22results about How to "Reduce dimensionality" patented technology

This specification pertains to the field of refining and chemical production processing technology, and particularly relates to a method and apparatus for optimizing refining and chemical production plans for a target secondary processing unit. The method includes: obtaining parameters of the secondary processing unit under a refining and chemical production optimization scenario; constructing a nonlinear constraint equation for product output based on the parameters of the secondary processing unit; performing an equivalent transformation on the nonlinear constraint equation to obtain an equivalent transformation equation; extracting the nonlinear constraint terms and performing a Taylor expansion; transforming the Taylor expansion formula into a linear approximation equation based on the proportion of the feed material to the output material of the blending tank, the feed material quantity to the blending tank, and the feed property values ​​of the blending tank, according to the property balance constraints of the blending tank; and then substituting these into the nonlinear constraint equation for product output, thereby transforming the nonlinear constraint equation for product output into a linear approximation equation containing only material information variables. This method effectively ensures model convergence and shortens the solution time.

The application relates to the field of flight control technology, in particular to a hovering control method and device for a short take-off and vertical landing aircraft of a tilt-rotor type, wherein the method comprises the following steps: constructing a hovering nonlinear dynamics model of the short take-off and vertical landing aircraft containing a tilt-rotor power system; converting the hovering nonlinear dynamics model of the short take-off and vertical landing aircraft into a high-order full-drive system model to design a state tracking controller; designing an adaptive law based on a neural network to estimate nonlinear terms in the hovering nonlinear dynamics model of the short take-off and vertical landing aircraft; and feeding back the nonlinear terms to the state tracking controller to perform hovering mode stable control. Thus, the problems that the hovering control method based on dynamic inversion needs a large amount of linearization processing, the actuator dynamic characteristics are significantly different, the controller needs to verify the closed-loop performance through repeated simulation and experiment, and the multi-actuator decoupling efficiency of the aircraft is low and the robust control performance is poor are solved.

The application belongs to the technical field of simulation analysis, and particularly relates to a switch cabinet condensation margin evaluation method based on simulation analysis and order reduction reconstruction, steps of which comprise: establishing a simulation analysis model of the switch cabinet, adding a physical field and performing physical field coupling and mesh partitioning; solving the simulation analysis model to obtain the temperature and humidity distribution inside the switch cabinet; optimizing the simulation analysis model; replacing electromagnetic heat with loss data as a heat source input into a non-isothermal flow field; constructing a physical field snapshot library for order reduction model training; processing the physical field snapshot library based on a POD method to construct an order reduction model; training a Kriging model to reconstruct the temperature and humidity field of the switch cabinet; constructing a condensation margin evaluation cloud map; in the actual operation process of the switch cabinet, calculating an actual dynamic dew point temperature to generate an actual operation condensation margin cloud map, and completing online real-time evaluation. The application can realize efficient and accurate reconstruction of the temperature and humidity field inside the switch cabinet and efficient evaluation of the condensation margin of the switch cabinet.

This invention provides a hybrid-mode MRE vibration isolator and its design method. The hybrid-mode MRE vibration isolator is installed on the drive shaft of rotating equipment and includes an irregularly shaped stacked MRE. The irregularly shaped stacked MRE is frustum-shaped, and contains multiple layers of spacers and MRE material layers arranged in parallel at intervals. The spacers are made of ferromagnetic metal. By employing a frustum-shaped stacked MRE with different upper and lower diameters, this hybrid-mode MRE vibration isolator reduces the dimension of the controlled object compared to existing cylindrical MRE vibration isolators. This hybrid-mode MRE vibration isolator directly transfers abnormal vibration energy from large rotating equipment to the MRE material through the drive shaft. The change in MRE stiffness can suppress abnormal vibrations. This vibration isolator is suitable for intelligent vibration reduction of large rotating equipment, especially in rotating shear applications.

The application provides a robot and a control method, device and readable storage medium thereof. The control method comprises: acquiring a point cloud image containing a grasped object; inputting the point cloud image into a preset grasping network to enable the preset grasping network to perform classification prediction according to the point cloud image to obtain a contact point between a fingertip and the grasped object; constructing a first rotation matrix of a coordinate system with the contact point as an origin relative to a world coordinate system according to coordinate information of the contact point; determining coordinate information of a joint according to the coordinate information of the contact point, a vector between the joint and the fingertip and the first rotation matrix; determining a transfer matrix of a coordinate system with the joint as an origin relative to the world coordinate system according to the coordinate information of the joint; and controlling the robot to work in a grasping posture corresponding to the transfer matrix.

