49 results about "Chaotic search" patented technology

A genetic algorithm (GA) approach is used to adapt a wireless radio to a changing environment. A cognitive radio engine implements three algorithms; a wireless channel genetic algorithm (WCGA), a cognitive system monitor (CSM) and a wireless system genetic algorithm (WSGA). A chaotic search with controllable boundaries allows the cognitive radio engine to seek out and discover unique solutions efficiently. By being able to control the search space by limiting the number of generations, crossover rates, mutation rates, fitness evaluations, etc., the cognitive system can ensure legal and regulatory compliance as well as efficient searches. The versatility of the cognitive process can be applied to any adaptive radio. The cognitive system defines the radio chromosome, where each gene represents a radio parameter such as transmit power, frequency, modulation, etc. The adaptation process of the WSGA is performed on the chromosomes to develop new values for each gene, which is then used to adapt the radio settings.

The invention relates to a hybrid global optimization method. A particle swarm algorithm is used for solving an optimization problem to obtain one group of current optimal solutions; a particle jumpsout of a local extremum by using a chaotic searching algorithm; and local optimal point searching is accelerated by introducing a sequential quadratic programming algorithm into the each generation ofiteration process of the particle swarm algorithm, so that a global optimal solution to the optimization problem is obtained. According to the invention, the concept of particle swarm fitness variance is introduced and the chaotic search and sequential quadratic programming method are combined. When the particle swarm fitness variance is smaller than a given critical value, the particle is easy to fall into local optimum; and chaotic searching is carried out on the optimal particle, so that the particle jumps out of the local optimum. Moreover, according to the particle evolutionary speed andthe particle aggregation degree, the inertia weight is changed adaptively, so that the motion state of the particle is changed and thus the particle is protected from falling into local optimum. During the each iteration process of the particle, the sequential quadratic programming optimization is introduced, so that the searching of the local optimal point of the particle is accelerated and theoverall searching efficiency of the algorithm is improved.

The invention discloses a method and a device for detecting cloth flaws based on adaptive orthogonal wavelet transform. Manual eye detection and an original automatic flaw detecting method in which wavelet transform is carried out after a wavelet basis is manually selected are replaced. The defects of traditional manual eye detection, such as low detection speed, low efficiency, false detection and high detection leaking rate are overcome. The problem of the original flaw detecting method based on wavelet transform that the detection precision is low as the wavelet basis is not optimized is solved. The optimal wavelet basis matched with a cloth texture is selected by an improved quantum rotating gate quantum genetic algorithm, the quantum rotating angle is regulated by a dynamic strategy, fine adaptive search is realized, the variety is enriched through introducing mutation operation, and the optimization capability of the algorithnm is improved through combining chaotic search. The flaw detecting method has the advantages of high speed, high accuracy, simplicity in operation and high efficiency and has great application prospects.

The invention belongs to the technical field of network security and particularly relates to an APDE-RBF (Affinity Propagation Differential Evolution-Radial Basic Function) neural network based network security situation prediction method. The APDE-RBF neural network based network security situation prediction method comprises the steps of dividing and clustering sample data by utilizing an AP clustering algorithm to obtain the number of nodes of hidden layers of the center and network of the RBF; obtaining population diversity by using AP clustering, changing a zoom factor and a crossover probability of a DE algorithm adaptively and optimizing the width and connection weight of the RBF; meanwhile, performing chaotic search on elite individuals and population diversity center of each generation of population in order to avoid falling into local optimization and jumping out of a local extreme point; and determining a final RBF network model, inputting a test dataset and outputting a situation prediction value. The APDE-RBF neural network based network security situation prediction method aims at improving the prediction precision for the network security situation while enhancing the generalization ability.

