60 results about "Mutation probability" patented technology

The invention discloses a temperature and humidity sensor data high-dimensional feature compression method based on quantum approximate optimization, and the method comprises the steps: inputting a temperature and humidity sensor time sequence data matrix, carrying out the quantum entanglement coding, and generating a quantum state; constructing a variable component sub-circuit of a quantum approximate optimization algorithm based on the quantum state, and dynamically updating circuit parameters through a genetic algorithm to obtain an output quantum state; performing projection measurement on the output quantum state to generate a candidate feature subset, updating a genetic algorithm population through quantum interference, and executing a dynamic crossover operation to generate a new feature subset; calculating a mutation probability by using a quantum gradient, executing an adaptive mutation operation, and optimizing a feature subset; the nonlinear relation between temperature and humidity data features is captured through quantum entanglement coding and quantum interference, dynamic parameter optimization and quantum gradient variation are combined, robust feature selection in a high-noise environment is achieved, feature compression efficiency and precision are improved, and the method is suitable for high-dimensional data processing in an Internet of Things scene.

The invention provides a remanufacturing workshop scheduling method based on reinforcement learning and evolutionary algorithm fusion, relates to the technical field of production scheduling optimization, and solves the problem of remanufacturing system scheduling in three stages of disassembly, reprocessing and assembly. A four-dimensional decision model covering process sorting, factory distribution, machine selection and speed gear scheduling is constructed, and an initial population with diversity and high-quality characteristics is generated by adopting a multi-strategy hybrid initialization method. A reinforcement learning decision module based on Q-learning is introduced, an optimal combination is dynamically selected from various crossover operators, mutation operators and neighborhood search strategies, the crossover probability and the mutation probability are dynamically corrected according to the distribution characteristics of the Pareto leading edge, and a dual escape mechanism is integrated to enhance the capability of the algorithm to jump out of local optimum. According to the scheme, the group search advantage of the evolutionary algorithm is exerted, the dynamic optimization of the search process is realized, and an efficient and accurate scheduling solution is provided for a complex remanufacturing system.

The invention relates to a multi-protocol self-adaptive multifunctional data acquisition system and method based on an FPGA (Field Programmable Gate Array) technology, in particular to the field of data acquisition, and is characterized in that electrical and time sequence characteristics of an original electrical signal accessed to a physical channel are analyzed in real time and are matched with a protocol characteristic library pre-stored on an FPGA chip to identify a protocol type and load corresponding analysis logic; performing numerical difference processing on the analyzed single sensor data sequence, calculating a physical quantity change rate and an acceleration, and inputting the physical quantity change rate and the acceleration into an FPGA built-in Bayesian network model to obtain a data point mutation probability; a risk state vector is formed by combining the sudden change probability and the spatial position coordinate of each sensor channel, the risk state vector and a preset catastrophe mode weight vector are subjected to Hadamard product operation to obtain a weight coefficient of each channel, and data acquisition frequency and processing resource allocation are adjusted; and performing tensor contraction operation on the multi-channel data with the aligned timestamps and a preset multi-dimensional failure mode feature kernel, and generating and preferentially sending a fusion early warning data packet when a result exceeds a corresponding risk threshold.

The invention provides an RPA script minimum increment repairing method based on evolutionary swarm intelligence and reinforcement learning, and relates to the technical field of RPA process automation, and the method comprises the steps: obtaining an event, and generating a rule JSON set; analyzing and mapping condition keys of the rule JSON set, and extracting a decision chain; performing rule coverage vector locking encoding on the decision chain, setting a mutation probability according to a structure influence factor to generate candidate individuals, crossing the individuals with similar structures, and sequentially completing grammar, variable and interface permission verification to obtain an initial patch candidate group with complete coverage; converting the initial patch script into a chain graph, inputting the chain graph into a local-global double-flow enhanced network for script optimization, outputting optimized patch candidates with composite scores, sorting according to the composite scores and the number of node changes, selecting a dominant pedigree to execute controlled micro mutation and block crossing, and obtaining a final patch script meeting a convergence condition; and carrying out full regression test on the final patch script, and after the test is passed, carrying out deployment and archiving a running log.

