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

35results about How to "Reduce optimization time" patented technology

Mould temperature self-adaptive adjusting method and system based on machine learning

The invention provides a mold temperature self-adaptive adjustment method and system based on machine learning, and relates to the technical field of temperature adjustment, and the method comprises the steps: collecting real-time temperature data and process parameters related to the temperature in a mold production process, carrying out the feature extraction of the real-time temperature data and the process parameters related to the temperature, obtaining a plurality of candidate features, and carrying out the feature extraction of the plurality of candidate features; according to the obtained target temperature adjustment key feature set, a multi-target optimization model of mold temperature uniformity and product quality is constructed, and an optimal solution of the multi-target optimization model is obtained; the method comprises the following steps: constructing a temperature adjustment model, solving the temperature adjustment model to obtain an initial temperature adjustment strategy, issuing the initial temperature adjustment strategy to an edge computing node of a workshop site, triggering a strategy online updating mechanism based on behavior cloning when an abnormality is detected, and performing adaptive optimization on the initial temperature adjustment strategy by using newly collected temperature data during the abnormality. And generating a target temperature adjusting strategy for guiding real-time control of the mold temperature.
Owner:NINGBO LONGYUE TECH CO LTD

Wind power plant yaw angle optimization control model construction method and device and control strategy and device

The invention relates to a wind power plant yaw angle optimization control model construction method and device and a control strategy and device. The construction method comprises the following steps that 1, position information, environment information and fan parameters of all wind turbine generators in a wind power plant are obtained; 2, transforming the coordinates of the wind turbine generator to obtain wake flow environment parameters of the wind power plant; 3, constructing an initial wake flow directed graph, performing sparse processing on the initial wake flow directed graph, and obtaining and constructing a wind turbine generator set subset based on a sparse wake flow directed graph; 4, constructing a wind power plant yaw angle optimization control model based on the wind turbine generator subsets, and training the yaw angle optimization control model based on a wind power plant environment; the device comprises a data acquisition module, a parameter acquisition module, a relation construction module and a model construction module, the operation resources of a yaw control strategy are reduced, the optimization time is shortened, the yaw angle control effect of the wind power plant in the complex and changeable wind direction environment is effectively improved, the total output power of the wind power plant is improved, and the better optimization effect and robustness are achieved.
Owner:HUANENG CHENGDE WIND POWER GENERATION CO LTD

Wind power plant wind speed prediction method, system and equipment and storage medium

The invention discloses a wind power plant wind speed prediction method, system and device and a storage medium, and the method comprises the steps: optimizing the white noise amplitude weight and noise addition times in adaptive noise ensemble empirical mode decomposition CEEMDAN through employing an improved energy valley optimization algorithm IEVO, and carrying out the CEEMDAN decomposition of the historical data of a wind power plant; the decomposed data is preprocessed by adopting sample entropy SE, so that the calculation complexity of the data is reduced; for the preprocessed data, introducing a random forest algorithm RF feature selection of a heuristic strategy for optimization, and eliminating redundant features; converting the optimized data from one-dimensional time sequence data into a two-dimensional image by using a GASF (Grubby Amplitude Shift Function), and extracting image features; the extracted image features are sent to a time sequence block converter Patch TST model for wind speed prediction, and a training algorithm GPTuner based on a gradient boosting decision tree is introduced into the Patch TST model to adjust model parameters; compared with a traditional method, the accuracy of wind speed prediction can be effectively improved, and stable operation of a wind power plant is guaranteed.
Owner:HUAIYIN INSTITUTE OF TECHNOLOGY

Magnetic pole optimization method for reducing torque ripple of permanent magnet synchronous motor

