92 results about "Population evolution" patented technology

The invention proposes a steelmaking-continuous casting scheduling method utilizing a priority policy hybrid genetic algorithm. The method comprises the following steps: establishing a production scheduling plan target function; establishing a constraint condition set; performing iterative calculation on the target function by utilizing the priority policy hybrid genetic algorithm; and calculating decision variables. The calculation of the decision variables specifically comprises the steps of performing model initialization; calculating a feasible solution: designing a segmented combined real number code composed of casting time information of a continuous casting machine and information of a heat machining device, randomly generating operation time according to a distribution law, and obtaining a time conflict-free scheduling plan by backward inference calculation and conflict elimination methods; and performing population genetic optimization: quantitatively describing a matching relationship among machining devices in reality by using processing weight assignment of a task executable device, and introducing the matching relationship to genetic operation in the form of a device selection priority policy to perform population evolution. The method can solve the problem of uncertainty of device selection and operation time in production to obtain an optimized executable production scheduling plan.

The invention discloses a method for partitioning communities in a complex dynamic network by virtue of multi-objective local search based on decomposition, and the method is mainly used for solving the problem of poor community partitioning accuracy in the course of processing the complex dynamic network in the prior art. The method is implemented through the following steps: (1) determining objective functions; (2) constructing an initial solution population, and initializing individuals in the solution population by a neighborhood real-number encoding method; (3) sequentially selecting the individuals from the solution population and then carrying out cross variation on the individuals to obtain progeny individuals; (4) updating the solution population by virtue of the progeny individuals; (5) locally searching and updating the solution population; (6) judging whether the population evolution process is terminated: if iterations reach the preset times, executing a step (7), otherwise, transferring to the step (3); and (7) selecting the optimum community partition according to the maximum module density principle. The method disclosed by the invention has the beneficial effects that two objective functions can be optimized at the same time, synchronous analysis of community partition and community evolution is realized, the community partitioning accuracy is improved, and the problem of detection of a community structure in the complex dynamic network can be solved.

The invention discloses an infrared thermal image defect feature recognition method based on dynamic multi-objective optimization. The transient thermal response of a pixel point is selected by changing the step length of a thermal image sequence; FCM is used for classification. obtaining the category of the transient thermal response of each pixel point; the pixel value similarity of each type ofpixel points and the same type of pixel points is considered; the difference with different types of pixel points is realized; constructing a corresponding multi-objective function; meanwhile, afterthe environment is changed each time; Prediction mechanism, a guiding direction is provided for population evolution; a multi-objective optimization algorithm is helped to quickly respond to the new change; The method has the advantages that the dimension reduction result of the thermal image sequence is acquired by the aid of the feature extraction algorithm, the defect features of the infrared thermal image are extracted by the aid of the pulse coupling neural network, accordingly, accurate selection of transient heat representations (temperature points) can be realized, the accuracy of defect feature extraction can be guaranteed, and computing consumption of the transient heat representations for acquiring various types of information in dynamic environments can be reduced.

The invention discloses a selection method for subintervals of near infrared spectral characteristics based on a simulated annealing-genetic algorithm. The method comprises the following steps: pretreating a near infrared spectrum; then dynamically dividing subintervals on the pretreated near infrared spectrum, introducing an Metropolis criterion in the simulated annealing algorithm to gene exchange and gene selection operators, and selecting an optimal character subinterval with the simulated annealing-genetic algorithm; and finally judging the best subinterval division method to be combined with the optimal character subinterval and building a PLS model for the selected optimal character subinterval. In the selection method, high-quality offspring individuals can be generated through improved variation and commutating operators, not only adaptability levels of overall populations are improved, but also enough power for population evolution is provided; and deficiency brought by the total number of the spectrum subintervals manually designated according to the experiences in the process of modeling can be avoided, and spectral models with high precision and strong prediction ability can be rapidly obtained.

