22results about How to "Speed ​​up the optimization process" patented technology

The invention discloses a chip built-in self-test memory grouping method based on a BPPC algorithm, and belongs to the technical field of calculation, reckoning or counting. The method comprises the following steps: extracting memory file information, preprocessing, and storing in a memory information structure array; through a K-means + + algorithm, performing preliminary clustering on the memories according to the attributes of the memories; constructing a constraint relationship between the memories through distance constraint, and representing the constraint relationship by using a conflict matrix; a compatible memory group is decomposed into memory groups without a distance relation by using a vertex coloring problem model, the memory groups without a constraint relation are subjected to one-dimensional boxing by using an FFD method, a grouping condition is optimized by using a particle swarm algorithm, and the grouping condition is assigned to a corresponding controller. A BPPC algorithm and an MBIST test method are combined, and an optimal solution with the minimum number of controllers is sought under the limitation of the memory distance and the maximum power consumption. According to the method, a multi-stage optimization method and a multi-target method are adopted, so that the grouping result is more accurate.

The invention relates to the technical field of glass, in particular to a glass preparation raw material ratio automatic control system and method, and the system comprises a formula management module, a data processing module, an initial ratio determination module, a state information acquisition module, an RBC model establishment module, a raw material ratio determination module, a raw material ratio control module and an abnormity management module. The raw material formula is managed through the formula management module; the data processing module collects and preprocesses historical data; the initial ratio determination module and the RBC model establishment module are combined with expert experience to generate an initial ratio and store the initial ratio into an experience playback pool; the state information acquisition module acquires current state information according to an equipment request, and the raw material ratio determination module generates a ratio behavior through a TD3 model; the control module is used for generating and storing an experience sample for using a TD3 model so as to optimize a matching behavior; and the exception management module is responsible for monitoring and processing exceptions. The accuracy of system control is effectively improved, and the glass production efficiency and the product quality are improved.

The invention relates to the technical field of phototherapy instruments, in particular to a light system of a phototherapy mask and a phototherapy method.The light system comprises a mask body, a flexible lamp panel, a lamp wick module, a phototherapy detection module, a silica gel film and a breathable film, the mask body is provided with a sinking groove, the flexible lamp panel is arranged in the sinking groove, the lamp wick module and the phototherapy detection module are both arranged on the flexible lamp panel, and the silica gel film is arranged on the silica gel film. The silica gel film is arranged on the sinking groove and covers the lamp wick module and the phototherapy detection module; the phototherapy detection module comprises a temperature sensing module, a distance measuring module and a humidity sensing module, the silica gel film is provided with a light-transmitting groove, the light-transmitting groove is opposite to the lamp wick module, the breathable film is arranged on the silica gel film, the breathable film is provided with a through groove, and the through groove is opposite to the light-transmitting groove, so that the lamp wick module is exposed. Through ingenious combination of the mask body, the flexible lamp panel, the lamp wick module, the phototherapy detection module, the silica gel film and the breathable film, high integration of the phototherapy equipment is realized.

The invention discloses a double-layer optimization method considering well control and profile control and flooding agent parameter setting, and belongs to the field of oil and gas field development engineering.The method comprises the following steps that an oil reservoir profile control and flooding synergistic optimization control model is built, and dynamic profile control and flooding optimization variables are defined; based on actual reservoir operation constraints, constructing a concentration and dosage constraint judgment method of the profile control and flooding agent; a data-driven optimization algorithm is adopted, and a prediction model is trained and constructed to evaluate the effects of different profile control and flooding schemes; a plurality of injection agent opportunity schemes are generated based on a Gibbs sampling method, and each injection agent scheme is optimized to obtain the optimal injection and production liquid quantity and the optimal injection agent concentration; constructing a proxy model mapping relation; iteratively optimizing the profile control and flooding scheme, performing profile control and flooding simulation real evaluation, and updating the profile control and flooding experience library; and iteratively optimizing and outputting an optimal scheme. By introducing the dynamic profile control and displacement strategy and the advanced optimization algorithm, the design efficiency and effect of the profile control and displacement scheme in the complex oil reservoir environment are improved, and powerful support is provided for efficient development of oil and gas fields.

