[0058] In one embodiment, the foreign matter condition is specifically expressed as follows:

[0059]

[0060] Wherein, isExist represents the judgment result of whether there is a foreign object in the current mold small area image. When isExist indicates that there is no foreign object, step S5A is executed; when isExist indicates that there is a foreign object, step S5B is executed; result is the classification result of the current small area image of the mold; P target is the foreign body confidence of the current small area image of the mold; max and min are the maximum confidence threshold and the minimum confidence threshold respectively; cf A and cf B They are respectively the classification result of the current small area image of the mold and the dynamic confidence threshold corresponding to the foreign body confidence. The specific calculation is as follows:

[0061] cf A =w A ×cf MAX +w B ×cf MIN +bias

[0062] cf B =w B ×cf MAX +w A ×cf MIN +bias

[0063] In the formula, cf MAX and cf MIN Respectively represented as P result and P target The maximum and minimum confidence between them; bias is expressed as offset; w A and w B They are the dynamic weights of the classification result and foreign body confidence, and the specific calculation is as follows:

[0064]

[0065] In the formula, Δp is represented by P result and P target The absolute value difference between .

[0066] Accordingly, the dynamic confidence threshold of the present invention dynamically adjusts the weight according to the difference between the classification result and the foreign body confidence, and combines the offset to achieve a flexible response to different confidence combinations, thereby ensuring that when the confidence of one model is higher, the requirements for another model can be appropriately relaxed, thereby reducing the missed detection rate while ensuring high detection accuracy, and significantly improving the production quality of the automobile stamping production line.

[0067] Furthermore, the specific calculation of the offset is expressed as follows:

[0068]

[0069] In the formula, α is the tolerance coefficient.

[0070] The present invention further introduces the calculation of the offset. When there is a high-confidence result, a certain tolerance is given; when there is a low-confidence result, a more stringent judgment is given; if neither the high-confidence nor the low-confidence conditions are met, the default judgment standard is maintained, thereby significantly optimizing the balance of foreign body detection, effectively reducing production stagnation caused by misjudgment of a single high-confidence result, and reducing quality problems caused by missed detection of a single low-confidence result, thereby improving the efficiency and reliability of the entire automobile stamping production line.

[0071] A foreign body monitoring device for an automobile stamping die, comprising a die image acquisition unit, an image region segmentation unit, a foreign body image classification unit, a foreign body recognition unit, a foreign body judgment unit, an iterative monitoring and judgment unit, a foreign body early warning unit and a die stamping control unit;

[0072] The mold image acquisition unit is used to acquire an image of the mold area before the sheet material enters the mold;

[0073] The image region segmentation unit is used to segment the current mold region image using a moving window mechanism to obtain the current mold small region image;

[0074] The foreign body image classification unit is used to classify the current small area image of the mold using a foreign body image classification model to obtain a classification result of the current small area image of the mold;

[0075] The foreign body recognition unit is used to use a foreign body recognition model to perform fine recognition on the current small area image of the mold to obtain the foreign body confidence of the current small area image of the mold;

[0076] The foreign body judgment unit is used to judge whether the classification result and foreign body confidence of the current small area image of the mold meet a foreign body condition: if not, the iterative monitoring judgment unit is called; if yes, the foreign body early warning unit is called;

[0077] The iterative monitoring and judging unit is used to judge whether the current mold small area image is the last small area image: if not, the image area segmentation unit is called to select the next small area image; if yes, the mold stamping control unit is called;

[0078] The foreign body early warning unit is used to issue an early warning according to the foreign body confidence of the current area image and clean the mold; wherein, after the mold is cleaned by the foreign body early warning unit, the mold stamping control unit is called to continue the stamping operation;

[0079] The mold stamping control unit is used to convey the sheet material to the mold for stamping, and convey the stamped sheet material to the next process; wherein, after the sheet material is stamped by the mold stamping control unit, if the current mold is in an empty state, the mold image acquisition unit is called.

[0080] Further, the foreign body image classification model includes a feature extraction module and a foreign body image classification module;

[0081] The specific calculation of the feature extraction module is expressed as follows:

[0082] F i =Pool(ReLU(Conv 3×3 (F i-1 )))

[0083] F 1 =Pool(ReLU(Conv 3×3 (I small )))

[0084] In the formula, F i Represents the features of the small area image of the mold at layer i; F i-1 Represents the output of the previous layer; I small The small area image of the mold extracted from the current window; Conv 3×3 ReLU represents the convolution layer with a convolution kernel of 3×3; ReLU represents the activation function; Pool represents the pooling layer;

[0085] The specific calculation of the foreign body image classification module is as follows:

[0086] P result =σ(H n )

[0087] Where Presult is the classification result of the current small area image of the mold, that is, the probability value of whether the foreign matter exists; σ is the sigmoid function; H n It is represented as the output of the nth fully connected layer, and its specific calculation is as follows:

[0088] H n =ReLU(FC n (H n-1 )))

[0089] H 1 =ReLU(FC 1 (F i ))

[0090] In the formula, H n Represents the output of the nth fully connected layer, whose nth fully connected layer FC n The number of neurons n The specific calculation is expressed as:

[0091]

[0092] Where n∈[2, N], the calculation of N is expressed as:

[0093]

[0094] Among them, neuron 1 is the number of neurons in the first fully connected layer;

[0095] The foreign body recognition model includes a backbone network, a neck network and a head network;

[0096] The backbone network is used to perform multi-level feature extraction on the input small area image of the mold and output feature maps of several scales;

[0097] Among them, the specific calculation of preliminary feature extraction is expressed as follows:

[0098] Feature 1 =Focus(I small )