The invention provides a multi-objective scheduling method for a wind power-electric automobile-thermal power combined operation model, relating to the field of electrical power systems. The method comprises the steps: S1, a plurality of groups of 24-time-interval wind speed values are generated randomly through the Weibull distribution function; S2, 24-time-interval wind power output and an average value of daily output of the wind power are calculated; S3, an electric automobile is charged and discharged, the charging power and discharging power of the electric automobile are obtained, and the generated output of a thermal power generating unit is calculated; S4, the maximum value and the minimum value of two functions are calculated respectively; S5, fuzzy processing is carried out on the two functions so as to obtain the maximum desirability function; and S6, population evolution is carried out on the maximum desirability function so as to obtain the optimal output. Aiming at the random and indeterminate output of the wind power, the invention provides the method of using ordered charging and discharging of electric automobiles, namely an energy storage system, to stabilize the fluctuation of the wind power, and abandoned wind power is reduced. And meanwhile, the fluctuation of the wind power is reduced, so peak-load regulation and spinning reserve pressure of the thermal power generating unit is reduced, and economic benefits of a wind power-electric automobile-thermal power combined operation system are maximized.

The invention relates to a positioning method for a distribution circuit fault section based on BPSO and a GA. The mixture of a binary system particle swarm and the genetic algorithm is achieved by a bi-population evolution and information interchange strategy utilized by the method, and a binary system mixed algorithm is formed; two subpopulations are each provided with an individual scale, an evolutionary process of each generation is not affected, after evolution of each generation is completed, information interchange transmission is conducted, an optimal individual is selected, optimizing searches are carried out on the next generation of the two populations respectively until an optimal solution is found out. The probability of immature convergence occurred in a fault positioning process can be reduced by the algorithm, a certain fault tolerance is obtained, and compared with fault section positioning conducted by single binary system particle swarm or the single genetic algorithm, the convergence speed is obviously improved.

The present invention relates to a genetic algorithm-based advanced plan scheduling system and method. The system comprises a basic setting module, a data management module and a scheduling module. Optimal solutions are successively generated from potential solution populations by using the characteristics of mutation and population evolution in a genetic algorithm, so as to solve the scheduling problems of machining workshops of aviation enterprises.

The invention discloses a complex network community mining method based on an improved genetic algorithm and belongs to the technical field of complex network community mining method research. The complex network community mining method based on the improved genetic algorithm uses the improved genetic algorithm based on clustering and double population thought fusion to mine communities in a complex network. The complex network community mining method based on the improved genetic algorithm uses a normalization common information similarity standard as the standard for measuring the similarity between individuals in the population and fuses the clustering and double population thought. The complex network community mining method based on the improved genetic algorithm includes that introducing the clustering thought, using a minimum spanning tree clustering method to classify the population, introducing the double population thought, and determining the main type and auxiliary type for the clustering. The main type maintains the population evolution direction to get close to the optimal solution of an objective function; the auxiliary type is mainly used for duly providing diversity for the main type so as to enable the main type to be capable of coming out to search the other solution space to realize the complex network community mining when the main type is located at the local optimum.

The invention relates to an unmanned aerial vehicle cluster combat game decision method based on a quantum krill population evolution mechanism, which comprises the following steps: establishing an unmanned aerial vehicle cooperative combat game decision model; initializing the quantum krill group; calculating the fitness value of each quantum krill position in the quantum krill group according toa fitness function; updating a quantum rotation angle and a quantum position of each quantum krill; carrying out fitness calculation on the updated position of each quantum krill in the quantum krillgroup, obtaining the updated position of each quantum krill through a mapping rule, and calculating the fitness of the position; determining the global optimal quantum position of the quantum krill population; circularly judging; outputting the global optimal position of the quantum krill group and mapping the global optimal position into a mixed strategy combination of games. According to the method, the unmanned aerial vehicle cluster combat command decision is analyzed in combination with the game theory, so that both sides of the operation can obtain the maximum benefit through the rational decision analysis, the battlefield environment of the unmanned aerial vehicle cluster operation is better met, and the applicability is stronger.

The invention discloses a self-adaptive genetic algorithm based on the population evolution process, including the first step, setting the parameters of the BAGA algorithm, setting the number of iterations of the algorithm, the number of populations in each generation, the discrete precision of the independent variable, and the total number of shooting times , a constant; the second step is to use binary code to generate the initial population; the third step is to judge whether the maximum number of iterations is satisfied, and if so, output the optimal individual of the last generation, which is the optimal value found, otherwise turn to the fourth step; The fourth step is to establish the relationship between the objective function and the fitness function, and then calculate the fitness of each individual and the average fitness of contemporary individuals, save the individual with the largest contemporary fitness, and calculate the evolutionary degree of the contemporary population, the degree of population aggregation, and Balance factor, crossover probability and mutation probability; the fifth step, selection, crossover and mutation operations to generate new populations, the selection operator uses roulette technology, the crossover operation uses univariate crossover, and the mutation operation uses basic bit mutation; the sixth step, Find the best individual in the contemporary population, keep it, and then go to the second step.

