34 results about "Cascade network" patented technology

The invention discloses a multi-cascade network security risk dynamic assessment and protection system, and relates to the technical field of network security. Comprising a multi-cascade data acquisition and preprocessing module, a dynamic data traceability graph construction module, a distributed security knowledge graph collaboration module, a multi-cascade risk causal evaluation module and a dynamic protection and closed-loop optimization module. According to the method, a collaborative architecture of multi-cascade data acquisition and preprocessing, dynamic data traceability graph construction, distributed security knowledge graph collaboration, multi-cascade risk causal evaluation and dynamic protection and closed-loop optimization is constructed, and system operation parameters are continuously optimized through a closed-loop feedback link. The dynamic adaptation capability of network security risk assessment to the multi-cascade architecture and the comprehensiveness of assessment results are remarkably improved, and the problems that in the prior art, network security assessment mostly depends on single-dimension data, cross-module deep collaboration is lacked, and dynamic changes of the multi-cascade architecture are difficult to adapt can be solved.

The invention relates to the field of geological data, in particular to a cascade Transform fusion method and system based on multi-source heterogeneous geological data. The method comprises the steps of obtaining a historical paper geological data set and a real-time multi-source geological monitoring data stream, and generating a multi-source heterogeneous geological feature set based on the historical paper geological data set and the real-time multi-source geological monitoring data stream; based on this, performing coarse-to-fine multi-level feature extraction and cross-modal attention fusion through a cascaded Transform network, and generating a deep fusion feature field; on the basis, multi-target collaborative optimization calculation is carried out by integrating geological prior knowledge rules, and a risk-resource integrated three-dimensional geological model for quantifying disaster risk probability and resource economic value is generated; on the basis, concealed disaster targeted treatment and resource re-exploitation optimization are carried out through a decision mapping engine, and a collaborative optimization engineering scheme set is generated. In the data cascade fusion process, the intelligent level and comprehensive benefits of geological engineering activities are remarkably improved.

The invention discloses a night electric worker protection equipment detection method based on a deep cascade network architecture. The method comprises the following steps: constructing an improved YOLO v8 model; carrying out the preprocessing of a low-illumination and high-noise image through the input part of the improved YOLO v8 model, and generating an optimized image tensor; performing feature extraction on the optimized image tensor through a backbone network of an improved YOLO v8 model to obtain feature maps of different scales; capturing a content relationship between image features of the large-scale feature map through a Transform module in the backbone network; transmitting the feature map to a detection head of an improved YOLO v8 model for detection; and when the improved YOLO v8 model is trained, a sliding loss function is introduced, and a detection result with the annotation information of the improved YOLO v8 model is output. According to the invention, the performance and accuracy of target detection under the low-light condition are significantly improved.

The invention discloses a multi-type split part splicing error detection and position correction method based on a two-stage cascade network, and the method comprises the steps: 1, carrying out the data collection and processing of multi-type split parts, and enabling the data to serve as the input of two-stage network cascade training of a MoE-RT-DETR network and an HRNet network; 2, performing model training based on a two-stage cascade network; step 3, reasoning based on the trained two-stage network model, extracting pixel coordinates of key points, and converting the pixel coordinates into physical world coordinates through preloaded industrial camera calibration parameters; and step 4, carrying out splicing error detection based on the converted physical coordinates, calculating a key point difference value and guiding position correction adjustment. The invention further discloses a detection and position correction system for implementing the method, and the detection and position correction system has a wide application scene.

The invention discloses an energy rebalance control method for a fault power unit of a high-voltage cascade networking energy storage system, and belongs to the technical field of power electronics and energy storage systems. The method aims to solve the problems that residual energy cannot be recycled after a fault power unit bypasses, voltage unbalance of a healthy unit is caused, and overcurrent impact is caused in the rebalancing process. According to the method, a multi-dimensional state sensing dynamic feasible region model is constructed, weight optimization distribution, phase smooth transition and multi-stage rate control are combined, and efficient smooth transfer of residual energy is achieved on the premise that system safety and network construction stability are guaranteed. According to the scheme, the available capacity, the voltage quality and the dynamic stability of the system under the fault working condition are remarkably improved.

