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

11results about How to "Fully explore" patented technology

Intelligent ore blending method and system based on sintering optimization

PendingCN119129917AOptimize the sintering ore blending processReduce smelting costForecastingChemical processes analysis/designProcess engineeringIron ore sintering
The invention discloses an intelligent ore blending method and system based on sintering optimization, and belongs to the technical field of iron ore sintering production, and the method comprises the steps that an equipment state monitoring module monitors the operation state and performance parameters of sintering equipment in real time; the online data analysis module is used for detecting and analyzing the quality of the sintered finished product in real time in the sintering process to obtain the relationship among the quality of the sintered finished product, the raw material composition and the process parameters; the quality prediction module imports the ore blending scheme, the operation state and the performance parameters into a sintered ore quality prediction model to obtain a prediction result of a sintered finished product; the ore blending optimization module firstly generates one or more initial ore blending schemes according to the current raw material inventory, production plan and sintering process requirements, and then sends the ore blending schemes to the quality prediction module to obtain one or more prediction results; and finally, according to requirements, selecting an optimal ore blending scheme, and carrying out a sintering process according to the selected ore blending scheme. According to the invention, automation and intelligentization of the batching process can be realized.
Owner:TIANJIN IRON WORKS CO LTD

Underground expressway reinforcement learning intelligent line selection method based on GIS and InSAR and computer system

The invention discloses an underground expressway reinforcement learning intelligent line selection method based on a GIS and an InSAR, and the method comprises the steps: providing urban environment multi-source data based on the GIS and the InSAR, building a rasterized observation space, building an initial linear continuous line space, and jointly building a line selection space of a reinforcement learning model; the strategy network of the reinforcement learning model receives parameter information of the line selection space and outputs linear parameters; the linetype builder corrects linetype parameters and updates the line selection space; the multi-index evaluation model outputs reward and punishment values according to the parameter information of the new line selection space, a value network of the reinforcement learning model receives the reward and punishment values, calculates a gradient for updating, and transmits a gradient updating strategy model; circulating until a round of line selection is completed, and calculating an accumulated reward value; and when the accumulated average reward value does not reach the optimization target, circulating until the optimization target is reached, and finding the optimal design. The method has the advantage of being beneficial to improving the efficiency and accuracy of underground road design.
Owner:TONGJI UNIV

Roll-to-roll multilayer overprinting control method based on improved simulated annealing optimization LQR

The invention discloses a reel-to-reel multilayer printing control method based on improved simulated annealing optimization LQR, and belongs to the field of multilayer printing flexible electronics. According to the reel-to-reel multilayer printing flexible electronic control method based on the improved simulated annealing optimization LQR, initial LQR controller design is carried out on an overprinting system according to a reel-to-reel overprinting system dynamic model, and a simulated annealing algorithm is selected to carry out LQR controller optimization; and self-adaptive annealing, dynamic step length, mixed neighborhood search and other methods are used to make up for the defects of slow convergence speed, difficult temperature control and the like of the traditional simulated annealing algorithm, so as to obtain the optimal control quantity and improve the overprinting precision and control stability of the system. The control quantity optimization of the overprinting system is realized, the control stability of the overprinting system is ensured, and the overprinting precision is improved.
Owner:JIANGNAN UNIV

Map generation method and related equipment

The invention discloses a map generation method which can be applied to robot mapping scenes in families, hotels, restaurants, shopping malls, airports, hospitals, scenic spots, factories and other scenes. The method comprises the following steps: acquiring a plurality of obstacles in a scanning range of a sensor; controlling the terminal equipment to navigate to a first obstacle, wherein the first obstacle is the obstacle closest to the terminal equipment in the plurality of obstacles; and then determining a next navigation point of the terminal device, the next navigation point being an obstacle which is the smallest distance from the first obstacle in the plurality of candidate obstacles, or the next navigation point being an obstacle which is not selected in the plurality of obstacles and the terminal device does not pass through. And generating a map based on the navigation trajectory of the terminal device. In the map generation process, the candidate obstacles can be updated in real time, so that comprehensive exploration is carried out, and mapping is completed under the condition that no static map exists.
Owner:HUAWEI TECH CO LTD

