116 results about "Gravitational search algorithm" patented technology

The invention discloses a universal gravitation search-based unmanned plane air route planning method, which comprises the following eight steps: 1, establishing an unmanned plane air route planning mathematical model; 2, setting initialization improved universal gravitation search algorithm parameters and battlefield environmental parameters; 3, randomly initializing N routes and initial positions and accelerated speeds of various particles, and establishing a rotating coordinate system; 4, calculating threat cost of each route according to threat information and the mathematical model; 5, updating inertial mass Mi(t) of the particles according to a weight-based rule; 6, calculating the sum of accelerated speeds of each particle in all directions according to a universal gravitation standard, and updating the speeds of the particles according to a group information speed updating rule; 7, updating the position of each particles according to the updated speed of each particle and the choice of survival of the fittest; and 8, if the number of iterations is greater than the maximum number of iterations, exiting a circulation, otherwise, returning to the step 4 for next iteration. The obtained optimal air route coordinate is subjected to coordinate inverse transformation and a result is output.

The invention relates to an automatic setting method for control parameters of a water turbine speed regulating system. According to the method, firstly, T-S fuzzy model identification is conducted on a control object of the water turbine speed regulating system of a real unit to obtain a high-precision simulation system of the water turbine speed regulating system; secondly, according to the simulation system, a target function with the PID control parameters as optimization variables is set up, and the target function is worked out through a gravitational search algorithm to obtain the optimal PID control parameters. Due to the fact that the precision of the set simulation system is high, the characteristics of the real unit can be really reflected, the control parameter optimization result obtained through the simulation system can be directly applied to the real unit, and the dynamic quality of the unit speed regulating system is effectively improved.

The present invention provides a multi-unmanned aerial vehicle cooperation sequential coupling task distribution method of a mixing gravitation search algorithm, and relates to the unmanned aerial vehicle cooperation task distribution field. The method comprises: a multi-unmanned aerial vehicle cooperation task distribution model is constructed in the time coupling constraint, a fitness function and a task constraint are obtained, in the gravitation search algorithm based on genetic operators, the individual discretization coding and the population are initialized, the individual is decoded, and the fitness function is employed to calculate the fitness and perform individual update. Because the genetic operators are added in the gravitation search algorithm, the multi-unmanned aerial vehicle cooperation sequential coupling task distribution method of the mixing gravitation search algorithm has good general applicability, the number of times of long-term simulation tests and data statistics constructs a more improved database to allow the model to be more improved; and compared to the discrete particle swarm algorithm, the mixing gravitation search algorithm can be rapidly converged, the searching optimization result is optimal, the iteration process is brief, and the convergence speed is fast.

The invention discloses a multi-objective optimization method based on an improved gravitation search algorithm. According to the algorithm, a memory strategy is introduced into a universal gravitation search algorithm, so that particle swarm information and information of previous generations and next generations of particles are shared, the global search capability and the local search capability of the particles are balanced, and the premature convergence problem is solved. On this basis, a diversity enhancement mechanism is introduced into the algorithm, namely, particle speed and position are controlled each iteration, so that the diversity loss is relieved, the particle diversity is improved, and diversity and distributivity of non-dominated solution sets are enhanced. Therefore, by means of the multi-objective optimization method based on the improved gravitation search algorithm, the phenomenon that multi-objective optimization is caught in a local extremum can be effectively avoided, and convergence, diversity and distributivity of non-dominated solutions are remarkably improved when the gravitation search algorithm is applied to the field of multi-objective optimization.

The invention discloses a multi-target coordinated operation optimization method of wind and photovoltaic storage electricity generation units and relates to the technical field of wind and solar storage electricity generation control. The method comprises the steps of determining output power models of the electricity generation units, wherein the output power models comprise the output power models of wind driven generators, the output power models of photovoltaic generators and the output power models of energy storage batteries; building multi-objective functions of the wind and photovoltaic storage electricity generation units, wherein the multi-objective functions comprise the electricity-generation-unit total-cost minimum objective functions and the renewable-energy-source loss-ratio minimum objective functions; setting constraint conditions of the multi-objective functions, wherein the constraint conditions comprise the power balance constraint conditions, the generator output constraint conditions and the energy-storage-battery capacity constraint conditions; solving the multi-objective functions through an improved multi-target universal gravitation search algorithm to obtain an active output value of each period of each electricity generation unit. On the basis that renewable energy sources are fully used, the longest service life of each storage battery is achieved, and therefore overall operating efficiency of the wind and photovoltaic storage electricity generation units is improved.