The invention discloses a hybrid learning-based flexible job shop energy-saving batch scheduling method, which relates to the technical field of shop scheduling and comprises the following steps of: establishing a flexible job shop energy-saving scheduling model by taking minimization of maximum completion time and total energy consumption of a machine as optimization objectives; the method comprises the following steps of: constructing a mapping relationship between an operation process and machine selection by adopting a three-layer coding mode, initializing a population through multiple initialization strategies, decoding a coding part, and generating an initial solution; constructing a neighborhood structure, performing population evolution through an adaptive crossover and mutation operator, and adjusting the crossover and mutation probability according to the population evolution degree; searching an optimal solution through a plurality of search strategies; traversing the population to perform non-dominated sorting, and adjusting the crossover mutation rate according to a non-dominated sorting result; and judging whether an iteration termination condition is met or not, if not, continuing iteration, and if so, outputting the optimal Pareto frontier solution. According to the invention, the energy consumption is reduced while the processing time is minimized.

The application relates to a house interior design selection method, a terminal device and a storage medium, and the method comprises the following steps: setting a chromosome code composed of a plurality of room codes and a room position code, setting the value interval of each room code and room position code; setting the maximum value and minimum value of each gene on all individual chromosomes; randomly generating an initial population; according to the input mutation probability and the crossover probability, the population is iteratively updated through the mutation rule and the crossover rule; drawing the corresponding house plan of each individual in the kth generation population before and after the crossover; when the selection result of the better house plan is received, the individual chromosome corresponding to the selected better house plan is used as the individual in the k+1th generation population. The application can enable the user to participate in the design process of the indoor plan in a timely manner, and improve the design efficiency and the user satisfaction.

This application discloses a sliding mode control method, device, equipment, and storage medium for a permanent magnet synchronous motor, belonging to the field of control technology. It includes: determining the objective function corresponding to M sets of optimized parameters included in the first-generation optimized parameters; determining the target set of optimized parameters included in the first-generation optimized parameters; determining the fitness of the M sets of optimized parameters based on the objective function corresponding to the M sets of optimized parameters; determining the crossover probability and mutation probability corresponding to each of the M sets of optimized parameters based on the fitness of the M sets of optimized parameters; generating the next-generation optimized parameters including M sets of optimized parameters based on the crossover probability and mutation probability corresponding to each of the M sets of optimized parameters; and so on, until the target set of optimized parameters including G-generation optimized parameters is determined; and controlling the permanent magnet synchronous motor through the sliding mode controller based on the target set of optimized parameters including G-generation optimized parameters. This application can improve the control effect of permanent magnet synchronous motors.

The present invention discloses a method, system, and medium for economic load distribution of a new energy power system. The method includes: constructing an objective function of the new energy power system; initializing a population according to preset constraints; calculating the fitness value of each particle according to the objective function and the position of each particle; calculating the individual optimal value of each particle and the global optimal value of the population according to the fitness value of each particle; updating the speed and position of each particle in the population according to a particle swarm algorithm; performing selection, crossover, and mutation operations on the population using a genetic algorithm to obtain a new population, and updating the crossover probability and mutation probability; when an end condition is met, outputting the particle corresponding to the global optimal value, and using the economic load parameter of each generator set at the position of the particle as the optimal distribution result. The present invention is planned according to the actual situation of the new energy power system, is more adaptable to the actual situation of the new energy power system, and can achieve optimal economic load distribution.

The invention relates to the technical field of artificial intelligence, in particular to a cue word automatic optimization method based on an evolutionary algorithm, and the method comprises the steps: generating an initial cue word population through analyzing a business demand, and verifying the validity; performing mutation operation of dynamic mutation probability adjustment on the current population to generate a filial generation candidate set; a standardized failure case set is used as an evaluation sample, and the combined population is subjected to test sorting; executing an elitism and tournament selection strategy based on a sorting result to screen high-quality individuals to obtain a next-generation population; judging whether a termination condition is met or not, and if yes, outputting a candidate optimal cue word; and carrying out automatic business verification on the candidate prompt words, and if the verification is not passed, automatically adjusting parameters based on failure reasons and triggering secondary iteration until the verification is passed. According to the method, directional optimization can be carried out on the business failure case, the evolution pressure is dynamically adjusted, the efficiency and accuracy of cue word optimization are improved, and automatic closed-loop iterative optimization of cue words is realized.