A method for matching selection of a hull, a main engine and a propeller

PendingCN122413563AExcellent open water efficiencysimple designPropellerHull
The application discloses a method for matching selection of a ship body, a main engine and a propeller, and comprises the following steps: step 1, setting ship parameters, design requirements and propeller parameters; step 2, constructing a propeller hydrodynamic performance prediction model based on a support vector machine, wherein the input of the model is the propeller parameters, and the output of the model is the open water power of the propeller; step 3, constructing a four-stage matching method, and optimizing a disc area ratio in each stage; step 4, performing cavity checking and strength checking on the matching results output in step 3, and taking the matching results meeting the checking as effective propellers; and step 5, sorting the effective propellers by a double optimization target method, and taking the optimal effective propeller as the final matching result. The application can quickly provide the matching selection result of the ship body, the main engine and the propeller, can comprehensively design the main engine and the propeller parameters, and ensures that the open water efficiency of the propeller reaches the optimum, and reduces the labor cost in the design process.
Owner:JIANGSU UNIV OF SCI & TECH +1

Message transmission method fusing priori routing and dtn and storage medium

The application particularly relates to a message transmission method combining a priori routing and a DTN and a storage medium. The method comprises the following steps: establishing and maintaining a routing table in each node of the network based on a priori MANET routing protocol mechanism; when a message source node transmits a message to a message destination node: firstly, the message is transmitted by using the priori MANET routing mechanism; otherwise, a message copy distribution algorithm based on location information is used, and a DTN mechanism is used to distribute the message copy to a relay node at the topological boundary of the message source node end, so that the relay node becomes a virtual source node; if the message transmission is unsuccessful, the message copy is stored in the relay node at the interruption, so that the relay node becomes a virtual source node; the virtual source node broadcasts routing query information to its neighbor nodes, and the routing table of the neighbor nodes is inquired; when an opportunity to establish a connection with the message destination node is found, the above steps are repeated. The application can improve the reliability of message transmission by using the DTN routing mechanism, and can fully explore the connectable sub-topology in the MANET network.
Owner:ARMY ENG UNIV OF PLA

Gift design scheme optimization method and system fusing multi-modal user demand perception

This invention discloses a method and system for optimizing gift design schemes by integrating multimodal user demand perception, relating to the field of data processing technology. The method includes: acquiring a set of gift size demand features; calculating the weight coefficients of each gift size demand feature through sensitivity analysis combined with historical gift design schemes; constructing a collaborative optimization objective function for gift size, using size design parameters as independent variables and maximizing the overall matching degree as the optimization objective, while setting cost constraint thresholds and material size matching thresholds as optimization constraints; acquiring the gift size design range, iteratively solving the collaborative optimization objective function to obtain multiple candidate size design schemes that satisfy all constraints, and the overall matching degree corresponding to each candidate scheme; selecting the candidate size design scheme with the highest overall matching degree and single-dimensional matching degree to obtain the optimal gift size design scheme set. This invention effectively improves the overall matching degree of gift size design under multimodal user demand.
Owner:BEIJING SHENGSHI MINGLI TECHNOLOGY CO LTD

A Multi-Objective Optimization-Based Reverse Design Method for Wharf Foundation Piles

