62 results about "Performance comparison" patented technology

The invention discloses a multi-unmanned aerial vehicle cooperative task allocation and path planning method based on a genetic algorithm, and relates to an unmanned aerial vehicle path planning method. And operating a Dijkstra algorithm to accurately solve the shortest feasible path between all airports and task points, and finally generating a global path cost matrix for quick query. A complete and safe flight path that each unmanned aerial vehicle starts from an airport, sequentially accesses task points and returns is graphically displayed, a convergence curve of an algorithm, population diversity changes and performance comparison data under different task scales, unmanned aerial vehicle numbers and obstacle densities can be output, and a parameter sensitivity analysis function is supplemented. And the effectiveness, the stability and the practical value of the proposed method in a static urban environment are comprehensively verified.

The invention provides a front-end development performance analysis and construction configuration reverse optimization method. Performance timeline data, including a resource loading time sequence, main thread task decomposition and key rendering performance indexes, of a browser developer tool are automatically collected in a running environment, and all-around monitoring of page running performance is achieved; based on the performance bottleneck of correlation between data identification and construction configuration, a low-efficiency mode of relying on artificial experience analysis is broken through; the performance problem type is mapped into the specific configuration parameter through the preset rule base, the optimization configuration item is automatically generated, and the problem that general configuration lacks pertinence is solved; an output strategy is further dynamically adjusted in combination with environmental parameters, and it is ensured that configuration adapts to multi-scene requirements; and finally, performance comparison data before and after configuration change is displayed through a visual report, a closed-loop feedback mechanism is formed, the developer optimization threshold is remarkably reduced, and the cross-environment performance consistency and iteration efficiency of front-end applications are improved.

The invention provides an A / B link performance comparison and strategy optimization method and system based on service flow, and belongs to the field of network performance monitoring and network strategy verification. The method comprises the following steps: firstly, performing bypass collection on real service traffic to obtain original data; copying the same copy of original data, injecting the original data into the link A and the link B at the same time, and then respectively collecting service flows of the link A and the link B; establishing a session alignment model, and judging whether the service traffic of the link A and the link B belongs to homologous traffic or not; after time drift compensation is carried out on sending timestamps of the homologous flow in the two paths, visible time sequence fields of homologous events are extracted respectively, differential indexes of the homologous events of the two paths on key time sequence parameters are calculated, and different percentile values of all the differential indexes under each parameter type in a preset time window are counted; and link performance comparison and strategy verification are carried out according to the difference index and the percentile value. According to the invention, the authenticity and efficiency of performance comparison and strategy optimization of different paths are improved.

A machine learning device includes an image set acquiring unit to acquire an image set including images, and an image set selecting unit to select an image set similar to the acquired image set from a plurality of image sets different from the acquired image set. In addition, the machine learning device includes a performance comparison unit, and a preprocessing acquisition unit to select a learning model from a plurality of machine-learned learning models based on a performance comparison result by the performance comparison unit and to acquire preprocessing performed on an image set used for machine learning of the learning model selected. Furthermore, the machine learning device includes a model learning unit to perform the acquired preprocessing on the acquired image set and to cause a learning model that has not yet trained to perform machine learning using the preprocessed image set.

The invention discloses a cross-scale virtual-real synchronization method and system for unmanned system cluster experiment teaching, and the method comprises the steps: S1, generating a corresponding digital twinborn simulation scene through a system according to a template parameter according to an algorithm template selected by a user in a graphical interface; s2, timestamp alignment and delay compensation are carried out through a cross-scale virtual-real synchronization engine, the digital twin simulation scene is synchronously mapped to a semi-physical simulation node and a physical cluster, and state cross-scale synchronization and synchronization error detection among digital twin, semi-physical simulation and the physical cluster are realized; s3, executing an algorithm task in a real object cluster, and performing real-time monitoring and control by a dynamic security fence; and S4, after the experiment is finished, generating an experiment report through the automatic evaluation engine according to the preset performance indexes. According to the invention, seamless migration among three modes can be realized without changing codes, and rapid verification, performance comparison and teaching reproduction of algorithms such as formation, obstacle avoidance and collaborative SLAM can be completed.