The invention relates to a load power consumption mode identification method. The load power consumption mode identification method includes the steps: acquiring the electrical load at a sampling time interval T, and obtaining L daily load curves corresponding to L days of time; performing spatial clustering based on density on the obtained daily load curves, and obtaining a classical load power consumption mode; extracting characteristics describing the power consumption behavior of a user in different time scale; and utilizing a gravitation search algorithm to cluster the obtained power consumption characteristics of the user; repeating clustering, utilizing a cluster evaluation index to evaluate the clustering result, and selecting the optimal clustering result, that is, the identification result of the load power consumption mode. The gravitation search algorithm used by the load power consumption mode identification method has high searching capability and high convergence speed, and is not easy to fall into local optimal solution, and is better than a traditional clustering algorithm on the identification effect, so that identification of the load power consumption mode can be effectively realized and powerful guidance for design of the demand side response scheme, analysis of load characteristics and high-accuracy prediction can be provided.

The invention provides a method for monitoring the state of a gearbox of a wind power generation set. The method includes the following steps of: collecting historical data of a wind power generation set SCADA system, screening out the active power, wind speed, cabin temperature, principle shaft rotation speed and gearbox oil temperature of the set under the healthy operation condition, and establishing a standard expert database; optimizing the penalty coefficient and the nuclear parameter of a least squares support vector regression machine by using a gravitational search algorithm, and establishing a gearbox oil temperature mapping model under the healthy operation condition by taking the active power, wind speed, cabin temperature, principle shaft rotation speed in the expert database as inputs and the gearbox oil temperature as an output and based on the optimized vector machine model; monitoring the gearbox of the wind power generation set in real time by using the mapping model, inputting the actually measured values of the active power, wind speed, cabin temperature and principle shaft rotation speed to obtain the predicted value of the gearbox oil temperature, defining the quotient of the predicted value of the oil temperature and the actually measured value as a judging index, and judging that a failure occurs in the gearbox of the wind power generation set and giving an alarm, if the statistical property of the judging index is abnormal. The method can be widely applied to early warning of the gearbox of the wind power generation set.

The invention relates to the machine vision detection field, and discloses a method and a device for detecting surface color defects of solar silicon chips through the machine vision technology. The detection object is distribution information of the surface colors of the silicon chips after a process of plasma enhanced chemical vapor deposition (PECVD). The classifying scheme includes using an image filtering technique, a color image segmentation technique, a color image hue, saturation, and lightness (HIS) spatial analysis technique and the like for processing and analyzing collected images; extracting feature information of the images; classifying the silicon chips into good silicon chips and defect silicon chips according to surface quality after training and testing of the information through a mode identifying method which combines a support vector machine with an improved gravitational search algorithm; sending a classifying result to an executive mechanism and controlling a uniaxial robot to take out the defect silicon chips. According to the method and the device, mechanism is simple, maintenance and operation are facilitated, and detecting requirements can be satisfied.

The invention discloses a wind speed section prediction method and system based on an artificial neural network, and the method and system are used for the short-time wind speed prediction of a wind field. The method comprises the steps: decomposing an initial complex time sequence into a plurality of time sequences in a simple structure through VMD (variational mode decomposition); carrying out the feature selection through GSO (Gram-Schmidt orthogonal); taking a processed wind speed sequence as the input of the ANN (artificial neural network), wherein the output of the ANN is the upper and lower bounds of wind speed at a future moment; finally training the weight and bias of the ANN through an MOGSA (Multi objective gravitational search algorithm), taking two contradictory indexes (coverage rate and section width) as an optimization target, and obtaining an optimal scheme set. The wind speed section predicted through the method has a higher coverage rate for the actual wind speed section, and is small in section width. The above combined model enables the prediction accuracy to be improved to a very high level.

The invention discloses an optimizing method for product assembly sequences. The optimizing method includes the following steps that firstly, a three-dimensional space assembly interference matrix is constructed according to the geometrical relationship, the cooperative relationship and the motion constraint relationship of parts of a product to be assembled, and feasible product assembly sequences are obtained; secondly, the assembly cost serves as the index of program evaluation of the product assembly sequences, and a fitness function suitable for the universal gravitation search algorithm is constructed; thirdly, the calculation formula of the universal gravitation search algorithm is defined and transformed again, and a new universal gravitation search and calculation formula is constructed; fourthly, the new universal gravitation search and calculation formula is used for conducting iteration solving on the assembly sequences of products to be assembled, and an obtained calculation result is the optimal assembly sequence. According to the optimizing method for the product assembly sequences, the assembly cost serves as the index of program evaluation of the assembly sequence, the optimal assembly sequence can be rapidly and reliably obtained through the revised universal gravitation search algorithm, and the combination explosion problem of the assembly sequences of complex products is solved.

