Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

319results about How to "Quick update" patented technology

Method and system for performing paragraph matching knowledge questioning and answering on air traffic control industry based on large model

The invention discloses a paragraph matching knowledge question-answering method and system for an air traffic control industry based on a large model, belongs to the technical field of natural language processing, and aims to solve the technical problem of how to realize efficient and accurate information retrieval for a scene of big data question-answering in work in the current air traffic control industry. According to the technical scheme, the method comprises the following steps of: initializing a knowledge base and optimizing a structure; according to the enhanced BGE retrieval mechanism, in the retrieval process, based on basic keyword matching, an advanced semantic retrieval technology BGE model is adopted; the BGE model and the Baichuan model are matched, so that the retrieval accuracy is improved, and the flow field experience is provided for a user; real-time feedback and interactive optimization are carried out; continuous learning and knowledge base iteration are carried out; and through a multi-level indexing and caching strategy, a retrieval result is optimized.
Owner:SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD

Multi-task processing method and system for large language model fused with LoRA

The embodiment of the invention relates to the technical field of large language modules, and discloses a multi-task processing method of a large language model fused with LoRA, which comprises the following steps: receiving task processing information input by a user, and performing feature extraction on the task processing information to determine each scene task feature; performing data matching with a pre-LoRA module parameter set based on the scene task features to obtain a LoRA module parameter set associated with the scene task parameters, and performing parameter updating operation on the large language model according to the LoRA module parameter set; and inputting the scene task features into the large language model subjected to the parameter updating operation for identification to obtain corresponding identification result information, and outputting the corresponding identification result information. According to the scheme of the invention, by fusing the LoRA module and the routing mechanism, the adaptive selection and optimization capability for specific tasks is realized, and the performance of the model in processing diversified tasks is improved.
Owner:GUANGDONG WIND POWER CO LTD

Signal processing method of computer system

The invention relates to multi-mode signal processing, and provides a signal processing method of a computer system. The method comprises the following steps: acquiring different modal signal data by using a plurality of sensors and performing timestamp synchronization; a depth time sequence alignment network and a multi-layer dynamic time warping algorithm are utilized to ensure signal time consistency; multi-modal signal features are extracted and fused through a multi-stream depth feature extraction network and a cross-modal attention mechanism; the system adopts a dynamic convolution kernel generation and meta-learning technology to carry out adaptive signal processing; noise suppression and signal optimization are carried out by using a multi-mode noise reduction auto-encoder and a generative adversarial network, and parameters are optimized and processed through closed-loop feedback control and reinforcement learning strategies. According to the method, synchronization, fusion, adaptive processing, noise suppression and real-time feedback control of multi-mode signals are realized, and the method has the advantages of high precision, high robustness and real-time performance.
Owner:LUOYANG INST OF SCI & TECH

Transform-based natural language processing system

The invention relates to the technical field of natural language processing, and discloses a natural language processing system based on Transform, comprising: a neural architecture search assembly for automatically searching and optimizing a Transform model architecture for natural language processing; the multi-task learning component is used for simultaneously training a plurality of natural language processing tasks on the basis of the shared model layer; the meta-learning component is used for optimizing parameter initialization of the model, so that the model can quickly adapt to a new task through a small amount of data and training steps; and the dynamic data enhancement component is used for generating diversified training data and enhancing the generalization ability and robustness of the model. According to the method, knowledge sharing and resource efficiency are enhanced through the multi-task learning and meta-learning component, dependence on a large amount of data is reduced, the generalization ability and rapid adaptability of the model are improved, the adaptability to a new scene is enhanced through the dynamic data enhancement component, and the robustness of the model is improved.
Owner:NANJING UNIV

Bridge deflection intelligent accurate measurement method based on artificial intelligence

