437 results about "Selection (genetic algorithm)" patented technology

The invention discloses a wind power forecasting method based on a genetic algorithm optimization BP neural network, comprising the steps: acquiring forecasting reference data from a data processing module of a wind power forecasting system; establishing a forecasting model of the BP neural network to the reference data, adopting a plurality of population codes corresponding to different structures of the BP neural network, encoding the weight number and threshold of the neural network by every population to generate individuals with different lengths, evolving and optimizing every population by using selection, intersection and variation operations of the genetic algorithm, and finally judging convergence conditions and selecting optimal individual; then initiating the neural network, further training the network by using momentum BP algorithm with variable learning rate till up to convergence, forecasting wind power by using the network; and finally, repeatedly using a forecasted valve to carry out a plurality of times of forecasting in a circle of forecast for realizing multi-step forecasting with spacing time interval. In the invention, the forecasting precision is improved, the calculation time is decreased, and the stability is enhanced.

A Soft Computing (SC) optimizer for designing a Knowledge Base (KB) to be used in a control system for controlling a suspension system is described. The SC optimizer includes a fuzzy inference engine based on a Fuzzy Neural Network (FNN). The SC Optimizer provides Fuzzy Inference System (FIS) structure selection, FIS structure optimization method selection, and teaching signal selection and generation. The user selects a fuzzy model, including one or more of: the number of input and / or output variables; the type of fuzzy inference model (e.g., Mamdani, Sugeno, Tsukamoto, etc.); and the preliminary type of membership functions. A Genetic Algorithm (GA) is used to optimize linguistic variable parameters and the input-output training patterns. A GA is also used to optimize the rule base, using the fuzzy model, optimal linguistic variable parameters, and a teaching signal. The GA produces a near-optimal FNN. The near-optimal FNN can be improved using classical derivative-based optimization procedures. The FIS structure found by the GA is optimized with a fitness function based on a response of the actual suspension system model of the controlled suspension system. The SC optimizer produces a robust KB that is typically smaller that the KB produced by prior art methods.

The invention discloses an intelligent layout method used for a rectangular part. The method comprises the steps that S1 relative parameters of the genetic algorithm are initialized; S2 relative information of the rectangular part is extracted from a rectangular part bank to be laid out; S3 relative information of raw material boards is extracted from a board tank; S4 the obtained information is coded, and primary species are generated randomly; S5 one-by-one decoding is conducted on the primary species by means of the lowest horizontal line search algorithm to obtain solution using efficiency; S6 selection, crossover and mutation operation is conducted according to the genetic algorithm until iteration is finished, and the optimal layout scheme is output. According to the intelligent layout method, the process requirement of the rectangular part can be met well, the intelligent algorithm and the heuristic algorithm are combined, one optimizing scheme can be found rapidly and efficiently, and therefore the material using rate of an enterprise is greatly improved, layout time can be obviously shortened, and layout efficiency is improved.

The invention relates to a task observation plan solution method and system based on a genetic algorithm for multiple agile satellites. The method and system can support task planning of the agile satellites, and a target function and a constraint analysis model are constructed according to the features of the agile satellites; by figuring out a solution to the constructed constraint analysis model satisfying task planning, selection, overlapping and variation of genetic searching algorithms are conducted to achieve conflict between every two adjacent tasks, an observation planning scheme is optimized, an optimal observation plan satisfying constraint conditions is generated, the resource utilization rate of the satellites is improved, and a timeliness problem during task execution of theagile satellites is solved. For different task conditions, different disposal methods are selected to achieve reasonable distribution of satellite resources, the quantity of single-track observation tasks is increased, and the response timeliness is improved.

The invention belongs to the technical field of personalized recommendation, and particularly relates to a method and system for solving a cold start problem in a collaborative filtering technology. The method for solving the cold start problem in the collaborative filtering technology comprises the steps that a data set is selected; an initial user or project clustering model is built through an optimized genetic algorithm; clustering is conducted on the basis of the initial user or project clustering model, and a user or project clustering model is obtained; entropy values of new users or new projects to all kinds of clusters in the clustering model are calculated, and the new users or the new projects are subjected to class cluster dividing; the new users or the new projects are recommended. The invention further provides a system for solving the cold start problem in the collaborative filtering technology. The system comprises a selection module, an initial model building module, a clustering module, a class cluster dividing module and a recommendation generation module. Accordingly, an improved genetic algorithm is utilized for conducting K-Means clustering, the initial user or project clustering model is generated, and recommendation is generated for the new users or the new projects.

