Stacker crane control system

Abstract

The invention discloses a stacker crane control system which is characterized in that in the stacking process, firstly, a mold table component surface state image of a mold table component is obtained through an industrial camera, and local implicit features and global semantic features of the mold table component surface state are extracted by adopting an image recognition algorithm based on deep learning; according to the method, the state of the die table component is described more comprehensively, then feature selection is performed on the extracted surface state features of the die table component to remove redundancy in the features, so that the characterization capability of the surface state features of the die table component is improved, and further, the characterization capability of the surface state features of the die table component is improved based on the surface state features of the die table component after feature selection. Therefore, the defect identification of the mold table component is realized. By means of the mode, the system can guarantee efficient production, meanwhile, the precision and reliability of mold table component quality detection are improved, and then the intelligent level of the stacker crane control system is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent control, and more specifically, to a palletizer control system. Background Art

[0002] In the field of industrial automation, palletizers, as an indispensable part of the logistics and manufacturing process, undertake the important task of stacking products in a specific pattern or taking them out from the stacking position. As the manufacturing industry continues to increase its requirements for efficiency and quality, traditional palletizing methods have gradually shown their limitations, especially when dealing with products with complex shapes and high precision requirements such as mold base components. Traditional palletizer control systems often rely on pre-set action sequences to perform tasks, which not only limits the flexibility of the system, but also makes it easy to make mistakes when facing components with non-standard sizes or abnormal surface conditions, resulting in reduced product quality or interruption of the production process.

[0003] Patent CN112850172A provides a control system and control method for a palletizer, in which the palletizing process is a highly integrated and intelligent system, which exchanges information with the curing kiln system and the assembly line system through a controller and a communication module. In this process, the palletizer performs actions based on the task information obtained from the two systems to ensure that the mold pallet components can flow smoothly between the curing kiln and the assembly line. Specifically, when the mold pallet needs to be stored in the curing kiln, the palletizer will first transfer the mold pallet from the assembly line to its pallet, and then move it to the designated destination bin by accurately controlling the layer and column positions, and complete a series of operations such as opening the bin door, pushing the mold pallet into the curing kiln, and closing the bin door; on the contrary, when the cured mold pallet needs to be taken out, these steps will be performed in reverse, and the mold pallet will eventually be sent back to the assembly line. This system not only realizes the automatic flow of mold pallet components between the curing kiln and the assembly line, but also introduces an intelligent control method to optimize the storage and retrieval process. However, in this highly integrated and automated process, if defective components are not effectively identified and removed, these defective products may enter the subsequent processes, causing more serious quality problems and even affecting the overall performance of the finished product. Therefore, ensuring the quality of each mold base component has become a key point that cannot be ignored.

[0004] Therefore, an optimized palletizer control system is expected. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a palletizer control system, which, during the palletizing process, first obtains the surface state image of the mold base component of the mold base component through an industrial camera, and uses an image recognition algorithm based on deep learning to extract the local implicit features and global semantic features of the surface state of the mold base component to more comprehensively describe the state of the mold base component, and then performs feature selection on the extracted surface state features of the mold base component to remove redundancy in the features, thereby improving the characterization ability of the surface state features of the mold base component, and further based on the surface state features of the mold base component after feature selection, to realize the defect recognition of the mold base component. In this way, the system can improve the accuracy and reliability of mold base component quality detection while ensuring efficient production, thereby improving the intelligence level of the palletizer control system.

[0006] According to one aspect of the present application, a palletizer control system is provided, which includes: a controller and a communication module; the controller communicates with a curing kiln system and an assembly line system through the communication module; the controller is also configured to obtain task information of the curing kiln system and the assembly line system through the communication module, and control the action of the palletizer according to the task information to realize the transfer of the mold platform components between the curing kiln and the assembly line, characterized in that it also includes:

[0007] An industrial camera, used for collecting a surface state image of the mold base component of the mold base component, wherein the mold base component is in a state of being transferred between the curing kiln and the assembly line;

[0008] The communication module is also used to transmit the surface state image of the die table component to the controller;

[0009] The controller is also used to perform image recognition on the surface state image of the die table component to obtain a recognition result, and the recognition result is used to indicate whether the die table component has defects;

[0010] The controller is also used to generate a stacking abnormality warning prompt in response to the recognition result that the mold platform component has defects.

