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

51results about How to "Good decision" patented technology

Start deployment and cooperative processing method for multi-core heterogeneous system

The invention provides a multi-core heterogeneous system-oriented startup deployment and cooperative processing method, which comprises the following steps of: when the system runs, obtaining startup codes after a master core and a slave core are electrified, respectively obtaining mirror image files of Linux and RTOS (Real Time Operating System) on the basis of synchronous running and storage partition, and running the mirror image files on the master core and the slave core after moving the mirror image files; and after the heterogeneous operating system is loaded, generating an interrupt signal based on inter-core interrupt and a corresponding register through a CLINT module in the main core, and realizing data communication between the main core and each slave core based on the interrupt signal and the shared memory. By means of the method, after the system is powered on, the multiple cores can synchronously run the starting codes, and time delay and uncertainty possibly caused by one-by-one starting of the single cores are avoided; communication and data transmission among multiple cores are realized through interruption and memory sharing, the synchronism and consistency of data are ensured, and misjudgment and decision errors caused by data delay and inconsistency are avoided, so that the real-time performance of the system is remarkably improved.
Owner:WUHAN LINGJIU MICROELECTRONICS CO LTD

Cross-regional air conditioner regulation and control strategy modeling method and cross-regional air conditioner regulation and control method and system

The invention provides a cross-regional air conditioner regulation and control strategy modeling method and a cross-regional air conditioner regulation and control method and system, and is applied to the technical field of intelligent regulation and control of air conditioners. The method comprises the steps that clustering processing is conducted on air conditioner load data of users in all regions, and a clustering result is obtained; constructing a regional cold supply system simulation model corresponding to the clustering cluster based on the users in the same clustering cluster in the clustering result; the operation safety of an actual regional cooling system is considered, modeling is carried out on the regulation and control process of the simulation model based on the Markov decision process, and an optimization strategy model is constructed by taking expected return maximization of a value function corresponding to an operation strategy of the simulation model as a target; and training an optimization strategy model based on simulation operation data of the simulation model. According to the method, the problems that in the process that the DCS participates in power grid load regulation and control, a trial-and-error training-based model is prone to system damage in practical application, and single-model regulation and control cannot guarantee the load regulation and control effect of a whole power grid are solved.
Owner:CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +2

Vehicle positioning method based on multi-view and multi-scale feature fusion

The invention belongs to the technical field of vehicle positioning, and particularly discloses a vehicle positioning method based on multi-view and multi-scale feature fusion. According to the method, a multi-view and multi-scale pyramid fusion neural network is provided, at the input stage of the network, a multi-channel distance image RIV of laser radar point cloud projection and BEV representation generated through normal distribution transformation are utilized, mutual complementation can be achieved on the global scale and the local scale, the overall understanding ability of a scene is improved, and the overall performance of the scene is improved. The limitation of a single view angle is effectively relieved through multi-view-angle input, and the robustness and anti-interference performance of the model are improved. On the network architecture level, a self-attention mechanism using Mama is provided. According to the method, not only can the complementary correlation among multiple views be fully utilized, but also the context information can be coded and integrated across multi-scale features, the finally generated global descriptor features are rich, and the accuracy of vehicle positioning is improved.
Owner:SHANDONG UNIV OF SCI & TECH

Village and town industry development planning system based on land comprehensive improvement data

The invention discloses a rural and town industry development planning system based on land comprehensive improvement data, which is characterized in that a data processing module processes, cleans and extracts massive land comprehensive improvement data to effectively remove redundant and abnormal data and ensure the quality and accuracy of the data; the data analysis module can deeply mine a potential association relationship between data sets and is helpful to discover new industrial development opportunities and potential risks, the algorithm model module can accurately carry out industrial development deduction, and an algorithm model can predict the future trend of industrial development and possible problems by simulating different scenes and conditions, so that the development efficiency of the industrial development is improved. The evaluation and verification module strictly verifies the algorithm model deduction result to ensure the accuracy and reliability of the deduction result, the result generation module facilitates understanding and analysis of a planning decision maker according to the verification result, and the system realizes whole-process intelligent and automatic processing from data to the result, so that the working efficiency is improved, and the working efficiency is improved. And errors and risks of human intervention are reduced.
Owner:GUANGDONG PULAN GEOGRAPHIC INFORMATION SERVICE CO LTD