The invention provides a multi-unmanned aerial vehicle cooperative task allocation method based on an improved genetic algorithm. The method comprises the following three steps: establishing constraint equations such as the minimum turning radius of an unmanned aerial vehicle and the number of tasks required by a target, and a multi-unmanned aerial vehicle cooperative task allocation model based on Dubins flight path cost; generating an initial population of a predetermined scale conforming to model constraint conditions; taking the Dubins track path cost of the unmanned aerial vehicle as a fitness function, and iteratively updating the initial population by using genetic operations such as elite strategy, selection, crossover, variation and the like of an improved genetic algorithm to generate a feasible solution which minimizes the target function in fixed iteration times, and taking the feasible solution as a result of multi-unmanned aerial vehicle cooperative task allocation and route planning. The method has wide application value in multi-unmanned aerial vehicle cooperative task combat, is beneficial to implementation of multi-unmanned aerial vehicle multi-target cooperativetask execution, and improves the task completion efficiency. The method has important significance in the field of multi-unmanned aerial vehicle cooperative control.

The invention provides a method for generating MIMO (multiple-input and multiple-output) radar orthogonal polyphase code signals on the basis of genetic-tabu hybrid algorithm. The method includes: firstly, randomly generating an initial population; secondly, judging whether a stop criterion of genetic algorithm is satisfied or not; thirdly, calculating a fitness function; fourthly, selecting by proportional selection; fifthly, intersecting; sixthly, mutating by tabu search algorithm; seventhly, updating the population, and returning to the step 3 for continuing genetic algorithm with the new population. Transmission signals with fine self-correlation and cross-correlation can be designed, and polyphase code waveform designed by the method has fixed phase and is easy to generate and more suitable for practical application.

The present invention relates to an automatic stereoscopic warehouse selection operation scheduling modeling and optimizing method based on a Petri network and an improved genetic algorithm, belonging to the technical field of automatic stereoscopic warehouse operation scheduling optimization analysis. The method comprises the steps of (1) establishing an automatic stereoscopic warehouse selection operation scheduling Petri network model, (2) carrying out operation scheduling optimization algorithm designing based on the combination of the Petri network and the improved genetic algorithm, (3) designing an automatic stereoscopic warehouse selection operation scheduling optimization system according to the designed operation scheduling optimization algorithm based on the combination of the Petri network and the improved genetic algorithm, comparing the designed algorithm and standard genetic algorithm solution process efficiency and optimization results, and verifying the advantages of the designed algorithm. According to the method, the automatic stereoscopic warehouse selection operation scheduling modeling and operation scheduling fast and excellent quality optimization can be realized, and the zero load invalid operation time in an automatic stereoscopic warehouse selection operation execution process is reduced.

The invention discloses an intelligent stock-layout optimization method for woodworking sheet parts. The intelligent stock-layout optimization method includes the steps of S1, initializing relative parameters of a genetic algorithm, S2, selecting information of rectangular parts to be subjected to stock layout from a part library, S3, selecting relative information of woodworking sheets, capable of being used for stock layout of the rectangular parts, from a woodworking stock library, S4, encoding the information of the rectangular parts to be subjected to stock layout and generating an initial population randomly, S5, decoding the initial population one by one by a surplus rectangle filling based 'guillotine cutting' algorithm to acquire utilization rate of each stock layout scheme, and S6, optimizing the stock layout schemes by means of selection, crossover and mutation operations through the genetic algorithm, and outputting the optimal scheme correspondingly. According to the intelligent stock layout optimization method, 'guillotine cutting' process requirements for woodworking rectangular parts can be met, the optimal scheme can be found rapidly by means of combination of the intelligent algorithm and the heuristic algorithm, and thus, stock layout time is shortened obviously while material utilization rate of enterprises is increased greatly, and stock layout efficiency is increased.

The present invention discloses an active power distribution network frame planning method on the basis of a bi-level planning. The active power distribution network frame planning method on the basis of the bi-level planning comprises the following steps: the first step, bi-level planning model constitution; the second step, gene code; the third step, formation of an original scheme; the fourth step, individual good and bad evaluation; the fifth step, genetic operation; and the sixth step, selection of an optimal scheme. According to the invention, a model is established about an active power distribution network frame planning problem on the basis of a bi-level planning concept, and an improved genetic algorithm is used for solution. Compared with a traditional active power distribution network frame planning method, the bi-level planning concept and the improved genetic algorithm are led in the active power distribution network frame planning method on the basis of a bi-level planning to solve problems. In respect of modeling, the bi-level planning model adopted by the invention is converted to a bi-level planning problem, namely an upper layer planning problem is the construction of a line and the lower layer planning problem is minimum active power output excised amount of distributed generation under the network frame.