The invention discloses a magnetic pole optimization method for reducing torque ripple of a permanent magnet synchronous motor. The magnetic pole optimization method comprises the following steps: step 1, analyzing a stator magnetomotive force and a stepped permanent magnet excitation magnetic potential during load operation by using an analytical method; step 2, obtaining air gap flux density harmonic amplitudes and orders respectively generated by the armature magnetic potential and the permanent magnet excitation magnetic potential; 3, solving a resultant magnetic field under the combined action of the permanent magnet and the armature magnetic potential, calculating the total output torque during load operation, and obtaining the relation between the working harmonic wave and the average output torque and the torque pulsation; and 4, based on the relationship between the working harmonic waves of the magnetic field and the output torque, the air gap flux density amplitude of the order related to the average torque is kept unchanged by adjusting the parameters of the stepped magnetic poles, and the air gap flux density amplitude of the order related to the torque pulsation is reduced. The motor obtained through the method can output the expected average torque, meanwhile, the torque pulsation is reduced, and the better torque performance is achieved; and good economic benefits can be generated.
Owner:南京思来智能科技有限公司

Distributed AI training service-oriented 6G computing power network adaptive splitting federated learning method

The invention discloses a distributed AI training service-oriented 6G computing power network adaptive splitting federated learning method, and belongs to the technical field of communication networks. The method comprises the following steps: establishing a 6G computing power network model, and constructing a distributed AI training service-oriented adaptive splitting federated learning model; analyzing the time delay of each intelligent terminal in the model training stage and the model aggregation stage; constructing a service total time delay minimization optimization problem; and carrying out joint optimization on the model segmentation mode, cooperative node selection and a multi-domain resource scheduling mode in the model training stage and the model aggregation stage by utilizing a shortest path search algorithm. Through joint optimization of a model segmentation mode, node selection and multi-dimensional resource allocation in a multi-base-station scene, the problem of network congestion caused by the fact that a single-base-station learning framework processes a large number of intelligent terminal model aggregation is relieved, the method adapts to heterogeneous intelligent terminal computing power and differentiated channel quality in an actual network, and the method is suitable for large-scale popularization and application. And the efficiency and generalization ability of model training are improved.
Owner:NANJING UNIV OF POSTS & TELECOMM

Fracturing parameter optimization method considering stress disturbance between fractures

PendingCN119066899AEffectively guide on-site fracturing constructionIncrease productionFluid removalDesign optimisation/simulationElement modelHorizontal wells
The invention belongs to compact conglomerate oil reservoir development, and discloses a fracturing parameter optimization method considering stress disturbance between fractures, which comprises the following steps: S1, calibrating rock mechanical parameters of a horizontal well section; s2, establishing a finite element model by adopting a node splitting method, simulating a perforation process by adopting a pipe flow unit and a perforation unit, and establishing an in-segment multi-cluster crack expansion finite element model considering stress disturbance; s3, solving a multi-cluster crack expansion path under different segment-cluster-hole combination parameters under stress disturbance by adopting a Newton iteration method; s4, a crack difference coefficient is calculated, and if the difference coefficient is smaller than a judgment threshold value, the corresponding fracturing parameter is the optimal scheme; otherwise, adjusting the parameter and recalculating until the difference coefficient is smaller than the judgment threshold value. According to the method, the finite element model considering the stress disturbance between the fractures is established based on cohesion node splitting, the optimal section-cluster-hole combination parameters are determined based on the fracture difference coefficient, compact conglomerate oil reservoir fracturing construction can be effectively guided, and the fracturing effect and the single well yield are improved.
Owner:PETROCHINA CO LTD

Local parametric modeling and optimizing method, device and equipment for automobile air conditioner pipeline

The invention discloses a local parametric modeling and optimizing method, device and equipment for an automobile air conditioner pipeline, and relates to the technical field of automobile air conditioner system optimizing.The method comprises the steps that a pipeline model of an air conditioner system is obtained, a to-be-optimized area is deleted, and the pipeline model with the to-be-optimized area deleted is imported into simulation software; re-modeling the to-be-optimized area to obtain a pipeline local model, and fusing the pipeline local model with the pipeline model imported into the simulation software to obtain a fused model; selecting model parameters for optimizing the local model of the pipeline, and setting the model parameters to obtain a plurality of pipeline performance optimization schemes; and performing performance simulation calculation on the fused model based on a pipeline performance optimization scheme, and determining an optimal pipeline performance optimization scheme according to a simulation result. The optimization time of the automobile air conditioner pipeline can be shortened, and the optimal design scheme of the pipeline can be quickly obtained.
Owner:DONGFENG MOTOR GRP

