38 results about "Chaotic genetic algorithm" patented technology

A soft measurement method of industrial production melt index on PP polymerization includes selecting nine variables influencing variation of melt index as input variables of soft measurement mode, using master element analysis to pick up main composition from input variables for eliminating off relativity between variables, applying radial based function neuro-network to set up nonlinear model between input and output as well as simultaneously utilizing fuzzy genetic algorithm to carry out optimum selection on model parameter.

Disclosed is an on-chip network mapping method based on the ant-colony chaos genetic algorithm. The standard ant-colony algorithm is basically used and the genetic algorithm is introduced in the on-chip network mapping method, parameters about each ant are coded by real numbers, codes of the ants are utilized as chromosome in the genetic algorithm, and algorithm parameters of coded ants are adjusted by the genetic algorithm in each iteration. During running of the algorithm, recycled results of each iteration of the algorithm are monitored, if the fact that the algorithm is trapped in a local optimum solution is monitored, mutation probability of the genetic algorithm is increased by a method of introducing a chaos model, and further, the parameters of the ant-colony algorithm are changed by means of the genetic algorithm. By the aid of the on-chip network mapping method, capability of the anti-colony chaos genetic algorithm for searching the solution space can be improved effectively, and trapping in the local optimum solution is avoided. In addition, the on-chip network mapping method has excellent practical values and wide application prospect for solution of massive on-chip network mapping.

The invention relates to an unmanned aerial vehicle emergency communication path planning method and system. The method includes following steps: step 1, performing three-dimensional grid division on space in which an unmanned aerial vehicle flies to acquire grid nodes, building a grid chart, marking a starting point and a target point of the unmanned aerial vehicle, and marking radar distribution and topographic information; step 2, according to the radar distribution and the topographic information in the space in which the unmanned aerial vehicle flies, building a flying threat model and a flying limitation model at the same time; step 3, building flying paths according to the flying threat model and the flying limitation model; step 4, optimizing the flying paths through a chaos genetic algorithm to determine a final flying path. Compared with the prior art, the unmanned aerial vehicle emergency communication path planning method and system have the advantages that interference of low-altitude obstacles and radar can be avoided safely, shortest flying time and optimal paths to reach specified end points can be realized, and instantaneity and quickness are high.

The invention discloses an optimal allocation method of basin water resources based on a multi-objective chaotic genetic algorithm, and belongs to the technical field of optimal allocation of water resources. The method includes the steps of obtaining basic information of basin water resources; establishing a multi-objective water resource optimal allocation mathematical model and performing allocation model parameter calibration; solving a water resource optimal allocation alternative scheme set by using a multi-objective chaotic genetic algorithm; and finally, determining a best equilibrium scheme of water resource optimal allocation through a chaotic neutral network comprehensive evaluation model. According to the invention, the chaotic ergodicity and the inversion of the genetic algorithm are coupled, the speed of the algorithm is improved, the optimal solution is stable, and the multi-objective optimal allocation requirements of a basin water resource complex system are met.

The invention relates to a comprehensive power distribution network optimization planning method based on a gene modified chaos genetic algorithm. The comprehensive power distribution network optimization planning method is characterized by including the steps of (1), establishing a power distribution network COP (coefficient of performance) investment model, (2) determining optimization variable, and (3) a GR-CGA (gene-repair chaos genetic algorithm). The comprehensive power distribution network optimization planning method has a certain value on theoretical research and practicability value, a power distribution network COP scheme can be generated via a program to perform quantitative analysis on power grid loss, quantitative treatment measure optimization and effectiveness evaluation for a power grid, an experiential treatment measure can be changed to a quantitative scientific decision treatment measure, treating effect is controllable, best treating effect can be achieved with the least cost, and an optimal investment program scheme can be provided to limited programming reformation investment for the current power grid.

