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

1413results about How to "Rapid deployment" patented technology

Lightweight image classification neural network architecture system based on knowledge distillation

ActiveCN119514594ALow classification error rateHigh precisionNeural learning methodsData setEngineering
The invention belongs to the technical field of image classification neural networks, and discloses a lightweight image classification neural network architecture system based on knowledge distillation. The invention provides a lightweight image classification neural network architecture system based on knowledge distillation. The lightweight image classification neural network architecture system comprises a data set preprocessing module, a teacher model preprocessing module, a subnet model construction module, a personalized training module, a real loss calculation module, a distillation loss calculation module, a total loss calculation module and a student model construction module. The invention provides a lightweight neural network architecture system based on knowledge distillation, and designs a brand new training mode by using the superiority of knowledge distillation for teacher model weight extraction: the knowledge distillation of teacher and student models is combined with a deep compression method; the system for constructing the lightweight network can be used for training various complex image classification neural networks so as to improve the network performance.
Owner:NORTHWEST A & F UNIV

Short text clustering method and device based on large language model

The invention discloses a short text clustering method and device based on a large language model, and belongs to the technical field of natural language processing, and the method comprises the steps: converting a short text into vector representation, and carrying out the preliminary clustering of the vector representation through a clustering algorithm, and obtaining an initial category; for all the corresponding short texts in each initial category, generating an abstract by using a large language model, generating a plurality of theme titles for summarizing the core meanings of the texts according to the abstract, respectively taking the theme titles as sub-titles, inputting the plurality of sub-titles into the large language model, and carrying out theme combination to obtain a parent title, constructing the parent title and the child titles into a hierarchical theme system; the large language model allocates to-be-classified short texts to one or more categories according to the hierarchical topic system to complete short text clustering; and performing quality evaluation and error pattern analysis on a short text clustering result to optimize a clustering algorithm and a large language model. According to the method, the theme of the short text can be automatically found and classified, and the classification accuracy and efficiency are improved.
Owner:HANGZHOU COOPER MEDICAL TECH CO LTD

Ecological environment commanding and dispatching system and method based on audio and video fusion

The invention discloses an ecological environment commanding and dispatching system and method based on audio and video fusion, and relates to the technical field of ecological environment dispatching. The commanding and dispatching platform is in communication connection with a data acquisition module, a data preprocessing module, an event detection and identification module, a severity evaluation module, a commanding and dispatching module and a resource management module, and all the modules are in electric signal connection; the data acquisition module is used for collecting real-time audio and video data from various sensors and monitoring equipment which are deployed in advance. According to the invention, through real-time monitoring and automatic detection technologies, abnormal events are identified at the first time, and an early warning mechanism is started immediately, so that compared with traditional manual inspection, the time for finding the abnormal events can be shortened, in addition, the automation characteristic of the system reduces delay caused by human factors, and the system is more convenient to use. Therefore, resources and personnel can be quickly mobilized in emergency, and the influence of events can be effectively controlled and relieved.
Owner:YANGZHOU RICE INFORMATION TECH CO LTD

Dam safety monitoring agent system based on multi-dimensional large model and digital twinning

The invention discloses a dam safety monitoring agent system based on a multi-dimensional large model and digital twinning, and belongs to the technical field of safety monitoring of water conservancy and hydropower engineering. According to the method, a cognitive decision kernel is used as a core innovation module, multi-source data is collected by relying on a sky-ground hydraulic engineering integrated sensor network, cross-modal data fusion and anomaly recognition are achieved through a multi-dimensional large model cluster, and multi-physics coupling simulation is completed in combination with a digital twinborn body; the cognitive decision kernel generates an optimal combination scheme through case retrieval and measure unit adaptation degree calculation, a control instruction is output after digital twin rehearsal verification, and finally closed-loop control of dam safety real-time early warning, autonomous decision making and efficient disposal is achieved through an autonomous response mechanism. The problems of data island, passive response, expert dependence and the like of a traditional monitoring system are solved, the dam safety management intelligent level and the emergency response capability are remarkably improved, and the method has wide engineering application value.
Owner:CHANGJIANG SPATIAL INFORMATION TECH ENG CO LTD (WUHAN) +1