[0011] Compared with the prior art, the present application provides a palletizer control system, which first obtains the surface state image of the mold base component of the mold base component through an industrial camera during the palletizing process, and uses an image recognition algorithm based on deep learning to extract the local implicit features and global semantic features of the surface state of the mold base component to more comprehensively describe the state of the mold base component, and then performs feature selection on the extracted surface state features of the mold base component to remove redundancy in the features, thereby improving the characterization ability of the surface state features of the mold base component, and further based on the surface state features of the mold base component after feature selection, to achieve defect recognition of the mold base component. In this way, the system can improve the accuracy and reliability of mold base component quality detection while ensuring efficient production, thereby improving the intelligence level of the palletizer control system. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0013] Figure 1 is a block diagram of a palletizer control system according to an embodiment of the present application;

[0014] Figure 2 A schematic diagram of data flow of a palletizer control system according to an embodiment of the present application;

[0015] Figure 3 4 is a block diagram of a controller in a palletizer control system according to an embodiment of the present application. DETAILED DESCRIPTION

[0016] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0017] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0018] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.

[0019] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0020] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0021] It should be understood that during the palletizing process, if defective components are not effectively identified and removed, these defective products may enter the subsequent processes, leading to more serious quality problems and even affecting the overall performance of the finished product. Therefore, ensuring the quality of each pallet component has become a key point that cannot be ignored.

[0022] Based on this, in the technical solution of the present application, it first collects the surface state image of the mold base component in the state of circulation between the curing kiln and the assembly line through an industrial camera, and transmits the surface state image of the mold base component to the controller in real time through the communication module. Then, the controller performs image recognition processing on the received surface state image of the mold base component to analyze whether the mold base component has defects, and obtains corresponding recognition results. In response to the controller determining that the mold base component has defects, a stacking abnormality warning prompt is generated to notify the operator or the system to take corresponding measures to ensure that the problematic mold base component will not continue to participate in subsequent processes, thereby ensuring product quality and smooth operation of the production process.

[0023] Specifically, in the technical solution of the present application, a palletizer control system is proposed. Figure 1 4 is a block diagram of a palletizer control system according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of a palletizer control system according to an embodiment of the present application. Figure 1 and Figure 2As shown, according to an embodiment of the present application, a palletizer control system 300 includes: an industrial camera 310, which is used to collect a surface state image of the mold base component of the mold base component, and the mold base component is in a state of flowing between the curing kiln and the assembly line; a communication module 320, which is used to transmit the surface state image of the mold base component to the controller; and a controller 330, which communicates with the curing kiln system and the assembly line system through the communication module.

[0024] In particular, the industrial camera 310 is used to collect the surface state image of the mold base component of the mold base component, and the mold base component is in a state of circulation between the curing kiln and the assembly line. In one example, the industrial camera can be installed at a key position, such as the exit of the curing kiln or the entrance of the assembly line. The purpose of this setting is to ensure that whenever the mold base component passes through these fixed points, its surface state can be accurately photographed. In order to accurately control the timing of shooting, the industrial camera will be connected to a sensor network in the system, such as a photoelectric sensor or other types of proximity switches. Once the sensor detects that the mold base component is close to or reaches the specified position, it will trigger the industrial camera to start working, thereby obtaining high-quality image data.