The application discloses a network security management and control method and system based on different scenes, and the method comprises the following steps: when the number of elements in a to-be-responded queue is less than a preset number, performing SQL injection detection on each request parameter based on a first interception rule to obtain an SQL injection detection result; when the number of elements in the to-be-responded queue reaches the preset number, simultaneously performing SQL injection detection on each request parameter based on a second interception rule to obtain an SQL injection detection result; and based on the SQL injection detection result obtained based on the first interception rule or the second interception rule and the request parameter to be responded, performing a corresponding response operation. The application can provide corresponding SQL injection detection schemes for different scenes, and can accelerate the response speed of a large number of SQL access requests in a short time.

This invention relates to the field of drone scheduling technology, and particularly to a method and system for regional route collaborative scheduling of logistics drones. The method includes: constructing a drone monitoring platform; determining whether flight interference exists based on a preset minimum interference distance, acquiring flight information of drones involved in the interference, and sending it to the corresponding drones; calculating yaw information for each drone based on the flight information and a built-in force field simulation obstacle avoidance model, and controlling the drones to fly based on the yaw information; when the distance between drones is greater than the minimum interference distance, outputting return-to-home information based on the force field simulation obstacle avoidance model, and controlling the drones to return to their flight paths. This invention provides a regional route collaborative scheduling method for logistics drones that treats each drone as an intelligent agent autonomously moving in a three-dimensional force field, decoupling complex global path planning from real-time obstacle avoidance, and greatly reducing the dimensionality and complexity of distributed computing.

The invention discloses a micro-grid large signal stability analysis method for controlling a heterogeneous inverter, and relates to the technical field of stability analysis. Comprising the following steps: constructing a plurality of GFM inverter equivalent oscillator models and a plurality of GFL inverter equivalent oscillator models of the series-parallel island microgrid; all the equivalent vibrator models are simultaneously established, and an island series-parallel micro-grid network vibrator model is obtained; respectively determining a first stability domain between each GFM inverter and a paired GFM inverter connected with the GFM inverter, and a second stability domain between each GFM inverter and a paired GFL inverter connected with the GFM inverter; and traversing and crossing the first stability domain and the second stability domain of each GFM inverter to obtain the overall frequency stability domain of the system, and determining the large signal stability according to the overall frequency stability domain of the system. According to the method, the dimensionality and complexity of the stability criterion are reduced, and the criterion of the large signal stability of the micro-grid is easier to analyze and calculate.

The application discloses a PON uplink frame reorganization method: based on service data frame authorization use and release reorganization serial number, dynamic mapping with PON uplink T-CONT, converting reorganization information table based on T-CONT binding into reorganization information table based on service data frame, and reducing reorganization information table and data cache. The application reduces reorganization information table dimension through dynamic mapping, reduces chip data cache resources; converts Combo PON parallel reorganization of wavelength division multiplexing into serial reorganization of time slot access, time division multiplexes circuits, and reduces chip area; through authorized use of reorganization information table, dynamic mapping, converting information table based on T-CONT into authorization and release based on data frame, and reducing logical circuit implementation difficulty; combining frame serial number management with DBA of the PON system, and strengthening robustness; through a more flexible reorganization strategy, different size slices of each channel input can form blocks of any size or complete service frames. The application also provides a corresponding PON uplink frame reorganization device.

This invention belongs to the interdisciplinary field of biomedical engineering and artificial intelligence-assisted diagnosis. It discloses a training method for a SERS spectral classification prediction model and its application. The disclosed SERS spectral classification prediction model training method combines CatBoost feature selection and deep learning. First, surface-enhanced Raman spectroscopy (SERS) data of serum from different categories of subjects is collected. After baseline removal, filtering, and normalization preprocessing, CatBoost gradient boosting algorithm is used to evaluate feature importance, considering the high-dimensional redundancy of the spectral data, and to select a subset of discrete feature bands containing key biomarker information. This feature subset is then input into a one-dimensional convolutional neural network model for training. The model constructed by this invention possesses deep feature mining capabilities, and the biological interpretability of the decisions is verified through SHAP analysis. It effectively solves the problems of large spectral noise interference and difficulty in extracting weak pathological features in traditional methods. For example, it can be used for the auxiliary diagnosis of coronary heart disease, achieving non-invasive, rapid, and high-precision classification and diagnosis of coronary heart disease and its subtypes.