Gene data analysis method based on large language model

The invention relates to the technical field of gene analysis bioinformatics, and particularly discloses a gene data analysis method based on a large language model.The method comprises the steps that the quality of gene data to be analyzed is analyzed, whether the gene data to be analyzed is available or not is judged, and a gene sequence segmentation scheme of the available gene data is determined; inputting the gene data after gene sequence segmentation into the large language model to obtain a gene data association feature data set and a gene data analysis result, determining a gene data analysis accuracy feature value, and judging whether the gene data analysis result conforms to expectation or not; the problems that quality and integrity problems of traditional biological data challenge the accuracy of analysis results and effective integration and analysis of multi-modal data still need to be improved are solved, the data processing efficiency is optimized in the whole process, repeated calculation, misjudgment and invalid results are reduced, the analysis efficiency is improved, and resource waste is reduced.
Owner:JILIN AGRICULTURAL UNIV

Vehicle environment perception method based on multi-view and multi-scale feature fusion

The invention belongs to the technical field of vehicle environment perception, and particularly discloses a vehicle environment perception method based on multi-view and multi-scale feature fusion, and the method builds a vehicle environment perception network based on multi-view and multi-scale feature fusion for the problem of information loss in the projection process of a projection-based point cloud segmentation method. In the aspect of network input, a multi-level multi-projection fusion deep learning network is designed through double coding of multi-layer distance view representation and aerial view features, the information extraction precision of targets in point clouds with relatively prominent vertical information and relatively long distance is effectively improved, and information loss of separated projection is reduced. In the aspect of a network structure, the invention provides a multi-view fusion module which combines MFB and MMViT to calculate high-order correlation between BEV features and RV features and deeply fuses multi-view features. According to the invention, the loss generated in the projection process is avoided, and the vehicle environment perception capability is improved.
Owner:SHANDONG UNIV OF SCI & TECH

Internet of Things equipment power consumption self-adaptive optimization method and system based on edge computing

The invention relates to the technical field of internet of things equipment power consumption optimization methods, in particular to an internet of things equipment power consumption self-adaptive optimization method and system based on edge computing, and the method comprises the following steps: firstly, collecting historical operation data of different edge computing equipment, including but not limited to resource utilization rate, power consumption and network bandwidth; then, learning the historical operation data by using an improved multi-target deep reinforcement learning algorithm to obtain an equipment model; thirdly, predicting the optimal power value of the equipment through the equipment model; then, comparing the optimal power value with the actual operation power value of the current equipment, and when the optimal power value is inconsistent with the actual operation power value, sending an optimization instruction to the edge computing equipment; and finally, adjusting the parameter value of the edge computing device according to the optimization instruction to realize self-adaptive optimization of the power consumption of the device, so that the power consumption can be obviously reduced under various load conditions, and the task completion rate and the system response speed can be improved at the same time.
Owner:WUXI INSTITUTE OF TECHNOLOGY

Asset management system based on Internet of Things

The invention relates to the technical field of asset management, and particularly provides an asset management system based on the Internet of Things, which comprises an asset registration module, a region classification module, a communication module, an asset positioning module, a map module, an asset state monitoring module, a data updating module and a report generation module, the communication module comprises a main communication node and a plurality of branch communication nodes, and the main communication node communicates with the plurality of branch communication nodes by establishing direct connection or indirect connection; each branch communication node is arranged in a sub-region module; the asset registration module, the region classification module, the communication module, the asset positioning module, the asset state monitoring module, the data updating module and the report generation module are simultaneously integrated in the system, and the modules are mutually associated and matched to help enterprises to comprehensively, efficiently and quickly manage and use the assets of the enterprises; and a scheme optimization basis for asset maintenance, optimization and service life prolonging is provided for enterprises.
Owner:WUXI HANXIN TECHNOLOGY CO LTD