[0025] In particular, the communication module 320 is used to transmit the surface state image of the mold platform component to the controller. In one example, first, the industrial camera needs to be connected to the communication module through an appropriate interface (such as GigE Vision, Camera Link, etc.). This hardware connection ensures that the image data can be stably and quickly transmitted from the industrial camera to the communication module. Considering the complexity and variability in the industrial environment, choosing a suitable interface is crucial to ensuring the quality of image data transmission. For example, in a large factory environment, using an Ethernet interface may be the best choice. The Ethernet interface provides long-distance transmission capabilities and good anti-interference performance, and is also easy to integrate with other network devices. Next, to ensure that the image data can be smoothly transmitted to the controller, the communication module needs to support a data transmission protocol that matches the industrial camera. If the industrial camera uses the TCP / IP protocol for network communication, the communication module should also have the function of processing such data streams. In actual operation, this means that the communication module must not only be able to receive data packets from the industrial camera, but also have the ability to accurately forward these data to the controller. Furthermore, when the industrial camera completes a shot, an image file containing the surface state of the mold platform component is generated. These image files are encoded into a format suitable for transmission over the network and packaged by the communication module and sent to the controller. In this process, the application of compression algorithms may be involved to reduce bandwidth usage and speed up transmission. Especially in the case of high-resolution images, effective compression technology can greatly improve transmission efficiency without significantly losing image quality. In addition, considering the importance of image data, the communication module should also have error detection and correction mechanisms to ensure high data integrity even under poor network conditions.

[0026] In particular, the controller 330 communicates with the curing kiln system and the assembly line system through the communication module; and is configured to obtain the task information of the curing kiln system and the assembly line system through the communication module, and control the action of the palletizer according to the task information to realize the flow of the mold platform components between the curing kiln and the assembly line, and the specific steps include: receiving the first state information of the curing kiln system through the communication module to form a fetch task queue; receiving the second state information of the assembly line system through the communication module to form a storage task queue; determining the operation state information according to the first state information and the second state information to form a scheduling task queue; and controlling the palletizer to perform corresponding actions according to the scheduling task queue through the function control module of the controller to realize the scheduling and flow of the components on the mold platform between the curing kiln system and the assembly line system. In particular, the first state information of the curing kiln system received specifically includes: the curing state information of the components in the curing kiln, the attribute information of the components, the priority of the components, and the storage information of the curing kiln; the second state information of the assembly line system received specifically includes: the attribute information and the priority of the components on the assembly line. In particular, during the palletizing process, the controller is further used to perform image recognition on the surface state image of the mold platform component to obtain a recognition result, and the recognition result is used to indicate whether the mold platform component has defects. Figure 3 As shown, the controller 330 includes: an image processing unit 331, which is used to perform grayscale processing on the surface state image of the mold platform component to obtain a grayscale image of the surface state of the mold platform component; a mold platform component surface state semantic coding unit 332, which is used to input the grayscale image of the surface state of the mold platform component into a dynamic convolutional labeling model including a CNN layer and a Transformer model to obtain a set of semantic coding features of the surface state of the mold platform component; an adaptive feature sparsification unit 333, which is used to perform adaptive feature sparsification processing on the set of semantic coding features of the surface state of the mold platform component to obtain a set of semantic sparse features of the surface state of the mold platform component; a defect recognition unit 344, which is used to determine whether the mold platform component has defects based on the set of semantic sparse features of the surface state of the mold platform component.

[0027] Specifically, the image processing unit 331 is used to grayscale the surface state image of the mold platform component to obtain a grayscale image of the surface state of the mold platform component. It should be understood that when the mold platform component is in the process of circulating between the curing kiln and the assembly line, the surface state image collected by the industrial camera is a color image. Although the color image contains rich color information, color changes are often not a decisive factor for defect detection; on the contrary, changes in brightness and contrast can better reflect the geometric shape of the mold platform component and the texture characteristics of the component surface. Therefore, in the technical solution of the present application, the collected surface state image of the mold platform component is first converted into grayscale to eliminate the interference of color differences on the recognition of the mold platform component, so that the system can focus more on the edges, contours and other structural features of the component. This is crucial to improving the accuracy and robustness of subsequent image recognition algorithms, especially in the face of changing lighting conditions, complex backgrounds and diverse properties of mold platform component materials.