The invention relates to a nanoindentation and reliability characterization technology thereof, in particular to a heterogeneous material welding reliability characterization method applied to a brush type sealing structure. By means of the nanoindentation technology, mechanical properties such as hardness, elasticity modulus and plastic deformation of the welded joint are obtained by analyzing indenter deformation and indentation morphology. Meanwhile, indentation testing is carried out on different positions of the brush type sealing welding joint, and the performance comparison condition of all areas of the welding joint is obtained. Compared with a traditional reliability characterization means, the device and the method have the advantages that various areas of the heterogeneous welding joint including a base material, a heat affected zone and a fusion zone are tested under the nanoscale, various material performance indexes such as hardness, elasticity modulus and plastic deformation are measured at the same time, and the device and the method have high-precision and multifunctional testing capacity and are suitable for popularization and application. And moreover, the joint cannot be damaged or other properties cannot be influenced, and compared with a room-temperature stretching result, the nanoindentation technology has relatively high reliability and repeatability, and an accurate characterization result is obtained.

The invention relates to a fan low-efficiency unit identification control method and a medium, and the method comprises the steps: building a multi-dimensional power curve model fusing a plurality of environmental factors based on a machine learning algorithm, deploying intelligent monitoring equipment on each fan of a wind power plant, collecting key parameters in real time, and generating a fan operation monitoring data set; according to the collected monitoring data, bin-divided BIN curve fitting is carried out on the draught fan, performance expressions of the draught fan in different wind speed and wind direction intervals are analyzed, space-time performance comparative analysis is carried out in combination with historical operation data, and by comparing performance data of the draught fan in different time periods and different wind speed intervals, a low-efficiency time period and a low-efficiency reason are determined; by constructing the multi-dimensional power curve model and combining the warehouse BIN analysis and the space-time performance comparison technology, the low-efficiency unit identification accuracy rate is 100%.

The invention provides a multi-personality decision simulation and game method for military artificial intelligence. Simulation of an AI opponent model on complex human behaviors is enhanced through a DIKWP semantic framework. The system firstly configures personality parameters based on a psychological model (such as MBTI, big five personalities), and maps the personality parameters to an AI cognitive model to construct a behavior preference model; then, a noise injection algorithm is adopted to simulate emotion and cognitive deviation, and unique deviation of different personalities in decision making is reproduced; the multi-agent self-gaming engine enables AIs with different personality characteristics to repeatedly game in a red-blue confrontation environment, optimizes a strategy and evaluates winning rate distribution. And the decision fusion analysis module summarizes the data, generates personality performance comparison and behavior pedigree diagrams under each tactical situation, and predicts opponent behaviors. The DIKWP semantic integration interface ensures that a personality simulation result can be seamlessly connected with a knowledge graph and a strategic intention module of an existing AI system. According to the method, AI opponent modeling is enriched on the semantic level, the decision simulation degree of a real commander is improved, and as a supplement of an existing AI simulation system, the ability of military AI in the aspects of strategic pre-judgment and cognitive game is enhanced.

The application discloses a kind of dynamic partitioning method and system based on data skew model, it is related to big data technology field, including collecting data and pre-processing data, establish data skew evaluation model to predict pre-processed data, according to data characteristics, the data skew degree in job processing process is predicted, determines partition optimization strategy, designs evaluation experiment to compare dynamic partitioning with static partitioning, and repeatedly optimizes dynamic partitioning.This application proposes dynamic partitioning algorithm based on data skew model, which can select suitable partitioning strategy according to the skew degree of the data being processed, use the algorithm of three optimization methods based on Spark dynamic partitioning to process data performance comparison experiment, design and verify the universality and efficiency of the above dynamic partitioning scheme, can make the load balancing of the whole computing cluster, make full use of the computing resources of cluster, more efficiently complete data processing and calculation.