Flexible job shop scheduling method based on deep reinforcement learning

The invention relates to the field of production scheduling and resource optimization, in particular to a flexible job shop scheduling method based on deep reinforcement learning, which is characterized by comprising the following steps: 1) constructing a flexible shop scheduling environment; (2) a flexible workshop scheduling environment is abstracted to be Disjunction Graph, and the flexible workshop scheduling environment is abstracted to be Disjunction Graph; 3) extracting state features; 4) coding the state features; 5) executing a decision based on the encoded features to obtain scheduling probability distribution; and 6) generating a scheduling plan according to the probability distribution. According to the invention, through multi-level feature extraction and fusion, accurate perception of a production environment is realized, and the accuracy and robustness of a scheduling decision are effectively improved; by utilizing a deep reinforcement learning framework, the dynamic change of the production environment can be adaptively learned, the scheduling strategy is continuously optimized, and the generalization ability is relatively high; and feature representation is enhanced through an attention mechanism, so that the model can still quickly find a global optimal solution when facing a large-scale and high-complexity FJSP problem.
Owner:SHENYANG GOLDING NC & INTELLIGENCE TECH CO LTD

High-recognition low-power-consumption high-voltage interlocking circuit and controller

ActiveCN222089281USolve the problem of short circuit power consumptiongood decisionElectric devicesEmergency protective arrangement detailsLevel shiftingTerminal voltage
The embodiment of the utility model provides a high-recognition low-power-consumption high-voltage interlocking circuit and a controller, and belongs to the field of battery power. The high-voltage interlocking circuit comprises a main power supply line, a control unit, a self-holding unit, a level conversion detection unit, a current detection unit and an input detection unit, the current detection unit is used for judging current returned by a loop, the state of the current can be obtained and output to a single chip microcomputer, and the problem of power consumption caused by short circuit of the loop can be solved; when the output circuit is short-circuited with a power supply, the control unit forms an access, weak reverse current exists, so that voltages at two ends of a resistor on the output access are reversed, and the current detection unit outputs the voltages to the single chip microcomputer; when the loop is short-circuited to the ground, the output short circuit can be automatically cut off by using the change of the output voltage, and four states of the loop can be accurately detected, so that the system decision is better and the cost is lower.
Owner:ANHUI SHARP INNOVATION ENERGY TECH CO LTD

Railway infrastructure multi-source data fusion system and method

The invention belongs to the technical field of railway multi-source data fusion, and particularly relates to a railway infrastructure multi-source data fusion system and method. According to the method, the time features of each reference data source are analyzed, the data sources with the centralized features and the dispersive features can be accurately recognized, the corresponding fusion rules are formulated accordingly, the scientificity and reasonability of the data fusion process are ensured, abnormal fusion nodes can be found and processed in time, and the fusion efficiency is improved. In addition, the abnormal fusion nodes can be dynamically adjusted according to the fusion deviation value, the continuity and stability of the data fusion process are ensured, the deviation in the data fusion process can be found and corrected in time through real-time monitoring and backtracking analysis, and the data fusion accuracy is improved. Therefore, decision errors caused by data fusion errors are avoided, and accurate and timely data support is provided for maintenance and management of railway infrastructures.
Owner:EAST CHINA JIAOTONG UNIVERSITY +1

Vehicle localization method based on multi-view and multi-scale feature fusion

The present invention belongs to the technical field of vehicle positioning, and specifically discloses a vehicle positioning method based on multi-view and multi-scale feature fusion. A multi-view multi-scale pyramid fusion neural network is proposed in the method of the present invention. At the input level of the network, a multi-channel range image RIV projected by a lidar point cloud and a BEV representation generated by a normal distribution transformation are used to complement each other at global and local scales, thereby improving the overall understanding of the scene. Multi-view input effectively alleviates the limitations of a single view and improves the robustness and anti-interference of the model. At the network architecture level, a self-attention mechanism using Mamba is proposed. The present invention can not only make full use of the complementary correlations between multiple views, but also encode and integrate contextual information across multi-scale features. The global descriptor finally generated is feature-rich, thereby improving the accuracy of vehicle positioning.
Owner:SHANDONG UNIV OF SCI & TECH

Smart factory edge data collection method, system and medium based on the Internet of Things

The present invention relates to the field of edge data acquisition, and specifically to an edge data acquisition method, system and medium for a smart factory based on the Internet of Things, comprising: an edge acquisition module, a local modeling module, an abnormality recognition module, an edge communication module and a local adjustment module. The edge acquisition module is used to collect working parameters and environmental parameters of production equipment, the local modeling module is used to calculate end point coordinates and an environmental impact matrix, the abnormality recognition module is used to correct the acquired environmental data and identify abnormal sensors, the edge communication module is used to build a communication link, and the local adjustment module is used to adjust the variable parameters of the production equipment and automatically adjust them. The present invention can achieve the integration and consistency of different data sources, ensure the quality and availability of data, and at the same time help to improve data quality, timely discover sensor failures or inaccurate data, and achieve a more efficient and safer production mode.
Owner:RONGAN CLOUD NETWORK (BEIJING) TECH CO LTD