The invention, which belongs to the field of precise modeling and control optimization of the hydro electric generating set of the power system, discloses a fuzzy fractional order PID control method for a speed regulating system of a pump storage group. On the basis of a fractional calculus and a fuzzy control theory, a fuzzy fractional order PID controller for a pump storage group is established; modeling of a speed regulating system of the pump storage group is carried out, wherein a regulator model, an approximate elastic water hammer model of a conduit system, a total-characteristic-curve-based pump turbine model, and a generator and load model are established; and then a controller parameter is optimized by using a provided parallel gravitation searching algorithm. According to the control method, requirements of hydroelectric energy system simulation, power system analysis, and optimized pump storage group control can be met to the greatest extent.

The invention discloses an intelligent microgrid building load power dispatching method improving gravitational search. First, all power using loads in an intelligent microgrid building are classified, an objective function and constraint conditions of building load dispatching are clarified, and a load power dispatching model is built. Then a gravitational search algorithm is subjected to binary discretization and a parasite population and a host population are established. At the same time, the memory and population information sharing capabilities of particles in a particle swarm algorithm are introduced, and parasitic behaviors of organisms are simulated. Through co-evolution of the two populations, the convergence speed and search precision of the algorithm are improved, the diversity of the populations and the global search ability are improved, and the shortcomings of the original gravitational search algorithm such as premature convergence and low optimization accuracy are overcome. The method considers the objectives including resident economy, comfort and stability of a power grid and adopts the improved gravitational search algorithm for multi-objective optimization, so that the least electricity cost, the most comfort and the least impact on the power grid are achieved for residents.

The present invention provides a kind of power system environmental economic dispatching strategy based on improved multi-objective gravitational search algorithm, and the method comprises the following steps: 1. Constructing while considering that the minimum operating cost of the system and the minimum discharge of pollutants are objective functions, and establishing electric power System environmental economic optimization scheduling model; II. Established a power system environmental economic scheduling model that comprehensively considered system operating costs and pollutant discharge costs, and proposed an improved multi-objective gravity search algorithm to solve the model; III. For basic In order to solve the problem of slow convergence speed of the gravity search algorithm, in the process of updating the individual position, inspired by the particle swarm optimization algorithm, the position update formula of the gravity search algorithm has been improved; IV. In order to guide the group to approach the Pareto optimal solution set area and ensure the algorithm The solution set is evenly distributed, and the elite retention strategy is adopted; V. The fuzzy set theory is used to generate the best compromise solution, and a scheduling plan is provided for decision makers.

The invention discloses a multi-target cloud task balanced scheduling method, a server and a storage medium. According to the invention, the method comprises steps of carrying out initialization processing on the target parameters of the current multi-target cloud task; generating N population particles for the current multi-target cloud task based on each target parameter according to a preset rule, wherein each population particle represents a scheduling result of each cloud task on different cloud resources, each population particle represents an m-row n-column matrix, and a single elementof the matrix represents a scheduling result of a single cloud task on one cloud resource; calculating the particle speed of each group particle based on a gravitation search algorithm; updating a matrix corresponding to each population particle according to the particle speed of each population particle; taking the updated matrix as a final scheduling solution, and finally selecting a task scheduling optimal solution from the final scheduling solution. According to the task scheduling method and the task scheduling device, under the condition that constraint conditions of task predetermined completion time and task execution budget exist at the same time, balanced scheduling of the current multi-target cloud tasks can be realized.

The invention provides a short-term wind speed prediction method based on phased global optimization. A wind speed mixed prediction model characterized in that variational mode decomposition is employed for a time series data composition model, Gram-Schmidt orthogonal is employed for a feature extraction model and an extreme learning machine is employed for a basic learning model; a gravitationalsearch algorithm is employed for global optimization of the parameters of the wind speed mixed prediction model; the optimal prediction model parameters suitable for short-term wind speed prediction can be selected preferentially to achieve accurate prediction of the wind speed. The invention also provides a short-term wind speed prediction system based on phased global optimization.