Serverless large model reasoning service system, method, equipment and medium

The embodiment of the invention relates to the field of large model facilities, and discloses a Serverless large model reasoning service system, method and equipment and a medium. Receiving an inference service creation request sent by a user, and forwarding the inference service creation request to a corresponding cluster; processing the north-south traffic of the cluster; converting the reasoning service creation request into an object, and configuring a running environment; according to the object, a Pod is created, the Pod is used for controlling a model service workload, the Pod comprises a user container, and the user container is constructed based on a basic mirror image comprising an operating system, a Supervisor and a Docker and is used for running a large model service; and the queue agent is responsible for processing routing, load balancing and request queuing of an incoming request based on a lightweight agent Sidecar. The technical problem that large model reasoning service deployment is difficult can be solved at least.
Owner:上海和今信息科技有限公司

Folding photovoltaic power generation container and photovoltaic energy storage container

The invention discloses a folding photovoltaic power generation container and a photovoltaic energy storage container, and relates to the technical field of photovoltaic energy storage. The single photovoltaic modules are connected to the top end of the box body in a sliding manner; the folding photovoltaic module comprises a plurality of photovoltaic modules, and the upper ends and the lower ends of the plurality of photovoltaic modules are hinged in sequence, so that the folding photovoltaic module can be unfolded and folded; and the lifting mechanism is arranged in the box body, and the folding photovoltaic module is arranged on the lifting mechanism. The photovoltaic energy storage container further comprises a container body and an energy storage battery, and the container body is installed on the top of the container body through corner fittings and twist locks. The folding photovoltaic power generation container is small in height, can be folded or unfolded, is convenient to transport after being folded, and is large in light receiving area after being unfolded; the single photovoltaic module can be used as a top cover of the box body and can also be used for photovoltaic power generation. The folding type photovoltaic power generation container and the photovoltaic energy storage container are designed in a split type structure, and flexibility and adaptability are high.
Owner:SHANGHAI ZHONGHYDROGEN NEW ENERGY TECH CO LTD

Method and system for realizing multi-node cloud hard disk performance test

The invention discloses a method and system for realizing a multi-node cloud hard disk performance test, and belongs to the technical field of data storage, and the system comprises at least one main management node which is responsible for configuring a test environment, distributing a test task, and collecting and analyzing a test result; the plurality of work execution nodes are distributed on virtual machines associated with different cloud hard disks, execute the test tasks distributed by the main management node and report test data; instruction transmission and data exchange are carried out between the main management node and the work execution node through persistent TCP (Transmission Control Protocol) connection or an optimized HTTP (Hyper Text Transport Protocol) communication protocol; and analyzing the configuration file in the YAML format through a configuration file analysis module, and guiding the system to automatically configure a test environment and parameters. According to the method, the test efficiency and precision can be improved, resource optimization and cost control are realized, the flexibility and expansibility of the system are enhanced, test synchronization and data consistency are ensured, and finally the use experience and service quality of a terminal user are improved.
Owner:SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD

Near-electricity construction operation safety early warning method and system

The invention relates to a near-electricity construction operation safety early warning method and system, and belongs to the field of near-electricity construction operation equipment early warning, and the method comprises the steps: scanning a power transmission and transformation project construction site through three-dimensional laser, and forming a high-precision laser point cloud three-dimensional data model; quickly dividing an electrified body and a non-electrified body in the three-dimensional laser point cloud model, and carrying out attribute hooking on the safe distance range and the electrified body; rTK positioning sensors are installed on an operator and a construction machine, and high-precision real-time positioning and spatial distance measurement of the operator and the machine are achieved through Beidou RTK; real-time space distances between operators, machines and electrified bodies are monitored on the basis of a safety distance detection algorithm, reminding in different modes such as safety warning and prohibition warning is set according to requirements of safety operation regulations, and it is ensured that the operators, machines and the like keep enough safety distances from the electrified bodies.
Owner:STATE GRID SHANDONG ELECTRIC POWER CO +1

Defense system for complex collaborative attack in power distribution network

The invention provides a defense system for complex cooperative attacks in a power distribution network, and relates to the technical field of power system network security. The defense system comprises a data behavior analysis unit, an attack identification early warning unit and a system response and report unit; the data behavior analysis unit comprises a data acquisition preprocessing module, a feature extraction module, a behavior baseline establishment module, an anomaly detection module and an attack source positioning module; the data acquisition preprocessing module is in one-way connection with the feature extraction module; the feature extraction module is in one-way connection with the behavior baseline establishment module; the behavior baseline establishment module is in one-way connection with the anomaly detection module; the anomaly detection module is in one-way connection with the attack source positioning module; according to the invention, real-time data of key nodes are collected through the data acquisition and preprocessing module, and deep analysis is carried out by using the feature extraction module, the behavior baseline establishment module and the anomaly detection module, so that multiple sections of abnormal behaviors and potential threats in the power distribution system can be accurately identified.
Owner:SOUTHEAST UNIV +1