Living body detection method and system based on language guide picture feature extraction

The invention discloses a living body detection method and system based on language guide picture feature extraction, and the method comprises the following steps: carrying out the preprocessing of a video data set for face fraud detection, and constructing a picture encoder and a text encoder; constructing a picture-picture projector and a text-picture projector, constructing a contrast learning module to shorten the distance of corresponding projection features, and generating a plurality of groups of text cue words by a text design module; the method comprises the following steps: constructing a text screening module, constructing a frozen text encoder module, freezing a pre-training weight of a text encoder, calculating a text cue word which is most matched with a human face through cosine similarity calculation and binary cross entropy, and judging whether the human face is true or false by a classifier according to whether the text cue word is described. And supervising and training three output results of the comparison learning module, the picture text feature alignment module and the classifier, and obtaining a face true and false prediction result based on the trained model. The method is higher in face authenticity judgment accuracy and better in generalization performance.
Owner:SOUTH CHINA UNIV OF TECH

Simulation evaluation and optimization method and system for parachute opening impact strength of wheeled air-drop vehicle

The invention belongs to the technical field of airdrop and special vehicles, and particularly discloses a wheel type airdrop vehicle parachute opening impact strength simulation evaluation and optimization method and system. Comprising the following steps: performing parachute opening dynamics simulation to obtain an accurate boundary of parachute opening strength impact simulation; performing whole vehicle parachute opening strength dynamic simulation analysis to obtain an analysis result of vehicle body strength and deformation, evaluating the analysis result, outputting design parameters if the analysis result meets requirements, and otherwise, performing failure reason analysis; air-drop system modal analysis is added, and failure reasons are judged; according to failure reasons, partial grids are intercepted or static simulation is adopted to replace dynamic simulation, and a reduction optimization model is obtained; and based on HyperStudy, carrying out multi-objective optimization according to the structural characteristics of the parts of the failure parts and failure reasons. According to the method, high-precision calculation of the re-loading air-drop process of multi-stage parachute opening of multiple parachutes is achieved, and scientific optimization of the parachute opening strength structure of the air-drop vehicle is achieved by optimizing the simulation means.
Owner:DONGFENG OFF ROAD VEHICLE CO LTD

Genetic programming and reinforcement learning fused interpretable intelligent flow control method

According to the interpretable intelligent flow control method, an automatic differential mechanism in a neural network is introduced into linear genetic programming, an explicit expression obtained by the linear genetic programming is automatically adjusted through a gradient descent algorithm, and the time needed by control law optimization can be greatly shortened; compared with a neural network control law, the explicit symbolic expression control law has higher interpretability, so that researchers can better understand a control mechanism and find new physical knowledge; the framework can set state sensors and different reward functions according to different control targets, and has very high universality.
Owner:AIR FORCE UNIV PLA

Method for optimizing periodic multi-phase modulation radar interference based on simulated annealing algorithm

The invention discloses a periodic multi-phase modulation radar interference optimization method based on a simulated annealing algorithm. The method comprises the following steps: S1, setting an initial temperature of annealing; a feature vector matrix PTs is randomly generated, a modulation phase sequence is randomly generated, and the value range of each random phase value is [-pi, pi]; the fitness interpolation sequence is used for recording the interpolation of the current solution and the new solution of the phase sequence, and is negative; and accepting probability: accepting the new solution at a certain probability when the fitness of the new solution is lower than that of the current solution. S2, calculating a feature vector matrix FTs according to the PTs and the modulation phase sequence: simulating a process that a jammer receives a physical target and sends an interference signal, defining a related phase period and a time step length, and carrying out PMPM operation on the processed PTs to obtain FTs; and S3, pairing the nearest PT and FT, and then performing summation operation on the distances of all PT and FT pairs as an output result of the fitness function. S4, disturbance is given to the current solution, and if the sum of the distances obtained by the new modulation phase sequence is smaller than the current value, the new solution is accepted; otherwise, if the sum of the distances obtained by the new modulation phase sequence is larger than the current value, the new solution is accepted at a certain probability and serves as the current solution. S5, circulating annealing is a core structure of a simulated annealing algorithm model, the temperature is reduced after annealing, the modulation phase sequence variation amplitude is reduced, and the disturbance giving and accepting process is repeated; and when the temperature reaches the final temperature, a global optimal solution is obtained.
Owner:ZHEJIANG UNIV OF TECH