The invention relates to the technical field of formation lithology identification, in particular to a formation lithology automatic identification method based on a machine learning optimization model, which comprises the following steps: acquiring logging curves of a plurality of wells, and drawing a formation lithology distribution diagram based on the logging curves of the plurality of wells; carrying out denoising processing on the logging curve of each well by utilizing wavelet transform processing, and screening out representative data segments of various lithologic data to form a data set; performing model construction based on the data set by using a machine learning algorithm, and obtaining an automatic stratum lithology identification model through hyper-parameter optimization and performance comparison; and analyzing the contribution amount of the characteristic parameters of the stratum lithology automatic identification model by using a random forest algorithm, carrying out intersection analysis on the logging curve of each well in sequence, and determining an influence factor sequence of stratum lithology identification. According to the method, the machine learning model for automatically identifying the stratum lithology is constructed, the automatic identification of the stratum lithology can be realized, and the lithology identification efficiency is improved.

The utility model discloses a water treatment filter material performance contrast experiment device which comprises a water tank and a water inlet pipe, experiment liquid is pumped into the water tank through the water inlet pipe, the water tank is arranged in an inclined mode, a notch is formed in the bottom of the water tank, and fin grooves are formed in the outer side of the lower end of the water tank. The fin groove comprises a flow guide part opposite to the notch and a storage part mounted at the side lower end of the flow guide part, the flow guide part and the storage part form a containing chamber for containing a filter material, the side, away from the flow guide part, of the storage part is rotationally connected with the lower end of the water tank, and the flow guide part is in a fin shape. According to the utility model, relevant operation in a laboratory is facilitated, and the experiment efficiency is further improved.

The application discloses a kind of composite insulation coated metal soft magnetic powder and coating method and application.By system process flow implementation and performance comparison analysis, the soft magnetic powder composite insulation coating technology provided by the application shows significant advantages.Three-layer composite shell structure (flexible buffer layer+insulation layer+nanometer layer) effectively solves the problem of shell microcrack, insulation degradation and high dielectric loss under high frequency, high pressure and high temperature environment in traditional coating.The optimized key data: MLD / Al2O3 / [Al2O3 / HfO2] shell continuity rate reaches 99.8%, bulk resistivity is 5.2*10 9 Ω•cm, 100kHz loss is reduced by 67.1%, salt spray weight loss is only 38% of the control, fully meets the demand of high frequency magnetic device.The application provides a reliable material basis for the miniaturization and high efficiency of high frequency power electronic device.

The application relates to the technical field of intelligent coal mining, in particular to a coal mine fully-mechanized coal mining face intelligent operation online evaluation method based on dynamic correction of geological conditions, which comprises the following steps: collecting geological data of a working face and operation data of key equipment of the working face, obtaining key equipment automatic operation monitoring indexes of the fully-mechanized coal mining face, and a fully-mechanized coal mining face automatic operation index; correcting the key indexes under a standard condition based on geological conditions; calculating the key indexes under the influence of geological conditions based on the corrected key indexes, and calculating the fully-mechanized coal mining face automatic operation index based on the key indexes, the automatic operation monitoring indexes and the fully-mechanized coal mining face automatic operation index; correcting the key indexes under the standard condition and the key equipment automatic operation monitoring indexes of the fully-mechanized coal mining face, optimizing the fully-mechanized coal mining face automatic operation index, grading the operation level of the intelligent fully-mechanized coal mining face, and feeding back the evaluation result. The application can automatically quantify and strip the influence of geological condition differences, and realizes fair performance comparison between working faces.

Systems and methods are described for comparing execution of two or more artificial intelligence (AI) AI agents. A platform can provide a user interface (UI) that allows for selection or creation of multiple AI agents. The AI agents can utilize different agent objects, such as different prompts, datasets, or models. The AI agents can be displayed on a single UI screen, where execution of the AI agents is simultaneously simulated. The same inputs can be provided to the multiple AI agents, and the corresponding outputs can display on screen. The platform can also vectorize and compare the semantic similarity of the outputs, presenting an indication of the semantic similarity on the same UI screen.