[0099] In the formula, the Focus module is used to slice the input image to obtain the initial feature map Feature 1 ;

[0100] For the feature extraction of the i-th level, the specific calculation is expressed as:

[0101] Feature i =C3(CONV(Feature i-1 ) 2 ), i∈[2,n-1]

[0102] In the formula, CONV represents the convolution module, and its specific structure is:

[0103] SILU(BN(Conv2d(F x )))

[0104] In the formula, F x is the input image, Conv2d is the two-dimensional convolution, BN is the batch normalization and SILU is the activation function;

[0105] C3 represents the residual block, and its specific structure is:

[0106] CONV(Concat(Add(CONV(F x ) 3 ,CONV(F x )),CONV(F x ) 2 ))

[0107] In the formula, Add means element-by-element addition, and Concat means concatenation operation;

[0108] The specific representation of feature extraction at the final level is as follows:

[0109] Feature n =C3(SPP(CONV(Feature i-1 )))

[0110] In the formula, Feature n Represents the feature map of the final scale; SPP is spatial pyramid pooling;

[0111] The neck network is used to perform feature fusion on feature maps of several scales to obtain fused feature maps of several scales, which are specifically expressed as follows:

[0112] F fusion ={FPN({Feature i |i∈[2,n]})}

[0113] In the formula, F fusion Represents a fusion feature atlas of several scales; FPN is a feature pyramid;

[0114] The head network is used to predict the fused feature maps of several scales, generate several prediction frames, and filter the several prediction frames using non-maximum suppression to obtain the foreign body confidence of the current small area image of the mold.

[0115] Furthermore, the foreign matter condition is specifically expressed as follows:

[0116]

[0117] Wherein, isExist represents the judgment result of whether there is a foreign object in the current mold small area image. When isExist indicates that there is no foreign object, step S5A is executed; when isExist indicates that there is a foreign object, step S5B is executed; result is the classification result of the current small area image of the mold; P target is the foreign body confidence of the current small area image of the mold; max and min are the maximum confidence threshold and the minimum confidence threshold respectively; cf A and cf B They are respectively the classification result of the current small area image of the mold and the dynamic confidence threshold corresponding to the foreign body confidence. The specific calculation is as follows:

[0118] cf A =w A ×cf MAX +W B ×cf MIN +bias

[0119] cf B =w B ×cf MAX +w A ×cf MIN +bias

[0120] In the formula, cf MAX and cf MIN Respectively represented as P result and P target The maximum and minimum confidence between them; bias is expressed as offset; w A and w B They are the dynamic weights of the classification result and foreign body confidence, and the specific calculation is as follows:

[0121]

[0122] In the formula, ΔP is expressed as P result and P target The absolute value difference between

[0123] The specific calculation of the offset is as follows:

[0124]

[0125] In the formula, α is the tolerance coefficient.

[0126] An automatic stamping production equipment for automobile parts, comprising a conveyor belt, a stamping machine, a camera device and a foreign body monitoring device;

[0127] The conveyor belt is used to convey the sheet material to the mold, and convey the sheet material after being punched by the punching machine to the next process;

[0128] The punching machine comprises an upper frame and a workbench, and is provided with a die;

[0129] The die comprises an upper die and a lower die, wherein the upper die is fixedly mounted on the upper frame of the punching machine and is provided with a punch; the lower die is provided with a forming cavity matching the upper die and is fixed on the working table of the punching machine; the punching machine is used to apply pressure to the sheet material through the upper die and the lower die to form the sheet material into a component of a preset shape;

[0130] The camera device is used to take a picture of the idle mold, obtain an image of the mold area before the sheet material enters the mold, and transmit the image to the foreign matter detection device;

[0131] The foreign body monitoring device is used to identify foreign bodies on the input image and obtain foreign body identification results. If the foreign body identification results indicate that foreign bodies exist, the production equipment is suspended and an early warning is issued, waiting for the mold cleaning to be completed; if the foreign body identification results indicate that no foreign bodies exist, the mold is continuously monitored;

[0132] Wherein, the foreign matter monitoring device is the foreign matter monitoring device for the automobile stamping die mentioned above.

[0133] For better understanding and implementation, the present invention is described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0134] Figure 1 It is a simplified structural schematic diagram of the foreign matter monitoring device for automobile stamping dies according to the present invention;

[0135] Figure 2 It is a simplified schematic diagram of the process of the foreign matter monitoring method for automobile stamping dies according to the present invention;

[0136] Figure 3 It is a simplified structural diagram of the foreign body image classification model;

[0137] Figure 4 It is a simplified structural diagram of the foreign body recognition model described in the present invention. DETAILED DESCRIPTION

[0138] In order to solve the problem that it is difficult to accurately monitor foreign matter in the mold in the existing technology in the automobile stamping process, the present invention obtains the area image before the sheet material enters the mold, and adopts a moving window mechanism to segment the current area image to obtain the current mold small area image of the mold; and simultaneously adopts a foreign matter image classification model and a foreign matter recognition model to classify and finely recognize the current mold small area image to obtain the classification result and foreign matter confidence of the current mold small area image; and judges whether the classification result and foreign matter confidence of the current mold small area image meet a foreign matter condition: if so, an early warning is issued according to the foreign matter confidence of the current area image, and the mold is cleaned; if not, it is judged whether the current mold small area image is the last small area image: if not, the next small area image is selected for classification and fine recognition; if so, the sheet material is transported to the mold for stamping, and the stamped sheet material is transported to the next process. Based on this, the present invention significantly reduces the false detection rate of foreign objects and improves the accuracy of foreign object recognition by performing graded processing on small area images respectively and combining the classification results with the confidence judgment of finely identified foreign objects, thereby reducing production stagnation caused by mold jamming, wear and other problems and improving the stability and continuous production capacity of the entire production line.