Defect positioning method and system based on language model

The invention relates to the technical field of workpiece detection, in particular to a defect positioning method and system based on a language model, and the method comprises the steps: S100, obtaining an image of the surface of a workpiece, and carrying out the preprocessing; s200, inputting the preprocessed image data into a preliminary positioning model to obtain a preliminary positioning result; s300, generating semantic description according to the image features extracted by the CNN; querying a historical image according to the preliminary positioning result, and extracting historical image features according to the CNN to generate a target semantic description; s400, converting the semantic description into a semantic vector, and converting the target semantic description into a target semantic vector; s500, the semantic vector is optimized; and S600, determining the position of the workpiece defect through the optimized semantic vector to obtain a current positioning result, and comparing the current positioning result with the preliminary positioning result to obtain a final position. According to the method, the workpiece defect detection efficiency and accuracy can be improved.
Owner:CHONGQING UNIV

Method for automatically generating oscillator pixelated resonant cavity based on knowledge-driven reverse design

The invention provides a method for automatically generating a pixelated resonant cavity of an oscillator based on knowledge-driven reverse design. The method comprises the following steps: determining a topological region range of VCO resonant cavity design; determining a reverse design target; a priori knowledge driving pixel matrix drawing strategy is established, pixelated inductor topological structure drawing is completed in the topological region based on the drawing strategy, and a primary pixelated inductor topological structure quality factor and a secondary pixelated inductor topological structure quality factor are calculated; according to a reverse design target, searching a Q value of a primary pixelated inductance topological structure from a binary n * n matrix assembly at a given target frequency, and meanwhile, achieving a maximized optimal solution to obtain an optimal pixel topological structure; and constructing the voltage-controlled oscillator in combination with the optimal pixel topological structure. According to the method, batch automatic simulation and optimization of the optimal resonant cavity structure can be realized, and compared with manual design, the time cost is saved, and meanwhile, the performance is further improved.
Owner:NANJING UNIV OF SCI & TECH

A group target RCS optimization method based on space mapping and multi-level electromagnetic modeling

The application discloses a group target RCS optimization method based on space mapping and multi-stage electromagnetic modeling, and the method comprises the following steps: under a given RCS threshold, for initial group target space distribution positions and postures, a hummingbird optimization algorithm is combined with an electromagnetic scattering solver based on a physical optical method to perform parameter optimization; the optimal solution of a coarse model is used as an initial design value of a fine model, a mode reconstruction algorithm is combined with a fast multipole technique to accelerate electromagnetic coupling calculation between targets; if the fine model result meets the RCS threshold requirement, the optimization is terminated; if the threshold is not met, a space mapping relationship between the coarse model and the fine model is established through parameter extraction, the next fine model design value is predicted, and RCS is recalculated for threshold judgment until convergence is achieved. The space mapping algorithm is combined with the coarse model with high calculation efficiency and the fine model with high precision, RCS optimization of the group target formation is realized quickly and accurately under the premise of ensuring electromagnetic calculation precision.
Owner:NANJING UNIV OF SCI & TECH

An optimization design method and system for isolation sections based on FFD method

