116results about How to "Strong global optimization ability" patented technology

The invention relates to an optimized design method for modelling of an end wall of a high load fan/compressor. The method comprises eleven steps. As the stage pneumatic load is improved, internal flow of the fan/compressor is more severe, massive secondary flow is easily generated in an area close to the end wall, and a risk of flow stall exists. The modelling of the end wall has important influence on control over the secondary flow in an end area of the high load compressor, and becomes an important research direction. Firstly, an end wall modelling parameter defining method is researched; secondarily, based on an adaptive genetic algorithm and an artificial neural network response surface model, which are developed by the research group, an orthogonal experimental design, end wall parameter definition and a flow field value simulating technology are combined to realize automatic global optimization of the end wall of the compressor; thirdly, the effectiveness of the optimizing method is verified through different test functions; finally, a blade grid of the compressor is subjected to nonaxisymmetrical optimization based on the method. A result shows that the blade grid after modelling has good pneumatic performance.

The invention discloses a method and system for multi-target reactive power optimization of electric power systems. The method comprises the following steps of: establishing a multi-target reactive power optimization model; generating positions of N initial bird nests by utilizing Kent chaotic mapping, taking the positions of the N bird nests as initial populations, calculating a fitness value of each bird nest, establishing an external file set according to a Pareto dominance relation, updating the positions of the bird nests according to self-adaptive weights, updating the external file set according to the dominance relation and calculating a congestion distance to control the capacity of the file set; carrying out a differential evolution operation on each bird nest and updating the external file set; and when an iteration termination condition is satisfied, outputting an optimum Pareto optimal solution set. According to the method and system, a plurality of target functions are considered, so that the disadvantages that the traditional method is used for converting a plurality of targets into a single target and is difficult to determine the weight coefficients are optimally overcome; an improved cuckoo search algorithm is high in convergence rate, high in precision and good in individual diversity; and the obtained optimal solution set has favorable diversity and uniform distributivity, and can be well adapted to solving the multi-target reactive power optimization problems of the electric power systems.

The invention relates to a mobile-robot route planning method based on an improved genetic algorithm. A raster model is adopted to preprocess a working space of a mobile robot, in a rasterized map, an improved rapid traversing random tree is adopted to generate connections of several clusters between a start point and a target point, portions for the mobile robot to freely walk on in the working space are converted into directed acyclic graphs, and a backtracking method is adopted to generate an initial population which is abundant in diversity and has no infeasible path on the basis of the directed acyclic graphs. Three genetic operators, namely a selection operator, a crossover operator and a mutation operator, are adopted to evolve the population, wherein the selection operator uses a tournament selection strategy, the crossover operator adopts a single-point crossover strategy, and the mutation operator adopts a mutation strategy which displaces an aberrance point with an optimal point in eight-neighbor points of the aberrance point. A quadratic b-spline curve is adopted to smooth an optimal route, and finally, a smooth optimal route is generated. According to the method, the route planning capability of the mobile robot under a complex dynamic environment is effectively improved.

An inventory forecasting model and its construction method based on chaotic neural network. The inventory of finished products is the key factor in precise distribution. If the inventory of finished products is sufficient, accurate delivery will be guaranteed, but the high inventory of finished products will bring a negative impact on the enterprise. The risk is high. On the one hand, it is difficult to process other materials after the original roll is processed into finished products. Once the user does not use it, it is likely to become a waste product. On the other hand, the finished product inventory takes up a large inventory space, which will make Limited storage capacity is getting tighter. The present invention divides the work into two phases. The first is the learning phase. The data of all the distribution users of the sample companies in the past three years are used as samples to establish a model, and these samples are used to learn and adjust the connection weight coefficients of the chaotic neural network, so that the network Realize the given input-output relationship; then the implementation stage, use the trained neural network to obtain the expected effect, establish a perfect calculation model, and realize the reasonable setting of the inventory.

The invention relates to a high-efficiency global optimization method using adaptive radial basis function based on fuzzy clustering, belonging to the technical field of modern engineering optimization designing. The method comprises the following steps: gradually constructing a proxy model of a complicated analysis model relating to an engineering design problem by the adaptive radial basis function; classifying the function values of a proxy model on a known mesh point aiming at the proxy model by adopting a fuzzy clustering method; searching a key area which is possibly saved to the global optimal point; and optimizing the proxy model by using the global optimizing algorithm in a small range in the key area until the optimal value of the engineering design problem is acquired. The optimization method overcomes the defect of time-consuming operation when the traditional global optimization method is used in the engineering design problem, can effectively reduce operation cost, improve optimization efficiency, is advantageous to shortening the period of engineering optimization design, and has the capability of global searching.