[0139] Based on the above-mentioned design of the foreign body identification scheme, the present invention proposes a foreign body monitoring method for an automobile stamping die, and based on the method, proposes a foreign body monitoring device for an automobile stamping die.

[0140] Please also see Figure 1 and Figure 2 , Figure 1 This is a simplified structural diagram of the foreign body monitoring device for automobile stamping dies according to the present invention. Figure 2 The present invention is a simplified schematic diagram of the process of monitoring foreign matter in automobile stamping dies.

[0141] The foreign body monitoring device for the automobile stamping die includes a die image acquisition unit 1, an image area segmentation unit 2, a foreign body image classification unit 3A, a foreign body identification unit 3B, a foreign body judgment unit 4, an iterative monitoring and judgment unit 5A, a foreign body early warning unit 5B and a die stamping control unit 6.

[0142] The mold image acquisition unit 1 is used to execute step S1: acquiring an image of the mold area before the sheet material enters the mold.

[0143] Specifically, a photographing device is used to photograph the mold to obtain an image of the mold area before the sheet material enters the mold.

[0144] The sheet material is used in the automobile stamping process to manufacture the car body, chassis, etc., and exists in the form of large-sized metal sheets before being cut, stamped and formed;

[0145] The mold includes an upper mold and a lower mold, which work together to complete the forming of the sheet; the upper mold is installed on the slider or upper frame of the punching machine, and is usually designed with a forming cavity, a punch or other forming tools; the lower mold is fixed on the workbench of the punching machine, and usually includes a forming cavity for accommodating the sheet and assisting the relative movement between the sheet and the upper mold. The lower mold is usually also provided with a discharge device or a waste channel for removing the waste or sheet after stamping; accordingly, the upper mold and the lower mold are used to apply pressure to the sheet through the punching machine to deform it into the required shape of the component to complete the forming of the sheet.

[0146] The present invention obtains images in an empty mold and performs real-time foreign matter monitoring on it to ensure that there is no foreign matter in the mold before each sheet enters the mold, thereby effectively avoiding the influence of foreign matter on the stamping process of the sheet, preventing scratches, indentations, deformation of the sheet or the production of defective parts due to foreign matter inside the mold, thereby improving production efficiency and product quality.

[0147] The image region segmentation unit 2 is used to execute step S2: segment the current mold region image using a moving window mechanism to obtain the current mold small region image.

[0148] Specifically, the moving window mechanism is specifically expressed as follows:

[0149] I small = {I[x,y]|x∈[x 1 , x 1 +w],y∈[y 1 ,y 1 +h]}

[0150] In the formula, I small represents the small mold area image extracted by the current window, whose size is w×h; I represents the current mold area image, that is, the image of the empty mold; x 1 and 1 They represent the starting coordinates of the current window in the image; w and h represent the width and height of the window respectively;

[0151] Based on this, a small area image of the mold is extracted by sliding the window in the image. small , thereby extracting local areas from the entire mold image for foreign body detection, preventing the global features from being affected by environmental interference or the large overall size of the mold, thereby ensuring more accurate foreign body detection and effectively reducing the risk of false detection or missed detection.

[0152] See also Figure 3 , Figure 3 This is a simplified structural diagram of the foreign body image classification model.

[0153] The foreign body image classification unit 3A is used to execute step S3A: classify the current small area image of the mold using a foreign body image classification model to obtain the classification result of the current small area image of the mold.

[0154] Specifically, the foreign body image classification model includes a feature extraction module and a foreign body image classification module. The feature extraction module is used to extract the features of the input small area image of the mold. The specific calculation expression is as follows:

[0155] F i =Pool(ReLU(Conv 3×3 (F i-1 )))

[0156] F 1 =Pool(ReLU(Conv 3×3 (I small )))

[0157] In the formula, F i Represents the features of the small area image of the mold at the i-th layer, i∈[1,15]; F i-1 Represents the output of the previous layer, that is, the features extracted by the i-1 layer; Conv 3×3 ReLU represents a convolutional layer with a convolution kernel of 3×3, which is used to extract features from the input image or the feature map of the previous layer; ReLU represents an activation function, which is used to introduce nonlinear transformation and set the negative values ​​output by the convolutional layer to zero, thereby enhancing the significance of positive features; Pool represents a pooling layer, which is used to reduce the spatial dimension of the feature map, reduce the amount of calculation, and retain the most important feature information.

[0158] The foreign body image classification module is used to classify the features of the input mold small area image to obtain the classification result of the current mold small area image. The specific calculation expression is as follows:

[0159] P result =σ(H n )

[0160] Where P result is the classification result of the current small area image of the mold, that is, the probability value of whether a foreign object exists; σ is the sigmoid function, which is used to map the output to a probability value between 0 and 1, indicating the confidence of the presence of foreign matter in the input feature; H n It is represented as the output of the nth fully connected layer, and its specific calculation is as follows:

[0161] H n =ReLU(FC n (H n-1 )))

[0162] H 1=ReLU(FC 1 (F i )), i=15

[0163] In the formula, H n Represents the output of the nth fully connected layer, whose nth fully connected layer FC n The number of neurons n The specific calculation is expressed as: And n∈[2,N], the calculation of N is expressed as:

[0164]

[0165] Among them, neuron 1 is the number of neurons in the first fully connected layer, that is, the total number of neurons in the input layer, which is set to 2048.