The invention relates to a high-precision multi-joint serial connection mechanical arm anti-kinematics solution. A hybrid particle swarm optimization and gravitational search algorithm (PSOGSA) is used, a formula (please see the formula in the description) of a nonlinear weight distribution coefficient s is introduced, the early stage of algorithm design is partial to the gravitational algorithm, and the middle stage and the later stage of algorithm design are partial to the particle swarm optimization, so that search efficiency is improved. Three improvement strategies including improvement point dynamic and narrow boundary, non-linear time-varying weight and local optimal correction combination and super-inter-belt weak directivity return diffusion are adopted. By means of the algorithm and the improvement strategies, a unique inverse solution is obtained within a small number of iteration, errors are always stabilized in the 10<-8> level, and theoretical calculation time can be reduced to 2.58 ms each time. According to the special structure mechanical arm with three shafts intersected at a point, the position and posture separation inverse solution strategy is used, solution performance can be further improved, the errors can be reduced to 10<-14> level, and theoretical calculation time can be reduced to 1.597 ms each time.

The invention discloses a multi-vehicle vehicle route optimization method, a server and a system. The multi-vehicle vehicle route optimization method comprises the steps of: 1. constructing a vehiclerouting optimization model of multiple vehicle type; 2, solving a vehicle route optimization model of multiple vehicle types; mapping the particle position in the gravitational search algorithm to thecustomer point sequence, and assigning the vehicle to the customer point. The crossover operator and mutation operator of genetic algorithm are introduced in the gravitational search algorithm. If the crossover operator and mutation operator are better than the original particle fitness value, the position of the particle is updated. When the maximum number of iterations is reached, the optimal solution is output.

The invention relates to the field of transformer real-time hot spot temperature prediction, in particular to a transformer real-time hot spot temperature prediction method, which comprises the stepsof firstly obtaining historical data of load current, environment temperature, top oil temperature and real-time hot spot temperature of a transformer, and preprocessing the historical data to generate a training sample set and a test sample set; then selecting a training sample set to establish an SVR prediction model; training the SVR by adopting a training sample, optimizing the parameters of the SVR by adopting an improved gravitation search algorithm in the training process, and improving the prediction capability of the prediction model; and finally, inputting the test sample into the trained SVR for prediction to obtain a real-time hot spot temperature prediction value of the transformer. According to the method, the problem of localized optimization of a gravitation search algorithm is effectively solved, the problem that parameters of the support vector machine are difficult to select is effectively solved, the prediction performance of the support vector machine is enhanced,and the real-time hot spot temperature prediction precision of the transformer is improved.

The invention discloses a chaotic swarm intelligent optimization high-precision optimal soft measuring instrument for a propylene polymerization production process. The instrument comprises a propylene polymerization production process, a field intelligent instrument, a control station, a DCS database storing data, an optimal soft measuring model optimizing a chaotic least square support vector machine based on an improved gravitational search algorithm, and a melt index soft measurement value display, wherein the field intelligent instrument and the control station are connected with the propylene polymerization production process and are connected with the DCS database, the optimal soft measuring mode is connected with the DCS database and the soft measurement value display, and the optimal soft measuring model optimizing the chaotic least square support vector machine based on the improved gravitational search algorithm comprises a data preprocessing module, a chaotic analysis module, a least square support vector machine module, a model update module, and an improved gravitational search algorithm optimization module. The optimal soft measuring instrument for the propylene polymerization production process realizes swarm intelligent optimization, high-precision chaos forecast.

The invention discloses a DER grid-connected admission capacity planning method based on dual-layer scene interval power flow. The planning method proposes the dual-layer scene interval power flow bysufficiently utilizing the multi-scene technology and interval power flow features, the method comprises the following steps: performing Latin hypercube sampling based on the accumulative probabilitydistribution of the wind power and the photovoltaic to obtain the whole sample space, and obtaining two layers of scene sets by using a K-means clustering algorithm, wherein the first layer scene setperforms computation by using the interval power flow, and the subordinate second layer scene sets meet the constraint if the node voltage satisfies the constraint, or performs the power flow computation by selecting the classic scene for each subordinate scene sets, thereby judging whether satisfies the constraint; solving the node voltage line-crossing probability, and establishing the DRE grid-connected admission capacity model based on the dual0layer scene interval power flow by taking the maximized DRE grid-connected admission capacity as the target and the node voltage as the chance constraint, and performing the solution by applying a universal gravitation search algorithm.