ActiveCN121637645Bprecise definitionflexible definitionGeometric CADClimate change adaptation
This invention provides a reverse design method for wharf foundation piles based on multi-objective optimization, belonging to the field of civil engineering structural design technology. In the composite load space composed of vertical, horizontal loads, and bending moments, this invention uses a shape parameter vector containing dimensions and coupling coefficients to define and parameterize the target failure envelope. By performing numerical limit state analysis and fitting on design samples, the actual shape parameters are obtained. This is used to train a machine learning model that can quickly predict the shape of the corresponding envelope from the design parameters. Using the difference between the predicted shape and the target shape as the optimization objective, and combined with construction costs, the model is used to evaluate candidate designs. A multi-objective optimization algorithm is used iteratively to obtain a set of design parameters that optimally balance performance and cost. The selected design is verified through high-precision simulation. After confirming that its actual performance matches the target, the parameters and performance information are integrated into a standard digital file to directly drive automated construction.
Owner:CCCC THIRD HARBOR ENGINEERING CO LTD

Automatic driving lane changing decision-making method and device and storage medium

PendingCN121947495ASolve computing bottlenecksEfficient search spaceBiological modelsKnowledge based modelsAlgorithmEngineering
The invention discloses an automatic driving lane changing decision-making method and device and a storage medium, and the method combines frequency space action marking (FAST) and Monte Carlo tree search (MCTS): firstly, compressing and coding a continuous driving action sequence into low-dimensional discrete marks by using a FAST model, and constructing an efficient semantic action space; further, a strategy neural network is trained, diversified candidate action marking sequences are predicted in the marking space according to the current environment state, and a plurality of smooth intention tracks are obtained after FAST decoding; and finally, expanding and simulating the intentional tracks as feasible actions of the MCTS, and selecting a lane changing strategy with the optimal long-term benefit through a search evaluation mechanism. According to the method, the search space of the MCTS is greatly reduced through discretization compression of the action space, so that accurate evaluation of decision-making long-term benefits becomes possible, and anthropomorphic, safe and comfortable lane changing behaviors can be efficiently generated.
Owner:JIAXING UNIV

Multi-unmanned aerial vehicle content caching and trajectory planning method based on federal deep reinforcement learning

ActiveCN119071816ASolve the problem of fair communicationfully exploreInternal combustion piston enginesParticular environment based servicesSimulationUncrewed vehicle
The invention provides a multi-unmanned aerial vehicle content caching and trajectory planning method based on federal deep reinforcement learning, and the method comprises the steps: constructing an air-ground wireless communication caching network, and obtaining the cumulative average throughput of the air-ground wireless communication caching network; based on the cumulative average throughput, constructing an optimization objective function of the trajectory of the unmanned aerial vehicle; constructing a cache replacement model in the unmanned aerial vehicle as a first MDP model, and constructing the trajectory design of the unmanned aerial vehicle as a second MDP model; and calculating global parameters of the first MDP model and the second MDP model by adopting a federal deep reinforcement learning algorithm based on the optimization objective function, and performing multi-unmanned aerial vehicle trajectory planning and cache replacement based on the global parameters. According to the method, more sufficient exploration can be carried out on the premise of protecting privacy, so that the problems of cache hit and fair communication of users are solved.
Owner:BEIJING UNIV OF POSTS & TELECOMM

Multi-domain oriented joint strategy selection and budget allocation method and system

PendingCN122712271Afully explorefast convergence
The application discloses a multi-domain-oriented joint strategy selection and budget allocation method and system, relates to the technical field of artificial intelligence and machine learning, and comprises the following steps: acquiring an unlabeled sample pool divided into a plurality of heterogeneous domains in advance and historical learning gains of each heterogeneous domain; performing feedback-driven domain budget allocation calculation based on the historical learning gains of each heterogeneous domain to obtain query sample quotas of the domains; performing strategy selection through preset Thompson sampling based on the query sample quotas of the domains to obtain an optimal strategy; and screening the unlabeled sample pool of the plurality of heterogeneous domains based on the optimal strategy to obtain candidate samples; and calculating a budget-aware composite reward of the candidate samples based on a preset gating coefficient, so that higher classification accuracy and lower labeling cost are achieved.
Owner:NANJING UNIV OF POSTS & TELECOMM +1