The invention is suitable for the technical field of contactor detection, and provides a multi-channel direct current contactor control detection system, which comprises a plurality of programmable controllers, a data switch and an industrial personal computer, each programmable controller is connected with any direct current contactor and is used for acquiring opening and closing time data of the connected direct current contactor; the data switch is connected with each programmable controller and is used for transmitting each opening and closing time data; and the industrial personal computer is connected with the data switch and is used for carrying out data statistical analysis on the opening and closing time data and determining a performance detection result of each direct-current contactor so as to realize performance comparison of each direct-current contactor. According to the technical scheme provided by the invention, accurate detection and full-period statistics of the multi-channel opening and closing time interval of the direct-current contactor are realized, and real-time detection under the same aging test condition can be carried out on multiple direct-current contactors of different models at the same time; the method is used for comparing parameters such as service life and stability of direct current contactors produced by different processes.

The invention discloses an intelligent driving vehicle ADAS performance evaluation method, device, equipment and medium, and relates to the technical field of vehicle performance test.The method comprises the steps that multiple ADAS test scenes are created, multiple intelligent driving vehicles are tested to obtain test results, and the ADAS test scenes and the corresponding test results are stored in a scene test result database; defining performance evaluation rules and indexes based on ADAS performance evaluation requirements of the current vehicle so as to screen a corresponding ADAS test scene from the scene test result database, and setting scene evaluation parameters so as to calculate and obtain an ADAS performance score of the current vehicle; creating performance evaluation rules and indexes used for carrying out ADAS performance comparison with similar vehicles, and obtaining ADAS performance comparison scores of the similar vehicles; and obtaining a comprehensive scoring result of the ADAS performance of the current vehicle in combination with a weight calculation mode. The performance evaluation result is more accurate, and the cost is lower.

The present disclosure relates to a method for generating an object feature extraction model and an object recognition method. The method comprises: obtaining a plurality of to-be-integrated models from a plurality of object feature extraction models; performing feature extraction performance testing on the plurality of to-be-integrated models to obtain a first test result corresponding to each of the plurality of to-be-integrated models; selecting a current integrated model corresponding to a target test result from the plurality of to-be-integrated models; performing model integration processing on the current integrated model and a preset integrated model to obtain a target integrated model; performing extraction performance comparison processing on the target integrated model and the preset integrated model to obtain a target comparison result; and generating a target object feature extraction model based on the preset integrated model in a case where the target comparison result indicates that the object feature extraction performance of the preset integrated model is superior to the object feature extraction performance of the target integrated model. The embodiments of the present disclosure can improve the object feature extraction performance of the target object feature extraction model and improve the model deployment efficiency.

The invention relates to the technical field of formation temperature and pressure analysis, in particular to a formation temperature and pressure machine learning analysis method based on sparrow search algorithm optimization, and the method comprises the following steps: obtaining a logging curve, formation temperature data and formation pressure data; through analysis of a logging data scatter diagram matrix and a correlation thermodynamic diagram, the correlation relation between a logging curve and the formation temperature and the formation pore pressure is determined; and based on the correlation, establishing a machine learning model for quickly calculating the formation temperature / pressure by using the logging curve and the formation temperature / pressure data to obtain a formation temperature / pressure prediction model, and optimizing the parameters of the formation temperature prediction model by using a sparrow search algorithm. According to the method, a complete analysis process including data correlation analysis, multi-model training, SSA optimization and performance comparison and screening is constructed, and it is ensured that the selected optimal model has strong generalization ability through final evaluation on the first prediction set and the second prediction set.

The application discloses a real ship propeller performance prediction method, comprising the following steps: processing propeller model test data, performing Fourier transform to obtain pressure amplitude at the first five orders of blade frequency, and obtaining pressure amplitude theoretical baseline at each order under each state; real ship monitoring data preprocessing, eliminating abnormal data, and retaining data under normal weather; real ship fluctuating pressure monitoring value processing, performing cavitation judgment and real ship propeller performance comparison. The application can collect data of the real ship propeller under different load conditions and different weather conditions, accurately evaluate the performance change of the propeller, and provide performance decline early warning.

The invention provides an acquisition method and an extraction method of a house crack information extraction model, and the method comprises the steps: constructing a house data set, and carrying out the model training of each learning model in a pre-constructed model set through the house data set; performing performance comparison on the trained learning models, and selecting the learning model with the optimal performance as a target model of the working area; according to the method, the optimal extraction model matched with the house crack generation characteristics in the working area can be rapidly, efficiently and accurately obtained, the extraction efficiency and accuracy of the house crack information are effectively improved, and the method provided by the invention also has relatively high adaptability and expansibility.