A real-time interface data exception feedback and dynamic re-push method of an aluminum electrolysis MES system

A kind of aluminum electrolysis MES system real-time interface data exception feedback and dynamic re-push method, it is related to aluminum electrolysis production informatization management technical field, including steps S1, set interface data exception data rule, according to the abnormal data rule to the real-time monitoring and abnormal perception of multi-source interface data;Step S2, set exception data level, according to exception data level, MES system receives exception data and carries out hierarchical feedback;Step S3, according to the server state exception interface data dynamic re-push condition setting, MES system according to the server load state dynamically re-pushes exception data to external system etc..The present application makes up the problem that existing aluminum electrolysis MES system and external system exist in interface data interaction process in the production process, and exception feedback lag and re-push mechanism rigidification, ensure the accuracy and reliability of interface data.
Owner:SHENYANG ALUMINIUM MAGNESIUM INSTITUTE

A non-conservative intelligent vehicle decision planning integrated method

ActiveCN116523156Bhigh trafficgood decision
The application relates to a non-conservative intelligent automobile decision planning integrated method in a complex heterogeneous environment, which comprises the following steps: constructing a social interaction knowledge learning model offline and training; acquiring surrounding traffic participant state data and intelligent automobile state data in real time online, and obtaining an environment state after splicing processing; taking the environment state as the input of the trained social interaction knowledge learning model to obtain the predicted trajectories of all traffic participants including the intelligent automobile; updating the environment state based on the predicted trajectories; re-inputting the updated environment state into the social interaction knowledge learning model to iteratively complete intelligent automobile trajectory decision planning, wherein the planning trajectory of the intelligent automobile is the splicing result of the first point of the predicted trajectory obtained in each iteration. Compared with the prior art, the application has the advantages of considering the influence of social interaction prediction on the trajectory, decision planning integration and the like.
Owner:TONGJI UNIV

An industrial Internet information interaction method and system based on industrial algorithm

The present invention discloses an industrial Internet information interaction method and system based on industrial algorithms, and relates to the technical field of industrial Internet information interaction. Through the blockchain recording module, data cannot be tampered with during the process of collection, processing and storage, ensuring the authenticity and transparency of information; this improvement enhances the trust basis of all parties and avoids the generation of information islands. The real-time data analysis module integrated in the system can quickly analyze the data standard set and calculate the equipment efficiency coefficient and energy consumption efficiency coefficient. This real-time feedback mechanism enables problems in the production process to be quickly identified and solved, improving production efficiency and resource utilization. The smart contract module automatically triggers contract execution according to real-time data, realizes the automation of information interaction, and reduces the need for human intervention. By automatically issuing alarms and adjusting production parameters, the system can more flexibly respond to equipment failures and excessive energy consumption problems, reducing production risks.
Owner:SHENZHEN BANGQI MINE ELECTROMECHANICAL CO LTD

Vehicle and road cloud collaborative sensing method and system based on multi-source data fusion

The invention provides a vehicle-road cloud cooperative sensing method and system based on multi-source data fusion, and relates to the technical field of intelligent traffic, and the method comprises the steps: carrying out the heterogeneous sensing through a vehicle end sensing unit, a road side sensing unit and a cloud control platform, and forming a multi-source sensing data set; feature extraction is carried out based on the multi-source perception data set, a data feature set is generated, vehicle and road cloud collaborative perception is carried out according to the data feature set, and a vehicle and road situation perception result is generated, and the vehicle and road situation perception result comprises traffic target state parameters; and risk assessment is carried out according to the traffic target state parameters, decision reasoning is carried out according to risk assessment values, and a vehicle cooperative control cooperative sensing instruction is constructed. According to the method and the device, the technical problems that in the prior art, due to data heterogeneity, multi-source data are difficult to fuse in vehicle-road collaborative perception, decision making is inaccurate in a complex traffic environment, and traffic management efficiency is further influenced are solved, the fusion precision of the multi-source data is improved, and therefore the traffic management efficiency is improved.
Owner:INTELLIGENT INTER CONNECTION TECH CO LTD