The application provides a high-efficiency fuzzy test method based on a score matrix, only normal basic blocks with a block score greater than 0 are subjected to a plug-in operation, and branches with a reaching probability of 0 are deleted through a pruning mode, which can prevent the fuzzy test of the application from generating new irrelevant test case inputs; therefore, it can be seen that the application avoids the fuzzy test tool of the application from exploring paths to irrelevant codes through the optimization mode; meanwhile, test cases in the seed pool of the application can trigger new paths reaching the target basic block or trigger vulnerabilities in the code to be tested, and the application selects a test case according to the final score and the mutation probability corresponding to each test case in the seed pool to perform mutation, and continues to test the vulnerabilities of the code to be tested according to the test case after mutation, so that the test case can reach the target basic block as much as possible through a high-score path, and the vulnerability mining efficiency of the software system to be tested is improved.

This invention provides a rotor-bearing system fault diagnosis method and system based on virtual-real fusion, relating to the field of signal detection technology. The method comprises: deriving an expression for the magnetic pull of mixed eccentricity and imbalance, and establishing a rotor-bearing system twin model based on Hertzian contact theory; introducing rotor eccentricity and bearing inner / outer race faults to construct a twin model for multiple fault conditions; identifying multiple model parameters using an improved genetic algorithm (introducing feature sensitivity evaluation factors, adaptive crossover mutation probability, and simulated annealing) to obtain a modified twin model; generating twin fault samples based on the modified model, and training a one-dimensional cyclic generative adversarial network with a classifier (designed with a comprehensive loss function) to generate samples that closely resemble the true distribution; and finally, forming a balanced dataset from the virtual-real fusion samples, which is then trained using a one-dimensional convolutional neural network to achieve fault classification. This invention addresses the problems of insufficient fault data and significant discrepancies between the twin model and the real data, thereby improving the accuracy and reliability of fault diagnosis.

The application discloses an outlet SO2 mutation early prediction network and a feedforward probability fusion method, relates to the technical field of industrial process control and intelligent prediction, and comprises the following steps: obtaining outlet SO2 and related measuring point historical sequence data collected by a distributed control system, performing sliding window organization processing on the historical sequence data, forming a historical data matrix containing multivariate time sequences, and synchronously generating corresponding observation identification information. The application realizes early discrimination of mutation probability by introducing a feedforward variable and a working condition self-adaptive time lag alignment mechanism, drives prediction fusion of a smooth path and a mutation path, completes integrated output of prediction and early warning, improves adaptability by using physical time lag modeling and multi-scale alignment, enhances mutation response capability by rolling self-fusion and control plan injection, and realizes the transformation of prediction from history dependence to causal driving.

The invention discloses a mechanical arm trajectory planning method and system based on a hybrid particle swarm optimization, and the method comprises the steps: carrying out the interpolation of a multi-degree-of-freedom mechanical arm through a 3-5-3-degree polynomial, setting four key nodes, and obtaining the interpolation angle of each joint of the mechanical arm at the key nodes through inverse kinematics analysis; and taking the duration time of each section of track as particles, obtaining an optimal time distribution scheme by using a particle swarm algorithm, and generating a motion track of each joint on the mechanical arm based on the optimal time distribution scheme. In the speed updating process of the particle swarm algorithm, performing three-stage updating on the particle speed; in the first stage, an initial update speed is obtained according to the speed and position of particles; the second-stage speed obtains an intermediate update speed based on the adaptive crossover probability updated with the number of iterations; and in the third stage, obtaining the final updating speed based on the mutation probability.

The invention relates to a low-carbon scheduling parameter determination method and device of a micro-grid and computer equipment. The method comprises the following steps: randomly initializing scheduling parameter values of multiple groups of target microgrids to generate an initial current fox population in a fox optimization algorithm; according to the fitness function, calculating the individual fitness of each fox individual in the current fox population; according to the individual fitness, a scheduling parameter value corresponding to each fox individual in the current fox population is updated, and a candidate fox population is obtained; and based on a preset mutation probability, performing mutation operation on each fox individual in the candidate fox population to obtain a new current fox population, and returning to the step of calculating the individual fitness of each fox individual in the current fox population according to the fitness function until the current fox population meets a preset iteration condition, and if yes, obtaining a target low-carbon scheduling parameter value of the target microgrid according to the current fox population meeting the preset iteration condition. By adopting the method, the scheduling effect of the micro-grid can be improved.