The invention relates to a method for movie recommendation on the basis of an orthogonal and cluster pruning based improved multi-objective genetic algorithm. An improved algorithm OTNSGA-II is provided aiming at defects in distributivity and convergence of NSGA-II (non-dominated sorting genetic algorithm-II) and can be used for solving various multi-objective function optimization problems. By design of fault multi-objective orthogonal experiment initialization population, distributive deficiency caused by individual nonuniformity is avoided; by application of self-adaptive cluster pruning strategies, a population evolution process is maintained, and inferior individuals in an appropriate quantity are removed to keep convergence and distributivity of the population. By combination with information mining of user behaviors and movie properties, the algorithm is applied to solving of a practical problem of personalized movie recommendation, universality and effectiveness of the algorithm are explained by test comparison with existing algorithms, better recommendation results are obtained, recommendation accuracy rate, recall rate and coverage rate are increased, rich recommendation scheme combinations are provided, and interest points of users can be mined beneficially to provide more reliable recommendation services.

The invention discloses a scientific workflow data layout method oriented to time delay optimization in a hybrid cloud environment, which considers the characteristics of data layout under the hybridcloud environment, combines the dependency relationship among scientific workflow data, and considers the influence of factors such as the bandwidth between cloud data centers, the number and capacityof private cloud data centers and the like on transmission time delay. Firstly, preprocessing is carried out to improve the efficiency of the data layout strategy in the later period. By introducingcrossover operator and mutation operator of genetic algorithm, the problem of premature convergence of particle swarm optimization algorithm is avoided, the diversity of population evolution is improved, the data transmission delay is effectively reduced, and the data transmission delay of scientific workflow in hybrid cloud environment is effectively reduced. The invention improves the executionefficiency of the data layout strategy and optimizes the transmission delay of the scientific workflow data layout.

The present invention discloses a spaceflight product assembly quality problem classification method based on big data analysis. The method comprises: constructing a big data analysis platform based on Hadoop, constructing an initial SVM model, utilizing genetic algorithm to perform optimization selection of the parameters of the initial SVM model, and obtaining the parameters of the optimal classification precision SVM model; and finally, obtaining a GA-SVM model. The GA-SVM model can classify different quality problems and has high classification precision. The spaceflight product assembly quality problem classification method based on the big data analysis utilizes the big data analysis technology to make the operation more effective, the crossover operation and the variation operation in the genetic algorithm consider the dynamic nature of the population evolution, the optimal solution can be rapidly and accurately found, and the genetic algorithm is applied to the optimization of the parameters of the support vector machine so as to improve the precision of the quality problem classification.

The invention discloses a personalized recommendation method based on risk income management on a P2P platform. According to the method, a loan recommendation problem in the P2P lending platform is converted into a multi-objective optimization problem, and the loan recommendation problem existing in the P2P platform is solved by performing modeling analysis, problem conversion, population initialization and population evolution on historical investment records of investors in the P2P platform. According to the invention, different loan combinations recommended to different users not only accord with interest preferences of the users, but also can obtain very good benefits on the premise of undertaking lower risks, so that the trust degree of the users on the P2P loan platform can be improved, and the P2P loan platform can better operate and develop.

The invention discloses a multi-target optimal management method for remediation of underground water with uncertainty. According to the method, target function random evaluation, a random Pareto domination concept and a random ecological niche fitness sharing method are imported into a population evolution operation of an EMOTS on the basis of a multi-target random tabu search algorithm PEMOTS of an elitism selection strategy. The PEMOTS inherits the global search advantage of the EMOTS, Latin Hypercube Sampling LHS is imported into an elitism selection strategy adopted by the EMOTS so as to generate neighborhood solutions, so that non-interior solutions obtained through the algorithm can be convergent to true solutions and can be uniformly distributed along a trade-off curve. The core difference between the PEMOTS and similar methods is adopting sequential Gaussian simulation SGSIM to reduce the uncertainty of water-bearing system parameters; and meanwhile, the random multi-target evolution operation is imported, the variability of the search of Pareto optimal solutions is reduced. The method disclosed in the invention is coupled with an underground water flow program MODFLOW and a solute transport program MT3DMS, so that relatively strong reliability and robustness are provided in the process of solving a multi-target management model for the pollution abatement of the underground water with uncertainty.