[0028] Specifically, the mold base component surface state semantic encoding unit 332 is used to input the mold base component surface state grayscale image into a dynamic convolutional labeling model including a CNN layer and a Transformer model to obtain a set of semantic encoding features of the mold base component surface state. It should be understood that in the field of industrial automation, especially for products such as mold base components with complex shapes and high precision requirements, accurate detection of their surface states is crucial. Traditional pixel-level image recognition methods are difficult to fully adapt to the diversity of mold base component material properties, colors, and reflection characteristics, which may lead to misjudgment. The DynamicViT model is a new visual Transformer model that combines a convolutional neural network (CNN) and a Transformer model, which can significantly improve the depth and accuracy of understanding the surface state of mold base components. Specifically, the CNN layer can efficiently capture the subtle structure and texture features of the mold platform component surface, which is crucial for identifying the surface defects of the mold platform component; while the Transformer model effectively models long-distance dependencies through the self-attention mechanism, which can better process global context information and help the system understand the state of the entire mold platform component. This combination enables the system to maintain high-precision defect detection capabilities in the face of changing lighting conditions, complex backgrounds, and diverse material properties of mold platform components. In a specific example of the present application, the grayscale image of the mold platform component surface state is input into a dynamic convolutional labeling model including a CNN layer and a Transformer model to obtain a set of semantic encoding features of the mold platform component surface state. Specifically, first, the grayscale image of the mold platform component surface state is segmented to obtain multiple local image blocks of the mold platform component surface state; then, the CNN layer is used to extract the local features of the mold platform component surface state for each local image block to generate multiple local feature maps of the mold platform component surface state. Then, all local feature maps are spliced ​​together to form a complete mold platform component surface state feature map. This step ensures that information obtained from different angles can be integrated together to provide a complete perspective for global analysis. Finally, the spliced ​​mold base component surface state feature map is input into the Transformer model. At this stage, the model not only takes into account the importance of local features, but also obtains a set of semantically encoded feature vectors of the mold base component surface state by learning global information. The set of semantically encoded feature vectors of the mold base component surface state not only reflects the specific morphology of the mold base component surface, but also contains key information about its potential defect mode.

[0029] Specifically, the adaptive feature sparseness unit 333 is used to perform adaptive feature sparseness processing on the set of semantic coding features of the mold base component surface state to obtain a set of semantic sparse features of the mold base component surface state. Since the set of semantic coding features of the mold base component surface state after being processed by the CNN layer and the Transformer model has the characteristics of high dimensionality and high redundant information. These feature vectors contain rich information about the surface state of the mold base component, such as texture, color, shape, etc., but may also contain a large number of irrelevant or weakly related details, which not only increases the computational burden, but may also lead to overfitting problems, affecting the generalization ability and interpretability of the model. Therefore, in order to extract the key features that best represent the surface state of the mold base component from the set of semantic coding features of the mold base component surface state, and focus on those information that are truly useful for detecting defects in the mold base component surface state, the set of semantic coding features of the mold base component surface state is further subjected to adaptive feature sparse processing to obtain a set of semantic sparse features of the mold base component surface state. Through the adaptive feature sparse processing, the model can dynamically identify and encode the key points or regions (i.e., "feature distribution hubs") of the mold base component surface state feature distribution in the set of semantic coding features of the mold base component surface state, so as to achieve effective sparseness of the mold base component surface state feature distribution. In this way, the system can more accurately understand the essential characteristics of the mold base component surface state, which can not only better support the subsequent quality control process, but also provide strong support for the subsequent mold base component defect identification, accelerate the discovery and handling of abnormal situations, and thus ensure the safe and stable operation of the production line.