The present invention discloses an optimization design method and system of an isolation section based on the FFD method, the method comprising: based on the shape of the air inlet outlet and the combustion chamber inlet, by adjusting the flow area change law in the isolation section, the first aerodynamic performance optimization of the isolation section shape is performed to obtain the discrete points of the initial isolation section; a cuboid that completely envelops the isolation section is divided in the local coordinate system, and a number of evenly distributed control points are selected on the cuboid to form a control point grid; the local coordinates of each control point in the control point grid are used as variables, and the total pressure recovery coefficient of the isolation section is used as the optimization target, and the global optimization algorithm is used to perform the second aerodynamic performance optimization, and the discrete points of the isolation section with the best aerodynamic performance are obtained, and a three-dimensional entity is generated. The present invention is applied to the field of hypersonic aircraft technology, and can significantly improve the total pressure recovery coefficient of the isolation section outlet. For hypersonic aircraft where every centimeter counts, the optimization effect is very considerable.
Owner:NAT UNIV OF DEFENSE TECH

A mapping method based on joint optimization of point, line and surface features and dynamic segmentation

The present invention discloses a mapping method and device for jointly optimizing point, line and surface features and dynamic segmentation, the method comprising: obtaining point, line and surface features according to color images and depth images to generate an initial map with these features, dividing the initial map into different areas according to the depth value of the depth image and assigning preset weight values ​​to generate a static probability map; then constructing a target function for jointly optimizing posture and dynamic object segmentation by constructing a reprojection error term and a regularization term to calculate the posture state and the weight estimation value of the features of each area in the image, thereby updating and optimizing the map elements of each area in the static probability map and constructing a map surface. The present invention can make more full use of environmental information to enhance the robustness of positioning and map construction by optimizing map weights and postures, and at the same time reduce the amount of calculation by dividing the map area and assigning weights, thereby improving the real-time performance of map construction.
Owner:SUN YAT SEN UNIVERSITY SHENZHEN +1

Low-noise tire pitch initial arrangement generation method and system and computer program product

The invention relates to the technical field of tire design, in particular to a low-noise tire pitch initial arrangement generation method and system and a computer program product. According to the method, the length difference of the adjacent pitches in the pitch arrangement and the continuous arrangement number of the same pitches are strictly controlled, and the uniform and low-noise initial population is generated, so that the optimization efficiency and precision of the genetic algorithm are improved. According to the method, 200 pitch arrangements meeting noise control requirements are automatically generated through programming, only three seconds are needed, and the optimization time is greatly shortened compared with five minutes of manual screening after traditional random generation. The optimized initial arrangement not only reduces the noise level of the tire, but also can effectively prolong the service life of the tire and improve the comfort and performance of the tire. The method is suitable for the design of various types of tires, including all-steel and semi-steel radial tires, engineering tires and the like. The method has the advantages of high efficiency, accuracy and automation, and a more reliable and economical optimization tool is provided for tire manufacturers.
Owner:ZHONGCE RUBBER GRP CO LTD +1

Continuum structure topological optimization method and system based on variable density method theory

The invention discloses a continuum structure topological optimization method and system based on a variable density method theory, and the method comprises the steps: carrying out the discretization of a continuum structure optimization region, and forming a plurality of middle density units; based on a variable density method theory, constructing a topological optimization model which takes the unit density of each intermediate density unit as a design variable, takes a preset volume fraction as a constraint condition and takes minimization of structural flexibility as a target; and adopting an interpolation model which punishes the unit density by an exponential function, and carrying out iterative optimization solution of eliminating gray units on the topological optimization model to obtain a topological optimization scheme. The method is higher in convergence speed and higher in capability of searching the optimal distribution of the material.
Owner:JIANGSU UNIV OF TECH

Spring contact finger structure design method and system based on dung beetle optimization algorithm