The invention discloses a method for optimizing cutting consumption and energy consumption of a machine tool based on an adaptive genetic algorithm, comprising the following steps: 1) a step of determining model optimization variables; 2) a step of determining an optimization objective function; 3) a step of determining constraint conditions in the model; 4 ) using an adaptive genetic algorithm to determine the cutting amount. The advantages of the present invention are: because the present invention adopts the self-adaptive genetic algorithm scheme, it is more reasonable in the selection of the cutting amount, effectively improves the utilization efficiency of the machine tool, and reduces energy consumption.

The embodiment of the invention provides a customer classification method and device based on an improved particle swarm optimization algorithm, and the method comprises the steps: initializing a particle speed and a particle position according to a classification number and a feature dimension, and setting an initial value, so as to build an initial population of a particle swarm; performing iterative updating operation on the inertia weight, the particle speed and the particle position of the population according to a preset fitness function including the customer characteristic data until apreset iteration frequency is reached; after the number of iterations is preset, respectively carrying out selection operation, crossover operation and mutation operation on the particle swarm according to a genetic algorithm after each update for next iteration update until the iteration update reaches the total number of iterations or meets a convergence condition; and obtaining a clustering center according to the particle swarm reaching the total number of iterations or meeting the convergence condition, and classifying the customers. According to the method, through organic fusion of thegenetic algorithm, falling into a local optimal solution can be avoided, the later convergence speed is increased, and the search precision is improved.

The invention discloses an air source heat pump multi-objective optimization design method of a non-dominated sorting genetic algorithm assisted by a SVR neural network. The method comprises the following steps: step 1, carrying out parameter selection and data processing according to design requirements; step 2, creating, training and testing a neural network; step 3, performing multi-objective optimization on the air source heat pump by using a non-dominated sorting genetic algorithm based on the trained SVR neural network; and step 4, obtaining the parameter value of the input variable of the optimal solution according to the Pareto solution through the above steps, thereby obtaining the design parameter value of each component, and feeding back the design parameter value to a designer.The SVR neural network assisted non-dominated sorting genetic algorithm-based air source heat pump multi-objective optimization design method provided by the invention is relatively high in precisionand can quickly realize COP and cost multi-objective optimization of a system.

The invention discloses an energy spectrum overlapping peak analysis method. The analysis method includes the steps that background rejection is carried out on energy spectrum sections which are obtained from radioactive measurement and to be subjected to overlapping peak resolution, and net peak areas of overlapping peaks and all channel net counts corresponding to the net peak areas of the overlapping peaks are obtained; the energy spectrum sections obtained after background rejection are regarded as a linear sum of multiple Gaussian functions; parameters of the Gaussian functions are combined into a chromosome; population initialization is carried out on the combined chromosome, probability construction fitness functions, from individuals, of the energy spectrum sections are combined, selection, cross and mutation operators of a genetic algorithm are adopted, the weight, average and standard deviation of all the Gaussian functions are obtained after multi-generation operation, and overlapping peak resolution is completed. Calculation is simple, the overlapping peaks overlapping three or more spectrum peaks can be resolved, and the overlapping peak resolving method can be effectively applied to qualitative and quantitative analysis for the spectrum peaks and is good in performance.

The invention relates to a soft measurement method for granularity of cement raw material grinded by ball mill. The method comprises: selection of auxiliary variables, wherein a rotating speed of a powder concentrator, a feeding flow, an inlet wind pressure of the powder concentrator and a load of the powder concentrator are used as auxiliary variables of the soft measurement model for granularity of finished products; Data pre-treatment, wherein original data are screened, filtered and standardized; soft measurement modeling based on GA-NN (genetic algorithm optimized neural network), wherein a learning algorithm used for neural network training is brought forward based on GA (genetic algorithm), weights needed to be adjusted in a network are recognized as chromosomal genes, and the network training process is completed through chromosome selection, crossover and mutation; and correction of the soft measurement model by using a long-term correction way. The method can measure quite important finished product granularity parameters which are hard to be directly detected, thereby being capable of implementing advanced control and optimized method for a raw material grinding process by the ball mill.