The invention discloses a bridge deflection intelligent accurate measurement method based on artificial intelligence, and relates to the technical field of bridge deflection measurement, and the method combines a Retinex algorithm with an HDR imaging technology, carries out the adaptive illumination correction and enhancement of images collected under different exposure conditions, and improves the accuracy of bridge deflection measurement. The image brightness and contrast under various illumination conditions are effectively adjusted, edge detection and color correction technologies are combined, the influence of uneven illumination on measurement is remarkably weakened, the adaptive background modeling and the Gaussian mixture model MOG2 are adopted, real-time subtraction of the dynamic background is achieved, the background model can be rapidly updated, and the real-time measurement accuracy is improved. According to the method, bridge deflection features are separated, deflection features are extracted based on a deep learning foreground segmentation network U-Net, dynamic background noise is filtered out, it is guaranteed that a measurement result is stable and reliable, space-time modeling of ST-GCN in combination with LSTM is carried out, space and time features are jointly modeled, a three-dimensional deflection field is constructed, and the capturing capacity of dynamic behaviors of a bridge structure is enhanced.
Owner:SICHUAN ROAD & BRIDGE CONSTRUCTION GROUP CO LTD

Customer service data aggregation method based on ODPS and server

The invention discloses an ODPS-based customer service data aggregation method and server, and relates to the field of electric digital data processing, and the method comprises the steps: carrying out the field classification of collected source data, and obtaining a plurality of source data sets; loading the source data sets to an ODPS platform, and performing first aggregation processing on the source data in the plurality of source data sets by using the ODPS platform to obtain a plurality of field wide tables; pulling the field wide table to a DRDS platform, and performing distributed data processing on the field wide table by using the DRDS platform to obtain a plurality of pieces of distributed data; determining a target data feature corresponding to a target report in a report request instruction according to the report request instruction sent by the user terminal; and extracting multiple pieces of target data corresponding to the target data features in the multiple pieces of distributed data, and performing second aggregation processing on the target data to generate a target report. By implementing the method, the data processing efficiency can be improved when the multi-azimuth data display of the customer service staff is carried out.
Owner:SHANGHAI SHENXUE SUPPLY CHAIN MANAGEMENT CO LTD

Cloud platform rapid deployment system and method

The invention discloses a cloud platform rapid deployment system and method. The system comprises a Docker, a container arrangement tool, a database service, a cloud platform application, a monitoring and management tool, a network infrastructure and a security component. The Docker is responsible for managing the complete life cycle of the container and providing a virtualization environment; the container arrangement tool is used for managing and arranging a Docker container; the database service is used for storing information in the cloud platform and carrying out communication through the network service of the Docker; the cloud platform application is a set of service logic and functions deployed in a Docker container; the monitoring and management tool is used for monitoring a running state and managing log information; the network infrastructure is used for ensuring network interconnection between the servers and supporting network communication of the Docker container; and the security component is used for protecting the cloud platform from external attacks and internal threats. According to the method, the deployment process can be simplified, the deployment time is shortened, manual intervention is reduced, the deployment efficiency is improved, resources are optimized, and the operation cost is reduced.
Owner:TONGLING VOCATIONAL & TECH COLLEGE

Position prediction method and device based on UWB digital key

The invention provides a position prediction method and device based on an ultra wide band (UWB) digital key, and a position prediction system applied to the UWB digital key, the position prediction system comprises a UWB tag and a plurality of UWB anchor points arranged on a vehicle, and the position prediction method comprises the following steps: determining whether UWB positioning information of the UWB tag is invalid; when the UWB positioning information is invalid, acquiring a velocity vector and a historical track set of the UWB tag and orientation information of the vehicle; and inputting the velocity vector, the historical trajectory set and the orientation information into a position prediction calculation model to calculate a predicted position of the UWB tag. The technical problem that when an existing automobile digital key is blocked by an obstacle and the digital key cannot be connected to an automobile UWB anchor point, the function of the digital key is in a failure or invalid state, and the user experience is affected is solved.
Owner:NINGBO JOYNEXT TECH CO LTD

Topographic data updating method and device and electronic equipment

The invention discloses a topographic data updating method, a topographic data updating device and electronic equipment. The method comprises the following steps: receiving initial topographic data of an operation scene of the transportation equipment and map boundary data of an operation area of the transportation equipment in the operation scene; based on the initial topographic data and the map boundary data, determining a work attention area; in response to running of the transportation equipment in the operation area, scanning the operation attention area through a sensing system of the transportation equipment to obtain current topographic data of the operation attention area; based on the current topographic data and the initial topographic data, determining a topographic change region in the work attention region; and controlling the transportation equipment to carry out topographic data acquisition on the region with the topographic change, and updating the initial topographic data of the work attention region and the map boundary data of the work region based on the acquired topographic data. According to the invention, the technical problem of poor freshness and precision of map updating of the mine operation scene is solved.
Owner:EACON TECHNOLOGY CO LTD