The invention discloses a cascade UNet network-based flow field multi-scale refined prediction method and system, and solves the problems of insufficient multi-scale feature capture, local detail loss and low prediction precision in turbulent flow field prediction. The method comprises the following steps: firstly, performing multi-scale processing on three-dimensional turbulence field data, and constructing a training sample containing a global scale and a local scale; secondly, constructing a dual-scale U-Net neural network model, wherein the dual-scale U-Net neural network model comprises a global U-Net for processing global low-resolution data and a local U-Net for processing local high-resolution data; constraining the consistency of local prediction and global prediction in a boundary region by adopting a boundary consistency loss function; implementing a staged training strategy, independently training a global U-Net, and then fixing parameters of the global U-Net to train a local U-Net; and finally, predicting a target flow field by using the trained dual-scale network to obtain a high-precision three-dimensional turbulent flow field variable. According to the method, high-precision direct mapping from the flow field time sequence data to the future state is realized, and the method has the characteristics of high intellectualization and automation.

A double-module dynamic series cascade network system for predicting preoperative T stage of gastric cancer belongs to the technical field of medical artificial intelligence. The system adopts a deep learning architecture of double-module dynamic series connection. The first module realizes T1-T4 stage screening based on a hybrid model of parallel CNN and hierarchical Transformer. If it is judged as T1-T3 stage, the output result is output, and the second module is not entered. If it is judged as T4 stage, the second module is automatically triggered to perform T4 subtype differentiation task based on ResNet-152 submodel, and the output result is T4a or T4b. The system uses postoperative pathological results as the T stage gold standard, and shows high accuracy and universality in multicenter retrospective and prospective verification. The results show that the macro average AUC of the model in external verification reaches 0.964, the accuracy is 94.4%, and the T4 subtype recognition accuracy is highest, reaching 96.2%. The present application does not depend on labeled data, can significantly improve the accuracy and consistency of preoperative staging of gastric cancer, realize automatic and fine intelligent evaluation, has strong generalization ability and important clinical application value.

The present invention discloses a method for detecting defects of transmission small fittings based on a cascaded network, belonging to the technical field of defect detection of transmission small fittings. The specific method includes: Step 1: Obtain the production line assembly drawings of transmission small fittings; set up the detection device for transmission small fittings; Step 2: Obtain several representative images of transmission small fittings, perform representative image processing, and obtain several groups of training sets and test sets; Step 3: Construct a convolutional neural network for detecting defects of transmission small fittings, and then train and test the convolutional neural network through the obtained training sets and test sets, and mark the successfully tested convolutional neural network as a defect detection model; Step 4: Obtain the detection data of the working simulation module in the detection device, judge whether the detection data is qualified. When the detection data is unqualified, record the corresponding unqualified area; when the detection data is qualified, proceed to the next step; Step 5: Detect the transmission small fittings passing through the detection area through the defect detection model.

The invention discloses a table structure extraction method based on a deep cascade network, and the method comprises the steps: obtaining a table image, extracting the visual features of the table image, coding the visual features to obtain enhanced features, and obtaining target query information according to the enhanced features; according to target query information, decoding the enhanced features to obtain a prediction result of a text region bounding box; decoding the prediction result of the text region bounding box to obtain a prediction result of a cell region bounding box; and performing logical position allocation according to a prediction result of the cell region bounding box to obtain table structure content.

The invention is suitable for the field of computers, and provides a supply chain inventory optimization method, device and equipment, and the method comprises the steps: obtaining supply chain graph data; inputting the supply chain graph data into a pre-trained supply chain dynamic cascade network, and encoding to obtain a node state vector; inputting the node state vector into a pre-trained spatio-temporal joint prediction function to obtain a prediction result; and if the current mode is not the training mode, obtaining a planned delivery quantity vector and a service constraint rule corresponding to the supply chain network, and inputting the predicted delivery quantity vector, the planned delivery quantity vector and the service constraint rule corresponding to the supply chain network into a preset decision constraint optimization function to obtain an executable delivery decision vector. According to the method, the problems of inaccurate dynamic prediction, lack of flexibility of replenishment strategies and high optimization complexity in the prior art are effectively solved, and an efficient, accurate and dynamically adaptive solution is provided.