The invention provides a loop antenna array spare method based on a multi-objective quantum spider population evolution mechanism. The method comprises the following steps that: establishing a loop antenna array spare model, setting a proper system parameter, and initializing the quantum position and the [0,1] coding position of each spider in a population in a solution space; designing a multi-objective fitness function; calculating the weight of each spider in the population, and dividing the gender of the spiders according to the weight; according to the initial population, generating an initial elite solution set; selecting a global optimal solution and a suboptimum solution from the elite solution set; then, independently updating the quantum positions of the female spider and the male spider, and converting the quantum position into the [0,1] coding position through a measurement way; updating the elite solution set, and updating the weights of all spiders in the population; finally, judging whether a maximum iteration number is achieved or not is judged, and outputting the elite solution set if the maximum iteration number is achieved; and otherwise, returning to carry out iteration. By use of the method, a problem that high-dimension discrete multi-objectives are subjected to spare construction by a multi-objective loop antenna array is solved.

The invention discloses a multi-target community detection method based on k node updating and a similarity matrix, so that problem that the community detection effect is poor and the multi-type network can not be process in the prior art can be solved. The method comprises: network data are inputted; a population and a weight vector are initialized to obtain each weight vector neighbor subscript set; a similarity value between any two nodes in a network is calculated to obtain a similarity matrix; network pre division is carried out by using a k node updating strategy; an individual objective function value in the population is calculated and the objective function reference point is initialized; evolution of individuals in the population is carried out to obtain offspring groups; an offspring group objective function value is calculated and the objective function reference point is updated by the objective function value; neighbors of individuals in a current-generation population are updated by using the offspring groups; a maximum evolutional generation is reached and detection is ended; and otherwise, transferring to population evolution is carried out until community detection is completed.

The invention discloses an image segmenting method based on a dynamic multi-population integrated differential evolution algorithm. According to the method, sub-populations are divided and redistributed by adopting an original population in the aspect of population structure planning so as to guarantee the diversity of a population evolution process and avoid a local optimum phenomenon; local search variation is combined with global search variation in the variation strategy so as to achieve a balance between an optimal threshold of population survey and accelerated convergence; and the shortcomings caused by fixed parameters of a standard differential evolution algorithm are effectively overcome through the parabolic dynamic incremental change of a cross probability factor. Compared withother evolutionary algorithms on a benchmark test set, the improved algorithm has the advantage that the optimization and convergence speed can be obviously and significantly improved; and the improved differential evolution algorithm has a significant effect in accuracy and speed when being applied to image segmentation.

A protein structure prediction method based on a residue contact information crossover strategy is disclosed. The method comprises the following steps of firstly, using Robetta and RaptorX-Contact toacquire a fragment library and a contact map; secondly, using contact map information so that population individuals dynamically enter into a segment assembling phase and a loop area fine-tuning phase, and using the crossover strategy of a specific test individual and a specific area; and finally, through clustering, acquiring a final prediction result. Through using contact map information, population evolution is dynamically performed, and the crossover strategy of the specific area is used to increase search efficiency and improve prediction precision.

The invention relates to a workflow scheduling method taking communication and computing costs into account under a multi-cloud environment. On the basis of the structure and execution characters of the workflow, related factors of the communication of the current cloud resource environment and execution costs, random two-point interlace operation of a genetic algorithm and a random single-point mutation operation idea, the method improves diversity in the population evolution process, integrates virtual resources, takes into account data communication costs and assignment computing costs, optimizes a resource utilization rate and reduces the execution costs on the premise of satisfying the workflow expiration date. According to the method, under the situation that fluctuation factors exist, great property performance can be achieved in the aspects of satisfying the workflow expiration date and executing cost control, and on the premise of satisfying the workflow expiration date as much as possible, the execution costs are reduced.

The invention discloses a method for reversely planning a treatment plan. The method comprises the following steps of: A, inputting a medical image of a patient; B, drawing the tissue profiles of the body surface of the patient, a target body and organs at risks; C, setting a reserve planning target; D, establishing an initial treatment plan; E, setting an iterative optimization parameter; F, generating an individual treatment plan; G, computing an individual treatment plan dose field; H, computing the degree of adaptability; I, selecting a current optimal plan; J, if evolution times are greater than population evolution times, turning to a step M, or otherwise turning to a next step; K, evolving a population to a new generation of population and turning to the step G; and M, stopping population evolution and outputting a current optimal plan. The invention also discloses a treatment plan system. A method for computing the degree of adaptability is used for selecting an optimal plan, so that the evolution efficiency of the population can be increased, and an optimizing process is efficient.