Industrial process monitoring model intelligent recommendation method and system

The invention discloses an intelligent recommendation method and system for an industrial process monitoring model, and the method comprises the steps: firstly, solving a problem that industrial time series data lacks visual features; extracting data set features of each case from four aspects of general statistical features, distribution shape features, task related features and exogenous knowledge embedding by adopting a data set feature engineering method; secondly, designing a mapping relation learning strategy based on width learning, mapping the data set feature of each case with the corresponding model score vector, and thus endowing the width learning network with the capability of predicting the model performance; and finally, providing a triple increment strategy for driving multiple increment demands of an industrial scene, and designing an updating strategy of a wide learning network for monitoring case increment, candidate model increment and recommendation node increment respectively, thereby continuously expanding and enhancing the recommendation capability of the method. According to the method, the detection model with the optimal performance can be recommended for the industrial process.
Owner:ZHEJIANG UNIV +2

Power system planning method based on multivariable dynamic analysis

The invention relates to the technical field of power system analysis, in particular to a power system planning method based on multivariable dynamic analysis, and the method comprises the steps: obtaining the related data of a power system, and constructing a DC optimal power flow model with the minimum power generation cost; converting the DC optimal power flow model based on multi-parameter planning; considering the influence of the dynamic change parameters on the power system and constructing a critical region; and solving a planning result according to the critical region and the mapping relation between the dynamic change parameters and the power system planning result. The objective of the invention is to solve the limitation caused by the change of technical and economic parameters during the planning and deductive analysis of a power system, achieve the deductive analysis of continuously changing technical and economic parameters, and improve the reliability of a planning result.
Owner:RES INST OF ECONOMICS & TECH STATE GRID SHANDONG ELECTRIC POWER

Intelligent human-shaped accompanying robot and voice interaction system thereof

The invention relates to the technical field of intelligent robots, in particular to an intelligent human-shaped accompanying robot and a voice interaction system thereof, and the system comprises a voice input collection and preprocessing module which collects a composite voice signal and a voice triggering instruction in a surrounding environment in real time through a distributed microphone array; the multi-sound-source voice separation module is used for combining and independently processing the potential sound source signals and separating the potential sound source signals into a plurality of independent sound source signals; the target user sound source identification and extraction module is used for predicting the change of a target sound source in continuous time frames by utilizing a dynamic Bayesian network and extracting a target user sound source signal; the semantic analysis and output module is used for generating a natural and smooth voice response through a voice synthesis technology; according to the method, the problem that the target user sound source is difficult to extract in a noisy environment, multi-sound-source overlapping and voice switching scenes is solved, and the robustness and the adaptive capacity of the system in a complex voice environment are greatly improved.
Owner:BEIJING HAIBAICHUAN TECH CO LTD

Method and device for generating obstacle avoidance route of unmanned aerial vehicle and electronic equipment

The invention relates to a method and a device for generating an obstacle avoidance route of an unmanned aerial vehicle, and electronic equipment, relates to the field of unmanned aerial vehicles, and solves the technical problem of how to quickly, effectively and automatically plan a new route to meet the obstacle avoidance requirement. The method for generating the obstacle avoidance route of the unmanned aerial vehicle comprises the following steps: step S10, acquiring position information of two end points of a leg passing through a no-fly zone in a planned route of the unmanned aerial vehicle; step S20, judging whether two end points of the leg passing through the no-fly zone are outside the no-fly zone, and if so, entering step S30; otherwise, determining a plurality of interconnected flight segments with two end points outside the no-fly zone from the planned route of the unmanned aerial vehicle, and entering step S30; s30, setting two end points outside the no-fly zone as a starting point and an ending point, and determining a passable area and a non-passable area according to the starting point, the ending point and the position information of each vertex of the no-fly zone; and S40, based on the passable area and the non-passable area, generating an obstacle avoidance route from the starting point to the terminal point by using a path planning algorithm.
Owner:CHENGDU UNITED AIRCRAFT TECHNOLOGY CO LTD