Portable bolt looseness detection device and detection method

The invention discloses a portable bolt looseness detection device and a detection method. The bolt looseness detection device comprises a box body, a man-machine interaction host, a sound wave emitter and a plurality of sound wave sensors, wherein the man-machine interaction host, the sound wave emitter and the sound wave sensors are arranged in the box body. According to the invention, through an advanced sound wave detection technology, tiny changes of bolt loosening can be accurately identified, so that the detection precision is obviously improved. The device accurately judges the fastening state of the bolt by analyzing the reflection and propagation time of sound waves according to the propagation characteristics of the sound waves in the bolt. And meanwhile, a machine learning algorithm is adopted to analyze the collected sound wave data, and the characteristics of bolt looseness are identified through a training model, so that the accuracy and reliability of detection are improved. A large number of tests are carried out in laboratories and on-site environments, compared with a traditional manual detection method, the detection precision of the device is improved by more than 30%, and equipment faults and safety accidents caused by bolt looseness are effectively reduced.
Owner:XUCHANG SIDA ELECTRIC POWER EQUIP

Emergency fire fighting question answering method and system based on AI big language model technology, and storage medium

The invention discloses an emergency fire fighting question answering method and system based on the AI large language model technology and a storage medium, and relates to the technical field of artificial intelligence, the emergency fire fighting question answering system comprises a front-end module, an AI preprocessing thread pool, a knowledge base module and a large model calculation engine module, the AI preprocessing thread pool receives a service request sent by the front-end module, and sends the service request to the AI preprocessing thread pool; different task threads are distributed, a knowledge base of a corresponding region category is automatically called according to the region category input by a service request to perform content similarity retrieval, knowledge content data obtained through retrieval and the corresponding service request are sorted and then uniformly sent to the large model calculation engine module supporting parallel processing to perform analysis and calculation, and the large model calculation engine module is used for performing analysis and calculation on the knowledge content data and the corresponding service request. By using the technical means of the invention, the user does not need to think what the keyword of the current question is, and can completely organize the question, directly ask the question, automatically query the local professional knowledge base and give professional and accurate answers according to the actual situation of the site, so that real barrier-free communication is realized.
Owner:杭州峰景科技有限公司

Spacecraft 1553B bus simulation test platform

PendingCN119644791AFully cover satellite communication testing requirementsGuarantee the development progressSimulator controlBus interfaceTestbed
The invention relates to a simulation test platform for a 1553B bus of a spacecraft, which is suitable for stand-alone test and system test of a 1553B bus interface of a satellite model, and comprises an application layer, a communication layer and a data interface connected with the application layer and the communication layer, the application layer comprises a main control module, a database module and a user interaction module; the communication layer comprises a non-periodic data communication module and a periodic data communication module. The method can be suitable for ground tests of multiple satellite models at the same time, the research and development cost is saved, great convenience is brought to the satellite ground tests, and therefore the development progress of the satellite models is effectively guaranteed.
Owner:BEIJING DONGFANG MEASUREMENT & TEST INST

Robot operation skill learning method for generating rewards based on large language model

The robot operation skill learning method for generating rewards based on the large language model comprises the steps of designing a prompt normal form of a large language model generation reward function, and obtaining prompt content; generating a reward function for the prompt content by using a large language model; integrating the reward function into a reinforcement learning algorithm for training, and detecting and correcting grammar errors and / or errors during operation; human user feedback is obtained, codes of the reward function are improved through the human user feedback by the large language model, and the improved reward function is used for achieving skill learning of the robot. According to the method, the accurate reward function is automatically generated by using the large language model, so that the robot is guided to optimize the behavior through self-learning; according to the method, the dependence on human professional knowledge is reduced, and the complexity and error rate of manual programming are reduced, so that the robot can realize higher learning speed and higher operation precision in a wider application scene, and the task learning efficiency and quality of the robot are improved.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Flexible joint collaborative robot control method based on self-adaptive jump and application