The application provides a face recognition processing method based on a multi-task cascaded convolutional network and a storage medium, and the method comprises the following steps: constructing a multi-task cascaded convolutional network, dividing the multi-task cascaded convolutional network into three convolutional neural networks, the first cascaded network is P-Net, the second cascaded network and the third cascaded network are R-Net and O-Net respectively; acquiring a single face image sample set to train the multi-task cascaded convolutional network, and obtaining a converged multi-task cascaded convolutional network; acquiring a face image to be detected, preprocessing the face image to be detected, inputting the preprocessed face image to be detected into the first cascaded network, and obtaining a face candidate window image; screening the face candidate window image through the confidence of the second cascaded network; inputting the face candidate window image screened through the confidence into the third cascaded network, and outputting a final face image through the third cascaded network.

A fast detection method for conductor and ground wire defects based on a lightweight cascaded network, comprising: manually annotating the conductor and ground wire images collected by a drone to generate a training set and a test set for conductor and ground wire defects. In the training module, use the image data of the annotated training set for conductor and ground wire defects to train the TCDNet model, and use the test set for testing to obtain a model weight file with the highest accuracy; send the trained model weight file into the model compression and pruning module to perform sparse training on the model weight file, iterate continuously to achieve compression and pruning, and output a lightweight TCDNet model weight file; deploy the lightweight TCDNet model weight file into the inference module, and then send the conductor and ground wire image to be detected into the inference module to obtain the detection result of the conductor and ground wire defects, and output the confidence, position and size of the defects respectively. The present invention does not require complicated manual data analysis, and has a high defect discovery rate, fast speed and few missed detections.

The embodiment of the invention provides a wide-area computing power cascade network architecture based on hierarchical Dragonfly + Fat-Tree, and the network architecture comprises at least one computing power cluster which comprises a plurality of computing power chips in communication connection; the at least one first network architecture comprises a plurality of first nodes, and the first nodes in the same first network architecture are in communication connection to form a tree topology structure; the first-level autonomous architecture comprises a plurality of second nodes, the second nodes in the same first-level autonomous architecture are in communication connection to form a direct connection topological structure, and different first-level autonomous architectures belong to different areas; wherein at least one computing power cluster is in communication connection with a first-stage autonomous architecture through a first network architecture, and the first-stage autonomous architecture is connected with the computing power cluster in an area to which the first-stage autonomous architecture belongs. Therefore, according to the embodiment of the invention, a super-large-scale network architecture can be constructed.

The invention discloses a dual-module dynamic series cascade network system for predicting gastric cancer preoperative T stage, and belongs to the technical field of medical artificial intelligence. The system adopts a double-module dynamic series connection deep learning architecture, and a first module realizes T1-T4 period primary screening based on a hybrid model of a parallel CNN (Convolutional Neural Network) and a hierarchical Transform. If the T1-T3 period is judged, outputting a result, and not entering the second module; if the T4 period is judged, the second module is automatically triggered to execute a T4 subtype distinguishing task based on the ResNet-152 submodel, and an output result is T4a or T4b. The system adopts a postoperative pathological result as a T-stage gold standard, and shows high accuracy and universality in multi-center retrospective and prospective verification. The result shows that the macro average AUC of the model in external verification reaches 0.964, the accuracy rate is 94.4%, and the highest T4 subtype recognition accuracy rate is 96.2%. The method does not depend on labeled data, the accuracy and consistency of gastric cancer preoperative staging can be remarkably improved, automatic and refined intelligent evaluation is achieved, and the method has high generalization ability and important clinical application value.