The invention provides a power distribution network anti-error optimization method. The power distribution network anti-error optimization method is characterized by comprising the following steps: 1, dividing a power distribution network topological system into a plurality of independent units according to a current running state, wherein each unit is provided with only one off switch and the number of the units is equal to the number of switches with off states; 2, performing real number encoding on the on-off state of each unit by a switch exchange algorithm, and connecting all the units into a chromosome; and 3, through a set objective function and set constraints, calculating the network by a chaos genetic algorithm so as to obtain an optimal solution. The invention has the advantages as follows: the power distribution network anti-error optimization method has certain theoretical study value and certain practical value; on the premise of meeting security constraints, the running way of a distributing line is changed by a switch operating method and the like, so that branch circuit overload and voltage out-of-limit are eliminated, feeder load is balanced and network loss is minimum; and the power distribution network anti-error optimization method has an obvious advantage in network loss improvement and convergence rate and is more suitable for on-site real-time application.

The invention relates to an STEP-NC based intelligent nonlinear process planning method. The method comprises the steps of determining a machining operation method corresponding to a component machining feature type through a pre-trained BP neural network model; sequencing all machining steps in the machining operation method based on pre-defined machining step sequencing principles to obtain a reasonable machining step sequence; and in allusion to each machining step in the machining step sequence, selecting resources matched with the machining step, and optimizing each machining step and process parameters of each machining step by adopting a chaotic genetic algorithm to obtain an optimal machining process plan. According to the method, the chaotic algorithm, the genetic algorithm and the BP neural network are organically combined and applied to process optimization for the STEP-NC, thereby being capable of performing efficient, accurate and intelligent logical reasoning, effectivelysolving a complex process planning problem, and having important significance for the further study of the STEP-NC theory.

The invention discloses a chaos genetic algorithm based test case intensive simple algorithm. The chaos genetic algorithm based test case intensive simple algorithm comprises initializing male parent body codes; performing fitness calculation on a male parent body; defining genetic operators are defined, wherein the genetic operators comprise three steps of selection, intersection and variation, the genetic variation and the optimization are performed on the male parent body mainly to obtain a new male parent body finally, the change of the variation to an optimal solution can be increased due to the production of the new male parent body, and accordingly the fitness evaluation needs to be performed on the new male parent body after the genetic operators are finished to determine whether the output conditions are met or not, an optimal filial generation is output if yes, and the chaos disturbance is added if not; performing continuous iteration until the difference between fitness average values calculated through twice calculation is less than a preset minimum positive number epsilon 1. According to the chaos genetic algorithm based test case intensive simple algorithm, the algorithm is simple, the test efficiency can be improved, and the test cost can be reduced.

The invention discloses a multi-target optimized rectification method of relay protection. The rectification method comprises the steps that (1) a target function of multi-target optimized rectification of relay protection is established, and according to performance requirements of relay protection, optimized indexes of relay protection are selected, and a multi-target optimization model of relay protection rectification is established; (2) rectification variables of multi-target optimization of relay protection are selected; (3) constrained conditions of the rectification variables in the multi-target optimization model of relay protection rectification are set; (4) the target function of multi-target optimized rectification of relay protection is solved by a chaos genetic algorithm to obtain a set of Pareto optimal solutions of the target function; and (5) one optimal solution which can satisfy an expected target of relay protection is selected from the set of Pareto optimal solutions in a fuzzy membership degree method. The method can realize integrated optimization of reliability, selective and quick action performance of relay protection.