Distributed deep Q learning method for multi-agent system path search

A distributed deep Q learning method for path searching of a multi-agent system comprises the following steps: 1) constructing a deep Q network of each agent, and forming a D-DMAQL model corresponding to the multi-agent system in combination with a UCB strategy for calculating the Q value of each agent at the current moment and the maximum Q value of each agent at the next moment; 2) establishing a D-DMAQL training module which is used for training a D-DMAQL model; 3) establishing a reasoning decision module used for calculating the decision value of each agent according to the Q value of each agent at the current moment and the corresponding environment state and action; 4) establishing a global optimizer for calculating a global loss function of the D-DMAQL model according to the Q value of each agent at each moment and the corresponding environment state, action, reward and decision value; and 5) performing path searching of the multi-agent system by utilizing the trained D-DMAQL model and combining a global loss function.
Owner:CHANGAN AUTOMOBILE (GRP) CO LTD

Cloud-edge collaborative resource scheduling method, system, electronic device and readable medium

The present invention discloses a cloud-edge collaborative resource scheduling method, system, electronic device and readable medium, the method comprising: establishing energy consumption models for IT equipment, power supply equipment and cooling equipment in the cloud-edge collaborative system respectively; setting the energy consumption optimization target of the cloud-edge collaborative system based on the energy consumption model; and using a reinforcement learning algorithm to generate resource scheduling decisions based on the current resource status, task request and energy consumption of the cloud-edge collaborative system to minimize the energy consumption optimization target. The cloud-edge collaborative resource scheduling method, system, electronic device and readable medium provided by the present invention respond to low-carbon operation and reduce energy consumption in a cloud-edge collaborative resource scheduling scenario for computing-network integration, while taking into account the energy consumption of IT equipment and infrastructure of edge clusters and data centers, and performing multi-dimensional joint optimization.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Construction system of power grid health degree evaluation model

The invention is suitable for the technical field of model construction, and provides a construction system for a power grid health degree evaluation model, and the system comprises a data quality management module which carries out the cleaning, denoising, difference and anomaly detection of data, and processing of the data; the data integration and consistency management module is used for performing format consistency processing on the multi-source data and integrating the data; the self-adaptability and flexibility enhancing module is used for setting configurable algorithms and model parameters to automatically adjust and optimize the model; the security and privacy protection module is used for matching a power grid data processing standard through an encryption technology, data desensitization, access control and security audit, and ensuring the security of the data in the processes of acquisition, transmission, storage and processing; and the continuous maintenance and update management module is used for regularly updating the model and the algorithm by implementing an automatic monitoring and feedback mechanism so as to ensure that the model performance is continuously optimized and adapts to new technology and data optimization. Misjudgment caused by a data quality problem is avoided, and the accuracy of the evaluation model is improved.
Owner:GUANGXI POWER GRID CO LTD NANNING POWER SUPPLY BUREAU

Tobacco financial data risk analysis system

The invention relates to the technical field of tobacco finance, and discloses a tobacco finance data risk analysis system, which comprises an authority management module, a data source collection module, a data processing module, a data analysis module and a risk assessment module. According to the tobacco financial data risk analysis system, an authorizer can directly obtain tobacco financial data after key input and fingerprint identification success, and a third-party authorizer needs to send a success signal to a confirmation window after third-party key and third-party fingerprint information identification success; the financial data source can be obtained only after the user confirms authorization, the safety and privacy of the financial data are effectively guaranteed, only the authorized user can access the financial data, data leakage or malicious tampering is prevented, manual intervention can be reduced by automatically collecting and processing data, the working efficiency is improved, human errors are reduced, and the user experience is improved. An enterprise is helped to identify and evaluate potential risks in real time, so that preventive measures are taken, and risk influences are reduced.
Owner:HENAN TOBACCO SHANGQIU

Out-of-distribution detection method and system based on abnormal activation and multi-source information fusion