The invention provides a comprehensive optimization method suitable for the efficiency and emission of a parallel hybrid power passenger plane. Aiming at the cruising stages under different voyage conditions, the performance comparison of the hybrid power passenger plane and the reference passenger plane under different operation mixing degrees is given, and the performance advantages of the hybrid power passenger plane in the aspects of energy consumption, oil consumption and NOx and CO emission are obtained; the change rule of indexes such as battery quality, energy consumption, oil consumption, NOx and CO emission along with the operation mixing degree is given; a comprehensive performance index is given, various performances of the hybrid power passenger plane are evaluated in a unified mode, the optimal value of the running mixing degree of the hybrid power passenger plane in the cruising stage under different voyage conditions is obtained, and comprehensive optimization of the efficiency and emission of the parallel hybrid power passenger plane can be achieved.

The invention, which relates to the technical field of building performance analysis and adjustment, discloses an integrated building performance analysis and optimization design platform system comprising a building form performance acquisition module, a building performance analysis module, a layout optimization module and a building impact simulation module. The system has the advantages that a performance comparison table of extreme weather-building shape-basic material arrangement-performance is constructed through the building form performance acquisition module, strong association of design parameters and extreme weather resistance is achieved, collaborative evaluation of safety performance and use functions is achieved through the design of comprehensive analysis and special unit combination, and the system has a good application prospect. Through linkage of the layout optimization module and the building impact simulation module, an optimization-simulation-re-optimization closed loop is constructed, building safety risks in extreme weather are reduced fundamentally, and through datamation, modularization and closed-loop technical logic, extreme weather adaptability is upgraded to a core driving factor from additional consideration of traditional building design.

The invention is suitable for the technical field of data processing, and provides a structured query language statement optimization method, terminal equipment and a storage medium, the method comprises the following steps: firstly predicting a first execution cost of a to-be-optimized initial SQL statement, then optimizing the initial SQL statement to obtain an optimized SQL statement, and predicting a second execution cost of the optimized SQL statement; determining whether the performance of the optimized SQL statement is improved or not by comparing the second execution cost with the first execution cost; by circularly executing the optimization steps, a plurality of candidate SQL statements with better performance are obtained; and finally, determining a candidate SQL statement with optimal execution from the plurality of candidate SQL statements as a final target SQL statement. According to the method, iterative optimization and a multi-candidate comparison and selection mechanism are adopted, the problem that single optimization is prone to falling into local optimum is effectively avoided, and SQL statements with more remarkable performance improvement can be screened out from a wider search space.

The invention discloses a dual-frequency radio frequency circuit based on a slow wave structure. The dual-frequency radio frequency circuit comprises a blocking capacitor Cblock, a dual-frequency input impedance matching network IMN, a series microstrip line, a rectifier diode, a filter capacitor CL, a direct current load RL, a second transmission line TL2 and a first transmission line TL1. By taking 0 dBm as a reference input power level, the dual-frequency rectification circuit based on the slow-wave structure provided by the invention shows a more excellent rectification effect under 0 dBm input power by comparing the performance of the dual-frequency rectification circuit based on the slow-wave structure provided by the invention with other designs in the existing literature in detail. While low-power high-efficiency double-frequency rectification is maintained, the size of the rectification circuit is greatly reduced, and the application scene of the rectification circuit is further widened.

The application provides a kind of server overall performance comparison test method, device, equipment and medium, belong to server performance test technical field, the method steps: the limit stress value when server sample is collected to carry out stress test, and record whether server sample can normally run under limit stress value;Extract the data characteristics corresponding to server sample when testing under safe stress value;Based on the training data set constructed by the data characteristics when running under safe stress value and the corresponding running results of limit stress value;Build BP neural network model, and use training data set to train, obtain data classification model;Extract the data characteristics corresponding to server safe stress value, and input server stress test classification model to data characteristics, predict whether server limit stress value can normally run.The application can predict whether server limit stress value can run by trained server stress test data classification model under server safe stress.