This application provides a health management method and system for energy storage power stations based on a multi-level evaluation system, relating to the field of power and energy technology. The method includes: extracting features from raw monitoring data to obtain feature data; calculating health scores for multiple preset cell health indicators and a total health score based on cell feature data; calculating health scores for multiple preset battery cluster health indicators and a total health score based on battery cluster feature data and the health scores of each individual cell; calculating health scores for multiple preset battery stack health indicators and a total health score based on battery pile feature data and the health scores of each battery cluster; calculating health scores for multiple preset power station health indicators and a total health score based on power station feature data and the health scores of each battery stack; and issuing an alarm when the health score at any level and / or the total health score falls below a threshold. This application enables comprehensive health monitoring of energy storage power stations.

This invention provides an automatic SEM image classification method and electronic device based on an improved ConvNeXt network model. The method involves acquiring a target image using a scanning electron microscope (SEM); the target image is a microscopic electron microscope image; the target image is input into an improved ConvNeXt network model to obtain the probability of the target image belonging to each image category; the ConvNeXt network model includes a channel attention mechanism (ECA) module and a global attention mechanism (GAM) module; the image category corresponding to the highest probability is determined as the target image category. Compared to existing technologies, by introducing the channel attention module (ECA) and the global attention mechanism (GAM), the interaction information between different channels can be effectively captured during training, and the network pays more attention to important information and suppresses interference from irrelevant information during learning, thus improving the image classification ability.

The invention belongs to the technical field of high-frequency transformer simulation, and discloses a high-frequency transformer electric field, magnetic field, temperature field and force field analysis method and simulation device. Comprising the steps of obtaining a high-frequency transformer electromagnetic structure and establishing a three-dimensional high-frequency transformer prototype model; segmenting the three-dimensional high-frequency transformer prototype model into basic units and determining information of each basic unit; performing calculation based on the basic unit information to obtain static field and magnetic field finite element calculation results of the high-frequency transformer; calculating to obtain a temperature-fluid field and force field finite element calculation result of the high-frequency transformer; and setting boundary conditions of a temperature field and a force field based on finite element calculation results of the temperature-fluid field and the force field of the high-frequency transformer, and carrying out iterative solution on the electromagnetic-thermal-fluid-force field by using a solver to obtain distribution of an electric field, a magnetic field, the temperature field and the force field of the whole high-frequency transformer. Reference is provided for calculation of the electric field, the magnetic field, the temperature field and the force field of the high-frequency transformer.

The present application relates to the technical field of printed matter detection, and relates to a printed matter online detection method and system based on machine vision, which comprises the following steps: acquiring a printed matter image library, classifying features of the printed matter image library to obtain a plurality of feature image libraries, training a pre-constructed discrimination model by using a training matrix set, a defect matrix set, a positive verification matrix set and a negative verification matrix set to obtain a defect discrimination model, constructing a generative adversarial network based on the pre-constructed VAE encoder and the defect discrimination model, discriminating a to-be-detected feature matrix based on a weight coefficient group and a plurality of completed adversarial networks to obtain a printing defect index, and confirming a plurality of printing defect images based on a plurality of printing defect indexes and a plurality of to-be-detected images to complete online detection of the printed matter. The present application can improve the accuracy and robustness of printed matter defect detection and improve the printed matter detection efficiency.

The application discloses a kind of based on context multi-arm tiger machine's self-adapting text classification model selection method and system, to solve the problem of inaccurate model selection caused by different classification models in online text classification system Different adaptability difference of different text samples.The application maps multiple text classification models as different machine arms in multi-arm tiger machine, and extracts context features from the text samples to be classified, to depict the statistical distribution characteristics, sparsity features, position distribution features and sentiment features of text.Through dimension division on context features, construct low-dimensional and structured context representation, and evaluate the expected performance of each classification model based on context multi-arm tiger machine mechanism, adaptively select the classification model suitable for the current text sample.Experiments show that the application can effectively reduce the cumulative error rate and average decision regret in the text classification process, improve the overall performance of online text classification system, and has good engineering application value.

This invention belongs to the field of reactive power generator simulation technology, specifically disclosing a decoupled parallel simulation method, system, terminal, and medium for reactive power generators. The method first uses a preset decoupling strategy to segment the original electrical system model into a network, generating multiple independent sub-module decoupled models and a system-level bridge arm equivalent circuit model; then, it performs task partitioning based on a CPU-GPU heterogeneous computing architecture; finally, it aggregates the solution results from both ends to advance the simulation step size. This invention effectively breaks through the computing power bottleneck of traditional pure CPU serial computing while ensuring high-precision electromagnetic transient simulation, significantly improving the simulation efficiency and numerical stability for large-scale cascaded reactive power generators.