The invention relates to a regional traffic coordinating and optimizing control system and method based on vehicle average delay. The regional traffic coordinating and optimizing control system comprises intersection nodes and a regional coordinating control node. The intersection nodes are used for collecting local traffic flow status information and outputting a timing plan of an intersection; and the regional coordinating control node is used for collecting regional road network traffic flow statuses, coordinating control over all intersections and outputting timing plans of all the intersections. The regional coordinating control node comprises a traffic information collecting module, a coordinating and optimizing module and a timing plan outputting module. The traffic information collecting module is used for collecting the traffic flow statuses of road networks; the coordinating and optimizing module is used for coordinating and optimizing the signal timing plans of all the intersections through a multi-intersection coordinating control device; and the timing plan outputting module is used for outputting the timing plans coordinated by the coordinating and optimizing module to all intersection nodes to be carried out. According to the regional traffic coordinating and optimizing control system and method based on vehicle average delay, dynamic characteristics of the regional road network traffic flow are analyzed, with the purpose of minimum vehicle delay, a regional vehicle delay model and the coordinating control method are established, according to the high-dimensional feature of the delay model and the system real-time requirements, a chaos genetic algorithm is adopted to coordinate, optimize and control the regional traffic signals, and the traffic efficiencyof the regional road networks can be effectively improved.

The invention relates to a chaos genetic BP neural network image segmentation method based on Arnold transformation. The method comprises BP neural network optimization through adoption of a chaos genetic algorithm and image segmentation by utilizing a trained neural network. The specific process of the chaos genetic algorithm is as follows: (1) a swarm is initialized, two swarms x, y are generated through chaos mapping, the small swarm x is taken as an initial swarm, and the large swarm y is standby; (2) individual fitness values in the initial swarm x are calculated; and individuals the number of which is set after the individual fitness values in the initial swarm x are replaced with individuals in the large swarm y, and fitness values of the individuals after replacement are calculated; and (3) according to the calculated individual fitness values, selection, intersection and chaotic variation operation are performed on the individuals in the initial swarm x until the fact that the maximum evolution frequency is reached or the maximum fitness is not changed, and then the algorithm stops. Ergodicity of a swarm evolution process can be effectively ensured, neural network training process is speeded up, and an image segmentation effect is enhanced.

The invention applies chaos genetic algorithm (CGA) to make united optimization design for the area of a radiating surface and the thickness of a thermal insulating layer of nano-satellite, so as to reach the temperature requirement ensuring the nano-satellite to work normally better. According to one aspect of the invention, a method for determining united optimization design parameter of satellite thermal insulating layer and radiating surface is characterized by comprising: the satellite is divided into a plurality of temperature set total units; a group of design parameter (Fr and delta s) with minimum value of one united optimization design objective function (f (Fr and delta s)) of the thermal insulating layer and the radiating surface is determined; the optimized objective function (f (Fr and delta s)) is corresponding to the temperature of each of the temperature set total units and has the positive correlation with the deviation of the preset optimum working temperature, including searching the optimization within the whole feasible solution range of the optimized objective function (f (Fr and delta s)), thereby determining the optimization design parameter which is better to satisfy the comprehensive evaluating indicator of the thermal insulating layer and the radiating surface.

A soft measuring meter based on bionic intelligence comprises on site intelligent meter connected with the industrial process object, storage device and upper position machine, intelligent meter, data storage device and the upper position machine connected sequentially, the said upper position machine being soft measurement intelligent processor, which comprises standardized handling module, radial basic function neural network establishment module, module parameter optimization module based on chaotic genetic algorithm, signal sampling module and soft measurement module. It also puts forward a failure diagnostic method. It is convenient, extensive in application, fine in measuring result, high in precision.

The present invention discloses an intelligent feature identification method facing STEP-NC 2.5D manufacturing features. The method comprises the following steps of: constructing the minimum subgraphbased on a STEP neutral file, wherein the construction mainly comprises extraction of geometric topology information based on the STEP neutral file and generation of the minimum subgraph based on convexity-concavity identification of edges; and performing feature identification through a neural network based on chaos-genetic algorithm optimization. The method disclosed by the invention combines the chaos-genetic algorithm, a genetic algorithm and a BP artificial neural network to overcome defects that BP nerve is low in convergence speed and is easy to fall into a local extreme, can effectively and accurately identify STEP-NC 2.5D manufacturing features, and has an active reference value for further improvement and enforcement of a STEP-NC standard.