The invention relates to the field of electric systems and discloses a weighting Voronoi diagram substation planning method based on a chaotic and genetic strategy. The method aims at solving the problems that a prior algorithm is low in rate of convergence, poor in capacity of local optimization and sensitive in initial value, premature convergence exists, the unreasonable phenomenon caused by division of power-supply districts according to the principle of proximity exists, the load rate of a planned substation can not be controlled, and the like, and optimizing site selection of the substation and division of the power-supply districts by means of certain algorithms. The method comprises the steps of setting parameters; chaotic initialization and generating initial population including N individuals; carrying out the site selection of the substation and load distribution on the N individuals; judging whether end criterion is satisfied; calculating the fitness variance sigma 2 of the population; chaotic search; and executing and saving an optimized genetic algorithm and then returning to the fourth step. The weighting Voronoi diagram substation planning method based on the chaotic and genetic strategy is mainly applicable to the electric systems.

The invention provides an integrated stabilization chaotic system based PID (Proportion Integration Differentiation) controller optimization control method. The analysis is performed on an integrated stabilization system dynamic model equation to obtain a chaotic system so as to solve the problem of ship stabilization. The chaotic behavior of the system under the certain conditions is verified by a phase diagram and Lyapunov exponent spectrum analysis method, controlled parameters are selected, and the chaotic behavior of the system can be effectively controlled by a nonlinear feedback control method. According to the integrated stabilization chaotic system based PID controller optimization control method, the chaotic dynamics behavior of the system is improved and the original dynamic characteristics of the system are reserved; a chaotic search algorithm is combined with an ant colony algorithm to implement the optimization of the PID control parameters and accordingly the global optimization capability of the ant colony algorithm is high, meanwhile the system convergence speed is improved, and accordingly the control system performance is significantly improved; the value of application to a controller device is high, wherein the ship rolling motion is effectively designed through the controller device.

The invention relates to a pre-stack non-linear fluid identification method for a fuzzy neural network of a chaotic quantum-behaved particle swarm. Fluid identification is always a key point and difficult point problem in the oil-gas exploration field. By aiming at deficiency in the common fluid identification method at present, a multi-attribute angle gather combination fluid identification factor is built by researching an AVO (amplitude versus offset) response characteristic comprising different fluids; a chaos search mechanism, a quantum-behaved particle swarm and a fuzzy system theory are organically combined to fully perform respective advantages and complementarities of the chaos search mechanism, the quantum-behaved particle swarm and the fuzzy system theory; a novel group intelligent optimization algorithm of a ''chaotic quantum-behaved particle swarm fuzzy system'' is developed and researched, and a mechanism and an optimizing performance of the pre-stack non-linear fluid identification method are researched from two aspects of the theory and practicality; problems of poor global search capability, premature convergence and the like in a traditional optimization algorithm are fundamentally improved; the optimization algorithm is introduced into fluid identification to form the pre-stack non-linear fluid identification method for the fuzzy neural network of the chaotic quantum-behaved particle swarm; the problem existing when a traditional fluid detection means is used for carrying out fluid identification is effectively solved; fluid identification precision is improved; and a new scientific and effect technical method is provided for the fluid identification.

The invention discloses an algorithm for solving a single-depot time-varying associated logistics transportation vehicle routing problem. The algorithm includes that a chaos taboo search algorithm is adopted, the algorithm takes speed time-varying influence in the process of vehicle traveling into consideration, an association form is added into a target function in a manner of associating penalty cost, and a math model of the single-depot time-varying associated logistics transportation vehicle routing problem is built; on the basis of the math model, the chaos taboo search algorithm is provided to solve the problem. A taboo search algorithm is improved by utilizing advantages, of a chaos search mechanism, like globality, randomness and ergodicity. A 2-opt mode and a routing point two-point exchange mode are used in the process of neighborhood structuring. Finish criteria of specified iteration steps and optimal solution maximum unchanged times are used to finish the algorithm, so that solving quality and convergence speed of the algorithm are improved to some extent.

The invention discloses a multi-objective optimization method of a combined cold heat and power supply system; for a coupling system of three kinds of energy of a cold load, a heat cold and an electric load, a system model and equipment operation constraints, load balance and other constraints are established; the economical efficiency, the environmental protection property and the energy utilization rate of the combined cold heat and power supply system are comprehensively considered, an optimization algorithm combining the chaotic search based on Tent mapping and a nonlinear self-adaptive particle swarm optimization is provided, and the algorithm has high performance in terms of convergence speed and convergence precision; the non-linear decreasing adaptive weight enables the algorithm to have relatively strong global searching capability at the initial stage, and the later local searching capability is stronger. The chaotic search based on the Tent mapping has ergodic performance, the chaotic sequence generated by chaotic search is more uniform compared with the existing mapping, and higher searching efficiency is achieved; and in the optimal solution of the combined cold heat and power supply system, a situation that the solving result is caught in the local optimal solution too early and the optimal solution cannot be output can be avoided.