1. The name of the design product: cascade networking configuration graphical user interface for electronic equipment. 2. The use of the design product: for an electronic device. 3. The design points of the design product: in the graphical user interface. 4. The picture or photo that best indicates the design points: front view. 5. The use of the graphical user interface: the graphical user interface is used for the user to join the cascade network between the cluster devices with one key, and view the network relationship between the local and other superior devices in the network topology diagram. 6. The human-computer interaction mode of the graphical user interface: in the front view, click the "start cascade networking" button on the left to jump to the interface change state diagram 1; in the interface change state diagram 1, input the text content in the corresponding edit box to jump to the interface change state diagram 2; in the interface change state diagram 2, click the "confirm" button to jump to the interface change state diagram 3; in the interface change state diagram 3, slide the mouse wheel to enter the interface change state diagram 4.

A cascade refinement coronary artery segmentation method based on geometric deformation enhancement includes the following steps: S1, image acquisition; S2, image preprocessing; S3, mesh construction; S4, model construction; and S5, model training. In view of the problem that coronary arteries have complex anatomical structures, in the present disclosure, by integrating a geometric deformation network, a cascaded network is designed for coronary artery segmentation and vectorization of results, which can generate continuous and accurate coronary artery meshes, adapt to complex coronary artery structures, and avoid fragmentation of segmentation results. Different from mesh results generated by traditional voxel-based cube methods, the algorithm provided in the present disclosure can reconstruct finer vectorized coronary artery meshes with regular morphology, and avoid problems of bifurcation adhesion and point cloud dispersion in complex branches.

The invention relates to a high-voltage cascade network construction type energy storage hierarchical grid-connected control method and system, and belongs to the field of energy storage control and power system optimization. According to the method, a plurality of energy storage units are connected in a cascading manner, so that flexible expansion and efficient integration of the system are realized, and the method is suitable for power requirements of different scales. On the basis, a hierarchical control strategy is provided, and two hierarchical control methods of local control and global coordination are adopted. Local control performs real-time optimization management on each energy storage unit to ensure efficient operation of the energy storage unit; and the global coordination is dynamically adjusted based on the overall power grid state, the overall output of the energy storage system is optimized, and coordinated and consistent grid-connected control is realized. According to the method, through hierarchical control and dynamic adjustment, optimized operation of the energy storage system is realized, and the reliability and stability of the power system are enhanced.

The application discloses a few-shot remote sensing spatio-temporal fusion method and system based on a degenerate fusion cascade network. In the first stage, a degenerate network is designed to learn the complex degenerate relationship between the high spatial resolution image to be fused and the low resolution image, instead of constructing a training set by traditional interpolation down-sampling. The high spatial resolution image is taken as input, and the low spatial resolution image is taken as a label to train the degenerate network. After the training is completed, the low resolution image is input into the degenerate network to obtain a low spatial resolution degenerate image. Then, a fusion network based on a cycle consistency generative adversarial network is trained by taking the low resolution image and the low resolution degenerate image as training data. The low resolution degenerate image is taken as input, and the low resolution image is taken as a label to train the fusion network. After the training is completed, the low resolution image is input into the fusion network to obtain a final fused high resolution image. The method has a lower requirement for the number of training samples, high fusion precision, and certain universality.

The invention provides a general routing configuration system and method for an SRIO (Serial Radio Input / Output) dual-redundancy cross-cascade network, and the method comprises the following configuration steps: carrying out cross-cascade connection on a dual-redundancy functional module and a switching module, defining an ID (Identity) address of the SRIO dual-redundancy cross-cascade network according to fields, and configuring a port routing information table of a host and a standby of the dual-redundancy switching module; and a network reconstruction step: when the dual-redundancy function module or the switching module fails, changing the ID address of the function module or the routing information table configuration of the port of the switching module to complete the reconstruction of the network system. According to the invention, the robustness of the network system is improved through the cross redundancy cascading between the SRIO end nodes and the switches and between the switches, the unified routing exchange address and port configuration of the network system is realized through the universal ID address definition of the SRIO end nodes and the universal routing information table configuration method of the switch ports, and the network system reliability is improved. And the adaptability of the dual-redundancy network system is improved.