The invention relates to the rehabilitation training field and aims to optimize the quantifying factor and scale factor of a fuzzy controller and the fuzzy control rules, then control the current mode of an FES system accurately, stably and instantly and effectively improve the accuracy and stability of the FES system. The technical scheme adopted by the invention is as follows: the walking aid electrostimulation fine control method based on genetic-ant colony fusion fuzzy controller comprises the following steps: firstly, converting the selection of fuzzy control decision variable to the combinational optimization problem adapting to the genetic-ant colony algorithm, coding the decision variable, randomly generating a chromosome composed of n-numbered individuals; secondly, using the genetic algorithm to generate the initial pheromone distribution of the ant algorithm, utilizing the ant colony algorithm to randomly search and optimize the membership function, quantifying factor and scale factor of the fuzzy controller; and performing repeated self-learning and self-regulating according to the system output, and finally using the processes in the FES system. The invention is mainly used for rehabilitation training.

The invention relates to a multi-objective optimization computing unloading method in a mobile edge computing network, and belongs to the field of Internet of Things and artificial intelligence. The method is based on a joint optimization model oriented to time delay and energy consumption, and power selection and proportional unloading of multiple users during task unloading are realized by designing an intelligent algorithm GPSO. Firstly, a network architecture of mobile edge computing is determined, modeling is conducted according to the network architecture, models comprise a system model,an application program model, a communication model and a computing model, then an objective function is solved according to the established models, and a problem is converted into a mixed nonlinearprogramming problem. And finally, a hierarchical calculation algorithm GPSO based on a particle swarm algorithm and a genetic algorithm is designed, thereby realizing user unloading proportion strategy and power selection under delay and energy consumption joint optimization. According to the method, optimal selection of a multi-user task unloading strategy in mobile edge computing is realized byutilizing related intelligent algorithms in the field of artificial intelligence.

Systems and methods are disclosed that utilize a genetic algorithm to search for an index configuration for a collection of data such as, e.g., a database. Genetic algorithms can include stochastic search heuristics that mimic processes of natural evolution including inheritance, mutation, crossover, and selection. A population of chromosomes representing candidate index configurations can evolve to increase or optimize the fitness of the population and to identify the best (e.g., most fit) index configuration. Fitness of a chromosome may be measured based at least in part on the cost of computer resources used for executing Structured Query Language (SQL) statements in the indexed database. In various implementations, virtual indexing may be used to simulate building an index, chromosomes may be encoded using non-bitmapped representations of index configurations, chromosomes may include genes representing a column in a table in a database, dropping an index from a table in a database, or a composite index for a database, and / or a participation pool may be used to select fitter genes for an initial population of chromosomes.

The invention discloses an air source heat pump multi-objective optimization design method integrating a BP neural network and a multi-parent genetic algorithm. The air source heat pump multi-objective optimization design method comprises the following steps that 1, performing parameter selection and data processing according to design requirements; Step 2, creating, training and testing a neuralnetwork; Step 3, performing multi-objective optimization on the air source heat pump by using a multi-parent genetic algorithm based on the trained neural network; And step 4, obtaining the parametervalue of the input variable of the optimal solution according to the Pareto solution through the above steps, thereby obtaining the design parameter value of each component, and feeding back the design parameter value to a designer. The BP neural network assisted multi-parent genetic algorithm air source heat pump multi-target optimization design method is high in precision and capable of rapidlyachieving multi-target optimization of COP and cost of a system.

The invention relates to an AGV scheduling method, in particular to an AGV scheduling method based on an ant colony and a genetic algorithm. A vehicle capacity factor and a time window factor are introduced into the ant colony algorithm to improve the ant state transition probability, and a pheromone volatilization factor is improved, so that the pheromone volatilization factor can be automatically adjusted along with a calculation process, meanwhile, a pheromone updating strategy is improved, and elite ants exceeding a globally optimal solution are rewarded. And finally, local optimization isperformed on an optimal solution obtained by the ant colony algorithm by using selection, crossover and mutation operators in the genetic algorithm. The algorithm convergence speed is increased, thesolution quality is improved, the defects that when a traditional optimization algorithm is used for path planning, the convergence speed is low, and local optimum is likely to happen can be obviouslyovercome, the solving efficiency of actual problems can be improved, and blindness of the iteration process is reduced.