The invention relates to the technical field of computer vision, in particular to an out-of-distribution detection method and system based on abnormal activation and multi-source information fusion and a computer readable storage medium, and the method comprises the steps: 1) calculating class related items based on an image classification probability outputted by a classifier, and obtaining class related information in a probability space; 2) calculating class irrelevant items based on the depth features of the input image sample extracted by the feature extractor so as to obtain class irrelevant information in the feature space; and 3) calculating an abnormal factor based on network activation, namely depth features. And calculating out-of-distribution scores based on the class-related items, the class-independent items and the abnormal factors, and distinguishing out-of-distribution samples and in-distribution samples by using the out-of-distribution scores. According to the method, various information of the feature space and the probability space is fused to calculate the distribution external score, so that the limitation of single-source information is overcome, and the complementary advantages of various types of information are fully exerted.
Owner:JIANGNAN UNIV

A multi-point cooperative gas emergency shutdown positioning method based on a gas monitoring system

The present application relates to a kind of multi-point cooperative gas emergency shutdown positioning method based on gas monitoring system, belong to the field of automation control technology. Among them, the method includes: real-time acquisition multi-source alarm signal;And the analog quantity and switch quantity of the multi-source alarm signal are uniformly converted into digital processing code;Multi-source alarm signal digital processing code is analyzed in real time to obtain alarm priority and associated equipment address, and data accuracy is verified by actual combat coefficient correction model;Combining dynamic networking and cooperative decision mechanism generates shutdown path;Shutdown path is executed, and execution result is fed back to host computer monitoring platform in real time, and field alarm lamp state and broadcast system are updated simultaneously;Through host computer monitoring platform, alarm history curve, equipment state and linkage logic of shutdown operation are recorded, and manual reset interface is provided to remove shutdown state. Efficient processing and accurate response of gas leakage accident are realized.
Owner:SHANGHAI SHENGSHENG ELECTRONIC TECH CO LTD

Method, device, program product and storage medium for ensuring data consistency

The present invention relates to a method, a device, a program product and a storage medium for ensuring data consistency. The method comprises: receiving data to be compared sent by a RocketMQ message queue with a delay, querying first summary information of the received data to be compared; obtaining second summary information from Redis; comparing the first summary information with the second summary information to see whether they are consistent, and if they are consistent, obtaining third summary information from an Elasticsearch server; comparing the first summary information with the third summary information to see whether they are consistent, and if they are consistent, deleting the second summary information in Redis, otherwise judging whether the comparison count is greater than a predetermined value; if it is greater than the predetermined value, the comparison fails, deleting the second summary information in Redis, and saving the business data that failed the comparison to a database, otherwise synchronizing the business data corresponding to the first summary information to the Elasticsearch server again, and sending the data to be compared to the message queue at the same time, and performing the comparison after a delay.
Owner:SHANGHAI JIAYING TECH CO LTD

Task file exception rereading method and device, equipment and medium

The invention relates to the technical field of data processing, can be applied to business system platforms of financial science and technology, medical treatment and health and the like, and discloses a task file exception re-reading method, device and equipment and a medium. Generating a to-be-executed task sub-file corresponding to the to-be-executed task main file according to the task configuration parameters; reading a reading progress value and a read data volume corresponding to the to-be-executed task main file, and monitoring a task data reading state of the to-be-executed task main file according to the reading progress value and the read data volume; when the task data reading state is reading failure, reading the to-be-executed task sub-file, and executing the to-be-executed task sub-file based on a reading result of the to-be-executed task sub-file to obtain a sub-file task execution state; identifying a reading abnormal factor of the main file of the task to be executed, and extracting a file configuration parameter of the reading abnormal factor; and synchronously updating the sub-file task execution state and the file configuration parameters to the to-be-executed task main file. According to the method, the task file exception rereading efficiency can be improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

Hydropower dispatching training simulation examination evaluation method and system

The invention discloses a hydropower dispatching training simulation test evaluation method and system, and relates to the technical field of hydropower dispatching, and the method comprises the following steps: obtaining various parameter information generated in a simulation platform operation process, including power grid load distribution information and hydropower resource utilization efficiency information; through obtaining power grid load distribution information and hydroelectric resource utilization efficiency information generated by a simulation platform and combining intelligent model analysis, an abnormal operation index is generated and real-time monitoring and evaluation are carried out. An index is generated for abnormal analysis of tidal current distribution and tidal energy balance, and potential anomalies are found in time. And when the abnormal index exceeds the standard, the system is divided into a high-risk operation state and gives out an early warning, so that the simulation accuracy and stability are ensured, and the decision-making quality of a dispatcher is improved. Continuous monitoring, evaluation and early warning effectively avoid misoperation, improve emergency processing capacity, reduce power grid accident risks and guarantee stable operation of a power grid.
Owner:HUANENG LANCANG RIVER HYDROPOWER CO LTD