The invention belongs to but not limited to the technical field of gas insulation, and particularly relates to a spring contact finger structure design method and system based on a dung beetle optimization algorithm, and the method comprises the steps: obtaining a three-dimensional structure model of a to-be-optimized spring contact finger, and the three-dimensional structure model comprises geometric parameters of a spring contact finger body, a conductor domain and a spring contact seat; boundary conditions are applied to the spring contact finger body, the conductor domain and the spring contact seat structure, and the contact temperature rise of the contact finger is solved through an electric-thermal coupling model; setting the diameter of a spring wire of the spring contact finger, the intermediate diameter of the spring, the number of turns of the spring, the inclination angle of a single-turn spring and the angle of a V-shaped groove of the contact seat as d, phi, n, alpha and beta, and respectively changing structural parameters for multiple times to carry out electrothermal coupling analysis on the spring contact finger to obtain a contact temperature rise data set; based on a dung beetle optimization algorithm, optimizing the spring contact finger structure by setting a decision variable and an optimization target, wherein the optimization target is that the contact temperature rise of the spring contact finger is minimum; and outputting the optimal structure parameters of the spring contact finger.
Owner:SHENZHEN POWER SUPPLY BUREAU

Energy storage power station charging and discharging optimization method based on lattice sampling and Levy flight genetic algorithm

The invention discloses an energy storage power station charging and discharging optimization method based on lattice sampling and a Levy flight genetic algorithm, which is an energy storage power station charging and discharging optimization method taking minimum cost and maximum benefit of an energy storage power station as objective functions and taking charging and discharging of the energy storage power station and generating capacity of a conventional unit as constraints. A charge and discharge optimization problem of an energy storage power station is converted into a problem of solving a charge and discharge Pareto frontier solution set, an initial population generation method based on lattice sampling is provided, and it can be ensured that initial populations of charge and discharge of the energy storage power station and power generation of a conventional unit are uniformly distributed in a constraint space; a filial generation population generation method based on Levy flight variation is provided, the algorithm can be effectively prevented from falling into a local optimal solution, and finally an energy storage power station charging and discharging optimization strategy with the lowest cost and the maximum benefit can be obtained.
Owner:ECONOMIC TECH RES INST OF STATE GRID HENAN ELECTRIC POWER +2

Lightweight simulation optimization method for integrated door ring of automobile and related equipment

The invention provides a lightweight simulation optimization method for an integrated door ring of an automobile and related equipment. The method comprises the following steps: establishing a whole automobile model in an initial state; determining a thickness partition, an initial splicing position and a splicing position change area of the integrated door ring; design variables, constraint conditions and optimization targets are defined, the design variables comprise thickness variables and splicing position variables of all thickness subareas of the integrated door ring, the splicing position variables refer to distances between a plurality of sub-areas which divide a splicing position change area at equal intervals and corresponding initial splicing positions, and the constraint conditions comprise vehicle collision indexes and vehicle collision indexes; the optimization objectives comprise improvement of the vehicle collision performance and reduction of the total weight of the integrated door ring; and solving the optimal design variable combination based on the constraint condition and the optimization target. According to the method, the thickness and the splicing position of the integrated door ring can be jointly optimized, a better integrated door ring design scheme can be found, the design efficiency is improved, and the personnel cost is reduced.
Owner:SAIC VOLKSWAGEN AUTOMOTIVE CO LTD

Nested watershed hydrological model parameter optimization method

The invention discloses a nested watershed hydrological model parameter optimization method, which comprises the following steps of: determining a research area of a watershed, layering the research area by utilizing elevation in the research area, and obtaining n sub-areas with different elevation levels; constructing a hydrological model equation of each elevation level sub-region; constructing a vector about dynamic parameters, performing crossover variation on the dynamic parameters in the vector by using a fitness function, and screening an optimal offspring individual vector; and sequentially optimizing the dynamic parameters of the hydrological model equation of each elevation level sub-region from top to bottom from the elevation level sub-region with the maximum elevation until the optimization of the dynamic parameters of the hydrological model equation of the research region is completed. According to the nested type watershed hydrological model parameter optimization method provided by the invention, the optimization time required by watershed parameter optimization is greatly shortened, and the parameter optimization efficiency is effectively improved.
Owner:水利部信息中心(水利部水文水资源监测预报中心)