The invention discloses a semiconductor workshop production scheduling method based on a genetic algorithm. The method comprises: (1) analyzing a semiconductor assembly line workshop scheduling problem; (2) determining the size of each individual matrix in combination with the encoding mode according to the processing time table of each workpiece process in a workshop; (3) initializing an intermediate variable under the condition that the optimal value is not improved; (4) carrying out crossing operation on any two individuals in the population; (5) combining new and old populations, and calculating the fitness value of each individual; (6) judging whether Q' and Q are the same or not; (7) executing selection operation on the merged population; (8) judging whether r or n meets a termination criterion or not; (9) judging whether the individuals meet mutation operation or not; (10) returning the mutated population to the step (4) for operation when the other n is equal to n+1; and (11) outputting the optimal individual of the population. According to the invention, the scheduling problem of complex flexible flow production workshops in the semiconductor industry is solved; and multiple unnecessary calculation processes due to the fact that the maximum number of iterations is set to be too large are avoided, the algorithm calculation time can be shortened, and the efficiency is improved.

The invention relates to a method and system for generating a boxing scheme of articles in a logistics warehouse, and the method is characterized in that the method comprises the following steps: 1) obtaining the three-dimensional size data of all types of boxes and all articles in an order; 2) adopting a heuristic search algorithm and a genetic algorithm, according to the three-dimensional size data of all types of boxes and all articles in the order and set proficiency degree parameters, for a specific box selection scheme, searching to obtain the minimum height of the box required for loading all articles in the order under each box selection scheme and all boxing schemes meeting the minimum height of the box; and 3) searching to obtain an optimal boxing scheme required by the order according to the minimum height of the box under each box selection scheme and all boxing schemes thereof, and preset starting conditions and cut-off conditions, so that the method can be widely appliedto the fields of space planning technologies and application systems.

The invention discloses a double-resource die job shop scheduling optimization method based on an AMAS-GA nested algorithm. On the basis of comprehensively analyzing energy consumption, completion time and equipment and personnel load conditions of a workshop, a double-resource job shop multi-target scheduling problem model is established, wherein the load balance condition of equipment and personnel is measured by calculating the standard deviation of the accumulated load of the equipment and personnel, and the energy consumption of the shop considers the energy consumption of the equipment in standby and processing states; secondly, an AMMS-GA nested algorithm is designed to carry out scheduling model optimization solution, and procedure sorting is carried out by adopting a genetic algorithm by an inner layer according to a resource selection result as a constraint; and finally, a scheduling scheme result is fed back to an outer layer algorithm to influence selection of ants on resources. The method can be used for workshop scheduling and production scheduling, the workshop production efficiency is improved, energy consumption is reduced, green and energy-saving production is promoted, and meanwhile equipment and personnel load balance in production can be met.

The invention discloses a centralized resource management method based on a genetic algorithm, and relates to the field of wireless communication. The method mainly includes the steps that S1, network resources and users in a system are integrated, two-dimension chromosome coding is carried out on resource allocation, and N individuals are generated randomly and serve as an initial population, wherein N is an integer larger than two; S2, dynamic power distribution is carried out on each chromosome, and based on the power distribution and user requirements, fitness functions of the individuals are built; S3, population propagation is carried out, wherein the population propagation includes the processes of selection, intersection, mutation and correction, and the number of filial generation individuals is kept to be identical to that of parent individuals; S4, the parent individuals are replaced by the filial generation individuals, and the population propagation processes are repeated until an iteration stopping condition is met. The use ration of the power of the system can be improved, under the condition that the real-time user requirements are met, fairness among non-real-time users can still be effectively ensured, and system performance is greatly improved.

The invention discloses a BP neural network wind speed prediction method based on genetic algorithm optimization. The method comprises the following steps: firstly, collecting wind speed data of a wind power plant, establishing a BP neural network prediction model, and estimating an initial value range; then, performing real number coding on the weight and the threshold of the neural network, randomly generating a group of initial individuals to form an initial population, and each initial individual represents an initial solution of a problem; calculating the fitness of each individual in thepopulation, performing selection, crossover and mutation operations to form a next generation of population, evaluating the fitness of the individuals in the new population, judging convergence conditions, selecting an optimal individual, and taking the optimal individual as an initial weight and a threshold of the neural network; and finally, training by utilizing matlab to obtain a wind speed prediction value. According to the method, the wind speed prediction efficiency and accuracy of the BP neural network are improved.

