12results about How to "Strong modeling ability" patented technology

The invention relates to the field of computer vision, in particular to an improved high-resolution remote sensing image road extraction method based on a CATransFuse model. The method comprises the following steps of: 1, acquiring a remote sensing image, and slicing the remote sensing image according to a fixed size to obtain remote sensing image slices; and a second step, inputting the remote sensing image slices into a trained network CATransFuse for forward propagation operation, obtaining road features in the network CATransFuse, and outputting the road features. According to the method provided by the invention, by optimizing the structure of the network CATransFuse and training the parameters, the network CATransFuse capable of accurately identifying the road features is obtained. In the training process, the ability of identifying various road features is achieved by optimizing the sample quality and the number. Therefore, the identified road features are closer to the actual situation, and the accuracy is higher. According to the method, the CBAM and ASPP modules are introduced, so that feature relevance, context information and road target modeling can be better processed, and better performance can be obtained in a road extraction task.

This invention discloses a method, system, and storage medium for multivariate time-series feature extraction and grade prediction in flotation processes. The method includes the following steps: Step S1: Raw data input and encoding; encoding and structured input of time-series data composed of various process variables; Step S2: Extracting dynamic features; Step S3: Condition-guided encoding modeling; Step S4: Enhancing the saliency of key variables and important time segments; employing a multi-head attention mechanism to match key-value pairs generated from target-guided query vectors and multi-scale features; Step S5: Outputting a prediction module; performing feature fusion and nonlinear mapping on the attention mechanism output to output the predicted concentrate grade and recovery rate for future times. The system and storage medium are both based on the above method. This invention has advantages such as higher intelligence, better controllability, and improved prediction accuracy and model adaptability for key indicators in the flotation process.

This invention proposes a method and system for predicting icing thickness on transmission lines, relating to the field of transmission line safety monitoring technology. The method includes: acquiring multi-dimensional meteorological data and corresponding icing thickness data of a target transmission line; preprocessing the multi-dimensional meteorological data; calculating the grey correlation value between the preprocessed meteorological data and the icing thickness data; when the grey correlation value is greater than a preset threshold, the current meteorological data is taken as strongly correlated meteorological data for icing thickness; constructing a lag feature vector between the current time and the previous L historical times based on the strongly correlated meteorological data; inputting the lag feature vector as an input vector into a hybrid kernel extreme learning machine model; optimizing the hyperparameter vector of the hybrid kernel extreme learning machine model using an improved Harris Eagle optimization algorithm; training the hybrid kernel extreme learning machine model using the optimized hyperparameters; and outputting the icing thickness prediction result using the trained model.

The invention discloses a conversion and classification prediction method for converting node classification into sub-graph classification. The method is characterized by comprising the following steps: converting a node classification data set into a sub-graph classification data set; injecting identity information into the sub-graph nodes; a subgraph encoder GIN based on a message passing framework encodes node information; and aggregating feature representations of different layers of the central node and the surrounding nodes, zooming different features by using a learnable factor to obtain feature representations, inputting the feature representations into a feedforward neural network to predict sub-graph tags, calculating cross entropy loss of the predictive tags and real tags, and calculating the cross entropy loss of the predictive tags and the real tags. And adjusting parameters and feature scaling factors of the graph neural network model according to the loss. Compared with the prior art, the method has the advantages that the sub-graph information is fused with the features of a single node, label conflicts are relieved, the model performance is improved, the problem that different labels need to be given to the same induction sub-graph only due to different types of starting nodes is solved, and the method has a good application prospect.

The present invention discloses a method for constructing a geographic element prediction model, a prediction method and related devices, which are applied to the field of geographic information technology, including: constructing a sample; the sample includes an environmental variable grid, a first distance grid and a geographic element of a sampling point in the same window; the first distance grid is a grid constructed according to the distance between the sampling point in the window and each control point in the window when the window is moved with a preset window and a window movement strategy; the preset geographic element prediction model is trained through the sample to obtain a trained geographic element prediction model. The beneficial effects of the present invention are: a machine learning model is used to fully integrate known environmental variable information and the first law of geography, and has stronger modeling capabilities and higher prediction accuracy.

The present invention discloses a thermal effect correction method and system based on Beta spline surface fitting, the method comprises: obtaining a thermal effect filter image of a thermal effect degraded image; sampling to obtain a discretized image, converting each point therein into a type value point of a cubic Beta spline surface, and optimizing the Beta spline surface problem as a spline curve problem; according to the deviation parameter and tangent parameter of the step spline curve within a preset range of the coefficient of determination, solving the optimal parameter group of all spline curves in the direction and direction; weightedly calculating the optimal deviation parameter and optimal tangent parameter of the surface according to the optimal parameter group of all spline curves, inversely calculating the corresponding surface control point matrix, solving the cubic Beta spline surface, and then gray-stretching the surface to obtain a thermal effect intensity field; iteratively optimizing the thermal effect degraded image to obtain a corrected image. The present invention can more effectively remove the thermal effect of optical imaging of supersonic aircraft targets.