The present invention proposes a nonlinear self-feedback chaotic neural network signal blind detection method, which uses a nonlinear function as the self-feedback item of the chaotic neural network, and applies the double Sigmoid function to the blind detection method. In each iteration, it first enters the chaos neural network, and then into the second activation function. Because the chaotic neural network has the advantage of being able to avoid being trapped in a local optimum, the present invention inherits this characteristic of the chaotic neural network and improves blind detection performance; and, compared with the chaotic neural network of the linear self-feedback item, the non-linear self-feedback The chaotic neural network has more complex dynamic behavior, which makes the internal state of the network have more efficient chaotic search ability and search efficiency. Under the same conditions, the method of the invention has better anti-noise performance than the traditional Hopfield signal blind detection method.

The invention discloses a wireless sensor network resource allocation method based on improved simulated annealing. The method comprises the steps of considering the characteristics of limited energyand real-time performance of sensor nodes, adding a time function into a perception degree matrix of a target function, and ensuring the fairness of a user by utilizing a weighting factor; and givinga sensing node detection target number constraint, so that the node sensing deviation is reduced, and constructing a resource allocation optimization model. Aiming at the characteristic that simulatedannealing optimization has cognitive insufficiency on an overall solution space, Logistic chaotic search is embedded into the simulated annealing optimization, and an effective resource allocation method based on improved simulated annealing is provided in combination with the rapid optimization capability of simulated annealing. Compared with similar methods, the method has the advantages that the target detection success rate is higher under the condition of different sensing numbers, the fairness of the user is ensured by the weight, the optimization time and the network power consumptionare effectively reduced, and the overall performance of the system is improved.

The invention relates to a short-term photovoltaic power forecasting method based on CDA-BP for a microgrid, belonging to the technical field of photovoltaic power generation. The randomness and fluctuation of photovoltaic power make it difficult to achieve the ideal precision of photovoltaic power forecasting, and improving the forecasting accuracy is the premise of optimal load distribution in amicro-grid. Therefore, the invention provides a short-term photovoltaic power forecasting method of a microgrid based on a chaotic dragonfly algorithm optimized BP neural network (CDA-BP neural network). Based on the influence of solar irradiation rate and temperature rate on photovoltaic output power, the chaotic dragonfly algorithm (CDA) is used to optimize the connection weight coefficient andthreshold of BP neural network model, and the optimal photovoltaic power prediction model is obtained. The CDA adopts chaotic search to prevent the algorithm from falling into local optimization, anduses adaptive inertial weighting factor to improve the convergence rate. The invention has good prediction accuracy for short-term photovoltaic power generation of a microgrid.

The invention relates to a method for building an LS-SVM prediction model based on the chaotic search. The method includes the following steps: (A) building a sample training data set; (B) calculating coefficients of the model; (C) conducting optimization with the chaotic search improvement algorithm, and obtaining the minimum value and the optimal chaotic variable of a to-be-optimized function; (D) determining the optimized LS-SVM prediction model; (E) updating a sample. By means of the method, the LS-SVM self-adaptation resource prediction model is built after parameters of the model are optimized with the chaotic search improvement algorithm, the operating state of prediction objects in cloud calculation can be dynamically predicted, prediction results have good adaptability, and it can be guaranteed that the prediction resultsmoreapproximate to true values of the prediction objects. The sensibility of the chaotic search to the initial value is remitted through the model; in addition, in the chaotic iterative search process, the second-time search can be rapidly carried out in the optimal solution neighborhood through the adjustment on the chaotic variable, the search efficiency is improved, and the possibility of being caught into the local optimum is decreased.