The invention provides a chip analysis method and device and a readable storage medium, and the method can divide a plurality of to-be-tested chips into a plurality of to-be-tested groups, test the to-be-tested chips in each to-be-tested group in sequence and determine a first statistical parameter, and also can test the to-be-tested chips in the to-be-tested groups after the to-be-tested chips in the to-be-tested groups are all tested. And generating a second statistical parameter based on the test result, thereby generating a corresponding optimization suggestion report and stopping the test when the first statistical parameter or the second statistical parameter meets a corresponding preset condition. The scheme provided by the invention can adapt to test requirements of chips of different numbers and types, ensures that chip analysis has better regularity and reliability through grouping test, can timely find test problems and improve the overall quality of the chips, generates a corresponding optimization suggestion report, provides a specific improvement direction, and improves the test efficiency. And an engineer is helped to quickly position a problem and formulate a solution, so that a subsequent test strategy is flexibly adjusted.

The invention provides an earthwork construction dynamic scheduling method and equipment based on deep reinforcement learning, and a storage medium. The method comprises the steps of obtaining construction information, determining an integrated scheduling target of constraint conditions and construction equipment, and setting a target function; expressing an integrated scheduling problem of the construction equipment as a Markov dynamic decision process, and generating a first agent; designing a reward function based on NSGA-II and DDQN algorithms to train the first agent; generating an initial scheduling scheme, and executing virtual scheduling based on the scheme; on the basis of the assumed disturbance event supplementary constraint condition, generating a second agent through a Markov dynamic decision process; distinguishing jobs in the initial scheduling scheme, and designing encoding and decoding methods of an NSGA-II algorithm according to a distinguishing result; designing a reward function to train a second agent based on the NSGA-II algorithm and the DDQN algorithm after the coding and decoding are designed; and deploying the intelligent agent after training stabilization in an actual construction environment, and generating a dynamic scheduling decision.

The invention discloses a vehicle frame lateral bending multi-parameter joint optimization method, system and device and a storage medium, and relates to the technical field of vehicle frame design and optimizing.The method comprises the steps that vehicle frame actual measurement related data are collected, and a vehicle frame dynamic model is built based on simulation software according to the collected vehicle frame actual measurement related data; initial setting is carried out on bushing preload and cross beam tolerance parameters in the vehicle frame dynamic model, and the bushing preload is adjusted, so that the lateral bending condition of the vehicle frame dynamic model is consistent with the actual measurement condition; performing static balance simulation analysis on the frame dynamic model under different cross beam tolerance combinations in combination with the adjusted bushing preload; and according to simulation results under different cross beam tolerance combinations, selecting a cross beam tolerance combination meeting set requirements. According to the method, the accuracy of frame lateral bending optimization can be effectively improved.

The invention discloses a high-voltage switch mechanical characteristic parameter optimization platform, and relates to the technical field of high-voltage switch mechanical characteristic parameter optimization, and the platform comprises a parameter collection module which is used for collecting mechanical characteristic parameters of a high-voltage switch in real time, and a data analysis module which is used for analyzing the mechanical characteristic parameters of the high-voltage switch based on the collected mechanical characteristic parameters. And analyzing the relevance between the high-voltage switch performance and the mechanical characteristic parameters through an adaptive optimization algorithm, and generating optimization reference data. According to the mechanical characteristic parameter optimization platform for the high-voltage switch, the influence degree and the mutual relation of each parameter on the performance can be accurately determined; based on the generated optimization reference data and adjustment reference data, parameters such as the on-off time, the switching-on time and the switching-off time of the high-voltage switch can reach better values, so that the comprehensive performance index is improved, parameter combinations can be comprehensively evaluated under various working conditions, potential performance problems can be found and adjusted in time, and the service life of the high-voltage switch is prolonged. And the high-voltage switch always keeps good performance in a complex actual operation environment.