The invention provides an airborne flight control system-oriented sparse coverage edge feedback-based efficient fuzzy test method, which comprises the following steps that: a fuzzy test system initializes a seed queue and constructs an initial probability distribution model for each seed, and the mutation probabilities of all byte positions are equal; the fuzzy test system tracks an execution path of a test case in real time in a variation process, and dynamically updates an enhanced control flow diagram to record edge hit times and path information; the fuzzy test system calculates a path fitness score based on the edge hit times and the path depth in the enhanced control flow diagram, adjusts a probability distribution model of seeds according to increments, and improves the mutation probability of high-contribution byte positions; and the fuzzy test system selects byte positions and mutation operators according to the adjusted probability distribution model to generate a new test case, and detects whether a new path is triggered to update the seed queue or not until a termination condition is met. According to the method, the abnormal condition of the detected program is efficiently, accurately and reliably detected, and it is guaranteed that security holes and defects of the airborne flight control system are found in time.

This invention discloses a mapping-guided fuzzing method for loop code, applied in the field of software testing. The method includes: continuously mutating test cases, inputting them into a test case queue, sending them to the program under test (CUPT) with instrumented loop code structures, and outputting a coverage statistics table when the fuzzing termination condition is met; training a deep learning model and back-calculating the weighted distance sum to construct and output a mapping relationship between the byte sequences of test cases and the coverage of the loop code structure; based on the mapping relationship, assigning mutation probabilities to the corresponding byte sequences in the test cases corresponding to the loop code structure coverage and performing mutations to generate child test cases, which are then used as input to the CUPT for fuzzing until the fuzzing termination condition is met, and outputting a fuzzing report. This method mutates the byte sequences of test cases based on mapping relationships, enabling the targeted generation of test cases that improve the coverage of loop code results.

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 application relates to a distributed cache parameter optimization method and device, computer equipment and a storage medium. The method comprises the following steps: randomly generating multiple groups of distributed cache parameters as an initial population; inputting the initial population into multiple learners of a cache performance prediction model respectively, predicting the cache performance of the initial population, and determining the health value of the initial population according to the cache performance of the initial population; performing evolution processing on the initial population according to the health value of the initial population, a mutation probability threshold and a crossover probability threshold to generate a new population; updating the new population as the initial population, returning to the step of inputting the initial population into the multiple learners of the cache performance prediction model respectively, and iteratively performing evolution processing to obtain a group of distributed cache parameters with optimal cache performance. The method can improve the efficiency and accuracy of distributed cache parameter optimization.

The application discloses a kind of based on the bending process planning method of improved NSGA-Ⅱ, step one, input processing information: including workpiece information, die library information, machine tool processing parameters;Step two, workpiece manufacturability check: check whether workpiece can be completed processing under existing bending equipment, if not, jump to step six;Step three, NSGA-Ⅱ initialization: set algorithm parameters, generate initial population;Step four, genetic evolution: the iterative process of strategy optimization algorithm using adaptive adjustment crossover mutation probability;Step five, result processing: according to the priority of optimization target from the pareto optimal solution set output in step four Optimal bending process is selected;Step six, output process scheduling results: if workpiece is manufacturable, output bending sequence, positioning sequence;Otherwise, output workpiece is not manufacturable.The application can obtain high processing efficiency bending process under the condition of meeting interference constraint, precision constraint and processing constraint.

The application provides a self-adaptive optimization method for process forming scheduling workshop process parameters, comprising the following steps: feature extraction and feature alignment are performed on multi-modal data of the process forming scheduling workshop to obtain feature vectors of the modal data; the contribution degrees of the modal data to the target are used to calculate the modal weight, and the feature vectors are weighted and fused; the process parameters and the processes are respectively coded into chromosomes, an adaptability function is constructed according to the weighted and fused feature vectors, the influence weight of the process parameters is calculated based on the sensitivity of the process parameters and the modal contribution degree, and the cross probability and the mutation probability of each parameter gene are adaptively adjusted according to the influence weight, so that the optimal process parameter and the process scheduling scheme are solved; the optimal process parameter and the process scheduling scheme are input into a simulation system and compared with online measured results, if the error between the predicted defect rate and the actual defect rate exceeds a threshold value, the step length of genetic search and the contribution degrees of the modes are updated and then re-iterated, otherwise, the optimal process parameter and the process scheduling scheme are issued to the production line for execution.