An ant-colony-algorithm-based extraction method of intelligent olfaction spectrum characteristics representing the difference of honey is disclosed. The ant colony algorithm belongs to the heuristic feature selection approach, and automatically starts to find the best result from the characteristic points by utilizing the automatic iterative evolution of algorithm until the best result is found. The extraction method is characterized in that: ant colony algorithm is applied to selection of characteristic points, and the ant colony algorithm is applied to simulate genetic algorithm. Bayes of selected characteristic points is utilized to judge the accurate rate, and selected characteristic points are utilized to construct a fitness function to find an optimum vector combination. The main innovation points of the algorithm comprises: (a) the number of selected characteristic points is added into the fitness function, a cost parameter is set, through the adjustment of the parameter, the number of the characteristic points and judgment accurate rate can be selected according to the needs; (b) in order to avoid the update direction error caused by special points, an optimum collection is established, and the optimum collection replaces the single optimum point to carry out selection; (c) the update grade of biotin is in a direct ratio relationship with the improvement of the fitness function, the optimizing effect of the algorithm is good, and thus the upgrade range is increased; (d) in order to accelerate the calculation speed, the volatile speed of vectors with a bad effect is accelerated, thus the concentration of pheromone is decreased, so that the disturbance on the latter calculation is reduced.

The invention discloses a multi-agent cooperative task assignment method based on income maximization under the condition of considering the difference of agents. The method takes a set as a model; for a defense penetration task and a detection task, an index value of defense penetration efficiency evaluation is provided, how to effectively realize detection of the area is provided, a task allocation function model is established based on constraint conditions, task selection scheme solving based on a genetic algorithm is performed on a target function under the constraint conditions, and an optimal solution set can be obtained. In a complex battlefield environment, the tasks are quickly allocated according to the defense penetration capability and detection capability of the unmanned aerial vehicle and the task target condition, so that the income is maximized.

The invention relates to an algorithm for identifying a key protein based on a genetic algorithm in a PPI network. The algorithm comprises the steps of generating an initial population in a protein interaction network; calculating the fitness of individuals; performing selection operation by a roulette wheel method; performing crossing operation and mutation operation among the randomly selected individuals; and performing local optimization on multiple individual solutions. According to the algorithm, the defects of existing methods are overcome; indexes are optimized and bio-information is fused, so that the reliability is higher and lots of unnecessary calculations are reduced; and the predicted key protein can be locally optimized, so that the efficiency of key protein identification is improved, and the application range and practicality of the technology in the field of the bio-information are expanded and improved.

The invention discloses a hybrid genetic algorithm-based calculation unloading method in mobile edge calculation, which comprises the following steps: S1, establishing a system model to obtain calculation time delay of a sub-task set in each processor and transmission time delay among the processors, and determining each task layer value in the sub-task set according to a constraint relationship of the sub-task set; S2, initializing a population according to the determined task layer value and a random strategy to obtain initial population individuals of the sub-task set, performing symbol coding to obtain a task scheduling sequence, and optimizing the individuals in the initial population; S3, constructing a fitness evaluation function, and performing selection operation on individuals inthe optimized initial population; S4, constructing a crossover mechanism, and crossover individuals in the new population by using crossover operation based on a tabu table search algorithm; S5, performing mutation operation on individuals in the new population by using mutation operation based on a simulated annealing algorithm; and S6, judging whether the iteration step length is reached or not, and if not, repeating the step S3-S5; and if so, outputting a globally optimal solution.

The invention relates to a fingerprint image segmentation method based on artificial immunogenetics and morphology, belonging to the technical field of image processing. In the invention, an optimal segmentation threshold is calculated by an artificial immunogenetic method; the algorithm integrates the immune mechanism and evolution mechanism, absorbs the advantage of parallel searching in the genetic algorithm, can effectively prevent the phenomenon of colony degradation on the basis of quick searching by vaccine inoculation and vaccine selection, and uses fingerprint image grey scale value consistency and antibody concentration in the segmentation method based on grey scale and gradient distribution as the affinity function of the antibody to carry out genetic iteration, thereby generating the optimal antibody; and therefore, the method can effectively segment the fingerprint image, has the characteristics of favorable segmentation effect, high robustness, low calculation amount and low time consumption, and can satisfy the requirement for real-time fingerprint identification.