[0166] Accordingly, the present invention adopts a convolutional neural network as a feature extraction module to extract the features of the small area image of the mold extracted by the sliding window mechanism, and uses a fully connected neural network, that is, a foreign body image classification module, to perform layer-by-layer refined learning to ensure high-precision separation, and uses a sigmoid function to output the confidence of the presence of foreign matter to achieve high-precision binary classification results, so as to reduce false detections and thereby improve the accuracy of foreign body detection in the mold during the automotive stamping process.

[0167] In order to increase the classification accuracy of the foreign body classification model, the present invention trains the foreign body classification model in the following manner, which specifically includes:

[0168] Data processing stage: Collect and annotate a large number of small area images of the mold, and ensure that all images are accurately labeled with foreign objects, which are used to indicate whether foreign objects exist;

[0169] Next, the small area image of the mold is combined with the corresponding label to form a classification data set; wherein, in order to improve the model's ability to classify foreign objects under different environments and conditions, a data enhancement method can be used to enhance the current classification data set, such as rotation, scaling or cropping, and the present invention does not specifically limit the data enhancement method;

[0170] Finally, the classification dataset is divided into training set, test set, and validation set to ensure the effectiveness of model training and the comprehensiveness of evaluation.

[0171] Training and optimization stage: Preprocess the small area images of the mold in the training set and input them into the current foreign body classification model to obtain the foreign body classification confidence;

[0172] The binary cross entropy is used as the loss function to calculate the loss value between the foreign object classification confidence and the corresponding label, and the gradient is calculated through the back propagation algorithm, and the current foreign object classification model weight is updated in combination with the optimizer (such as Adam);

[0173] Next, the test set is input into the model and the accuracy of the output is calculated. If the accuracy reaches the preset threshold or the training round reaches the end condition, it enters the next stage; otherwise, the training and optimization stages are repeated to further improve the model performance.

[0174] Model evaluation and verification phase: Input the verification set into the trained foreign body classification model, calculate and analyze indicators such as accuracy, recall rate and F1 score, and comprehensively evaluate the classification accuracy and robustness of the model. If the evaluation indicators of the verification set do not meet the requirements, it is necessary to adjust the hyperparameters and re-execute the training and optimization phase; if the indicators of the verification set meet the requirements, it is confirmed that a highly accurate foreign body classification model has been obtained and the training process is completed.

[0175] Accordingly, the present invention ensures that the foreign body classification model has high accuracy and strong generalization ability through data processing, training optimization and model verification processes, significantly reduces false detection and missed detection rates, thereby improving the accuracy and production efficiency of foreign body detection in the mold in the automobile stamping process.

[0176] See also Figure 4 , Figure 4 A simplified structural diagram of the foreign body recognition model described in the present invention

[0177] The foreign body recognition unit 3B is used to execute step S3B: using a foreign body recognition model to perform fine recognition on the current small area image of the mold to obtain the foreign body confidence of the current small area image of the mold.

[0178] Specifically, the foreign body recognition model includes a backbone network, a neck network and a head network; the backbone network is used to perform multi-level feature extraction on the input small area image of the mold and output feature maps of several scales. The specific calculation of the preliminary feature extraction in the multi-level feature extraction is expressed as follows:

[0179] Feature 1 =Focus(I small )

[0180] In the formula, the Focus module is used to slice the input image. e ), that is, the input image is downsampled to concentrate the information in the channel space and obtain the initial feature map Feature 1 ; For the feature extraction of the i-th level, the specific calculation is expressed as:

[0181] Featurei =C3(CONV(Feature i-1 ) 2 ), i∈[2,n-1]

[0182] In the formula, CONV represents the convolution module, and its specific structure is:

[0183] SILU(BN(Conv2d(F x )))

[0184] In the formula, F x is the input image, Conv2d is the two-dimensional convolution, BN is the batch normalization and SILU is the activation function;

[0185] C3 represents the residual block, and its specific structure is:

[0186] CONV(Concat(Add(CONV(F x ) 3 ,CONV(F x )),CONV(F x ) 2 ))

[0187] Wherein, Add represents element-by-element addition, and Concat represents a concatenation operation; wherein the stride of the convolution operation of the residual block in the present invention is 1, and the convolution kernel size is 3×3;

[0188] The specific representation of feature extraction at the final level is as follows:

[0189] Feature n =C3(SPP(CONV(Feature i-1 )))

[0190] In the formula, Feature n Represents the feature map of the final scale, and n is set to 5 by default; SPP is spatial pyramid pooling, which is used to enhance the ability to extract multi-scale features;

[0191] The neck network is used to perform feature fusion on feature maps of several scales to obtain fused feature maps of several scales, which are specifically expressed as follows:

[0192] F fusion ={FPN({Feature i |i∈[2,n]})}

[0193] In the formula, F fusion Represents a fused feature atlas of several scales; FPN is a feature pyramid used to fuse features of multiple scales.

[0194] The head network is used to predict the fused feature maps of several scales, generate several prediction frames, and filter the several prediction frames using non-maximum suppression to obtain the foreign body confidence of the current small area image of the mold.

[0195] Among them, the prediction box includes the location of the target, that is, the bounding box coordinates, and the foreign object confidence.

[0196] Accordingly, the present invention introduces element-by-element addition and splicing operations in the residual block (C3), wherein the element-by-element addition ensures the continuity and gradient flow of feature information, while the splicing operation helps to introduce more feature dimensions, thereby enhancing the model's recognition capability for fine-grained features (such as small objects or foreign objects); in addition, the present invention sets the convolution stride in the residual block (C3) to 1 to ensure complete retention of detail information, thereby improving spatial resolution and reducing information loss in the detection of small objects or foreign objects.