The application relates to the technical field of unmanned aerial vehicle flight base stations, and particularly discloses a three-dimensional deployment and power distribution joint optimization method for dispatching unmanned aerial vehicles as flight base stations to serve ground user clusters. The influence of line-of-sight transmission and non-line-of-sight transmission on the air-ground channel from the unmanned aerial vehicle to each user is considered, and a maximum system throughput model for jointly optimizing the three-dimensional position of the unmanned aerial vehicle and power distribution is established. The model is solved in a continuous state and action space by using a deep reinforcement learning method, namely a deep deterministic policy gradient, and the action space is reduced in dimension by combining a water injection algorithm, so that the unmanned aerial vehicle successfully learns an optimal three-dimensional deployment position and power distribution strategy to provide maximum throughput for the served users, and the energy efficiency of the unmanned aerial vehicle is improved under the condition that the energy of the unmanned aerial vehicle is limited.

This invention provides a control method for a UAV sling system based on input shaping and differential flatness, belonging to the field of UAV control. The method includes the following steps: First, dynamic modeling of the UAV sling system is performed; then, differential flatness is determined for the UAV sling system based on its state variables and input variables, thereby determining the UAV's reference trajectory according to the desired sling load trajectory and the UAV's yaw angle; further, zero-vibration and differential input shaping are used to process the input signals of the control system, and the UAV trajectory is controlled by the processed input signals, thereby achieving rapid balancing and attenuation of the sling load oscillations. This invention can reduce high-frequency, high-speed load oscillations caused by strong coupling between the UAV and the suspended load, improving the overall motion performance of the system.

This invention discloses an image processing system and method for processing images. The invention processes images by segmenting human portrait regions. It uses a hierarchical hybrid loss module to mask the portrait regions to generate masked portrait regions. The invention also uses data learning to mask the portrait regions.

The application provides a kind of power grid environmental protection monitoring ability evaluation method and device, belongs to environmental protection monitoring technical field.The method includes: obtaining the score data that multiple experts score the importance degree and overall importance degree of each environmental protection monitoring ability evaluation index, according to the score data, establish initial matrix;The covariance matrix of initial matrix is calculated, and according to each eigenvalue of covariance matrix, the corresponding eigenvector is selected to establish feature matrix;According to the feature matrix, the dimensionality of initial matrix is reduced to obtain the final matrix;According to the final matrix, the weight of each environmental protection monitoring ability evaluation index is calculated using the preset linear regression algorithm;Based on the weight and the historical data corresponding to each environmental protection monitoring ability evaluation index in the power grid project to be evaluated, the environmental protection monitoring ability evaluation result of the power grid project to be evaluated is determined.The environmental protection monitoring ability of power grid enterprise or project can be objectively and accurately evaluated.

This invention discloses a method, apparatus, and storage medium for event content verification based on a large model, belonging to the field of data processing technology. The method includes: identifying events in target text using a large model, rewriting the events in the target text according to target rewriting rules to obtain reference events; the target text is standard data that has been reviewed; storing the reference events in an event knowledge base; retrieving target reference events associated with the event to be verified from the event knowledge base based on the event to be verified; and comparing the event to be verified and the target reference events using the large model to obtain a comparison result characterizing whether the event to be verified is correct. This application utilizes the powerful semantic understanding capability of the large model to accurately identify events in standard data and rewrite the events to form structurally unified and semantically clear reference events, thereby constructing a high-quality event knowledge base and improving the accuracy of event content verification.

The application provides a kind of track traffic data light weight acquisition method based on depth clustering, in view of the problems that the existing track traffic video image data light weight method has high computational complexity, cannot intelligently identify and screen high value data, the application realizes the low-dimensional feature extraction of high-dimensional video image data, local structure capture and intelligent clustering through the cooperative work of data preprocessing, convolution auto-encoder, UMAP manifold learning and GMM clustering.The application discards the additional training process of the traditional clustering network, significantly reduces the computational complexity, reduces the network load and improves the transmission efficiency, accurately identifies and screens the data structure, meaning and value, provides technical support for the edge deployment, real-time response and resource saving of track traffic intelligent operation, and is suitable for video image data light weight processing in multiple scenes such as maintenance, work detection, station and platform.