The invention discloses a flexible joint collaborative robot control method based on self-adaptive jump and application. The control method comprises the following steps: calculating a combined error; calculating a feed-forward compensation item and a feedback control item; adding a feedforward item and a feedback item for control; wherein the combined error comprises first-order to third-order errors; the self-adaptive jump control comprises a PID subitem and an RISE subitem, the RISE subitem comprises a self-adaptive sliding mode gain, and the self-adaptive sliding mode gain is related to a second-order error and a first-order differential of the second-order error. According to the method provided by the invention, the calculation complexity is reduced, and the real-time calculation capability of the system is improved, so that the control system can keep a relatively high response speed under a high-dynamic working condition; due to the self-adaptive jump design, the resistance of the system to uncertainty and external disturbance is improved, and the high-frequency flutter problem caused by the flexible joint is remarkably reduced; and the adjusting process of the control parameters is simplified, and the method is particularly suitable for rapid deployment of the multi-degree-of-freedom collaborative robot.
Owner:NINGBO INST OF MATERIALS TECH & ENG CHINESE ACAD OF SCI

Emergency call method, system and equipment based on VONR (Voice Over Noise Ratio) technology

The invention provides an emergency call method, system and device based on the VONR technology, and relates to the technical field of emergency calls, and the method comprises the steps: determining an initial deployment scheme; quickly deploying the unmanned aerial vehicle base station in the air; n unmanned aerial vehicle base stations are started, and a VONR technology is started; n unmanned aerial vehicle base stations receive and analyze the emergency call data in real time, and output N dynamic resource priority schedules; the 5G core network allocates communication resources; dynamic flow sharing and rescue dynamic task allocation of the unmanned aerial vehicle base station are synchronously executed by adopting N dynamic resource priority scheduling and dynamic resource allocation scheduling, and emergency call guarantee is carried out. According to the invention, the technical problem that the rescue efficiency is affected due to poor emergency communication quality caused by inflexible communication resource allocation in an emergency in the prior art can be solved, and high quality and low delay of emergency communication are ensured through a VONR technology and intelligent resource scheduling, so that the rescue efficiency is improved.
Owner:广州云趣信息科技有限公司

Virtual power plant distributed data anomaly diagnosis method based on deep neural network

The invention provides a virtual power plant distributed data anomaly diagnosis method based on a deep neural network, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining the multi-modal data of each distributed energy of a virtual power plant, and obtaining the processed distributed data; modeling each node of the virtual power plant and the relationship thereof into a graph structure to obtain a multi-time-scale spatio-temporal feature vector; pre-training is carried out by constructing a self-supervised learning task, and effective features between different time scales and modal data are extracted; generating a normal data distribution model by using a generative adversarial network, and summarizing abnormal data samples into a comprehensive data set; obtaining a multi-task optimization model through sharing characteristics among tasks; a final optimized anomaly response system is obtained, and then the task of virtual power plant distributed data anomaly diagnosis is completed through the anomaly response system. According to the method, efficient anomaly diagnosis and response processing of the distributed data of the virtual power plant are realized, and the method has remarkable technical advantages and practical application value.
Owner:GUANGZHOU POWER SUPPLY BUREAU GUANGDONG POWER GRID CO LTD

Coal rock carbon content detection method and system based on multi-feature image spectrum technology

The invention belongs to the technical field of coal rock carbon content detection, and particularly discloses a coal rock carbon content detection method and system based on a multi-feature image spectrum technology, and the method comprises the steps: constructing a typical coal rock type and a feature spectrum and texture feature database corresponding to the typical coal rock type; performing text labeling on the image category of each pixel point in the spectral image of the mixed sample; taking the data in the database as source domain data, taking the hyperspectral data of the to-be-tested coal rock sample as target domain data, and realizing coal rock classification of the to-be-tested coal rock sample in the target domain through transfer learning; for the identified coal sample, identifying whether each pixel point on the spectral image of the coal sample contains carbon or not; and for the pixel points with the carbon content, the carbon content of each pixel point on the coal sample spectral image is obtained by utilizing the trained carbon content prediction model, so that rapid and accurate detection of the carbon content of the coal rock is ensured.
Owner:SHANDONG UNIV