The invention belongs to a license plate recognition system, and discloses a license plate character recognition method based on an SIFT operator and a chaos genetic algorithm. The method is characterized in that Chinese characters and alphanumeric characters of a license plate are separately recognized, that is, the Chinese characters are recognized by using an SIFT operator feature extraction and template matching method; and the alphanumeric characters are recognized by using a thirteen-point feature extraction method and a support vector machine, and the problem of low overall recognition rate of the license plate characters due to that most of the existing license plate recognition systems adopt a unified character feature extraction and recognition method for recognition is solved. Meanwhile, in order to improve the classification capability of the support vector machine, the method adopts the chaos genetic algorithm to optimize radial basis function parameters and penalty factors, license plate images of different backgrounds are collected and tested and simulated on matlab software, the overall recognition rate of the characters can reach more than 99%, and the chaos genetic algorithm has a higher character recognition rate and a faster convergence rate than a traditional genetic algorithm.

The invention discloses a combined chaotic genetic algorithm for resource allocation. The algorithm is characterized by firstly setting parameters and initializing each parameter, and definging the population gen=0; according to the specific resource allocation problem, generating a chaotic sequence, and then generating the initial population based on the chaotic sequence according to the scale ofthe specific resource allocation problem; judging whether gen is greater than max_gen, if gen is greater thanmax_gen, stopping the calculation flow and outputting the calculation result; otherwise, defining gen to be gen+1, sequentially carrying out the breeding operation, the hybridization operation and the mutation operation; then using the local search heuristic method to search for the best chromosomes in the population and preserving the best chromosomes in the population; then generating the next chaotic sequence for the next computation, after the calculation is completed, outputting the calculation result. The combined chaotic genetic algorithm of the invention effectively reduces the constraint number of the resource allocation model, improves the population quality, acceleratesthe convergence speed, and improves the global searching ability and the computational efficiency of the algorithm.

The invention relates to a chaotic inheritance of wind power in a microgrid. The BP neural network prediction method comprises the following steps: S1, collecting the historical data of the output power of the wind turbine generator system in the microgrid, and dividing the data set into training data and test data; S2, preprocessing the mixed normalization according to the distribution characteristics of the data set, so that the data distribution becomes uniform; S3, constructing a BP neural network and initializing weights, thresholds and other parameter values of the neural network; S4: optimizing the weights and thresholds of the neural network by using the chaotic genetic algorithm, and searching for the optimal neural network parameters; S5:using the processed training data to trainchaotic inheritance-BP neural network, and then the prediction data is output, and the prediction error is calculated. The invention can reduce the influence of the data distribution characteristic on the model, improve the prediction accuracy of the fan output in the micro grid, and provide certain reference for accurate wind power prediction of the micro grid.

The invention provides a new energy template machine addressing method and system based on a chaotic genetic algorithm. According to the method, whether template machine replacement is needed is determined, blower fans are divided into multiple large groups according to characteristics, and template machines are further re-calculated through the chaotic genetic algorithm; accurate relevant meteorological prediction data can be acquired through the new template machines to acquire accurate active / reactive prediction data. The method is advantaged in that quantitative indexes are employed to analyze template machine performance for disadvantages of a traditional subjective template machine selection method, real-time template machine replacement is realized through the chaotic genetic algorithm, theoretical generating capacities and air abandoning volumes of other blower fans in a wind power field can be accurately estimated through the proper template machines, and the method has quite important actual application values.

The invention relates to a high-proportion distributed photovoltaic grid-connected absorption capability analysis method. According to the method, a chaos disturbance formula is added to a chaos genetic algorithm, the diversity of a new generation of individuals is increased through an artificial degradation factor and a chaos disturbance factor, an immigrant operator is added, the population diversity is increased, and the problem of falling into a local optimal solution is effectively solved; and then the improved chaos genetic algorithm is applied to the new field of distributed photovoltaic consumption of the power distribution network. According to the method, the problem that the maximum capacity of the distributed photovoltaic power supply allowed to be accessed by the power distribution network cannot be accurately and quickly calculated by an existing calculation method can be solved.