[0197] In order to increase the detection accuracy of the foreign body recognition model, the invention trains the foreign body recognition model in the following manner, which specifically includes:

[0198] Data processing stage: Collect and annotate a large number of small area images of the mold to ensure that each image accurately identifies the location, shape and corresponding label of the foreign body, which is used to indicate whether the foreign body exists;

[0199] Draw a target frame based on the position and shape of foreign matter in the small area image of the mold, and build a target detection dataset by associating the target frame with the label;

[0200] In order to improve the model's ability to classify foreign objects under different environments and conditions, a data enhancement method may be used to enhance the current target detection data set, such as rotation, scaling or cropping. The present invention does not specifically limit the data enhancement method.

[0201] Finally, the object detection dataset is divided into training set, test set and validation set to ensure the effectiveness of model training and the comprehensiveness of evaluation.

[0202] Training and optimization stage: Preprocess the small area images of the mold in the training set and input them into the current foreign body recognition model to obtain the foreign body recognition confidence;

[0203] The binary cross entropy, IOU loss of the target box and L1 loss are used as the combined loss function to calculate the loss value between the foreign object recognition confidence and the corresponding label and target box, and the gradient is calculated through the back propagation algorithm, and the current foreign object classification model weight is updated in combination with the optimizer (such as Adam);

[0204] Next, the test set is input into the model and the accuracy of the output is calculated. If the accuracy reaches the preset threshold or the training round reaches the end condition, it enters the next stage; otherwise, the training and optimization stages are repeated to further improve the model performance.

[0205] Model evaluation and verification phase: Input the verification set into the trained foreign body recognition model, calculate and analyze indicators such as accuracy, recall rate and F1 score, and comprehensively evaluate the classification accuracy and robustness of the model. If the evaluation indicators of the verification set do not meet the requirements, it is necessary to adjust the hyperparameters and re-execute the training and optimization phase; if the indicators of the verification set meet the requirements, it is confirmed that a highly accurate foreign body recognition model has been obtained and the training process is completed.

[0206] In the training of the model, the introduction of element-by-element addition and concatenation operations significantly enhances the learning ability of the model. Through the direct path of low-level features, it ensures that the features of different levels are fully learned, thereby avoiding the performance degradation caused by poor information flow. At the same time, the concatenation operation can establish richer connections between different levels and scales, thereby enhancing the performance of the model when dealing with foreign body detection tasks of multiple scales, and thus enabling the model to automatically capture features of different scales during the training process, improving the model's expressiveness and generalization capabilities.

[0207] The foreign body judgment unit 4 is used to execute step S4: judging whether the classification result and foreign body confidence of the current small area image of the mold meet a foreign body condition: if not, calling the iterative monitoring judgment unit 5A; if yes, calling the foreign body early warning unit 5B.

[0208] Specifically, the foreign matter condition is specifically expressed as follows:

[0209]

[0210] Wherein, isExist is used to indicate the judgment result of whether there is a foreign object in the current mold small area image. When isExist indicates that there is no foreign object, the iterative monitoring judgment unit 5A is called; when isExist indicates that there is a foreign object, the foreign object early warning unit 5B is called; result is the classification result of the current small area image of the mold; P target is the foreign body confidence of the current small area image of the mold; max are the maximum confidence thresholds, which are set to 0.8 by default.

[0211] Accordingly, the present invention adopts a fixed threshold method, thereby minimizing the misjudgment rate while ensuring system stability, ensuring that the production line will not be frequently paused due to false detection, thereby improving production efficiency and system reliability.

[0212] In another embodiment, the foreign matter condition is specifically expressed as follows:

[0213]

[0214] Wherein, isExist is used to indicate the judgment result of whether there is a foreign object in the current mold small area image. When isExist indicates that there is no foreign object, the iterative monitoring judgment unit 5A is called; when isExist indicates that there is a foreign object, the foreign object early warning unit 5B is called; result is the classification result of the current small area image of the mold; P target is the foreign body confidence of the current small area image of the mold; max and min are the maximum confidence threshold and the minimum confidence threshold, respectively, and their default settings are 0.8 and 0.6 respectively; cf A and cf B They are respectively the classification result of the current small area image of the mold and the dynamic confidence threshold corresponding to the foreign body confidence. The specific calculation is as follows:

[0215] cf A =w A ×cf MAX +w B ×cf MσN +bias

[0216] cf B =w B ×cf MAx +w A ×cf MIN +bias

[0217] In the formula, cf MAX and cf MIN Respectively represented as P result and P target The maximum and minimum confidence between A and w B They are the dynamic weights of the classification result and foreign body confidence, and their specific calculation is as follows:

[0218]

[0219] In the formula, ΔP is expressed as P result and P target The absolute value difference between |P target -P result |; Its bias is expressed as an offset, and its specific calculation is as follows:

[0220]

[0221] In the formula, α is the tolerance coefficient, and its default value is 0.05.

[0222] The present invention uses a fixed maximum confidence threshold th in the foreign body condition max and the minimum confidence threshold th min To ensure that the presence of foreign matter can be accurately determined in the case of clear high confidence or low confidence; then, by dynamically adjusting the confidence threshold, the confidence threshold can be adjusted in P result and P target In the case of high confidence, the tolerance for close confidence is balanced. The tolerance coefficient of the offset in the dynamic confidence threshold can increase the tolerance for another target with lower confidence when there is a high confidence target, thereby avoiding missed detection due to overly strict judgment.

[0223] Accordingly, the present invention ensures that a certain tolerance is maintained in the presence of high confidence situations through flexible adjustment of dynamic confidence thresholds, while maintaining strictness in the presence of low confidence situations, thereby significantly reducing the false positive rate and missed positive rate.

[0224] The iterative monitoring and judgment unit 5A is used to execute step S5A: determine whether the current mold small area image is the last small area image: if not, call the image area segmentation unit 2 to select the next small area image; if so, call the mold stamping control unit 6.