An energy storage power station intelligent optimization method and system based on deep coupling learning

PendingCN122512492AImprove predictive abilityRelieve unnecessary circulatory pressure
The application discloses an energy storage power station intelligent optimization method and system based on deep coupling learning, relates to the technical field of energy storage power station optimization, and is used for solving the problems of maximum demand capture failure caused by production plan fluctuation and invalid charging and discharging loss caused thereby, extracting strong correlation characteristics of production procedures and power mutation, constructing a time-space matrix anchor peak value inducement, outputting a latent space feature vector through an encoder by using a deep coupling multi-task network, explicitly quantifying a demand refresh risk probability, introducing the peak value risk and a battery health soft measurement quantity into a target function based on an MPC-DRL rolling optimization framework, dynamically adjusting charging and discharging sensitivity, constructing a composite feedback signal by extracting extreme samples of missed or false peak values, and realizing closed-loop evolution of attention reconstruction and decision threshold prediction; the robustness of demand management under a complex production environment is improved, the power consumption cost is reduced, and the whole life cycle optimal balance of battery life and economic benefits is realized.
Owner:SHANGHAI OUBAO SHUNYAO NEW ENERGY TECHNOLOGY CO LTD

Environmental perception system based on intelligent driving

The present invention discloses an environment perception system based on intelligent driving, which relates to the field of intelligent driving technology. Environmental data is acquired in real time through sensors such as radar and laser radar, and SLAM technology is used to compare with a basic environmental model to identify false signal areas. The system further evaluates the degree of signal interference through signal strength and path complexity analysis, and divides it into high, medium and low interference levels, and adopts different processing strategies. For low interference levels, sensor data is directly used to update environmental models and dynamic object detection; for high interference levels, the system reduces the driving speed and corrects the path; for general interference levels, the system optimizes the path adjustment range according to the interference prediction results within a fixed time period, so as to ensure the safety, accuracy and stability of the automatic driving system in complex environments.
Owner:ZHILIAN INFORMATION TECH CO LTD

Electronic tag reading and displaying method and reading equipment based on commodity dynamic information

The invention belongs to the field of large electronic tags, and particularly relates to an electronic tag reading and displaying method and reading equipment based on commodity dynamic information, and the method comprises the steps: capturing the electronic tag information of a commodity selected by a user through a radio frequency reading device, and rapidly recognizing and obtaining the unique identifier of the commodity; secondly, in combination with the commodity identifier and the past search record of the user, an entity-relation extraction algorithm, a knowledge graph and a graph database are utilized to trace back in a commodity dynamic association information base and construct an association information chain of the selected commodity, and the chain not only covers direct related commodities, but also updates the latest information containing the associated commodities in real time; and finally, displaying the latest commodity information of the selected commodity and the related commodity through a set display terminal. According to the method, the dynamic display and recommendation efficiency of the commodity information is remarkably improved, and real-time shopping experience is provided for consumers.
Owner:WUXI PINGUANG IOT TECH CO LTD

A vehicle environment perception method based on multi-view and multi-scale feature fusion

The present invention belongs to the technical field of vehicle environment perception, and specifically discloses a vehicle environment perception method based on multi-view and multi-scale feature fusion. This method aims at the problem of information loss in the projection process of the projection-based point cloud segmentation method, and builds a vehicle environment perception network based on multi-view and multi-scale feature fusion. In terms of network input, the present invention uses multi-layer distance view representation and bird's-eye view feature dual encoding to design a multi-level multi-projection fusion deep learning network, which effectively improves the information extraction accuracy of targets in point clouds with prominent vertical information and long distances, and reduces the information loss of separated projections. In terms of network structure, the present invention proposes a multi-view fusion module, which combines MFB and MMViT to calculate the high-order correlation between BEV features and RV features, and deeply fuses multi-view features. The present invention is conducive to avoiding losses incurred during the projection process and improving the vehicle environment perception capability.
Owner:SHANDONG UNIV OF SCI & TECH