Dynamic routing method and system for concentrator

The invention discloses a concentrator dynamic routing method and system. The method comprises the following steps: storing an equipment code of each collector to a remote monitoring terminal; the concentrator obtains the equipment coding information of all collectors in the jurisdiction of the concentrator from the remote monitoring terminal; constructing a hierarchical routing network according to the broadcast response condition between the concentrator and the collector; and dynamically selecting a relay node for a lower-layer collector according to the communication quality evaluation score. According to the invention, all collector nodes can be automatically identified and layered, and a flexible and adjustable network topology is constructed; dynamically selecting an optimal relay node by adopting a comprehensive calculation method of multi-dimensional communication quality parameters; when a communication environment or an equipment state changes, automatic reconstruction of a hierarchical routing network and dynamic optimization of a relay node are supported. The method can effectively improve the communication efficiency and network stability between the concentrator and the collector, and is widely applied to the fields of intelligent meter reading, industrial control, environment monitoring and the like.
Owner:江苏思行达信息技术股份有限公司

Intelligent water affair light application rapid building system based on modularization

The invention relates to the technical field of water affair management, and discloses a modularization-based intelligent water affair light application rapid building system, which comprises a template library management module, which is used for storing and managing a plurality of preset function templates, and each function template is used for executing a specific function in water affair management; the parameter configuration module communicates with the template library management module and is used for performing parameterization configuration on the selected function template according to user requirements, and the parameterization configuration comprises data source configuration, operation parameter setting and output option selection; and the system combination and deployment module is used for combining the function templates subjected to parameterization configuration into a complete application system, and deploying the application system into a running environment through a containerization technology and a Kubernetes arrangement tool. Through modular design and template library management, the system can be rapidly configured and deployed according to different water affair management requirements, the construction time of the system is greatly shortened, and the system adapts to rapidly changing business requirements.
Owner:CHONGQING ZHONGDI INFORMATION TECHNOLOGY CO LTD

Two-stage training method for lightweight Chinese-English bilingual large language model

The invention provides a two-stage training method for a lightweight Chinese-English bilingual large language model. The method comprises the following steps: step 1, collecting and preprocessing Chinese-English training data; the preprocessing process comprises special mark clearing, sensitive data clearing, data duplicate removal, advertisement removal and formatting processing; 2, performing first-stage high-resource language training, namely performing model training by using English; 3, second-stage bilingual mixed training is carried out, and the Chinese data and the English data are mixed for second-stage training by adopting language migration training; wherein the step 3 comprises the following steps: step 31, performing word list expansion; and step 32, language migration training. The bilingual processing capability can be improved.
Owner:SOUTHEAST INST OF INFORMATION TECH BEIJING UNIV OF TECH +1

Stinel robot based on Robomaster multi-sensor fusion decision

The invention relates to the technical field of robots, and provides a Robomaster multi-sensor fusion decision-making-based sentry robot which comprises a chassis, a holder, an actuator module, a sensing module, a lower computer and an upper computer. The lower computer comprises a receiving module, a decision module, a distribution module and a motion control module; the upper computer comprises a laser radar navigation module and an image recognition processing module; the decision-making module is used for performing corresponding processing on the received data fusion robot according to the situation faced by the robot; and the distribution module is used for directly sending the received sensing data of the sensing module and the data of the judgment system to the laser radar navigation module and the image recognition processing module. According to the scheme, through multi-sensor fusion and a low-computing-power control system, a complex environment can be sensed more comprehensively, low-delay image processing and path planning are achieved, multiple independent and mutually decoupled modules are integrated, and high expansibility and stability are achieved.
Owner:QILU UNIVERSITY OF TECHNOLOGY (SHANDONG ACADEMY OF SCIENCES)

ROS 2 software package defect detection method based on large language model and coverage rate guidance

The invention belongs to the field of software testing, and relates to an ROS 2 software package defect detection method based on a large language model and coverage rate guidance. According to the method, function information is extracted from a to-be-tested program, and a regular expression is used for analyzing function definition, parameter characteristics and other information; the method comprises the following steps: presetting verification standards related to a to-be-tested program, and extracting physical constraints and document constraints from the verification standards; integrating the extracted function information, physical constraint and document constraint into accurate information, filling a cue word template with the accurate information, inputting the cue word template into a large language model, and generating an initial test seed; a mutation strategy is introduced, and diversified mutation operation is performed on the generated seeds, so that test cases with higher diversity are generated; optimizing the test case by adopting a coverage rate guiding mechanism, and guiding to generate a new test case by monitoring the coverage rate in real time; through a defect verification mechanism, dominant defects such as program crash and the like can be detected, and hidden defects such as violation of physical constraints or violation of document constraints and the like can be identified.
Owner:DALIAN UNIV OF TECH