[0225] Accordingly, the detection status of each small area image is iteratively detected, and whether the stamping task needs to be performed is determined based on whether all small area images have been detected, thereby avoiding missing any potential foreign body detection area.

[0226] The foreign body early warning unit 5B is used to execute step S5B: issuing an early warning according to the foreign body confidence level of the current area image and cleaning the mold.

[0227] Specifically, based on the foreign matter confidence information in the prediction box annotation of the foreign matter confidence of the current area image, that is, the position and size of the foreign matter, an early warning signal is issued, so that the foreign matter on the mold can be processed through cleaning equipment or other means.

[0228] When the cleaning is completed, the mold stamping control unit 6 is called to continue the stamping operation.

[0229] Based on this, when foreign matter is detected, an early warning is issued to the operator in a timely manner to prevent the foreign matter from adversely affecting the subsequent production process or product quality, while providing accurate cleaning instructions to improve the efficiency of mold management and production safety. In addition, the stamping operation is quickly resumed after cleaning is completed to avoid long pauses in the production process, thereby maintaining the production rhythm and improving production efficiency.

[0230] It is understandable that when the early warning signal is issued, the conveyor belt's conveying of the sheet material can be suspended through a control system, such as a PLC, thereby providing a certain amount of time for the operator to clean up foreign objects, thereby ensuring the safety of the production line during the cleaning of foreign objects.

[0231] The die stamping control unit 6 is used to execute step S6: conveying the sheet material to the die for stamping, and conveying the stamped sheet material to the next process.

[0232] Specifically, the sheet material is accurately conveyed to the lower die and a control signal is sent to the control system. The control system, such as PLC, controls the punching machine to apply pressure to the upper die of the mold, thereby punching the sheet material to achieve the forming of the sheet material and obtain a part of a predetermined shape.

[0233] Then, the parts with the predetermined shape are transported to the next process for subsequent processing.

[0234] When the sheet metal stamping is completed and the stamped parts are transported to the next process, if the current mold is in an empty state, that is, no sheet metal remains, the mold image acquisition unit 1 is called.

[0235] Compared with the prior art, the present invention divides the mold area image into multiple small areas by using a moving window mechanism, thereby effectively avoiding the problem of small foreign objects being missed or misdetected due to environmental interference under a large field of view; at the same time, the collaborative analysis of the foreign object image classification model and the foreign object recognition model is combined to ensure the high accuracy of the foreign object detection results, and significantly reduce the risk of misdetection and missed detection; further, by introducing a dynamic confidence threshold adjustment mechanism, it combines the calculation of dynamic weights and offsets to give appropriate tolerance to detection results with lower confidence under high confidence conditions, thereby enhancing the system's flexible response capabilities to different confidence combinations. Accordingly, the present invention significantly improves the efficiency and safety of automobile stamping production lines by combining multiple models with a dynamic threshold mechanism, and ensures the stable output of high-quality parts.

[0236] Based on the same inventive concept, the present application also provides an electronic device, which may be a terminal device such as a server, a desktop computing device or a mobile computing device (e.g., a laptop computing device, a handheld computing device, a tablet computer, a netbook, etc.). The device includes one or more processors and a memory, wherein the processor is used to execute a program to implement the foreign body monitoring method for an automobile stamping die according to an embodiment of the present invention; and the memory is used to store a computer program executable by the processor.

[0237] Based on the same inventive concept, the present application also provides a computer-readable storage medium, corresponding to the embodiment of the aforementioned foreign body monitoring method for an automobile stamping die, wherein the computer-readable storage medium stores a computer program thereon, and when the program is executed by the processor, the steps of the foreign body monitoring method for an automobile stamping die recorded in any of the aforementioned embodiments are implemented.

[0238] The present application may take the form of a computer program product implemented on one or more storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing program code. Computer-usable storage media include permanent and non-permanent, removable and non-removable media, and information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission medium that can be used to store information that can be accessed by a computing device.

[0239] The above-mentioned embodiments only express several implementation methods of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, and the present invention is also intended to include these modifications and modifications.

Claims

1. A foreign body monitoring method for automobile stamping dies, characterized in that: The following steps are involved: S1: Acquire the image of the mold area before the sheet enters the mold; S2: Use a moving window mechanism to segment the current mold area image to obtain the current mold small area image; S3A: using a foreign body image classification model to classify the current small area image of the mold, and obtaining a classification result of the current small area image of the mold; S3B: A foreign body recognition model is used to perform fine recognition on the current small area image of the mold to obtain the foreign body confidence of the current small area image of the mold; S4: Determine whether the classification result and foreign body confidence of the current small area image of the mold meet a foreign body condition: if not, execute step S5A; if yes, execute step S5B; S5A: Determine whether the current mold small area image is the last small area image: if not, execute step S2 to select the next small area image; if yes, execute step S6; S5B: issuing an early warning according to the foreign body confidence of the current area image, and cleaning the mold; wherein, after the mold is cleaned through the step S5B, executing step S6, and continuing the stamping operation; S6: conveying the sheet material to the mold for stamping, and conveying the stamped sheet material to the next process; wherein, after the sheet material is stamped through step S6, if the current mold is in an empty state, execute step S1.