[0030] Specifically, first, the template component surface state semantic feature distribution hub coding feature of the set of template component surface state semantic coding features is calculated. That is, in the technical solution of the present application, the set of template component surface state semantic coding feature vectors is input into the feature distribution hub search network to screen out those parts that best reflect the core information of the template component surface state, so as to obtain the template component surface state semantic feature distribution hub coding vector. In one example, the feature distribution hub search network is used to extract the feature distribution hub coding feature of the set of template component surface state semantic coding feature vectors using the following feature distribution hub calculation formula to obtain the template component surface state semantic feature distribution hub coding vector; wherein, the feature distribution hub calculation formula is:

[0031]

[0032] Wherein, X represents the set of semantic coding feature vectors of the surface state of the mold platform component, x1, x2, x i 、x j and x nare respectively the first, second, i-th, j-th and n-th semantic coding feature vectors of the surface state of the super mold platform component in the set of semantic coding feature vectors of the surface state of the mold platform component, S -1 represents the inverse matrix of the covariance matrix, (·) T is the transpose of the vector, N is the number of vectors in the set of semantic encoding feature vectors of the surface state of the mold platform component minus one, e i represents the semantic weight coefficient of the surface state of the ith mold platform component in the set of semantic weight coefficients of the surface state of the mold platform component, exp represents the exponential function value with the natural constant e as the base, n represents the number of weight coefficients in the set of semantic weight coefficients of the surface state of the mold platform component, and v h A hub encoding vector representing the semantic feature distribution of the surface state of the mold platform component.

[0033] Next, based on the hub coding feature of the module component surface state semantic feature distribution, the set of module component surface state semantic coding features is semantically fine-grained sparse to obtain the set of module component surface state semantic sparse features. That is, in the technical solution of the present application, first, based on the hub coding vector of the module component surface state semantic feature distribution, the sparse semantic fine-grained ablation factors of each module component surface state semantic coding feature vector in the set of module component surface state semantic coding feature vectors are calculated respectively to obtain a set of sparse module component surface state semantic fine-grained ablation factors. Specifically, the semantic fine-grained ablation factors of each module component surface state semantic coding feature vector in the set of module component surface state semantic coding feature vectors relative to the hub coding vector of the module component surface state semantic feature distribution are first calculated respectively, so as to measure the relationship between each module component surface state semantic coding feature vector and the hub coding vector of the module component surface state semantic feature distribution, thereby enhancing the model's ability to distinguish important features. That is, the semantic fine-grained ablation factor is used to quantify the correlation or difference between the semantic encoding feature vector reflecting the surface state of each mold platform component and the semantic feature distribution hub encoding vector of the surface state of the mold platform component, so as to help the model understand which features are crucial to describing the surface state of the mold platform component and which features may be redundant or insignificant, thereby improving the accuracy of identifying defects on the surface state of the mold platform component. Then, each mold platform component surface state semantic fine-grained ablation factor in the set of mold platform component surface state semantic fine-grained ablation factors is input into the sparse module based on the gating function to obtain the set of sparse mold platform component surface state semantic fine-grained ablation factors. It should be understood that, since each of the module platform component surface state semantic fine-grained ablation factors in the set of module platform component surface state semantic fine-grained ablation factors has different importance in the characterization of the module platform component surface state features, not every module platform component surface state semantic fine-grained ablation factor is important for understanding the module platform component surface state. Therefore, each of the module platform component surface state semantic fine-grained ablation factors in the set of module platform component surface state semantic fine-grained ablation factors is input into the sparse module based on the gating function to determine which features should be retained and which should be suppressed, so as to achieve effective sparseness of the module platform component surface state feature distribution. Among them, the gating function dynamically adjusts the parameters according to the input set of module platform component surface state semantic fine-grained ablation factors, so as to achieve the selection of the module platform component surface state features that are helpful for the recognition of the module platform component surface state features, so that the sparse module platform component surface state features have better interpretability and higher expressiveness in the expression of the module platform component state. In this way, the model can focus on those features that best reflect the core information of the module platform component surface state, while reducing the influence of redundant information.In one example, the sparse semantic fine-grained ablation factor of each mold platform component surface state semantic encoding feature vector in the set of the mold platform component surface state semantic encoding feature vector is calculated respectively by the following sparsification factor calculation formula to obtain a set of sparse mold platform component surface state semantic fine-grained ablation factors; wherein the sparse factor calculation formula is:.