The invention discloses a method, a battery and a device for testing the gas production rate of a lithium ion battery, and the method comprises the following steps: carrying out an EIS test on the lithium ion battery to obtain an EIS test result; analyzing an EIS test result by using relaxation time analysis, and determining the relaxation time center point frequency of the contact impedance; performing single-frequency impedance scanning in the charging process of the battery cell; the frequency adopts relaxation time center point frequency; comparing the contact impedance reduction rates of the first battery cell and the second battery cell, and determining the gas production rates in the first battery cell and the second battery cell; and the internal reserved spaces of the first battery cell and the second battery cell are the same. And the gas production rate test of the battery cell is completed under a nondestructive condition, so that the performance and the safety of the battery are improved, and the cost is reduced at the same time.

The invention discloses a drainage basin management measure space configuration optimization method, and relates to the technical field of ecological environment. The method comprises the following steps: construction and applicability analysis of a watershed non-point source model, description and screening of BMPs, and sensitivity analysis of NSGA-II parameters. An innovative optimization framework is provided and used for identifying and developing the optimal BMPs combination on the watershed scale, the framework considers the weights of the TN and the TP, the main target is to improve the comprehensive reduction rate to the maximum extent by coupling the TN and the TP, and the total cost related to implementation of 14 BMPs is reduced to the maximum extent. Three optimal BMP solutions based on Pareto optimum are obtained through simulation by using the framework; wherein the fusion of the NSGA-II and the BMPs database is derived from the output of the SWAT model after calibration and verification driven by local data, so that the optimization process is greatly accelerated, the calculation complexity is reduced, and the optimal BMPs combination is steadily sought, so that the nitrogen and phosphorus reduction rate is improved to the maximum extent, and the total cost is reduced.

The invention discloses a molecular marker related to the sucrose content of peanut seed kernels, a KASP primer group and application of the molecular marker and the KASP primer group, and belongs to the technical field of molecular genetic breeding. The molecular marker disclosed by the invention is positioned at 108307340bp of a B03 chromosome, and the polymorphism of the molecular marker is G / A. The molecular marker related to the sucrose content of the peanut seed kernels is provided, a KASP primer group and a KASP analysis technology are developed according to the molecular marker, and the molecular marker can be used for detecting the sucrose content of the peanut seed kernels. When the molecular marker and the KASP primer group thereof are used for early identification and genetic breeding or genetic resource improvement of peanut strains, the peanut breeding period can be shortened, the genetic resource improvement process is accelerated, and new genetic resources and theoretical basis are provided for molecular assisted breeding.

The invention discloses an optimal control method and system for reactive power compensation of a power distribution network, and the method comprises the steps: building a multi-target reactive power optimization model of the power distribution network based on the system parameters of the power distribution network, and carrying out the optimal control of the reactive power compensation of the power distribution network under the constraint condition of the multi-target reactive power optimization model of the power distribution network, solving the target function of the multi-target power distribution network reactive power optimization model by adopting a multi-target whale optimization algorithm to obtain an iterative optimization solution set output by the multi-target power distribution network reactive power optimization model, and processing the multi-target power distribution network reactive power optimization model based on the iterative optimization solution set and an improved multi-target grey wolf optimization algorithm to obtain a multi-target power distribution network reactive power optimization model. And taking a result output by the multi-target power distribution network reactive power optimization model as a node configuration optimal solution set of the power distribution network, and controlling the power distribution network by using the node configuration optimal solution set. According to the optimal control method and system for the reactive compensation of the power distribution network, the optimal control effect of the reactive compensation of the power distribution network is improved.

The present application discloses a method, device, equipment and medium for predicting the auxiliary jet air consumption of an air jet loom, and belongs to the field of industrial automation technology. The method comprises: obtaining the structural parameters to be measured of the nozzle to be measured in the air jet loom, the structural parameters to be measured include the inlet diameter, the straight tube diameter, the nozzle taper, the elliptical outlet major axis and the elliptical outlet minor axis; inputting the structural parameters to be measured into the air flow prediction model, and obtaining the nozzle air consumption of the nozzle to be measured output by the air flow prediction model, and the air flow prediction model is obtained based on the sample structural parameters and air consumption label training of the sample nozzle. The method can accurately predict the air consumption of the nozzle in a complex industrial environment.