The invention relates to a clustering routing protocol for a wireless sensor network, in particular to CRCGA (an Energy-efficient and load-balanced clustering routing protocol for wireless sensor networks using a chaotic genetic algorithm). The method comprises the following steps of: simultaneously selecting an optimal cluster head and finding an optimal path by using the chaotic genetic algorithm, and encoding the optimal cluster head and the optimal path into a single chromosome. When a fitness function is constructed, energy consumption minimization and load balancing are considered, and anew termination judgment condition is introduced, so that the algorithm is converged quickly. Moreover, the cluster is maintained by adopting the self-adaptive round cycle considering energy and loadbalance, and the routing path is correspondingly updated, so that the network energy consumption is reduced, and the network life cycle is prolonged.

The invention relates to a wireless sensor network (WSN) routing protocol, in particular to an improved multi-hop LEACH protocol based on chaotic genetic algorithm for wireless sensor networks (ICGA-LEACH) . The ICGA-LEACH considers the node residual energy, the ratio of the node residual energy to the load and the node centrality to define a cluster head election threshold function, so that the probability that nodes which are located in the center of the cluster, low in load and high in energy become cluster heads is high, therefore uniformly distributed clusters are formed, and the communication energy consumption in the clusters is reduced. In order to reduce inter-cluster communication energy consumption, a chaotic genetic algorithm is adopted to search for a globally optimal multi-hop routing path. Moreover, the cluster maintenance is carried out by adopting a self-adaptive round period, so that a large number of control messages generated by frequent clustering are reduced, andthe network energy consumption is further reduced. Therefore, the ICGA-LEACH improves the network energy efficiency while balancing the network load, and effectively prolongs the network life cycle.

The invention discloses a dam monitoring analysis method and system based on an image recognition technology, and the method comprises the steps: carrying out the preprocessing of a collected dam panoramic image through a preprocessing module; performing feature extraction on the preprocessed image by using a feature extraction module, and sending features to a feature fusion module; the feature fusion module establishes a dam crack detection model according to the features, and then optimizes the dam crack detection model based on a chaos genetic algorithm; inputting the panoramic image of the dam into the optimized dam crack detection model, and identifying the crack of the dam in real time; according to the invention, based on artificial intelligence technologies such as machine vision and deep learning, images are processed, analyzed and understood by using a computer, and defects occurring in the operation process of the dam can be accurately detected.

The invention discloses a voltage quality optimization treatment method based on chaos inheritance, and the method comprises the steps of collecting the three-phase active power and reactive power of the head end of a feeder line and the three-phase voltage of a bus through an SCADA system, and constructing a voltage optimization model according to the three-phase active power and reactive power and the three-phase voltage of the bus; calculating individual fitness according to the voltage optimization model, and generating an initial population by using a chaos genetic algorithm; performing selection, crossover and mutation operation on the initial population to obtain an evolutionary population; performing immigrant operation on the evolutionary population in combination with the fitness, and setting an iteration condition; if the iteration condition is not met, recalculating the individual fitness; otherwise, outputting a result, and obtaining an optimal solution of the voltage optimization model. The beneficial effects of the invention are that the optimization capability of individuals and the diversity of the individuals are improved through the chaos genetic algorithm, and the reactive loss reduction rate is improved at the same time.

The present invention relates to an improved LEACH clustering routing method CGA-LEACH (an improved LEACH algorithm for wireless sensor network based on chaotic genetic algorithm) based on chaotic genetic wireless sensor network, the method includes system model, population initialization, fitness function construction And four parts of chaotic genetic operation. Construct a fitness function by considering energy consumption and load, use conditional chaotic mapping to generate real coded chromosomes, and use chaotic genetic selection, crossover and mutation operations to improve the convergence speed and find the optimal cluster head, thus forming a uniform distribution and energy consumption and load-balanced cluster structure. Ultimately, the network life cycle is effectively extended, the network load is balanced, and the energy efficiency of the network is improved.