Knowledge graph ontology constrained vegetation remote sensing classification method

The invention discloses a knowledge graph ontology constrained vegetation remote sensing classification method. The method comprises the steps of data acquisition and data preprocessing, deep learning model selection and fusion of a knowledge graph ontology and a deep learning model. According to the method, the knowledge graph ontology and the FCN8s-ResNet 50 model are fused in the two stages of model training and classification post-processing. The result shows that 1) the classification accuracy of the deep learning model can be remarkably improved by fusing the mountain vegetation knowledge graph ontology in the two stages of deep learning model training and classification post-processing: the accuracy of the deep learning model constrained by the knowledge graph ontology is improved by 10%, and the overall classification accuracy of vegetation types reaches 89.2%; and 2) the deep learning model constrained by the mountain vegetation mapping knowledge domain ontology not only obtains excellent results in fine classification of vegetation types, but also improves the universality and interpretability of the model, so that powerful support is provided for wide-range remote sensing vegetation classification and application of the deep learning model.
Owner:INST OF GEOGRAPHICAL SCI & NATURAL RESOURCE RES CAS

Railway yard equipment BIM dynamic modeling method, medium and equipment

The invention relates to the technical field of railway informatization, and discloses a BIM (Building Information Modeling) dynamic modeling method for railway station equipment, a medium and equipment, and the method comprises the following steps: constructing a semantic information model of the station equipment; performing BIM modeling based on the station equipment semantic information model to obtain a station equipment BIM dynamic model; and automatically updating the station equipment BIM dynamic model based on the minimum influence domain. According to the method, the station equipment is subjected to classified representation, the incidence relation between the equipment is summarized and accurately described on the basis of a tree structure and hypergraph semantics, finally, the semantic information model of the station equipment is constructed, and the BIM dynamic model of the station equipment is automatically constructed on the basis of the semantic information model. The algorithm is updated through a model based on a minimum influence domain; after automatic BIM modeling is completed, the minimum influence range can be automatically solved for change operation, and equipment in the range is deleted and reconstructed; dynamic modeling and automatic updating are realized, and the design efficiency of designers is greatly improved.
Owner:CENT SOUTH UNIV

Intelligent medicine cabinet and method for conducting medicine management and control through intelligent cabinet

The invention provides an intelligent medicine cabinet which comprises a cabinet body and a control device, the cabinet body comprises a control bin and a storage box body, the interior of the storage box body is divided into a plurality of drawer storage spaces through multiple layers of partition plates, and a drawer is arranged in each drawer storage space; fRID tag readers are arranged at the positions, corresponding to the drawers, of the middles of the isolation plates, and the FRID tag readers are connected with the control device. A plurality of box containing cavities are formed in inner cavities of one or more drawers except the drawers in the drawer containing space on the bottom layer, first storage boxes are placed in the box containing cavities, and weighing sensors corresponding to the first storage boxes are installed at the bottoms of the inner cavities of the box containing cavities. Structural modules are reasonably and perfectly arranged, links such as medicine storage and use can be strictly monitored, and medicine loss and abuse are effectively prevented.
Owner:DONGGUAN PENGCHI INTELLIGENT EQUIP TECH CO LTD

Enterprise equity atlas construction method based on multi-dimensional data verification and storage medium

The invention discloses an enterprise stock equity atlas construction method based on multi-dimensional data verification and a storage medium, and relates to the technical field of knowledge atlas.The enterprise stock equity atlas construction method comprises the steps that a text is extracted from obtained document data, layout analysis and table structure reconstruction are conducted on the extracted text, and the text obtained after format conversion is input into a large language model; extracting the enterprise entity information and stock equity relationship in the text; constructing a preliminary equity atlas; detecting a loop in the preliminary equity atlas, performing benefit community identification on the equity atlas after contradiction resolution, and outputting a healthy equity atlas; enterprise entity information is extracted in real time, credibility verification is carried out, and the information is stored in a database. A set of complete automation technology chain is formed from data acquisition and OCR table reconstruction to LLM extraction, map construction, contradiction resolution, benefit community recognition and health map comparison, and the manual operation cost is greatly reduced.
Owner:CHINA DAAS TECH CO LTD