The invention relates to the traffic network field, and specifically relates to an urban agglomeration traffic network reliability restoration method under a random attack strategy. The urban agglomeration traffic network reliability restoration method under a random attack strategy includes the steps: 1) constructing an urban agglomeration traffic network model; 2) performing cascade failure simulation on the urban agglomeration traffic network; and 3) being an urban agglomeration traffic network reliability restoration method based on an improved binary particle swarm algorithm. The urban agglomeration traffic network reliability restoration method under a random attack strategy considers the characteristic that the load changes following the state of a restoration node, analyzes the process that all the normal nodes in the network share the load of pause nodes, thus being able to more objectively describe the urban agglomeration traffic flow phenomenon. As the urban agglomeration traffic network reliability restoration method under a random attack strategy provides a fine disturbance operator and a speed chaotic searching operator, the known fine degree is improved and also the known global searching capability is improved. Moreover, a restoration constraint operator enables all the particles to be feasible solution, thus guaranteeing high efficiency and simplicity of the algorithm, so that the restoration constraint operator is applied to urban agglomeration traffic network restoration to maximally restore the reliability of the urban agglomeration traffic network.

The invention relates to a piezoelectric actuator modeling method based on an improved chaotic quantum particle swarm and application. The modeling method adopts a Boc-Wen model to construct a hysteresis nonlinear model of a piezoelectric actuator, and parameters of the Bouc-Wen model are obtained through identification by an improved chaotic quantum particle swarm algorithm. The improved chaoticquantum particle swarm algorithm for parameter identification comprises the steps of initializing a solution space; carrying out iterative computation on the solution space by adopting a quantum particle swarm optimization algorithm, calculating an early-maturing coefficient after each iteration, judging whether the early-maturing coefficient is greater than a set value under continuous set times,if so, obtaining a new search range based on the current optimal solution, and carrying out chaotic search by using the new search range to obtain a new global optimal position; and after the iteration is finished, based on the final global optimal position, obtaining a Bouc-Wen model parameter. Compared with the prior art, the method has the advantages of capability of effectively simulating hysteresis nonlinearity, high parameter identification precision and the like.

The invention relates to an equipment health state detection method for improving a chicken flock optimization RBF neural network. The basic steps are as follows: (1) signal sampling; (2) noise reduction processing; (3) feature extraction; (4) data normalization processing; and (5) detection of the health state of equipment. According to the improved chicken flock optimization RBF neural network model provided by the invention, an optimal center vector is found by using an intelligent optimization method, so that the performance of an RBF network is improved. In order to solve the problem thatthe chicken flock algorithm is easy to fall into local optimum to a certain extent, an improved chicken flock is combined with a chaotic search strategy to optimize an initial population, and meanwhile, a part of cock particles are replaced with chicks with high use degree values through growth operation, so that the problem of falling into local optimum is solved as much as possible.

The invention discloses a PM2.5 concentration prediction method and system for optimizing RELM based on random forest and ISCA, and the method comprises the steps: (1) obtaining historical PM2.5 concentration data in a preset time range, carrying out the preprocessing of the PM2.5 concentration data, and obtaining a training set and a prediction set; (2) carrying out feature selection on the data by using a random forest algorithm to ensure the prediction precision; (3) training the processed PM2.5 concentration data by using a regularization extreme learning machine; (4) improving a sine and cosine algorithm by using a uniform algorithm, nonlinearity and chaos search; and (5) establishing a model for optimizing an extreme learning machine (RELM) based on an improved sine and cosine algorithm (ISCA). Compared with a traditional prediction model, the method and system show more excellent prediction precision, and can further improve the accuracy of PM2.5 concentration prediction.

The invention provides a chaotic search optimization method for traffic flow prediction of an adaptive neural network. The method comprises the following steps: S1, constructing a BP neural network model, and initializing network parameters; s2, initializing various parameters of a sparrow algorithm; s3, adding a Tent chaotic mapping initialization population; s4, calculating the fitness value of the sparrows in the population; s5, sorting the populations according to the fitness values; s6, updating the position of the producer; s7, updating the position of the follower; s8, updating the position of the sparrow in danger; s9, updating the optimal fitness value of the individual, then updating the optimal fitness value of the group, and entering the step S10; s10, judging whether the number of iterations is reached or not, and if not, returning to the step S5; otherwise, outputting the optimal fitness value and the global optimal position, and entering the step S11; and S11, endowing the optimal fitness value and the global optimal position to the BP neural network model, optimizing the weight and the threshold value of the BP neural network model, and performing prediction to complete the construction of the CSSA-BP model. The method is higher in prediction accuracy and higher in iteration speed.