2. The foreign matter monitoring method for automobile stamping dies according to claim 1 is characterized in that: The foreign body image classification model includes a feature extraction module and a foreign body image classification module; The specific calculation of the feature extraction module is expressed as follows: F i =Pool(ReLU(Conv 3×3 (F i-1 ))) F1=Pool*ReLU(Conv 3×3 (I small ))) In the formula, F i F represents the features of the small area image of the mold at the i-th layer; i-1 Represents the output of the previous layer; I small The small area image of the mold extracted from the current window; Conv 3×3 ReLU represents the convolution layer with a convolution kernel of 3×3; ReLU represents the activation function; Pool represents the pooling layer; The specific calculation of the foreign body image classification module is as follows: P result =H(H n ) Where P result is the classification result of the current small area image of the mold, that is, the probability value of whether the foreign matter exists; σ is the sigmoid function; H n It is represented as the output of the nth fully connected layer, and its specific calculation is as follows: H n =ReLU(FC n (H n-1 ))) H1=ReLU(FC1(F i )) In the formula, H n Represents the output of the nth fully connected layer, whose nth fully connected layer FC n The number of neurons n The specific calculation is expressed as: Where n∈[2,N], the calculation of N is expressed as: Among them, neuron1 is the number of neurons in the first fully connected layer.

3. The foreign matter monitoring method for automobile stamping dies according to claim 2 is characterized in that: The foreign body recognition model includes a backbone network, a neck network and a head network; The backbone network is used to perform multi-level feature extraction on the input small area image of the mold and output feature maps of several scales; Among them, the specific calculation of preliminary feature extraction is expressed as follows: Feature1=Focus(I small ) In the formula, the Focus module is used to slice the input image to obtain the initial feature map Feature1; For the feature extraction of the i-th level, the specific calculation is expressed as: Feature i =C3(CONV(Feature i-1 ) 2 ),i∈[2,n-1] In the formula, CONV represents the convolution module, and its specific structure is: SILU(BN(Conv2d(F x ))) In the formula, F x is the input image, Conv2d is the two-dimensional convolution, BN is the batch normalization and SILU is the activation function; C3 represents the residual block, and its specific structure is: CONV(Concat(Add(CONV(F x ) 3 ,CONV(F x )),CONV(F x ) 2 )) In the formula, Add means element-by-element addition, and Concat means concatenation operation; The specific representation of feature extraction at the final level is as follows: Feature n =C3(SPP(CONV(Feature i-1 ))) In the formula, Feature n Represents the feature map of the final scale; SPP is spatial pyramid pooling; The neck network is used to perform feature fusion on feature maps of several scales to obtain fused feature maps of several scales, which are specifically expressed as follows: F fusion ={FPN({Feature i |i∈[2,n]})} In the formula, F fusion Represents a fusion feature atlas of several scales; FPN is a feature pyramid; The head network is used to predict the fused feature maps of several scales, generate several prediction frames, and filter the several prediction frames using non-maximum suppression to obtain the foreign body confidence of the current small area image of the mold.

4. The foreign matter monitoring method for automobile stamping dies according to claim 3 is characterized in that: The specific expression of the foreign matter condition is as follows: The specific expression of the foreign matter condition is as follows: Wherein, isExist represents the judgment result of whether there is a foreign object in the current mold small area image. When isExist indicates that there is no foreign object, step S5A is executed; when isExist indicates that there is a foreign object, step S5B is executed; result is the classification result of the current small area image of the mold; P target is the foreign body confidence of the current small area image of the mold; th max is the maximum confidence threshold.

5. The foreign matter monitoring method for automobile stamping dies according to claim 3 is characterized in that: The specific expression of the foreign matter condition is as follows: Wherein, isExist represents the judgment result of whether there is a foreign object in the current mold small area image. When isExist indicates that there is no foreign object, step S5A is executed; when isExist indicates that there is a foreign object, step S5B is executed; result is the classification result of the current small area image of the mold; P target is the foreign body confidence of the current small area image of the mold; max and min are the maximum confidence threshold and the minimum confidence threshold respectively; cf A and cf B They are respectively the classification result of the current small area image of the mold and the dynamic confidence threshold corresponding to the foreign body confidence. The specific calculation is as follows: cf A =w A ×cf MAX +w B ×cf MIN +bias cf B =w B ×cf MAX +w A ×cf MUN +bias In the formula, cf MAX and cf MIN Respectively represented as P result and P target The maximum and minimum confidence between them; bias is expressed as offset; w A and w B They are the dynamic weights of the classification result and foreign body confidence, and the specific calculation is as follows: In the formula, ΔP is expressed as P result and P target The absolute value difference between .

6. The foreign matter monitoring device for automobile stamping dies according to claim 5, characterized in that: The specific calculation of the offset is as follows: In the formula, α is the tolerance coefficient.

7. A foreign body monitoring device for automobile stamping dies, characterized in that: It includes a mold image acquisition unit, an image area segmentation unit, a foreign body image classification unit, a foreign body recognition unit, a foreign body judgment unit, an iterative monitoring and judgment unit, a foreign body early warning unit and a mold stamping control unit; The mold image acquisition unit is used to acquire an image of the mold area before the sheet material enters the mold; The image region segmentation unit is used to segment the current mold region image using a moving window mechanism to obtain the current mold small region image; The foreign body image classification unit is used to classify the current small area image of the mold using a foreign body image classification model to obtain a classification result of the current small area image of the mold; The foreign body recognition unit is used to use a foreign body recognition model to perform fine recognition on the current small area image of the mold to obtain the foreign body confidence of the current small area image of the mold; The foreign body judgment unit is used to judge whether the classification result and foreign body confidence of the current small area image of the mold meet a foreign body condition: if not, the iterative monitoring judgment unit is called; if yes, the foreign body early warning unit is called; The iterative monitoring and judging unit is used to judge whether the current mold small area image is the last small area image: if not, the image area segmentation unit is called to select the next small area image; if yes, the mold stamping control unit is called; The foreign body early warning unit is used to issue an early warning according to the foreign body confidence of the current area image and clean the mold; wherein, after the mold is cleaned by the foreign body early warning unit, the mold stamping control unit is called to continue the stamping operation; The mold stamping control unit is used to convey the sheet material to the mold for stamping, and convey the stamped sheet material to the next process; wherein, after the sheet material is stamped by the mold stamping control unit, if the current mold is in an empty state, the mold image acquisition unit is called.