Firmware online upgrading method and system

The invention provides a firmware online upgrading method and system, and relates to the technical field of firmware online upgrading, the method is applied to a processor, the processor comprises an external memory, the external memory comprises a backup area and an upgrading area, and the method comprises the steps that when the processor is started, whether a program backup of an application program is set in the backup area or not is determined through a BootLoader program; if the program backup is set in the backup area, skipping to enter the application program through the upgrading area; when a firmware upgrading request is received, an upgrading file is stored in an upgrading area of the external memory; the application program is upgraded according to the upgrading file of the upgrading area, so that online updating of firmware is completed; and if upgrading fails, copying the program backup in the backup area to the processor, and restarting the processor. By simplifying the function of the BootLoader and optimizing the data interaction process, the upgrading speed and success rate of the application program are improved, and the stability and maintenance convenience of the system are enhanced.
Owner:HARBIN SIZHERUI INTELLIGENT MEDICAL EQUIP CO LTD

Automatic classification system in garbage truck transportation based on networking

The invention discloses an automatic classification system in garbage truck transportation based on networking. The automatic classification system comprises a truck head cabin, a garbage cabin, transportation data and a control module, according to the system, in the driving process of the garbage truck, the intelligent mechanical arm is used for classification according to sensor data, and the garbage classification efficiency and accuracy are improved through multi-sensor redundancy; the system integrates cloud data and a control module, realizes connection between the garbage truck and a cloud server, can collect and upload operation data, classification data and position data of the garbage truck in real time, optimizes a driving route and an operation strategy of the garbage truck, improves efficiency and reduces energy consumption; according to the garbage truck, compartment separation type design is achieved, the functions of garbage classification, compression, storage and the like are modularized, and all the modules can be independently operated, maintained and upgraded; according to the system, garbage classification and resource recycling can be promoted, the transportation cost and energy consumption are reduced, the working conditions of sanitation workers are improved, and the overall efficiency and environmental friendliness of garbage treatment are improved.
Owner:ZHUZHOU JIACHENG TECH DEV CO LTD

Framework model based on neural network learning and application method thereof

The invention relates to the technical field of medical science, in particular to a framework model based on neural network learning and an application method of the framework model. According to the model, a graph convolutional network (GCN, Transform architecture and long short-term memory network (LSTM) are fused, a multi-level analysis process is constructed, the spatial structure and sequence dynamics of drug molecules are deeply explored, and the model comprises the following specific steps: model training: performing model training by adopting data sets collected by people such as Cui, Q.Cui2020Improved and the like; the model test selects three independent test sets to comprehensively evaluate the performance of the model; according to the data preprocessing, an RDKit library is used, SMILES character strings are converted into molecular objects, a feature tensor is constructed and used for storing core features of each molecule in detail, data splitting is carried out, and the data splitting adopts versions, such as Ahmad, divided by people based on a Cui2020 data set to carry out training and testing of a machine learning model.
Owner:王晨旭

A single-frequency GNSS unmanned aerial vehicle positioning method, device, medium and product

ActiveCN119045025BHigh precisionSolve the positioning accuracySatellite radio beaconingTroposphereCarrier signal
The present application discloses a single-frequency GNSS unmanned aerial vehicle positioning method, device, medium and product, which relates to the field of unmanned aerial vehicle positioning. At any current moment: the distance and ionospheric delay of each satellite are determined based on the position coordinates of each satellite and the position coordinates of the unmanned aerial vehicle at the previous moment; the tropospheric delay at the current moment is determined based on environmental parameters; three satellites are determined as first target satellites, and two satellites are determined as second target satellites; pseudo-range observation values ​​are calculated based on the distance, corrected clock error data, ionospheric delay and tropospheric delay of each first target satellite; phase observation values ​​are calculated based on the distance, corrected clock error data, ionospheric delay, carrier phase integer ambiguity and tropospheric delay of each second target satellite; the position coordinates of the unmanned aerial vehicle are determined based on the pseudo-range observation values ​​and position coordinates of each first target satellite, and the phase observation values ​​and position coordinates of each second target satellite. The present application improves the accuracy of unmanned aerial vehicle positioning and reduces costs.
Owner:KUNMING UNIV OF SCI & TECH