The invention discloses an intelligent steel cord conveyer belt defect identification method and an intelligent steel cord conveyer belt defect identification system. The identification method includes the following steps: (1) electromagnetic loading; (2) defect signal acquisition; (3) feature extraction; (4) training sample obtainment; (5) class priority determination; (6) multi-class model establishment; (7) multi-class model training; (8) real-time signal acquisition and synchronous class: electromagnetic detection units are adopted for real-time detection, detected signals are synchronously inputted into a data processor, features are extracted and then sent into established multi-class models, and the defect class of a detected conveyer belt is automatically outputted. The identification system comprises an electromagnetic loader, a plurality of electromagnetic detection units, the data processor and an upper computer, the data processor can automatically output the defect class of the detected conveyer belt, and the upper computer bidirectionally communicates with the data processor. The design of the invention is reasonable, the invention is easy to operate and convenient to put into practice, moreover, the using effect is good, the practical value is high, the reliability of conveyer belt defect detection is enhanced, and the efficiency of defect identification is increased.

The invention discloses an optimization and design method for an MRI (magnetic resonance imaging) superconducting magnet, which is used for designing a solenoid-type superconducting magnet comprising a primary coil and a shielded coil. According to the cross section dimension of a superconducting tape, a feasible current-carrying zone is subjected to a rectangular net processing so that the axial size of each grid is equal to an integral multiple of the width of the superconducting tape and the radial size is equal to an even multiple of the thickness of the superconducting tape. The optimization and design method aims to minimize wire consumption under the constraint conditions of the central field strength, the magnetic field uniformity and the stray magnetic field of the superconducting magnet, the preliminary current distribution of the primary coil and the shielded coil can be obtained by a 0-1 programming algorithm; and different blocks of the superconducting magnet are subjected to rectangle formatting to obtain a final optimized result. By using the method, a globally optimal solution meeting design requirements can be obtained and the obtained design result is an integer turn, thus effectively avoiding round errors existing in a conventional method.

The invention discloses an automobile spare part loading optimization method based on an improved secondary particle swarm algorithm. The decision-making elements of cost, resources, service quality, and the like are comprehensively considered during the logistic transportation loading of automobile spare parts, and an automobile spare part loading optimization model is established. The secondary particle swarm algorithm is introduced for solution, and the improved secondary particle swarm algorithm is adopted aiming at the defect of low early particle diversity searched by the secondary particle swarm algorithm, a variation idea and an interchangeable updating mechanism of a genetic algorithm are adopted to enhance the diversity of a population so as to avoid premature convergence, and the optimization solution effect is improved. Simulation examples show that the particle diversity and the algorithm solution efficiency during the algorithm solution process are obviously better than those before improvement, and the probability for searching optimal overall situation is higher. The invention provides a method support for optimizing and improving a loading scheme of enterprise automobile spare parts and related goods in the logistics industry.

The invention discloses a method for optimizing a disaggregated model by adopting genetic algorithm. The method comprises the following steps of: 1, acquiring a training sample, wherein the acquiring process includes signal acquisition, characteristic extraction and sample acquisition; 2, selecting kernel function: radial basic function is selected as the kernel function of a disaggregated model needing to be established, and the disaggregated model is a support vector machine model; and 3, determining penalty parameter C and kernel parameter gamma: a genetic algorithm is adopted to optimize the penalty parameter C of the disaggregated model needing to be established and the kernel parameter gamma of the selected radial basic function and the optimization process includes population initialization, calculation on the fitness value of each individual in the initialized population, selection operation, interlace operation and variation operation, calculation on the fitness value of each individual in the offspring, selection operation and judgment on whether the termination condition is met. The method is reasonable in design, simple and convenient in operation, convenient to realize and good in use effect and high in practical value; the classification precision of the obtained disaggregated model is high, the training speed is high and the number of support vectors is less.

The invention relates to the technical field of risk control of the Internet financial industry, particularly to a fraud behavior detection method based on whale algorithm optimization LVQ neural network. The method comprises six steps. According to the invention, compared with BP, RBF, SOM and other neural networks, the LVQ neural network has the advantages of simple structure, short training time, stronger non-linear classification processing capability and the like; compared with optimization algorithms such as a genetic algorithm, a particle swarm algorithm and the like, the whale optimization algorithm has the characteristics of simple parameter setting, strong function optimization capability, strong global optimization capability, good convergence stability and the like; and the initial weight of the LVQ neural network is optimized by using the whale optimization algorithm to improve the global fitting capability, the learning rate and the prediction precision of the LVQ neuralnetwork, so that the requirement of real-time detection of networked financial fraud behaviors can be met.

The invention discloses an optimal configuration method of a fault current limiter based on an adaptive particle swarm algorithm. The method includes the following steps: 1, calculating short circuit current of each branch circuit, and selecting a standard-exceeding node; 2, building a mathematical model of an FCL optimization configuration problem, 3, conducting optimization configuration on the FCL by the adaptive particle swarm algorithm. According to the optimal configuration method, a more accurate optimal computation can be conducted on installation impedance of the FCL, the installation impedance value is optimized on the premise that fault current is limited, so that a reference is provided for the actual installation of the FCL in an electric power system.