The invention discloses a multi-task optimization method for solving a simultaneous goods taking and delivering vehicle path problem with a time window. The multi-task optimization method comprises the following steps: initializing populations of all tasks; the total operation cost of the vehicle path problem is used as an evaluation function, the adaptive value of each individual is calculated, and the path of each vehicle meets the vehicle capacity constraint, the client time window constraint and the simultaneous delivery demand constraint; calculating an accumulated average survival rate of offspring individuals generated by cross-task crossing in environment selection, and controlling knowledge migration between tasks; calculating compatibility scores of the candidate individuals under target task distribution, screening knowledge migration objects, and adjusting a compatibility screening threshold according to a historical migration success rate; and screening out a new generation of population based on a selection mechanism in a genetic algorithm, and selecting an individual with the optimal fitness from the final population to correspond to a final vehicle path scheme. According to the method, the opportunity, frequency and quality of knowledge migration can be more intelligently regulated and controlled, and stable search performance can be kept in a complex problem space.

The invention discloses a pure phase array directional diagram synthesis method and system based on an improved bat algorithm. According to the scheme, an array model constructed by a plurality of antenna units is set; constructing an optimization objective function of the array model; the objective function is minimized according to a bat algorithm, and optimization training of the array model is completed; and according to the array model obtained through optimization, pure phase array pattern synthesis is carried out. According to the embodiment of the invention, an initial phase distribution is created by using a parabolic function aiming at pure phase symmetrical directional diagram synthesis, the distribution has the characteristic of being approximate to a flat-topped mode, so that the optimization process is accelerated, in addition, excitation distribution is expressed in a polynomial form, the optimization problem is converted into optimization of polynomial coefficients, and the optimization efficiency is improved. Therefore, antenna pattern integration is realized, and the method can be widely applied to the technical field of computers.

The invention discloses an infrastructure emergency repair cooperative scheduling method for cascade time uncertainty, and relates to the technical field of emergency management and intelligent scheduling optimization. The method comprises the following steps: 1, carrying out structured modeling on a disaster infrastructure system, a failure unit, technicians and a road network topology; step 2, constructing a task allocation and collaborative path integrated optimization model with planning recovery time efficiency maximization as a target; 3, based on the mean variance and the normal quantile, establishing a probability constraint of step-by-step transmission and accumulation of the uncertainty of the repair duration and the arrival time along the path; step 4, realizing error controllable linearization of the square root relationship by adopting segmented secant lines; and 5, combining variable neighborhood search and integer programming local optimization to quickly solve and output an executable scheme. The method provided by the invention can effectively improve the timeliness of post-disaster first-aid repair and the robust performability of the scheme, and provides scientific decision support for the emergency first-aid repair of key infrastructures such as electric power, water supply, traffic, communication and the like.

The present invention relates to a subarray-level distributed frequency-controlled array sidelobe suppression method based on an improved genetic algorithm, and belongs to the field of array antenna signal processing. The method uses an improved genetic algorithm to simultaneously suppress the grating lobes or high sidelobes of the distributed frequency-controlled array in the angle dimension and the distance dimension; the improved genetic algorithm is a niche genetic algorithm based on a pre-selection mechanism, and a competition mechanism is introduced between the parent and the offspring. Only when the fitness value of the offspring individual is higher than that of the parent individual, the offspring individual can replace its parent individual accordingly, otherwise the parent individual is still retained in the next generation group, and the local and global optimal solutions are optimized in the feasible solution space; and taboo search is introduced to speed up the convergence speed, avoid the genetic algorithm from being premature and stagnant, and thus jump out of the local optimal solution. The present invention improves the optimization results of the subarray position and subarray frequency deviation of the subarray-level distributed frequency-controlled array, and achieves better sidelobe suppression results from the distance dimension and the angle dimension.