Provided is a network security situation assessment model based on LAHP-IGFNN; firstly, according to the method, linear programming and an analytic hierarchy process are combined, the linear programming is used for improving the consistency of judgment matrixes in the analytic hierarchy process, and the subjectivity problem of the analytic hierarchy process is reduced; then, the fuzzy neural network is optimized by using a gravitation search algorithm with an improved updating formula, so that the convergence speed of the algorithm is increased and the algorithm is prevented from falling intolocal optimum; simulation experiments show that the LAHP has reasonableness and better consistency, and the IGFNN has advantages in the aspects of convergence speed and fitness, so that the LAHP-has the advantages in the aspects of convergence speed and fitness. The IGFNN situation assessment method has better performance.

The invention discloses a constraint priority rule-based reactive power optimization method in a power system. The method comprises the following steps of (1) establishing a reactive power optimization mathematic model of the power system and setting algorithm parameters; (2) generating a random initial group; (3) performing load flow calculation to obtain a fitness value of particles and an out-of-limit condition of a state variable, and storing the best individual and the global best individual of the particles; (4) if iteration is carried out for the first time, directly performing the step 5, or otherwise, performing a constraint processing method proposed by the invention; (5) updating the particles according to a speed and position updating formula of a gravitational search algorithm to obtain a new group; and (6) judging whether the algorithm meets a stop condition or not, if yes, stopping the iteration and outputting a global optimal value, namely, an optimal solution of a reactive power optimization problem, or otherwise, returning to the step 3 and continuing to perform the iteration. The method has relatively good optimization effects of high search efficiency, good convergence effect, good robustness and high solution quality in an aspect of handling the reactive power optimization problem of the power system.

The invention provides a boiler drum water level PID parameter setting method, which comprises the following steps: a) for a given transfer function model of feed water flow for drum water level and a transfer function model of a PID controller, to begin with, determining sampling time and sampling frequency, and then, carrying out Z transformation on the transfer functions to obtain corresponding difference equations of the transfer functions; b) selecting a fitness function capable of judging whether the PID regulating parameters are optimum; c) initializing three parameters of the PID controller and improving relative parameters of a gravity search algorithm; and d) through the improved gravity search algorithm, setting boiler drum water level PID controller parameters. The method adopts the improved gravity search algorithm to set the boiler drum water level PID controller parameters; and simulation research shows that the method is better than an engineering setting method and a method for optimizing the PID controller parameters based on a genetic algorithm, has better global searching ability, can enable the boiler drum water level control effect to be better and is higher in robustness.

The invention discloses a network fishing detection method based on a douche group algorithm support vector machine. The method comprises the following steps of firstly, initializing basic parametersof the douche group algorithm, including population number, iteration times, individual dimension and search space; randomly initializing the position and range of the individual; and then dividing into leader vessel sea sheaths and follower vessel sea sheaths according to the magnitude of the fitness value, and excavating the optimal parameters of the support vector machine by using the coordination and cooperation of the two vessel sea sheaths. In each iteration, the function for evaluating the fitness value of the individual is the detection accuracy of the parameter carried by the individual on the phishing website data set by the support vector machine. Compared with the common optimization algorithms such as a genetic algorithm, a gravitation search algorithm, a bat algorithm and a particle swarm algorithm, the optimal parameter parameters of the support vector machine can be mined as much as possible on the optimized support vector machine, and the fishing detection accuracy ofthe support vector machine is improved.

The invention discloses a memory multi-point crossover gravitational search-based feature selection method. Each particle is set as the alternative solution of an optimal feature subset; the quality of the alternative solutions are evaluated through a band subset evaluation function; particles are guided to carry out information exchange, and fast convergence can be completed; and solutions corresponding to particles with best quality are optimal spectral feature subsets. According to the method, in order to improve the adaptability of the algorithm, a population evolutionary degree-based information exchange mechanism is put forwards based on a gravitational search algorithm: in an exploration stage, the algorithm fully learns from other particles in a population based on a multi-point crossover strategy so as to carry out extensive search; and in a development stage, the algorithm learns from the optimal experiences of the population and the algorithm itself in a centralized manner so as to ensure fast convergence. With the memory multi-point crossover gravitational search-based feature selection method of the invention adopted, an optimal spectral feature subset which has few bands and can obtain stable classification results can be selected out, and therefore, problems such as complex calculation and low classification accuracy which are caused by high redundancy of hyper-spectral remote sensing image data can be solved.