[0034]

[0035] Among them, ||·|| is the length of the vector, ε is the adjustment parameter, max is the maximum value, a i represents the i-th module platform component surface state semantic fine-grained ablation factor in the set of module platform component surface state semantic fine-grained ablation factors, mask is a masking operation, θ is a preset threshold, w i Represents the i-th sparse module component surface state semantic fine-grained ablation factor in the set of sparse module component surface state semantic fine-grained ablation factors.

[0036] Furthermore, each sparse mold base component surface state semantic fine-grained ablation factor in the set of the sparse mold base component surface state semantic fine-grained ablation factors is used as a weight to weight the set of the mold base component surface state semantic encoding feature vectors to obtain the set of the mold base component surface state semantic sparse feature vectors. That is, by mapping the importance of the features to a numerical range, those features that are considered to be more valuable for understanding the mold base component surface state are given a higher weight, while the less important features have a lower weight, so that the mold base component surface state semantic sparse features have better interpretability and higher expressiveness, improve the accuracy of mold base component surface state recognition, and provide strong support for subsequent mold base component defect recognition. In one example, the set of the mold base component surface state semantic encoding feature vectors is weighted by the following weighting formula to obtain the set of the mold base component surface state semantic sparse feature vectors; wherein the weighting formula is:

[0037] X'={x i '}={w i *x i}

[0038] Among them, x i ' represents the i-th semantic sparse feature vector of the surface state of the mold base component in the set of semantic sparse feature vectors of the surface state of the mold base component, and X' represents the set of semantic sparse feature vectors of the surface state of the mold base component.

[0039] Specifically, the defect recognition unit 334 is used to determine whether the mold platform component has defects based on the set of semantic sparse features of the surface state of the mold platform component. That is, in the technical solution of the present application, a linear output module based on a fully connected layer is used to classify the set of semantic sparse features of the surface state of the mold platform component to obtain a classification result, and the classification result is used to indicate whether the mold platform component has defects. Here, the linear output module based on the fully connected layer maps the set of semantic sparse features of the surface state of the mold platform component to a specific category, thereby realizing the binary classification of the surface state of the mold platform component: whether there is a defect or not. Specifically, first, the set of semantic sparse features of the surface state of the mold platform component is fully connected and encoded using multiple fully connected layers of the classifier to obtain an encoded classification feature vector; and the encoded classification feature vector is passed through a Softmax classification function to obtain the classification result. In this way, accurate identification of the surface state of the mold platform component is achieved, and strong support is provided for efficient production and quality control in the field of industrial automation.

[0040] It should be noted that in the technical solution of the present application, although the set of semantically encoded feature vectors of the mold platform component surface state is subjected to feature screening based on feature distribution hubs to extract representative features therefrom to reduce the amount of data processing and avoid information redundancy, the set of semantically encoded feature vectors of the mold platform component surface state will inevitably introduce noise during the acquisition process, which causes fine-grained offsets in the anchoring of the feature distribution hub and selection mismatches in the feature selection process. This causes the global mold platform component surface state semantic feature representation vector obtained by fully connected encoding to have insufficient long-distance encoding representation, thereby reducing the expression effect of the global mold platform component surface state semantic feature representation vector and affecting the accuracy of the attribute label of the first descriptive data item obtained by its input classifier.