The invention relates to the technical field of chip detection, in particular to a chip bump submicron defect online detection method which comprises the following steps: generating a bump submicron simulation image by using a simulation model; performing super-resolution processing on the simulation image by using the improved ESRGAN model; performing physical self-supervision augmentation on the super-resolution image; constructing a mixed image by using the augmented image and the production line image; inputting the mixed image into a meta-learning model, and outputting a defect type; and outputting a defect position by using a cascade network. According to the method, the problems of sub-pixel defect form distortion and poor defect image detection generalization performance in existing super-resolution image processing are solved.

The application relates to a high-voltage cascade network type energy storage grading grid-connected control method and system, belonging to the field of energy storage control and power system optimization. The method realizes flexible expansion and efficient integration of the system by connecting multiple energy storage units in a cascade manner, and is suitable for different scales of power demand. On this basis, a hierarchical control strategy is proposed, which adopts two-level control methods of local control and global coordination. The local control optimizes and manages each energy storage unit in real time to ensure efficient operation; the global coordination dynamically adjusts based on the overall grid state to optimize the overall output of the energy storage system and realize consistent grid-connected control. Through hierarchical control and dynamic adjustment, the method realizes the optimized operation of the energy storage system and enhances the reliability and stability of the power system.

The application discloses a kind of image detection method and system under rain condition, it is related to target detection technical field.The application carries out image detection under rain condition using cascade network, the cascade network includes rain removal network and target detection network.After training data is sent into rain removal network, the reconstruction loss of clean image calculated from rain-free image is output with the result, and the rain-free image and the image after rain removal are sent into target detection network.The initialization model of target detection network is the model trained using rain-free image.The feature map is obtained after rain-free image and reconstructed rain-free image after rain removal pass through feature extraction layer in target detection network, and the feature map of the two is used to calculate perception loss.The joint loss of reconstruction loss, perception loss and target detection loss is added as network, and the gradient of joint loss is fed back to rain removal network to update network weight.

The invention discloses a communication method, a cascade communication device, a source end device and an electronic device. The communication method is used for a current node in a cascade network and comprises the steps that at least one first message sent by a first source end connected with the current node is received, at least one second message sent by the current node in a previous-level node in the cascade network is received, each of the first message and the second message carries a scheduling mark, and the scheduling mark is sent to the current node; the scheduling value of the scheduling mark is set according to a preset coding rule; and continuously scheduling the object messages with the same scheduling value in the at least one first message and the at least one second message so as to send the object messages from the current node. The communication method realizes fair scheduling in the cascade network.

The invention discloses a face normal estimation method adopting a shared weight cascade network architecture. The face normal estimation method is realized by inputting a face image into a trained shared weight cascade network model. The shared weight cascade network model comprises a face feature extraction coding module, a decoding module and a plurality of cascade modules, the modules share network parameters in a cross-level mode through the shared weight modules, efficient multiplexing of the parameters is achieved, feature extraction and normal prediction from coarse to fine in a layer-by-layer progressive mode are achieved, and the prediction efficiency is improved. The total parameter number of the model is effectively reduced, the over-fitting risk is reduced, effective transmission and knowledge sharing of information between different levels are promoted, the model can utilize limited data resources more efficiently, the precision and robustness of normal estimation are remarkably improved, the prediction precision is improved, and the prediction efficiency is improved. And the adaptive capacity of the model to different face features is obviously enhanced, and the subtle change of the face surface can be captured more accurately.

Apparatuses and methods of manufacturing same, systems, and methods are described. In one aspect, a method includes generating a convolutional neural network (CNN) by training a CNN having a plurality of convolutional layers, and performing cascade training on the trained CNN. The cascade training includes an iterative process of a plurality of stages, in which each stage includes inserting a residual block (ResBlock) and training the CNN with the inserted ResBlock.