The invention discloses a power grid fault traveling wave positioning device stationing method based on an improved genetic algorithm. The method comprises the following steps: S1, establishing a mathematical model: establishing a mathematical model of a target function and a reclosing time function; encoding the information into a graph structure; s2, initial population generation: numbering lines to form an initial population; converting the node information into individual codes according to a coding rule, and calculating individual fitness through a fitness function; s3, genetic manipulation: performing selection, crossover and mutation operations on the initial population to generate new individuals; s4, algorithm termination judgment: if the optimal individual in the chromosomes has a plurality of genes, terminating the algorithm; and if the optimal individual has no gene, continuing genetic manipulation until a termination condition is met. The bidirectional fault current caused by the distributed power supply is accurately captured through three-state switch coding, the crossing / mutation probability is adjusted in real time through the Sigmoid function to achieve the dynamic genetic algorithm, and the convergence speed is increased; and the complex network is disassembled into non-overlapping sub-regions by an original topology grading strategy, so that the calculation complexity is reduced.

The present invention discloses a vehicle logistics scheduling optimization method based on an improved genetic algorithm. The method obtains order information, transport vehicle information, commodity vehicle information, and parking lot information; determines a function optimization objective and constraints; sets a population size, crossover probability, mutation probability, and iteration termination conditions; initializes the population and performs genetic encoding using a dual-chromosome natural number encoding, one for the order chromosome and one for the transport vehicle chromosome; dynamically decodes the encoding and calculates the function fitness value; and repeats the following operations: selection, crossover, mutation, and local optimization until the termination conditions are met and the optimal solution is output. By improving the genetic algorithm, using a greedy algorithm for initial population optimization, dynamic decoding of the dual-chromosome encoding, and local optimization, the present invention solves the comprehensive vehicle logistics optimization problem for multiple transport vehicle types, multiple commodity vehicle types, multiple parking lots, and mixed loading and unloading, while ensuring stable optimization results and relatively fast computational speed.

The invention relates to the technical field of soil detection, in particular to a soil harmful substance residue detection method, device and system, and the method comprises the following steps: comparing the difference between the spectral intensity under any channel and the distribution condition of all fluorescence intensities in the channel section where the channel is located; determining a spectral noise confidence coefficient by combining the mutation probability of the fluorescence intensity under any channel in each channel interval so as to screen out a spectral peak; and determining an asymmetric factor based on the difference between each spectral peak in the baseline adjacent region of each channel interval and all fluorescence intensity distribution in the corresponding channel interval and the spectral noise confidence coefficient, and carrying out baseline correction and denoising on the spectrum detected each time by adopting a denoising algorithm for soil harmful substance residue detection. According to the method, the asymmetric proportion in the BEADS algorithm is dynamically optimized, spectral noise is effectively inhibited, trace spectral peaks are reserved, and the precision of soil harmful substance residue detection is improved.

The invention discloses an NSGA-II (Non-dominated Sorting Genetic Algorithm-II) algorithm and a forest coverage type classification method. The algorithm comprises the steps of population initialization, non-dominated sorting, fitness evaluation, tournament selection, crossover and mutation operation, elitist retention and termination condition judgment. According to the invention, based on the improved NSGA-II algorithm, simplified congestion distance calculation is adopted, so that the required convergence speed is improved by 30-40%, the calculation time is reduced, and meanwhile, through cooperation of the adaptive crossover probability and the mutation probability, dynamic adjustment can be carried out according to the population evolution state, global exploration and local development are effectively balanced, premature convergence is avoided, and the convergence efficiency is improved. And the precision of outputting the optimal solution is improved.

The present invention discloses a design method, system, device and storage medium for AAV capsid protein, including: setting an initial temperature according to a preset temperature, the initial temperature characterizing the mutation probability of each position of the initial AAV sequence; determining a cooling rate according to the sum of the improvement rate of the targeting score and the yield score of the current AAV capsid protein sequence, the diversity score and a preset maximum cooling rate; determining the current temperature according to the initial temperature and the cooling rate, selecting a first preset number of AAV capsid protein sequences at the current temperature according to an objective function, and continuing cooling optimization until the preset index requirements are met, and stopping the cooling search; selecting a second preset number of AAV capsid protein sequences from all AAV capsid protein sequences that meet the preset index requirements for clustering to determine the final designed AAV capsid protein sequence. The embodiments of the present invention can reduce the risk of being trapped in a local optimal solution, improve the targeting and yield of AAV capsid proteins, and can be widely used in the field of bioinformatics.

