9 results about "Population size" patented technology

The invention relates to a factory job shop scheduling control optimization method and device, equipment and a medium, and the method comprises the steps: classifying workpieces irrelevant to all MPBPO sets into a first workpiece set, classifying the workpieces corresponding to each MPBPO set into one set to determine a second workpiece set, independently generating job task sorting sub-chromosome segments, and generating a job task sorting sub-chromosome segment; corresponding operation machine numbers and operation time are respectively filled into corresponding gene positions of the operation machine sub-chromosomes and the operation time sub-chromosomes, and the operation task sorting sub-chromosomes, the operation machine sub-chromosomes and the operation time sub-chromosomes are combined to obtain initial chromosomes so as to generate initial population individuals; genetic manipulation is carried out on the initial population individuals, and population individuals with the high fitness and the number of the population individuals being the population scale are selected as a next-generation initial population; and repeatedly executing, and outputting the production scheduling scheme with the optimal earliest completion time. According to the method, algorithm premature convergence can be avoided in a generalized job-shop scheduling problem with a forced parallel batch processing procedure.

The invention provides a self-adaptive knowledge migration multi-task optimization method based on a multi-population evolution framework. The method comprises the following steps: 1) initializing a population of each task; 2) selecting self evolution or migration evolution according to the migration probability to generate a filial generation, and using an enhanced migration strategy to improve the migration effect when an individual selects migration evolution; 3) generating a next-generation population through environment selection, combining a filial generation generated by migration evolution and a filial generation generated by self evolution, comparing the combined filial generation with a parent individual, selecting individuals with higher fitness to form the next-generation population, eliminating disadvantageous individuals through continuous iteration, and retaining a solution with better performance; 4) adaptively updating the migration probability; 5) reducing the size of the linear population, performing judgment after evolution of each generation of population is finished, and performing population reduction when conditions are met; and 6) when the maximum number of evaluation times is reached, outputting an optimal solution by the population. According to the method, the problem of continuous single-target multi-task optimization can be solved, and the core problem of a single-target multi-task optimization algorithm is improved.

The invention relates to a rectification system multi-objective optimization method based on dynamic NSGA-II, and belongs to the technical field of chemical process system optimization. The method comprises: determining a decision variable and a target function according to a rectification system model; a diversity index is obtained by calculating an invalid solution proportion of each generation of population and diversity of a target and decision space; and the crossover probability, the mutation probability and the population size are dynamically adjusted, a dynamic NSGA-II algorithm is constructed, the rectification system is optimized, and an optimal solution is obtained. According to the method, dynamic parameter adjustment is achieved by introducing the invalid solution proportion and the population diversity index, the number of non-convergent solutions can be effectively reduced, the population diversity is enhanced, premature convergence is avoided, the calculation cost is reduced while the optimization efficiency is improved, and an efficient and practical solution is provided for multi-objective optimization of a complex chemical system.

The invention relates to the technical field of communication, and particularly discloses a large-scale MIMO (Multiple Input Multiple Output) resource allocation method based on a genetic algorithm, which comprises the following steps: S1, setting the population size, and generating a candidate solution in each population; s2, calculating the fitness of each candidate solution in the population; s3, calculating the probability that each candidate solution is selected; s4, randomly selecting two candidate solutions in the population as a parent according to the selection probability, and mixing genes of the filial generation and the parent; s5, mutation operation is carried out; s6, repairing the generated offspring; s7, evaluating the obtained candidate solutions of the new offspring population, selecting an optimal solution in the current offspring population, if the current optimal solution is better than the global optimal solution, replacing the global optimal solution with the current optimal solution, otherwise, abandoning the current optimal solution; and S8, repeating the steps S1-S7 until the final result tends to converge. According to the technical scheme, the system performance and the resource utilization rate can be effectively improved.

The invention discloses a method for predicting an endangered grade of madrepore under future climate change based on a species distribution model. The method comprises the following steps of (1) species distribution information collection, (2) environmental factor selection, (3) model construction and model performance evaluation, and (4) species eradication risk evaluation under climate change. The invention discloses a method for evaluating the endangered grade of madrepore based on a species distribution model for the first time, and the method makes up for the dependence of the traditional IUCN evaluation on the field population quantity and trend data. According to the scheme for predicting the suitable habitat of the species under the climate change of the madrepore, the endangered grade of the madrepore under the climate change can be evaluated. The method provides beneficial enlightenment for the endangered level in evaluating or updating the eradication risk state of marine species and designing protective measures.

We provide the system. [Solution] A system having a computer program that manages multiple organisms and simulates changes in the population size of each organism in order to mimic an ecosystem, A means for calculating the fluctuations in the population of the organism based on the birth rate and death rate, A means for displaying the year-to-year changes in the population size of each of the aforementioned organisms, A system including means for performing a simulation at predetermined time intervals to mimic the passage of time.

The application relates to a multi-agent control strategy optimization method for multi-population multi-stage constraint multi-objective based on reinforcement learning, which comprises the following steps: generating a population matrix; generating optimal population sizes of various populations; screening parent individuals of an exploratory operator and a development operator from the population, and generating evolutionary offspring individuals; performing preliminary screening of the offspring individuals based on the parent individuals; judging the convergence state of the population according to the total sum difference of objective function values of adjacent two generations of individuals in the population and the number of non-dominated solutions in the population, so as to trigger the switching of the constraint processing mode; screening the offspring individuals and the parent individuals, updating various populations; if the iteration number reaches the maximum iteration number, outputting an external population, and obtaining an optimal strategy of current multi-agent control based on the external population; otherwise, increasing the iteration number by 1 and performing action selection. Compared with the prior art, the application can give an approximate optimal unmanned aerial vehicle three-dimensional deployment scheme, a device transmission power scheme and a computing resource allocation strategy.

The invention relates to the technical field of pest monitoring, and discloses a termite population number estimation method and system using diet special effects, and the system comprises a writable disturbance preference model and a read-only reference vitality model; in the disturbance estimation mode, opening a B chamber channel, and calculating an estimated population value by using a disturbance preference model; switching to a reference calibration mode, closing a B chamber channel, and calculating a calibration anchor point by using a reference vitality model; updating the disturbance preference model on line according to the calibration anchor point; and switching back to the disturbance estimation mode by using the updated model. The system comprises a data acquisition terminal and a data processing system, and the data processing system is provided with a state machine module, a dual-model storage module, a data decoupling calculation module and a dynamic response baseline calibration module so as to realize mode switching, closed-loop calibration and population value calculation of the method. By means of dual-mode switching and closed-loop calibration, the problem of model drifting is solved, the population number and the ingestion activity are decoupled, and high-precision estimation of the termite population is achieved.

This invention discloses a method for calculating optimal contribution for breeding and mating selection in endangered and rare cattle and sheep populations. The method includes: acquiring pedigree data and genomic information of the rare cattle and sheep; constructing a pedigree matrix based on the pedigree data; constructing a genomic kinship matrix based on the genomic information; minimizing the average kinship of the population using a genetic algorithm based on the pedigree matrix or genomic kinship matrix to determine the set of individuals to be culled; calculating the optimal contribution value of each individual using a simulated annealing algorithm for the set of individuals to be retained; and minimizing the average kinship between all pairs using a simulated annealing algorithm based on the optimal contribution values ​​of all individuals to obtain the target mating scheme. This invention balances constraints such as sex ratio and population size with kinship control, aiming to minimize the average kinship coefficient of the next generation population, greatly reducing the risk of inbreeding and ensuring population genetic diversity.