Text log management method and device based on embedded system, equipment and medium

The invention discloses a text log management method and device based on an embedded system, equipment and a medium. According to the text log management method based on the embedded system, a storage medium is provided, the storage medium is divided into storage areas, and the storage areas are divided according to partitions; the management method comprises a writing method, a quick retrieval method and a data reading method. The method can be conveniently applied to an embedded system with relatively few hardware resources, the contradiction between embedded system development and large-capacity log data storage requirements is solved, meanwhile, the requirement that field maintenance is simple and easy to use can be met, and the method can be suitable for various storage media, occupies few system hardware resources, can be rapidly deployed, and has high practicability. And the method also has the advantages of quick retrieval, sequential writing, data reading, automatic coverage, few occupied resources and the like.
Owner:SHENZHEN QIHUI ELECTRIC CO LTD

Whole tray warehouse-out system and method

The invention discloses a whole-tray warehouse-out system and method, and belongs to the technical field of cigarette manufacturing, and the system comprises a stacking robot, a cigarette carton temporary storage channel, a cigarette carton backflow channel, a latent AGV, an elevator, a tray on-line device and a whole-tray warehouse-out line; wherein the latent AGV is used for moving to a designated goods location of an ex-warehouse cache region to carry finished cigarette trays and carrying the finished cigarette trays to the tray online device, moving to a designated goods location of a target floor to carry the finished cigarette trays, descending to an ex-warehouse floor through the elevator and then carrying the finished cigarette trays to a connection platform on the same floor; then the tray is carried from the connection platform to the tray on-line device; and the whole-tray delivery line provides a conveying channel for the finished cigarette trays, so that the finished cigarette trays can be conveyed to a delivery area for whole-tray loading and delivery. According to the invention, accurate tracking and management of goods are facilitated, and the accuracy and efficiency of delivery of the whole pallet are improved.
Owner:CHINA TOBACCO HENAN IND CO LTD

Alarm tool for illegal external connection of encrypted optical disc

The invention belongs to the technical field of informatization security and secrecy, and particularly relates to an encrypted optical disc illegal external connection alarm tool which comprises a recording and printing tool recorded in an optical disc in an encrypted mode and an internet detection module. And automatically associating a specific website after the recording and printing tool is opened, and judging that the compact disc is used illegally if the association is successful. According to the invention, information security management can be enhanced, the management efficiency is improved, the information security cost is reduced, comprehensive monitoring and timely alarm of the secret-related optical disk are realized, and the security and confidentiality of the secret-related information are greatly improved.
Owner:LEIHUA ELECTRONICS TECH RES INST AVIATION IND OF CHINA

Distributed sonar buoy monitoring system

The invention discloses a distributed sonar buoy monitoring system. The system comprises a plurality of buoy monitoring nodes; the plurality of buoy monitoring nodes are deployed at different positions of a monitoring area in a distributed manner; each buoy monitoring node comprises an underwater sound data acquisition module, an underwater sound data transmission module, an underwater sound data processing module, a message transceiving module and an antenna transmission module; the underwater sound data acquisition module is used for acquiring underwater sound data in an area to be monitored and transmitting the underwater sound data to the underwater sound data processing module through the underwater sound data transmission module; the underwater sound data processing module comprises a processing unit; the processing unit is used for receiving and processing the underwater sound data and transmitting the processed underwater sound data to the message receiving and transmitting module; and the message receiving and transmitting module is used for receiving the processed underwater sound data and transmitting the processed underwater sound data to the shore-based terminal through the antenna transmission module, so that the shore-based terminal receives the processed underwater sound data. According to the invention, rapid acquisition and processing of underwater sound data in a large range are realized.
Owner:STATE OCEANIC ADMINISTRATION SOUTH CHINA SEA SURVEY TECH CENT (SOUTH CHINA SEA BUOY CENT STATE OCEANIC ADMINISTRATION) +1

Data-mode driven artificial intelligence model construction method for mineral product prediction