The invention discloses a multi-objective structure optimization method of a magnetic gear brushless direct current motor. The method takes volume minimization and efficiency maximization as optimization objectives, takes current, slip frequency, magnetic flux density, power factors and other related limiting conditions into consideration in the analysis process, and selects the number of stator slots, the number of rotor slots, the outer diameter of a rotor end ring and the inner diameter of a rotor end ring as optimization objects, so that the performance of the magnetic gear brushless direct current motor system is improved. The method mainly comprises the steps that chaotic search is concentrated in a chaotic search reverse learning difference method, and the reverse learning method isfused into a difference evolution method; the search capability of the differential evolution method can be improved, and only two control parameters need to be specified, so that the chaotic searchreverse learning differential method has robustness, and the framework has an online parameter adjustment capability, has a better structural optimization capability for the magnetic gear brushless direct current motor, and can effectively improve the dynamic characteristics of a driving system.

The invention discloses an engine model correction method based on an improved multivariate universe algorithm. The method is characterized in that after a correction factor is selected and a target function of a correction method is constructed, an improved multivariate universe algorithm is applied to target function optimization calculation of turbofan engine model correction; based on a conventional multivariate universe optimization algorithm, by modifying a wormhole mechanism formula, the optimization capacity of the algorithm to the problems such as strong nonlinearity and strong vectorcorrelation of the model is improved, a chaos thought is introduced, and the global exploration capacity of the algorithm is enhanced by chaos initialization of the universe and chaos search in the area near the optimal universe of each generation. According to the invention, the problem of large deviation between the calculation result and the test result of the mathematical model of the aero-engine can be well solved, the precision of the turbofan engine model corrected by the improved multivariate universe algorithm is obviously improved, the situation that the error of a single parameteris particularly large does not exist, and the precision requirement of engineering application can be met.

The invention relates to a radar signal sorting method based on dynamic correction chaos particle swarm optimization, and belongs to the technical field of population evolution and signal classification. Aiming at the problems of high pulse flow density and serious characteristic parameter overlapping degree of radiation source signals in a complex electromagnetic environment, a radar signal sorting method based on dynamic correction chaos particle swarm optimization is adopted, and the defects that a traditional clustering sorting algorithm is difficult to classify correctly and the optimization capacity of a particle swarm algorithm is insufficient are overcome. Chaos search is adopted to increase diversity of population later iteration; the updating of the particles is changed in real time according to the state of the population by adopting self-adaptive adjustment parameters; and a new fitness function is used and particle positions are dynamically corrected, so that optimization of the population is more accurate. Compared with other optimization methods, the method has great advantages under several common and new sorting indexes, has better sorting effects on convergence speed, stability and robustness, and can better adapt to a complex electromagnetic environment.

The invention provides a chaos ant lion optimization-based target grouping method. The chaos ant lion optimization-based target grouping method specifically comprises the following steps of reading data; cleaning data, using a chaos ant lion optimization algorithm to group the target formation; and outputting the formation grouping result. According to the invention, a Tent chaotic strategy is introduced to initialize a population; the ant lion selection strategy is used for replacing a roulette method to select the ant lion, a new solution is generated for ants and the ant lion with poor fitness in the population through Tent chaotic search, a chaotic operator and random walk of the ants are combined, the performance of the ant lion optimization algorithm is improved, and the accuracy andefficiency of target grouping are improved.