Mold temperature adaptive adjustment method and system based on machine learning

The present invention provides a method and system for adaptively adjusting mold temperature based on machine learning, which relates to the field of temperature adjustment technology, including collecting real-time temperature data and temperature-related process parameters in a mold production process, performing feature extraction on the real-time temperature data and the temperature-related process parameters to obtain multiple candidate features, and constructing a multi-objective optimization model of mold temperature uniformity and product quality according to the obtained target temperature adjustment key feature set to obtain the optimal solution of the multi-objective optimization model; constructing a temperature adjustment model, and obtaining an initial temperature adjustment strategy by solving the temperature adjustment model, and sending it to an edge computing node at a workshop site at the same time, and when an abnormality is detected, triggering a behavior cloning-based online strategy update mechanism, using the newly collected temperature data at the time of the abnormality to adaptively optimize the initial temperature adjustment strategy, and generating a target temperature adjustment strategy for guiding the real-time control of the mold temperature.
Owner:NINGBO LONGYUE TECH CO LTD

Method and system for preparing low-carbon cementing material by utilizing solid waste resources

The invention relates to the technical field of cementitious material preparation, in particular to a low-carbon cementitious material preparation method and system utilizing solid waste resources, and the method comprises the steps: obtaining a solid waste component database, constructing a plurality of cementitious material reference data based on the solid waste component database and a plurality of historical cementitious materials, performing high-performance material selection in the original solid waste material group based on the multiple pieces of cementing material reference data and the performance weight group to obtain a target solid waste material group, performing response surface optimization on the target solid waste material group to obtain an optimal solid waste proportion group, and inputting the optimal solid waste proportion group and the target solid waste material group into a target random forest model to obtain a target random forest model; and preparing the target low-carbon gel on the basis of the optimal solid waste ratio group, the target solid waste material group, the curing conditions and the exciting agent ratio. The accuracy of performance prediction of the cementing material and the efficiency of the preparation process can be improved.
Owner:SHANDONG YONGZHENG IND TECH RES INST CO LTD +3

An intelligent optimization method for cylinder piston sealing groove based on a new improved particle swarm algorithm

The present invention provides an intelligent optimization method for cylinder piston sealing grooves based on a new improved particle swarm algorithm, including the following steps: referring to a mechanical design manual and designing a plurality of sealing grooves of different sizes for the piston based on experience; building a cylinder motion trajectory tracking PID control test platform; preliminarily determining the value range of the PID controller parameters to be optimized to form a search space; setting the initial parameters and fitness function of the improved particle swarm algorithm; using the improved particle swarm algorithm to optimize the cylinder PID motion trajectory tracking control parameters when the sealing ring is located in different sealing grooves, and selecting the sealing groove with the best tracking accuracy. The new improved particle swarm algorithm proposed in the present invention can dynamically coordinate the relationship between the local search and the global search of the algorithm, and can effectively jump out when the particles fall into a local optimum. In addition, through the method proposed in the present invention, the traditional leakage prevention requirements in the design of the cylinder piston sealing groove are guaranteed, and the higher-precision motion servo control of the cylinder is also achieved.
Owner:JIANGSU UNIV

Automatic layout and optimization method for engineering machinery assembly workshop based on logistics simulation and genetic algorithm

The invention relates to an engineering machinery assembly workshop automatic layout and optimization method based on logistics simulation and a genetic algorithm, and belongs to the field of logistics simulation and genetic algorithms. According to the invention, the genetic algorithm module, the data processing and storage module, the simulation module, the evaluation analysis module and the visualization module are integrated on the logistics simulation platform, so that automatic layout and optimization of the discrete assembly workshop are realized. The method specifically comprises the steps that a genetic algorithm module is used for encoding functional areas and generating samples, a data processing and storage module is used for converting sample encoding information into coordinates needed by simulation, a simulation module is used for simulating operation and outputting index data, an evaluation analysis module is used for calculating sample fitness values, and a simulation result is obtained. And the genetic algorithm module performs selection, crossover and mutation operations according to the fitness value, and performs iterative optimization to obtain an optimal layout scheme. And the visualization module is used for displaying the simulation process and result. The optimization efficiency of the complex production system is improved, and the limitation of the prior art is overcome.
Owner:CMCU ENG

A method and apparatus for optimizing parameters of lightweight hydrogen storage cylinders based on adaptive optimization.