8. The foreign matter monitoring device for automobile stamping dies according to claim 7, characterized in that: The foreign body image classification model includes a feature extraction module and a foreign body image classification module; The specific calculation of the feature extraction module is expressed as follows: F i =Pool(ReLU(Conv 3×3 (F i-1 ))) F1=Pool(ReLU(Conv 3×3 (I small ))) In the formula, F i F represents the features of the small area image of the mold at the i-th layer; i-1 Represents the output of the previous layer; I small The small area image of the mold extracted from the current window; Conv 3×3 ReLU represents the convolution layer with a convolution kernel of 3×3; ReLU represents the activation function; Pool represents the pooling layer; The specific calculation of the foreign body image classification module is as follows: P result =H(H n ) Where P result is the classification result of the current small area image of the mold, that is, the probability value of whether the foreign matter exists; σ is the sigmoid function; H n It is represented as the output of the nth fully connected layer, and its specific calculation is as follows: H n =ReLU(FC b (H n-1 ))) H1=ReLU(FC1(F i )) In the formula, H n Represents the output of the nth fully connected layer, whose nth fully connected layer FC n The number of neurons n The specific calculation is expressed as: Where n∈[2,N], the calculation of N is expressed as: Among them, neuron1 is the number of neurons in the first fully connected layer; The foreign body recognition model includes a backbone network, a neck network and a head network; The backbone network is used to perform multi-level feature extraction on the input small area image of the mold and output feature maps of several scales; Among them, the specific calculation of preliminary feature extraction is expressed as follows: Feature1=Focus(I small ) In the formula, the Focus module is used to slice the input image to obtain the initial feature map Feature1; For the feature extraction of the i-th level, the specific calculation is expressed as: Feature i =C3(CONV(Feature i-1 ) 2 ),i∈[2,n-1] In the formula, CONV represents the convolution module, and its specific structure is: SILU(BN(Conv2d(F x ))) In the formula, F x is the input image, Conv2d is the two-dimensional convolution, BN is the batch normalization and SILU is the activation function; C3 represents the residual block, and its specific structure is: CONV(Concat(Add(CONV(F x ) 3 ,CONV(F x )),CONV(F x ) 2 )) In the formula, Add means element-by-element addition, and Concat means concatenation operation; The specific representation of feature extraction at the final level is as follows: Feature n =C3(SPP(CONV(Feature i-1 ))) In the formula, Feature n Represents the feature map of the final scale; SPP is spatial pyramid pooling; The neck network is used to perform feature fusion on feature maps of several scales to obtain fused feature maps of several scales, which are specifically expressed as follows: F fusion ={FPN({Feature i |i∈[2,n]})} In the formula, F fusion Represents a fusion feature atlas of several scales; FPN is a feature pyramid; The head network is used to predict the fused feature maps of several scales, generate several prediction frames, and filter the several prediction frames using non-maximum suppression to obtain the foreign body confidence of the current small area image of the mold.

9. The foreign matter monitoring device for automobile stamping dies according to claim 8, characterized in that: The specific expression of the foreign matter condition is as follows: Wherein, isExist represents the judgment result of whether there is a foreign object in the current mold small area image. When isExist indicates that there is no foreign object, step S5A is executed; when isExist indicates that there is a foreign object, step S5B is executed; result is the classification result of the current small area image of the mold; P target is the foreign body confidence of the current small area image of the mold; max and min are the maximum confidence threshold and the minimum confidence threshold respectively; cf A and cf B They are respectively the classification result of the current small area image of the mold and the dynamic confidence threshold corresponding to the foreign body confidence. The specific calculation is as follows: cf A =w A ×cf MAX +w B ×cf MIN +bias cf B =w B ×cf MAX +w A ×cf MIN +bias In the formula, cf MAX and cf MIN Respectively represented as P result and P target The maximum and minimum confidence between them; bias is expressed as offset; w A and w B They are the dynamic weights of the classification result and foreign body confidence, and the specific calculation is as follows: In the formula, ΔP is expressed as P result and P target The absolute value difference between The specific calculation of the offset is as follows: In the formula, α is the tolerance coefficient.

10. An automatic stamping production equipment for automobile parts, characterized in that: Includes conveyor belts, punching machines, filming equipment and foreign body monitoring devices; The conveyor belt is used to convey the sheet material to the mold, and convey the sheet material after being punched by the punching machine to the next process; The punching machine comprises an upper frame and a workbench, and is provided with a die; The die comprises an upper die and a lower die, wherein the upper die is fixedly mounted on the upper frame of the punching machine and is provided with a punch; the lower die is provided with a forming cavity matching the upper die and is fixed on the working table of the punching machine; the punching machine is used to apply pressure to the sheet material through the upper die and the lower die to form the sheet material into a component of a preset shape; The photographing device is used to photograph the idle mold, obtain an image of the mold area before the sheet material enters the mold, and transmit the image to the foreign matter detection device; The foreign body monitoring device is used to identify foreign bodies on the input image and obtain foreign body identification results. If the foreign body identification results indicate that foreign bodies exist, the production equipment is suspended and an early warning is issued, waiting for the mold cleaning to be completed; if the foreign body identification results indicate that no foreign bodies exist, the mold is continuously monitored; Wherein, the foreign matter monitoring device is the foreign matter monitoring device for an automobile stamping die as described in any one of claims 7-9.

Images