The invention discloses a power load probability prediction method based on a chaotic population algorithm and a Bayesian network, and the method comprises the steps: 1, obtaining the actual data of an air temperature, relative humidity, wind power and power load time sequence, carrying out the preprocessing of each column of data, and dividing a training set and test set data; 2, performing wavelet threshold de-noising processing on the original data of the power load, and restoring real information of a time sequence of the power load; 3, constructing a Bayesian network model to obtain an initial prediction interval; 4, calculating an interval change amplitude range, and obtaining an optimal interval change amplitude by applying a chaotic population algorithm; 5, chaotic search is adopted in the neighborhood of the optimal interval change amplitude, and a final prediction interval is obtained. The uncertainty of the power load can be measured by constructing the prediction interval,so that an effective reference can be provided for the optimized operation of the power system.

The invention discloses a wind power probability prediction method based on a chaotic firefly algorithm and a Bayesian network, and the method comprises the steps of 1, obtaining the wind speed, the wind direction, the air temperature and the wind power actual power data, preprocessing the data, and selecting the data of a training set and a test set; 2, performing empirical mode decomposition on the original data of the wind power to enable a wind power time sequence to be more stable; 3, constructing a Bayesian network model to obtain an initial prediction interval; 4, calculating an interval change amplitude range, and obtaining an optimal interval change amplitude by using a chaotic firefly algorithm; and 5, performing chaotic search near the optimal interval change amplitude to obtain a final prediction interval. According to the method, the uncertainty of measuring the wind power by constructing the prediction interval can be constructed, so that an effective reference can be provided for a power dispatching decision.

The invention discloses a wind and light storage capacity configuration method considering the full life cycle of an electric vehicle charging station. The method is characterized by comprising the following steps of: introducing an LCC (Life Cycle Cost) theory, and performing an objective function of a charging station configuration scheme by taking maximum net present value income and maximum renewable energy utilization rate obtained by a charging station operator as objectives; a multi-target group search algorithm (MGSOACC) based on adaptive covariance and chaos search is provided to solve a Pareto optimal solution set of the multi-target optimization problem, and the global search capability of the algorithm is improved by using a chaos search method. And finally, selecting an optimal compromise solution as an optimal scheme from the Pareto optimal solution set by applying a fuzzy set theory so as to realize the optimal capacity configuration of the wind and light storage electric vehicle charging station. According to the method, the optimal capacity configuration problem of the wind and light storage electric vehicle charging station is well solved, and the obtained configuration scheme has good comprehensive efficiency in the aspects of economy and environmental protection.

The present invention discloses a product manufacture-oriented combined optimization method. The combined optimization method enables the quality-cost control function in a product manufacturing environment. On the premise that the manufacturing cost is controlled not to exceed a target cost, the product quality is ensured to be optimal. The product diversity is further improved. According to the technical scheme of the invention, the chaotic initialization and chaotic upset strategy is adopted, and the advantages and disadvantages of a product combination scheme are evaluated based on a personalized fitness function. Combined items are classified, so that the number of combination is reduced. In this way, the complete enumeration of all product combination schemes is enabled, so that the search efficiency is improved. Meanwhile, a personalized interface is provided, and a personalized combination scheme of optimal cost performance is generated according to the personalized requirements of users. During the searching process of the optimal product combination scheme, the chaotic search is conducted and all possible optimum product combination schemes are fully traversed. Therefore, the diversity of product combination schemes is ensured.

The invention discloses a multi-target parameter optimization design method based on a dual-active full-bridge three-phase bidirectional AC / DC converter, and the method comprises the steps: selecting an energy transmission inductance value, a high-frequency transformer turn ratio and a phase shift ratio as three optimized parameters, and determining the three parameters as optimization objects; selecting a ratio of reactive power to active power of the high-frequency transformer, an energy transmission inductive current effective value and a current peak-to-peak value as optimization targets, and calculating to obtain expressions of the optimization targets and the optimization objects; determining constraint conditions among the energy transmission inductance value, the turn ratio of the high-frequency transformer and the phase shift ratio; the expressions of all the optimization targets are synthesized into a single-target optimization function according to the weight coefficients; a genetic algorithm and chaos search combined method is adopted to carry out iterative optimization to obtain a plurality of groups of optimal solutions, loss analysis is carried out according to an actual hardware circuit, and values of an energy transmission inductance value, a high-frequency transformer turn ratio and a phase shift ratio when the circuit loss is minimum are selected. The method is simple in optimization algorithm and good in optimization effect.