Method for providing container service, container system and related device

PendingCN119557042ACreate efficientlyReduce storage space usageSoftware simulation/interpretation/emulationSoftware deploymentComputer hardwareEngineering
The invention discloses a method for providing container service, a container system and a related device, and belongs to the technical field of containers. The method comprises the steps that a container system provides a basic mirror image and a public mirror image for a user, the basic mirror image is used for creating a container, the public mirror image is mounted, the public mirror image does not need to be downloaded, and occupied storage space of a node where the container is located is reduced. And moreover, the public mirror image independently exists, so that the public mirror image is convenient to manage and quickly update and upgrade. The public mirror image is mounted, so that the container created for the user can be quickly updated by quickly updating the public mirror image. And a public mirror image does not need to be downloaded, and container creation is more efficient through a mounting mode.
Owner:HUAWEI CLOUD COMPUTING TECHNOLOGIES CO LTD

Application full-life-cycle management method, system and device based on application center and medium

The invention relates to an application full-life-cycle management method, system and device based on an application center and a medium, and the method comprises the steps: receiving and processing an input software registration request, and calling a registration interface of a software platform to carry out application registration; executing non-containerized or containerized deployment operation on the edge side based on an input application deployment instruction containing a deployment mode and a specified application in combination with a mirror image pre-stored in a mirror image warehouse; in response to an input application upgrading instruction, stopping using the current application, executing upgrading operation on the edge side according to the selected deployment mode, and restarting the upgraded application after the application upgrading is completed; and in response to an input application uninstalling instruction, the current application is stopped, and an application uninstalling operation is executed on the edge side. By means of the method, full-life-cycle management, including registration, deployment, upgrading, destruction and other operations, of all the applications in the platform is achieved, and the efficiency and flexibility of application management are improved.
Owner:ZHEJIANG SUPCON INFORMATION TECH CO LTD

Distributed real-time library implementation method of power monitoring system and electronic equipment

The invention relates to a distributed real-time library implementation method of a power monitoring system and electronic equipment, the real-time library is based on a multi-master multi-slave architecture and comprises a plurality of master nodes and a plurality of slave nodes, and the master nodes and the slave nodes belong to the real-time library and map real power equipment; according to the hierarchical data structure defined by the real-time library, equipment in the power monitoring system is added into real-time library model information, the real-time library model information is updated, initialization of the real-time library is achieved, and measured equipment real-time data is synchronized to the real-time library. Compared with the prior art, the method has the advantages of realizing rapid data synchronization of the real-time library under the condition of high concurrent access, reducing data synchronization delay when the main node fails, accelerating data updating efficiency and the like.
Owner:ACREL CO LTD +2

Power marketing data query method and system of JointBERT model based on knowledge graph

The invention is suitable for the technical field of data query, and provides a power marketing data query method and system based on a JointBERT model of a knowledge graph, and the method comprises the steps: obtaining field background knowledge related to the power industry, and constructing the knowledge graph; a JointBERT model is constructed and trained, and the model comprises an input layer used for processing input text data; the coding layer is used for carrying out fusion coding on rich general semantic knowledge in a corpus and domain knowledge in the knowledge graph; the decoding layer is used for generating field and intention corresponding to the input text and slot labels corresponding to words; compressing and optimizing the model by adopting an early leaving mechanism and a knowledge distillation method to obtain a target model; and the power demand problem of the user, which is received in real time, is used as the input parameter and is input into the target model for data query and analysis, so that the enterprise information query efficiency of related workers is improved.
Owner:GUANGXI POWER GRID CORP

AI-driven comprehensive evaluation system for learning ability of primary and secondary school students

The invention discloses a primary and secondary school student learning ability comprehensive evaluation system based on AI driving, and the system comprises an information input module which is used for recording the basic information of students; the material management module interacts with the information input module and is used for centrally storing digital teaching resources and basic information of students; the evaluation module interacts with the information input module and the material management module and is used for learning progress and testing according to the digital teaching resources; the learning analysis module interacts with the evaluation module and provides error analysis and learning suggestions according to the student learning result evaluation result; and the man-machine interaction module is used for establishing interaction between a user and the comprehensive evaluation system. According to the method, the accuracy and individuation of evaluation are improved, learning weaknesses of students can be more accurately identified through automatic scoring and error analysis realized by the AI technology, and customized training questions are provided according to the weaknesses, so that the learning efficiency is improved.
Owner:NANJING HONGCHEN FENGYUN DIGITAL TECH CO LTD