This invention discloses a method and apparatus for optimizing parameters of lightweight hydrogen storage cylinders based on adaptive optimization. The method includes: constructing a multi-agent collaborative optimization framework to define the functional boundaries of ant colony agents, NSGA-II agents, quantum annealing agents, and surrogate model agents, and clarifying the information interaction rules between agents; performing parameter collaborative optimization based on the multi-agent collaborative optimization framework according to collected design parameter samples and corresponding performance data of the hydrogen storage cylinder; dynamically adjusting the collaborative weights and optimization strategies of each agent by real-time monitoring of surrogate model prediction errors, population diversity, and algorithm convergence speed; selecting candidate solutions from the final Pareto front for real-world simulation verification; if the performance meets the design requirements, outputting the optimal parameter combination for the hydrogen storage cylinder; if not, feeding back the simulation results to the surrogate model agent for updating, and re-performing the iterative optimization process until the optimal parameter combination that meets the requirements is obtained.
Owner:BEIJING CHINATANK IND

Segmentation and calibration method of pulmonary bronchi

ActiveCN112330686Breduce noiseIncrease the number of branchesImage enhancementImage analysisVoxelAirway tree
The present invention discloses a method for segmenting and calibrating pulmonary bronchi, comprising: step S1: extracting a pulmonary airway tree region from image data; step S2: setting a voxel region of interest according to the pulmonary airway tree region, and performing sharpening and filtering processing on the voxel region of interest; step S3: classifying the voxel region of interest through a deep learning convolutional neural network according to the processed voxel region of interest, removing leakage and tracing airway branches, and obtaining an optimized pulmonary airway tree region; step S4: extracting airway tree structure information from the optimized pulmonary airway tree region, and obtaining a set of candidate names for each airway and a weight of each candidate name through a pulmonary airway name labeling model according to the pulmonary airway tree region and the airway tree structure information; step S5: optimizing the name of each group of airway trees according to the weights, implementing accurate and automatic labeling of airway tree names, and obtaining airway name information.
Owner:罗雄彪 +3

Chip layout layer merging method, device and equipment and computer storage medium

The invention discloses a chip layout layer merging method, device and equipment and a computer storage medium. The method comprises the steps of obtaining a layout processing script file; according to a first operation command, determining a first layer which is operated by the first operation command, the first operation command being any one of the plurality of operation commands; executing operation corresponding to the first operation command on the first image layer to obtain a second image layer; according to the execution sequence of the operation command, judging whether the second layer is subjected to operation operation by other operation commands or not to obtain a judgment result; according to the category label of the first operation command and the judgment result, determining whether to perform merging operation on the target graphs in the second graph layer; and under the condition of determining to perform the merging operation on the target graphs in the second graph layer, performing the merging operation on the target graphs in the second graph layer. According to the embodiment of the invention, the layout optimization efficiency can be improved.
Owner:ORIENTAL CRYSTAL MICROELECTRONICS TECH (SHANGHAI) CO LTD

Method for optimizing official document semantics based on domain knowledge base and large model agent

PendingCN122509191AStable, reliable and authoritative data supportImprove professionalism
This invention relates to the field of semantic intelligence optimization technology, and particularly to a method for semantic intelligence optimization of official documents based on a domain knowledge base and a large-scale intelligent model agent. The method includes: acquiring the text to be optimized and a set of reference texts; constructing a semantic loss function based on the text to be optimized and the set of reference texts, the semantic loss function including an intent consistency loss component and an expression normativity loss component; and performing semantic optimization in two stages with the goal of minimizing the total semantic loss function: in the first stage, the core intent of the user text is fused and aligned with that of the superior text to reduce the intent consistency loss component; in the second stage, the user text is matched and adapted to the normative expressions of the superior text to reduce the expression normativity loss component. This invention constructs a semantic loss function that includes intent consistency loss and expression normativity loss, achieving high-fidelity semantic alignment between the generated text and the reference standard.
Owner:YUNNAN YUNTIANHUA INFORMATION TECHNOLOGY CO LTD