This invention provides a radar signal generation and data acquisition testing system using general-purpose instruments. Its hardware includes a host computer, a vector signal generator, and a spectrum analyzer. The host computer is used for baseband signal generation and hardware control; the vector signal generator outputs radio frequency (RF) signals; and the spectrum analyzer is used to acquire data from the RF signals emitted by the device under test (DUT). The system operates as follows: the host computer models the signal to generate waveforms; the waveforms are downloaded to the vector signal generator; the host computer controls the vector signal generator to output RF signals to the DUT; and the spectrum analyzer acquires data from the RF signals emitted by the DUT and transmits the acquired data to the host computer. This invention offers high flexibility and customizability, high cost-effectiveness, seamless connection between simulation and testing (achieving a closed loop from software algorithm simulation to hardware RF signal output, greatly facilitating the debugging and testing of the DUT), and strong controllability and repeatability, which is beneficial for troubleshooting and performance comparison.

The application discloses a design method of a macroscopic anisotropy structure based on a porous gas bearing, solves the problems of inaccurate performance prediction, non-systematic optimization design and the fact that the existing production conditions cannot realize micro anisotropy due to the isotropic assumption of the material of the porous gas bearing, and comprises the following steps: micro characteristic foundation and parameterization characterization: a prediction model of anisotropic permeability tensor is established; radial / circumferential low segmentation design: a partition design is adopted, and high permeability material is arranged in a bearing area; axial sandwich gradient design: a sandwich functional gradient design is adopted, and the thickness of high permeability material at both ends of the bearing is smaller than the thickness of low permeability material in the middle; system level performance simulation verification: macroscopic control equations coupled with porous medium seepage and gas film lubrication are solved, the bearing capacity, stiffness and gas film stability of the macroscopic anisotropic bearing are accurately predicted; performance comparison and optimization: performance comparison and verification are carried out with the performance of a traditional isotropic design.

The invention provides a method for evaluating the anti-rust performance of an oxidation film on the surface of cast iron, and belongs to the technical field of metal corrosion and protection. According to the evaluation method, by quantitatively detecting the content of Fe3O4, Fe2O3 and FeO in an oxidation film sample, the thickness of the oxidation film sample and the salt spray test time and electrochemical impedance of the oxidation film sample, an anti-rust performance comparison table with the synergistic effect of multiple evaluation parameters is established, and rapid mapping of evaluation parameters and anti-rust performance is achieved; and then quantitatively detecting the contents of Fe3O4, Fe2O3 and FeO in the oxidation film and the thickness of the oxidation film, and matching with the evaluation parameter-anti-rust performance comparison table to predict the anti-rust performance of the oxidation film. According to the evaluation method, the problem of inaccurate antirust performance judgment caused by single evaluation dimension and lack of systematicness of an evaluation method in related technologies is solved, and a scientific basis is provided for production process optimization and oxidation film quality control.

A substrate processing apparatus management system includes an information analysis device including a model generator that generates a representative model representing correlations in regard to a plurality of processing information pieces representing operations or states relating to a substrate process in a representative chamber among a plurality of chambers, and an assistance device that acquires a plurality of processing information pieces for each of the plurality of chambers, and generates assistance information relating to a maintenance work for another chamber based on comparison information in which correlations in regard to a plurality of processing information pieces for the other chamber are compared with a representative model.

The utility model relates to an anti-cutting glove practical training device. The device mainly comprises a cabinet body and a simulated cutting hand assembly, wherein the simulated cutting hand assembly is arranged in the cabinet body; wherein a transparent safety door is arranged on one side of the cabinet body; the simulation hand cutting assembly comprises a motor, a lead screw suite, a blade and at least two performance comparison gloves, the output end of the motor is connected with the lead screw suite, the blade is arranged on the lead screw suite through a connecting seat, the performance comparison gloves are arranged below the blade, and the performance comparison gloves are arranged on the lead screw suite. Each performance comparison glove is sleeved with an artificial hand; the blade, the performance comparison glove and the artificial hand are located in the visual range of the safety door. According to the utility model, the impression of safety education for sharp object cutting can be enhanced; and due to the arrangement of the safety door, the equipment does not cause actual harm to personnel, and safety risks existing in the education process are avoided.