The application discloses an intelligent temperature control method and system for an injection molding machine, which collects temperature values of a melt conveying section, a solid melting section and a solid conveying section of a material bucket of the injection molding machine, sets temperature target values of the three sections, predicts actual control values of the temperatures of the sections and a temperature target value of the whole material bucket of the injection molding machine and a temperature prediction value of the whole material bucket of the injection molding machine according to the temperature target values of the sections and temperature values collected by all the three thermocouples, outputs ideal control amounts of the temperatures of the sections of the material bucket of the injection molding machine and a temperature control amount of the whole material bucket of the injection molding machine after a temperature controller, and obtains temperature control amounts of the sections by fusing the two, acquires real-time compensation control amounts of the temperatures of the sections, and realizes decoupling compensation control on the temperature of the material bucket of the injection molding machine by combining the temperature control amounts of the sections and the real-time compensation control amounts of the temperatures. Compared with the prior art, the application can improve the accuracy, rapidity, robustness and comprehensiveness of temperature regulation of the injection molding machine.

A lithium ion battery state of health prediction method and system based on quantum gate coupling. The cycle operation data of the lithium ion battery is acquired, the health characteristics are constructed, and the time series samples are constructed. A quantum enhanced gate recurrent neural network is constructed, a plurality of parameterized quantum circuits are configured in at least one gate module, and a quantum gate coupling mechanism is established between different gate modules. The quantum feature representation output by the plurality of parameterized quantum circuits is fused with the inter-gate coupling information, and the gate function value is calculated. The gate function value is used to update the recurrent state, and finally the SOH prediction value is output. The application enhances the single gate expression capability through the structured combination of multiple quantum circuits, realizes information interaction and collaborative calculation through inter-gate coupling, and improves the nonlinear modeling capability of the model for the battery degradation process and the cross-cell generalization capability.

The invention belongs to the field of page layout and generative adversarial networks, and discloses a transformer-based page layout generative adversarial network method and a related system, which can automatically generate page layout through training of a TGAN model and reduce the demand of manual intervention. In the traditional design, a designer needs to manually adjust the layout of each element, the TGAN network based on the Transform can automatically generate the layout conforming to the design specification according to the training data, the design efficiency is improved, the Transform model is good at capturing the long-term dependency relationship, the complex structure and the long-distance relationship can be processed, and the design efficiency is improved. This enables it to better understand the relationship between different elements, and to more accurately generate designs that meet logic and aesthetic requirements during automatic layout.

This application relates to the field of image recognition technology, and in particular to a method and system for detecting heat-sealing anomalies in industrial heat-sealing equipment. The method includes: acquiring the temperature matrix of the heat-sealing area of ​​the industrial heat-sealing equipment; extracting spatiotemporal feature information from the temperature matrix; training a dynamic temporal model based on the spatiotemporal feature information; using the dynamic temporal model to detect the real-time temperature matrix to determine whether abnormal pixels exist; if so, clustering and morphological processing are performed to determine whether heat-sealing anomalies exist. This application effectively overcomes the temperature baseline drift problem caused by factors such as equipment preheating, workshop airflow, and changes in ambient temperature, avoiding the high false alarm rate of traditional methods; and solves the problem of difficulty in collecting negative samples covering all defect types in industrial settings. While ensuring low resource consumption and high real-time performance, it significantly improves the accuracy, robustness, and generalization ability of detecting heat-sealing anomalies in industrial heat-sealing equipment.

The utility model relates to the technical field of curtain walls, and discloses a large-span hyperbolic steel grating which comprises a steel grating body, and a fixing device is arranged on the steel grating body. The fixing device comprises a first main structure, the first main structure is arranged at the top of the steel grating, a first special steel part is fixedly connected to the bottom of the first main structure, a first bracket is fixedly connected to the right side of the first special steel part, and the first bracket is prefabricated in the steel grating and hoisted to the designated position of the first main structure. A second bracket is prefabricated in the steel grating and hoisted to a specified second main structure position, a third bracket is prefabricated in the steel grating and hoisted to a specified third main structure position, and a supporting block at the bottom is fixedly connected into a fixing groove in the right side of a fixing pile. And the decorative component and the structural component are integrated, so that the exterior facade of the building is unique in shape and simple, and meanwhile, compared with other processes, the decorative component has obvious cost advantage.

The present application belongs to the cross field of biomedical signal processing and artificial intelligence, and particularly relates to a sleep staging system and method based on a double-flow parallel neural network. The system comprises a brain electrical device, a data acquisition and preprocessing module, a HypnoMamba-Dual neural network model and a downstream application module connected in sequence; the brain electrical device is a single-channel electroencephalogram signal acquisition device for acquiring original EEG signals; the data acquisition and preprocessing module is used for filtering and windowing the original EEG signals for standardized operation; the HypnoMamba-Dual neural network model is used for analyzing and calculating the preprocessed EEG signal sequence and outputting a sleep staging sequence. The double-flow architecture of the present application, especially the introduction of the "local reserved flow", provides a mechanism for the model to resist the "context smoothing effect". When the context flow tends to ignore the short N1 period, the strong instantaneous features provided by the local reserved flow can effectively correct the decision, thereby significantly improving the F1 score of the N1 period.