The present application relates to the technical field of extrusion production line beat optimization, more particularly to a kind of MOEA-based extrusion production line beat on-demand control resource optimization configuration method and device, comprising the following steps: S1.gene coding;S2.population initialization;S3.construct objective function: the optimization target of objective function includes balance loss rate, station loss index, smoothing index and production waste amount;S4.get fitness function by objective function and solve, if the current fitness function value obtained by solving is optimal solution, then output current population, otherwise execute step S5;S5.gene crossover and mutation, generate new population, then return to step S4;Wherein, the crossover probability and mutation probability of generating new population are calculated according to population and fitness function.This application can solve the resource optimization configuration problem of extrusion production line, can optimize the resources of production line according to actual production order demand, improve the balance rate and production efficiency of production line.

The invention discloses a heterogeneous emergency resource scheduling optimization method considering fairness, and belongs to the field of emergency resource scheduling optimization. For close cooperation type heterogeneous resources, time and satisfaction rate dual-dimension modeling is adopted, a hybrid coding and decoding mode is adopted according to problem features, and an emergency resource scheduling scheme is expressed in a mathematical form; aiming at a target and a constraint condition, adopting a random rule with priority to ensure the quality of an initial population; by adopting a crossover operator combining shuffling crossover and partial matching crossover, the diversity and stability of the population in the iteration process are ensured; by adopting the adaptive crossover mutation probability, the diversity of the population is maintained, and the efficiency of the algorithm is improved; and an elitism strategy with a lowest crowding degree threshold is adopted, population diversity is increased, and premature maturity of the population is prevented. The method is suitable for scheduling optimization of close cooperation type heterogeneous resources under the condition of short supply in the early stage of disasters, and a new thought is provided for solving the problem of emergency resource scheduling of the heterogeneous resources.

The application discloses a star selection method and system based on an improved adaptive genetic algorithm, and relates to the technical field of image positioning and registration. The technical points of the application comprise: preprocessing obtained basic star table data; inputting the preprocessed basic star table data into a selection model based on an improved genetic algorithm for selection; using a binary mode for coding and carrying out population initialization; calculating individual fitness according to a fitness function, and calculating the crossover and mutation probabilities through an improved adaptive adjustment strategy according to the calculated fitness values, and then carrying out selection, crossover and mutation operations according to the calculated crossover and mutation probabilities; decoding the genes and calculating constraint conditions; and outputting a star selection result when the maximum number of iterations is reached and all the pointing field information has been optimally selected. The application can select uniformly-distributed stars in the premise that the number of stars in a given imager field of view is known, so as to provide the imager with observation and correct the pointing of the imager.

The embodiment of the invention discloses a game card combination generation method, device and equipment based on a genetic algorithm, and the method comprises the steps: calculating a first fitness value of each game card in a game card set according to a target function, and determining a plurality of target cards according to the first fitness values; performing recombination operation on the plurality of target cards to generate a plurality of recombination cards, determining a target adjustment coefficient corresponding to the number of iterations of the recombination operation, adjusting the capability value range of the recombination cards according to the target adjustment coefficient and the minimum capability value range corresponding to the types of the recombination cards, and generating a target variation range, determining a target variation probability associated with the target variation range; according to the method, the recombined cards with the target mutation probability exceeding the mutation probability threshold value are determined as the target recombined cards, mutation operation is performed on the target recombined cards to generate the multiple mutation cards, the multiple mutation cards and the multiple target cards are combined to generate the game card combination, premature convergence is avoided, and the rationality of the game card combination is improved.

The invention provides a multi-unmanned aerial vehicle task allocation method and system based on a multi-target blue whale hunting mechanism, and belongs to the field of unmanned aerial vehicle task allocation. The problems that an existing unmanned aerial vehicle multi-target task allocation method is prone to falling into local optimum, and later convergence precision is insufficient are solved. Segmented initialization is applied during initialization, initialization is performed according to task allocation in the first stage, so that an initial blue whale group is more reasonable, and a chaotic mapping idea is adopted in the second stage, so that initial distribution of the blue whale group has higher randomness and ergodicity; an elitism strategy is applied, excellent individuals of each generation are reserved, and the convergence speed is increased; a simulated annealing thought is introduced in each iteration process, so that a relatively high mutation probability exists in the initial stage of iteration to accept a relatively poor solution so as to jump out of local optimum; the blue whale positions are searched in a continuous space through continuous value coding, threshold conversion and an optimization algorithm, a blue whale group is guided to evolve to an excellent solution through fitness function feedback, and finally an actually executable task allocation scheme is obtained through mapping.