The invention relates to the field of intelligent optimization algorithms and discloses a method for improving population diversity in a gravitational search algorithm. The particle population diversity is calculated in each iteration process for performing optimization search through the gravitational search algorithm. When the population diversity is larger than the maximum threshold, each particle gets close to the current best position and the previous best position thereof, and the particles perform the suction operation of a bacterial chemotaxis process to improve the local optimization ability; when the population diversity is smaller than the minimum threshold, each particle gets away from the current worst position and the previous worst position, the particles perform the exclusive operation of the bacterial chemotaxis process to increase the population diversity; when the population diversity is located between the maximum diversity threshold and the minimum diversity threshold, the original velocity updating formula in the gravitational search algorithm is used. According to the method for improving the population diversity in the gravitational search algorithm, the exclusive operation of the bacterial chemotaxis process is led to the gravitational search algorithm to improve the particle population diversity and avoid premature convergence, and accordingly the optimization ability of the algorithm is improved.

The invention relates to a difference adaptive universal gravitation searching algorithm and a sewage processing control method based on the same. The searching algorithm comprises following steps of S1, initializing groups; S2, calculating fitness values of the groups; S3, calculating inertia mass M and accelerated speed alpha of each group; S4, updating an individual position; and S5, comparing to determine whether iteration times is reached, if yes, outputting an optimal value, and if not, repeating the steps S2, S3, and S4. The beneficial effects are that convergence speed is associated with step lengths during acceleration of the convergence speed, so the best way is that by updating the individual parameter G0 and the accelerated speed alpha in real time, the convergence speed of the algorithm can be effectively controlled and algorithm precision is improved.

The invention discloses a swarm-intelligence high-precision radar sea clutter prediction system, which comprises a radar, a database and an upper computer, wherein the radar, the database and the upper computer are sequentially connected; the radar illuminates a detected sea area and radar sea clutter data are stored to the database; the upper computer carries out modeling and prediction on the sea clutter data in the database; and the upper computer comprises a data preprocessing module, an extreme learning machine modeling module, an improved gravity search algorithm optimization module, a sea clutter prediction module, a discrimination model updating module and a results display module. The invention also provides a radar sea clutter prediction method for optimizing the extreme learningmachine based on the improved gravity search algorithm. The radar sea clutter prediction system and the method provided in the invention can realize swarm intelligence optimization and high precision.

The invention relates to the intelligent optimization algorithm field and discloses a method for improving a gravitation search algorithm by use of a compound form method. The compound form method is used for enhancing the local search ability of the gravitation search algorithm: the gravitation search algorithm is used for global search to find the optimal particle position; two premature decision conditions are introduced, the population fitness variance sigma 2 of the current population is less than alpha and the average distance D(t) between particles is less than beta (alpha and beta are predetermined small thresholds); if the two conditions are satisfied, the premature convergence phenomenon of the gravitation search algorithm occurs and then the compound form method is introduced, and the optimal particle position found by the gravitation search algorithm at present is taken as an initial compound form vertex and local search is carried out by use of relatively powerful local search ability of the compound form method; a compound form vertex formed at last is taken as a new particle position value of the gravitation search algorithm to continue searching. The method for improving the gravitation search algorithm by use of the compound form method is capable of effectively avoiding the premature convergence phenomenon of the gravitation search algorithm, and therefore, the optimal performance of the algorithm is improved.

The invention belongs to the code design field of DNA calculation, relates to the group intelligent optimization algorithm and DNA codes and particularly relates to a DNA sequence optimization methodof the improved gravitational search algorithm based on chaotic and hybrid Gaussian variation. The method is characterized in that firstly, all the DNA sequences are generated in the D-dimensional search space as the initial population, and the improved gravitational search algorithm based on chaotic and hybrid Gaussian variation is utilized for optimization, through continuous loop iteration, anoptimal solution to an optimization problem can be finally obtained; for the gravitational search algorithm, calculating the total combined force of each individual in different directions is needed,the individual's acceleration is then calculated according to the total combined force, the speed and the position of each individual are updated according to the acceleration, and so on, when the algorithm reaches the maximum number of iterations, algorithm search stops, and the better quality DNA sequence code can be finally constructed. The method is advantaged in that an optimal DNA code sequence satisfying multiple constraints can be searched.