Width learning-based water quality index BOD5 monitoring method for efficiently extracting data feature information

PendingCN119089182AImprove efficiencyMake up for the shortcomings in multiple featuresFeature extractionWater quality
The invention discloses a water quality index BOD5 monitoring method for efficiently extracting data feature information based on width learning. According to the method, under the inspiration of a loop network structure, recursive cascading is carried out on feature windows of a width learning system to extract time correlation features of process data. On this basis, a non-Gaussian feature extraction window is added, non-Gaussian features of sewage data are extracted by using an over-complete independent component analysis method, the ability of the model to extract different features of the data is enriched, and the accuracy of the model is improved. The method comprises an off-line training stage and an on-line monitoring stage. Besides, aiming at the condition that the model precision is insufficient in a severe environment and an operation condition in the sewage treatment process, the model provided by the invention can be reconstructed in an increment mode, the whole network does not need to be retrained from the beginning, and the network training can be completed in a very short time; therefore, the water quality index of the sewage can be rapidly monitored in time.
Owner:BEIJING UNIV OF TECH

Comprehensive energy system planning and scheduling method and device considering demand side response

The invention discloses an integrated energy system planning and scheduling method and device considering demand side response. The method comprises the following steps: establishing load models of price type demand response, excitation type demand response and alternative type demand response; establishing an initial planning scheduling model by taking the lowest annual operation cost and the lowest demand side response cost of the full-life-cycle integrated energy system as a first optimization target; solving the initial planning scheduling model in combination with operation constraint conditions and user satisfaction constraints to obtain load transfer quantity and reduction quantity after price-type demand response and excitation-type demand response, and a real-time pricing mechanism; carrying out alternative demand response based on a real-time pricing mechanism to obtain an optimized price curve and load substitution quantities of various energy sources; and solving the planning scheduling optimization model taking the lowest annual operation cost of the full-life-cycle integrated energy system as a second optimization target to obtain an optimal capacity configuration result and an operation scheduling plan of each energy device in the integrated energy system.
Owner:STATE GRID JIANGSU ELECTRIC POWER CO LTD CHANGZHOU BRANCH

Production control method, device and equipment for double-door ring

The invention discloses a double-door ring production control method, device and equipment, and the method comprises the steps: obtaining part information, and determining a first simulation double-door ring based on the part information; determining a target plating strategy for the first simulation double-door ring from a plurality of preset plating strategies, and obtaining a second simulation double-door ring based on the target plating strategy and the first simulation double-door ring; determining hot stamping process parameters based on the target coating strategy, and performing hot stamping simulation analysis on the second simulation double-door ring based on the hot stamping process parameters to obtain a third simulation double-door ring and a first simulation result; if the first simulation result meets a first preset requirement, carrying out collision simulation analysis on the third simulation double-door ring to obtain a second simulation result; and if the second simulation result meets the second preset requirement, actual production of the double-door ring is controlled based on the part information, the target coating strategy and the hot stamping process parameters. The technical problem that the production efficiency of the double-door ring is low is solved.
Owner:SHOUGANG GROUP CO LTD

Satellite ephemeris updating method and device and satellite-borne equipment

The embodiment of the invention provides a satellite ephemeris updating method and device and spaceborne equipment, and relates to the technical field of aerospace, and the method comprises the steps: obtaining the current position and current space environment parameters of a satellite; searching a grid adjacent to the current position from the plurality of grids, wherein the grid is associated with the position, the space environment parameter interval and the atmospheric density; predicting the atmospheric density of the orbit where the satellite is located by using the position, the space environment parameter interval and the atmospheric density associated with the adjacent grids, the current position and the current space environment parameters; and updating the ephemeris of the satellite by using the predicted atmospheric density. By applying the technical scheme provided by the embodiment of the invention, the prediction precision of the atmospheric density can be improved and the satellite ephemeris prediction precision can be improved under the condition that the computing power and storage of satellite-borne equipment are limited.
Owner:CHINA SATELLITE NETWORK INNOVATION CO LTD