A dynamic analysis method for the reflectance of vitrinite in continental hydrogen-rich shale based on normally distributed activation energy is proposed for oil and gas exploration and development, solving the problem that the existing Easy%Ro model is not suitable for the evolution analysis of vitrinite in continental hydrogen-rich shale. This invention includes: S1, a calibration method for the dynamic model of reflectance of vitrinite in continental hydrogen-rich shale; including a calibration method for the reaction dynamics model of vitrinite in hydrogen-rich shale based on in-situ thermal evolution simulation experiments or a calibration method for the reflectance dynamics model of vitrinite in hydrogen-rich shale based on paleothermal evolution history; S2, a forward modeling prediction method for geothermal evolution history based on the reflectance dynamics of vitrinite in continental hydrogen-rich shale. This invention establishes the SL_Ro model by obtaining data from in-situ thermal evolution experiments, which is more suitable for describing the reflectance evolution process of vitrinite in continental hydrogen-rich shale compared to the traditional Easy%Ro analysis method based on discrete distributed activation energy chemical kinetic models and exponential conversion relationships.

The present invention discloses a pump station optimization scheduling method based on virtual water in the field of reservoir scheduling, comprising the following steps: 1) obtaining pump station-water diversion area information; 2) constructing a pump station-water diversion area system database; 3) establishing a pump station optimization scheduling model based on virtual water: using C++ to connect to the database, reading the data information of each field of the pump station-water diversion area system in step 2), taking the maximum economic benefit of daily pump station water diversion as the objective function, taking into account the influence of electricity price fluctuations and tidal river sections on the pump station head, and satisfying the constraints of product import, pump station water diversion, water diversion capacity and non-negative decision variables, and establishing a pump station optimization scheduling model based on virtual water that is mutually fed back with the database; 4) for the model, a combined algorithm of 0-1 integer programming and whale algorithm is proposed to solve the model, and the present invention realizes the optimal configuration of regional water resources and achieves the maximum economic benefit during the scheduling period.

The application provides an irregular polygon patch antenna design method and device based on improved NSGA-Ⅱ, adopts an optimization strategy of irregular polygons, and gives the antenna higher flexibility and diversity in the premise of maintaining the continuity of the antenna shape. Specifically, a multi-objective quantum particle swarm optimization algorithm is combined with a non-dominated sorting genetic algorithm NSGA-Ⅱ, a quantum search mechanism is introduced, the global search capability of the solution space is significantly enhanced, the deficiency that the traditional particle swarm optimization algorithm is prone to local optimal solution is overcome, and the optimization process is accelerated; meanwhile, in combination with the NSGA-Ⅱ algorithm, the relationship between optimization objectives in the multi-objective optimization process can be effectively balanced, and the diversity of the solution set is ensured.

The present application relates to a wellbore multiphase flow model numerical solution and gas-liquid distribution state inversion method and system, belonging to the technical field of petroleum engineering, comprising: step 1: constructing and training the physical information neural network of drilling wellbore multiphase flow dynamic simulation and overflow gas distribution state inversion; determining the input and output of the physical information neural network; determining the loss function of the physical information neural network; training the physical information neural network; step 2: designing an adaptive optimization algorithm to optimize the final solution accuracy and convergence speed of the physical information neural network, obtaining an adaptive physical information neural network; designing an adaptive activation function; designing a residual-based adaptive sampling mechanism; step 3: realizing the numerical solution of the wellbore multiphase flow model and the gas-liquid distribution state inversion based on the adaptive physical information neural network. The present application effectively solves the problem that the traditional numerical method usually requires high-precision grid division and a large amount of computing resources.

The present application relates to the technical field of plant molecular breeding, and particularly relates to a Kasp marker PH-03-KASP-106 closely linked to corn plant height and application thereof, the marker comprises a single nucleotide polymorphism SNP site located at the position 163964821 of the 3rd chromosome of corn Chr3 and a KASP molecular marker primer set, PCR amplification of corn genomic DNA is carried out through the specific primer set, and the TT dwarf, CC high rod genotypes are distinguished according to fluorescence signal differences. The present application can be used for early identification, screening and molecular marker assisted breeding of corn plant height traits, can improve the efficiency of dwarf corn germplasm breeding, enhance the selection accuracy, clarify the breeding direction, and is simple in operation, high in cost-effectiveness, and suitable for corn breeding research and production practice of different scales.