The invention provides a method for determining the genome size of nymphaeaceae plants. The method is characterized by determining the genome size of three nymphaeaceae plants of NymphaeamexicanaZucc, NymphaeastellataWilld and Nymphaea alba L. by using Oryzasativa nipponbare and Zea mays L B73 as interior labels and utilizing flow cytometry. A result shows that the three plants are different in genome size, wherein the genome size of the Nymphaea alba L. is the largest, and the genome size of the NymphaeamexicanaZucc is the smallest. Basic data reference is provided for genomics and population evolution research of the plants.

The invention discloses a multi-path coverage method and system combining key point probability and path similarity. The method comprises the steps: firstly, dividing a theoretical path into an easily-covered path, a difficultly-covered path and an unreachable path; secondly, counting key point probabilities through the easy-to-cover path, calculating contribution degrees of individuals to generated test data according to the probabilities, improving a fitness function by utilizing the contribution degrees, and sorting target paths according to the key point probabilities; and finally, generating test data covering the target path by using a multi-population genetic algorithm, and continuously trying to cover the similar path of the target path after the sub-population covers the current target path in the evolution process. The fitness function is designed according to the probability of the key points, excellent individuals are protected, meanwhile, an individual information sharingstrategy is further perfected, individual resources in the population evolution process are reasonably utilized, it is avoided that too much time is wasted in the sub-population evolution process, andthus the test data evolution generation efficiency is effectively improved.

The invention discloses a multi-intelligent-agent manufacturing process optimization method based on a multi-object particle swarm optimization algorithm. The method comprises the following steps: constructing a multi-intelligent-agent based manufacturing process optimization model for a manufacturing process of the process industry, wherein the multi-intelligent-agent based manufacturing processoptimization model comprises a two-layer structure, the upper layer structure comprises a total control Agent and a pool Agent used for storing algorithms and data information, the lower layer structure comprises a raw material Agent, an equipment Agent, a management Agent and a waste Agent, and each intelligent Agent performs information interaction with the other Agents based on its own communication module; and using the Agent as a particle in the multi-object particle swarm optimization algorithm, endowing the Agent with the population evolution capability, establishing a corresponding data model for the multi-intelligent-agent based manufacturing process optimization model, and performing solution by using the multi-object particle swarm optimization algorithm to obtain an effective solution set. The overall cost after the optimization is lower than the actual consumed cost, so an optimized non-inferior solution set can be used as a reference in the actual production so as to improve the low consumption, high yield and high quality of the process industry manufacturing and to reduce the required cost.

The invention discloses an improved genetic method for complex computing based on a fast matching mechanism. A three-dimensional feature vector is obtained through feature extraction; during a population evolution process, a built similarity matching evaluation mechanism is used for calculating the fitness value and the confidence value of each chromosome; the chromosome is built to a spatial simplex through a simplex mutation operator; after equivalent effect space expansion at a certain proportion is carried out, mutated individuals are taken out according to a sequence, and corresponding mutation operation is carried out; and finally, in the late evolution stage, an optimal solution or an approximate optimal solution is generated according to a set stop condition. The individual evaluation times during the evolution process can be reduced, the algorithm optimal solution search speed is quickened, the method is intuitive, clear and universal, and the algorithm optimization time can be greatly reduced.

The invention relates to a residue contact information self-learning-based protein structure prediction method. According to the method, a fragment library and a contact map are obtained through Robetta and RaptorX-Contact; in the first stage of population evolution, residue pair distance distribution learning is performed, an information entropy index is established so as to reflect the convergence degree of a population, the purpose of automatic learning can be achieved; in the second stage of the population evolution, a scoring function is established with learned residue pair distance distribution information so as to assist an energy function in conformation space search; and a final prediction result is obtained through clustering. With the protein structure prediction method provided by the invention adopted, the residue pair distance information can be learned automatically so as to assist the energy function in conformation space optimization; and the information entropy indexis constructed, and therefore, the dynamic switching of the two stages can be realized.