The invention discloses a data-mode-driven artificial intelligence model construction method for mineral product prediction, and relates to the field of earth science, and the method mainly comprises the steps: determining source, transportation and storage substitution indexes according to a mineralization system; assembling a multi-source earth science data set; constructing a source, transportation and storage branch artificial intelligence model; establishing a power law function between the ore deposit space distribution density and the key ore control element distance; adding the power law function into a hidden layer of the artificial intelligence model, and constructing a metallogenic mode constraint artificial intelligence model; inputting the multi-source earth scientific data set into a source, transport and storage branch artificial intelligence model, and extracting a source, transport and storage alternative index layer; and inputting the layers into a metallogenic mode constraint artificial intelligence model, and delineating a metallogenic prospective area. By implementing the data-mode driven artificial intelligence model construction method for mineral product prediction, the interpretability and generalization ability of the artificial intelligence model for mineral product prediction can be improved, and the precision of predicting the metallogenic prospective area is improved.
Owner:CHINA UNIV OF GEOSCIENCES (WUHAN)

Photovoltaic-energy storage-charging multi-stage scheduling and market bidding optimization method and device

PendingCN122000910AMaximize operating incomeReduce losses such as breach of contract penaltiesMathematical modelsData processing applicationsNetwork deploymentReinforcement learning algorithm
The invention discloses a photovoltaic-energy storage-charging multi-stage scheduling and market bidding optimization method and a photovoltaic-energy storage-charging multi-stage scheduling and market bidding optimization device. The method comprises the following steps: constructing a data-driven random environment model reflecting photovoltaic output, electricity price fluctuation and charging load uncertainty by adopting a mode of combining time sequence clustering and a non-homogeneous Markov chain based on historical operation data; modeling a scheduling and bidding problem of the optical storage and charging integrated station into a multi-stage Markov decision process model which comprises day-ahead decision and joint optimization of multiple intra-day rolling adjustment; a deep reinforcement learning algorithm is utilized to train the network, and a strategy regulation and control network which can adapt to various uncertain scenes and meet equipment physical constraints is obtained; and deploying the trained strategy regulation and control network in an energy management system to realize global coordinated scheduling and bidding of the optical storage and charging integrated station. According to the method, the economic benefit is remarkably improved, the robustness is greatly enhanced, the decision is globally coordinated and optimized, the real-time decision capability is strong, and the expandability and portability are good.
Owner:STATE GRID LIAONING ELECTRIC POWER CO LTD +1

Modularized movable variable-structure floating body platform and operation method thereof

The invention belongs to the field of ocean engineering and floating body structures, discloses a modularized movable variable-structure floating body platform and an operation method thereof, and is suitable for multi-scene application of short-term or temporary operation on the sea. In the towing process of the platform, chain type arrangement is adopted, all floating body units are connected through spherical hinge connectors, water resistance is effectively reduced, towing efficiency is improved, and safe transfer is achieved through a tugboat and an auxiliary boat. After the platform arrives at a target area, the platform flexibly adjusts the floating body units through the tugboats, the auxiliary boats, the mechanical arms and the connecting rods, chain type arrangement is changed into an array type structure, stable multi-column arrangement is formed, and different operation requirements are met. Due to the modular design, the platform has high expansibility and is convenient to maintain and recombine. The marine floating body platform is flexible, low in cost and environmentally friendly, has high wind wave resistance and wide application prospects, and is particularly suitable for various temporary marine operations such as marine monitoring, equipment installation and marine emergency.
Owner:HAINAN UNIV

Collection probe management system and method

The embodiment of the invention provides an acquisition probe management system and method. The method can be used in distributed fields. The system comprises an acquisition probe deployment page management end, an acquisition proxy server end and an acquisition proxy end, the acquisition probe deployment page management end is used for providing a man-machine interaction function so as to create an operation task corresponding to operation task information based on the operation task information for an acquisition probe obtained by man-machine interaction; and sending the operation task to a collection agent server corresponding to the node, and displaying an execution state of the operation task, the acquisition agent server side is used for triggering the node to execute the operation task, and the acquisition agent side is deployed in the node; and the acquisition agent end is used for executing the operation task aiming at the acquisition probe. The method is used for achieving the effect of quickly deploying the corresponding acquisition probes to a plurality of servers and realizing unified management of the acquisition probes.
Owner:BANK OF CHINA