The invention discloses a dense subgraph detection method and system for a multi-cascade network, and the method comprises the steps: carrying out the initialization definition of the priority and network association density of a plurality of networks and nodes in a plurality of networks based on financial transactions, introducing a non-null constraint, and carrying out the initialization definition of conditions satisfied by the detection of abnormal nodes; the method comprises the following steps: modeling cross-part interaction information of a plurality of networks into affiliated information of a same adjacency relationship, decomposing through a coupling matrix sharing association constraints to obtain a low-rank factor matrix of each node of the plurality of networks, and primarily screening a plurality of groups of candidate solutions after truncation according to a preset threshold value; aggregating a plurality of sub-networks formed by each group of candidate solutions, and then solving by using a dense sub-graph solver; the dense subgraph association density is optimized through a neighborhood expansion method; and selecting the solution with the maximum correlation density from the multiple groups of feasible solutions, and outputting a final detection result. According to the method, the correlation density of multiple networks is provided, and the method has effectiveness, anti-interference performance and good expandability.

The present invention discloses a method for detecting EL defects of photovoltaic modules based on an improved YOLOv5 network, which establishes a detection model relying on upstream and downstream processes. Instead of taking a single cell as the detection unit, the module is used as the detection unit, and the detection and positioning of 13 common defects at present are realized. These defects not only include the defects in a single cell, but also include the overall defects with the cell module as the observation unit. Using the established photovoltaic module EL defect dataset to train and test the detection model, the experimental results show that the improved YOLOv5s cascade network model can efficiently and accurately identify various defects contained in the photovoltaic module EL image, and complete the comprehensive identification and precise positioning of complex EL defects.

The application relates to the field of geological data, in particular to a cascading Transformer fusion method and system based on multi-source heterogeneous geological data. The method comprises the following steps: acquiring a historical paper geological data set and real-time multi-source geological monitoring data flow, based on which a multi-source heterogeneous geological feature set is generated; based on this, coarse-to-fine multi-level feature extraction and cross-modal attention fusion are carried out through a cascading Transformer network to generate a deep-level fusion feature field; based on this, multi-objective collaborative optimization calculation is carried out by integrating geological prior knowledge rules to generate a risk-resource integrated three-dimensional geological model of quantitative disaster risk probability and resource economic value; based on this, the optimization of hidden disaster targeted management and resource re-mining is carried out through a decision mapping engine to generate a set of collaborative optimization engineering schemes. In the data cascading fusion process, the intelligent level and comprehensive benefits of geological engineering activities are significantly improved.

The invention belongs to the technical field of pancreatic tumor segmentation, and relates to a pancreatic tumor segmentation method based on a cascade network, which comprises a two-stage deep learning framework, in the first stage, coarse segmentation is performed on the whole pancreas based on a multi-scale U-Net backbone network to suppress background interference, and in the second stage, under the guidance of the output of the first stage, the pancreatic tumor segmentation is performed on the whole pancreas based on the multi-scale U-Net backbone network. Focusing in a pancreas area to carry out tumor fine segmentation; the two stages are tightly coupled through an interaction enhancement module, and the interaction enhancement module not only dynamically cuts and optimizes an input region of fine segmentation by using a coarse segmentation result, but also transmits space weight information to realize end-to-end joint optimization; in the second stage, an inter-class shared boundary measurement mechanism is introduced, and a loss function is fused, so that the sensitivity of the model to small-scale tumors and fuzzy boundaries thereof is enhanced; according to the method, it can be ensured that the training process is completely consistent with the reasoning process during actual deployment, performance fluctuation caused by process splitting is effectively avoided, and the stability and reproducibility of the model in a real clinical scene are remarkably improved.

The present invention discloses a rolling bearing fault diagnosis method based on a high-frequency multi-scale cascade network, comprising: applying a high-frequency multi-scale cascade network to perform fault diagnosis on a rolling bearing according to a bearing vibration signal, wherein the high-frequency multi-scale cascade network comprises a high-frequency convolution block and a multi-scale cascade block; the high-frequency convolution block is used to identify and suppress high-frequency noise in the vibration signal to obtain a vibration feature; and the multi-scale cascade block is used to output a fault feature based on the correlation of pulse signals in the vibration feature. The present invention can enhance the noise suppression and feature learning capabilities of the model by combining the high-frequency convolution block with the multi-scale cascade block, thereby improving the accuracy, robustness and interpretability of fault diagnosis.