[0041] Therefore, in one example, when the global mold platform component surface state semantic feature representation vector is input into a classifier, the global mold platform component surface state semantic feature representation vector is optimized, and the optimization includes the following steps:

[0042] Arranging the eigenvalues ​​of the global mold platform component surface state semantic feature representation vector in ascending order to form a global mold platform component surface state semantic feature representation sequential coding vector;

[0043] In response to the absolute value of the difference between the ith eigenvalue and the i+1th eigenvalue of the global mold platform component surface state semantic feature representation sequential encoding vector being less than or equal to the distance difference hyperparameter ε, the weighted sum between the ith eigenvalue and the i+1th eigenvalue is calculated as the optimized i+1th eigenvalue v' i+1 =α×v i+β×v i+1 ;

[0044] In response to the absolute value of the difference between the ith eigenvalue and the i+1th eigenvalue of the global mold platform component surface state semantic feature representation sequential encoding vector being greater than the distance difference hyperparameter ε:

[0045] Calculate the square root of the sum of squares of all eigenvalues ​​of the global mold platform component surface state semantic feature representation vector, multiply the square root by 2 and then divide it by the square of the length of the global mold platform component surface state semantic feature representation vector to obtain the global mold platform component surface state semantic feature representation space primitive value γ;

[0046] After multiplying the spatial primitive value γ of the global mold platform component surface state semantic feature representation by the i-th eigenvalue, the weighted subtraction between the product and the i+1th eigenvalue is calculated to obtain the optimized i+1th eigenvalue v' i+1 =δ×γ×v i -θ×v i+1 ;

[0047] The optimized i+1th eigenvalue of the global template component surface state semantic feature representation sequential coding vector is combined to obtain an optimized global template component surface state semantic feature representation vector, wherein the first eigenvalue of the global template component surface state semantic feature representation sequential coding vector remains unchanged.

[0048] In this way, in order to address the problem of insufficient global fully connected coding representation capability of the feature set of the global template component surface state semantic feature representation vector under a predetermined eigenvalue sequential distribution due to a long distance exceeding a predetermined local distribution interval threshold, the high-dimensional feature space primitive representation of the global template component surface state semantic feature representation vector based on self-inner product fusion is used to capture the complex structure of the global network interaction of its eigenvalues, thereby reconstructing the cross-domain fine-grained aggregation relationship between the eigenvalues ​​of the global template component surface state semantic feature representation vector by simulating scale-based high-dimensional feature space potential primitives, so as to achieve coding reconstruction of the real sequence distribution behavior of the global template component surface state semantic feature representation vector under long distance, improve the coding expression effect of the global template component surface state semantic feature representation vector, and improve the accuracy of the classification result obtained by its input classifier.

[0049] As described above, the palletizer control system 300 according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with a palletizer control algorithm. In a possible implementation, the palletizer control system 300 according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or a hardware module. For example, the palletizer control system 300 can be a software module in the operating system of the wireless terminal, or can be an application developed for the wireless terminal; of course, the palletizer control system 300 can also be one of the many hardware modules of the wireless terminal.

[0050] Alternatively, in another example, the palletizer control system 300 and the wireless terminal may also be separate devices, and the palletizer control system 300 may be connected to the wireless terminal via a wired and / or wireless network, and transmit interactive information in a predetermined data format.

[0051] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A palletizer control system, comprising: Controller, communication module; The controller communicates with the curing kiln system and the assembly line system through the communication module; The controller is also configured to obtain task information of the curing kiln system and the assembly line system through the communication module, and control the action of the palletizer according to the task information to realize the transfer of the mold platform components between the curing kiln and the assembly line, characterized in that it also includes: An industrial camera, used for collecting a surface state image of the mold base component of the mold base component, wherein the mold base component is in a state of being transferred between the curing kiln and the assembly line; The communication module is also used to transmit the surface state image of the die table component to the controller; The controller is also used to perform image recognition on the surface state image of the die table component to obtain a recognition result, and the recognition result is used to indicate whether the die table component has defects; The controller is also used to generate a stacking abnormality warning prompt in response to the recognition result that the mold platform component has defects.

2. The palletizer control system according to claim 1, characterized in that: The controller comprises: An image processing unit, used for performing grayscale processing on the surface state image of the mold platform component to obtain a grayscale image of the surface state of the mold platform component; A mold platform component surface state semantic encoding unit, used for inputting the mold platform component surface state grayscale image into a dynamic convolutional labeling model including a CNN layer and a Transformer model to obtain a set of mold platform component surface state semantic encoding features; An adaptive feature sparseness unit, used for performing adaptive feature sparseness processing on the set of semantic coding features of the mold platform component surface state to obtain a set of semantic sparse features of the mold platform component surface state; The defect recognition unit is used to determine whether the mold base component has defects based on a set of semantic sparse features of the surface state of the mold base component.

3. The palletizer control system according to claim 2, characterized in that: The mold platform component surface state semantic encoding unit is used to: Segmenting the grayscale image of the surface state of the mold platform component to obtain a plurality of local image blocks of the surface state of the mold platform component; Using the CNN layer to extract local features of the surface state of the mold platform component from each local image block of the surface state of the mold platform component in the multiple local image blocks of the surface state of the mold platform component to obtain multiple local feature maps of the surface state of the mold platform component; splicing the plurality of local characteristic maps of the surface state of the die table component to obtain a characteristic map of the surface state of the die table component; The mold base component surface state feature map is input into the Transformer model to obtain a set of mold base component surface state semantic coding feature vectors as the set of mold base component surface state semantic coding features.

4. The palletizer control system according to claim 3, characterized in that: The adaptive feature sparseness unit comprises: A feature distribution hub coding subunit, used for calculating a mold base component surface state semantic feature distribution hub coding feature of a set of the mold base component surface state semantic coding features; The fine-grained sparseness subunit is used to perform semantic fine-grained sparseness on the set of semantic coding features of the mold base component surface state based on the distribution hub coding features of the mold base component surface state semantic features to obtain the set of semantic sparse features of the mold base component surface state.

5. The palletizer control system according to claim 4, characterized in that: The feature distribution hub encoding subunit is used to: The set of the mold base component surface state semantic encoding feature vectors is input into a feature distribution hub search network to obtain a mold base component surface state semantic feature distribution hub encoding vector as the mold base component surface state semantic feature distribution hub encoding feature.

6. The palletizer control system according to claim 5, characterized in that: The fine-grained sparseness subunit includes: The secondary subunit for calculating the sparse factor is used to calculate the sparse semantic fine-grained ablation factor of each module platform component surface state semantic coding feature vector in the set of module platform component surface state semantic coding feature vectors based on the module platform component surface state semantic feature distribution hub coding vector to obtain a set of sparse module platform component surface state semantic fine-grained ablation factors; The feature sparsification secondary subunit is used to perform feature sparsification on the set of semantically encoded feature vectors of the surface state of the mold platform component based on the set of sparse mold platform component surface state semantic fine-grained ablation factors to obtain a set of mold platform component surface state semantic sparse feature vectors as the set of mold platform component surface state semantic sparse features.

7. The palletizer control system according to claim 6, characterized in that: The sparsification factor calculation secondary subunit is used for: Respectively calculating the semantic fine-grained ablation factor of each mold platform component surface state semantic coding feature vector in the set of mold platform component surface state semantic coding feature vectors relative to the mold platform component surface state semantic feature distribution hub coding vector to obtain a set of mold platform component surface state semantic fine-grained ablation factors; Each of the module platform component surface state semantic fine-grained ablation factors in the module platform component surface state semantic fine-grained ablation factor set is input into a sparse module based on a gating function to obtain the sparse module platform component surface state semantic fine-grained ablation factor set.

8. The palletizer control system according to claim 7, characterized in that: The feature sparse secondary subunit is used to: Using each sparse module component surface state semantic fine-grained ablation factor in the set of sparse module component surface state semantic fine-grained ablation factors as a weight, the set of module component surface state semantic encoding feature vectors is weighted respectively to obtain the set of module component surface state semantic sparse feature vectors.

9. The palletizer control system according to claim 8, characterized in that: The defect recognition unit is used to: A linear output module based on a fully connected layer is used to classify a set of semantic sparse features of the surface state of the mold platform component to obtain a classification result, and the classification result is used to indicate whether the mold platform component has defects.

Images