The invention provides a mid-and-long term runoff forecasting method based on a bacteria foraging optimization algorithm, and belongs to the technical field of hydrologic forecasting. In the method, firstly a circulation index which has a large correlation coefficient and has physical influence on the runoff of a drainage basin to be forecasted is taken as a forecast factor, and the forecast factor value is subjected to normalization processing; then the historical samples of the drainage basin to be forecasted are selected and are divided into a training set and a testing set; a support vector regression machine (SVR) model is trained by means of the training set, the parameter value of the model is determined by means of the bacteria foraging optimization algorithm, and the bacteria with the maximum adaptability value is output; the bacteria is decoded, and the optimum value and the preliminary forecasting result of the SVR model parameter are obtained; the preliminary forecasting result is compared with the testing set, and the error is analyzed, if the error is within a set scope, the final forecasting result is outputted. According to the invention, the forecasting accuracy, the generalization ability and the practicality of the mid-and-long term runoff forecasting method employing the SVR model are improved, and the mid-and-long term runoff forecasting method can serve as an effective method for mid-and-long term runoff forecasting.

The invention discloses a multi-robot full-coverage task allocation method. The technical scheme includes the steps of first performing decomposition modeling on a full-coverage environment to obtaina topological graph G, and based on G, generating a pop directed generation trees, i.e., individuals, as the 0th generation of population; adopting an individual adaptation calculation method to calculate adaptation of T1, T2,..., Tk.., Tpop separately according to the number of blocks q into which G is to be segmented; finding the individual best with the lowest adaptation and the individual worst with the highest adaptation; and iterating maxgen generations, each generation using selection crossover and mutation operators to select potential individuals and generate more potential individuals, adopting an individual adaption calculation method to calculate the adaptation of individuals of the (maxgen)th generation, and recording an obtained a cutting scheme in the calculation process. Byadoption of the multi-robot full-coverage task allocation method, only a relatively small population and a relatively small evolution generation number are needed to obtain an approximate solution which is very close to an optimal solution.

The invention provides an SCR denitration system prediction model optimization method based on machine learning. The SCR denitration system prediction model optimization method comprises the followingsteps: S1, collecting the NOx concentration of a boiler outlet in an SCR denitration system and real-time sample data of related indexes influencing the NOx concentration; s2, carrying out dimensionreduction processing by utilizing principal component analysis; s3, establishing a support vector machine model; s4, introducing an exponential decay model to iteratively update the step size value ofthe longicorn beard algorithm, and optimizing vector machine parameters; s5, performing simulation of a support vector machine; and S6, repeating the step S1S5. The invention provides an SCR denitration system prediction model optimization method based on machine learning, which solves the problem that accurate control of ammonia injection quantity is difficult to realize in the existing thermalpower plant; and the invention comprises performing dimension reduction processing on sample data based on a PCA method, iteratively updating a step size value by introducing an exponential decay model, and optimizing by improving a BAS algorithm to obtain optimal support vector machine model parameters, and establishing an optimized support vector machine regression (SVM) model.

The invention provides a hybrid fruit fly algorithm based on double-objective job shop scheduling. The method comprises the following steps: a mathematical model is built; the constraint conditions for the processing order of different working procedures of each work piece are built; the constraint conditions for the processing order of the working procedures of different work pieces on each machine are built; an objective function is built; fruit fly individual and fruit fly population initialization are carried out; a new fruit fly population is obtained, and a global collaboration mechanismis carried out; the new obtained fruit fly population is evaluated and iterative optimization is carried out; and if termination conditions are met, non-inferior sets obtained through multiple timesof operation are combined and screened to obtain a pareto solution set. Only two parameters need to be set, the algorithm is simple to realize, the complexity of job shop scheduling is reduced, and the job shop scheduling efficiency is enhanced; besides, the global optimization ability is strong, and the job shop scheduling problem can be effectively solved; and the hybrid fruit fly algorithm based on double-objective job shop scheduling has the advantages of few set parameters, strong convergence and strong robustness and the like.

The invention provides a method for identifying a protein complex based on BSO (Brain Storm Optimization); the method comprises the following steps: by utilizing strong global optimization searching capability of a BSO algorithm, regarding a protein-protein interaction network as a full network connected graph, combining gene ontology annotation function information of the protein with a topological structure of the protein-protein interaction network to define a distance among protein nodes, and carrying out preliminary clustering according to an improved k-means algorithm; then, according to four optimization searching principles of the BSO algorithm, generating a new fitness value, respectively carrying out module internal and module external optimization searching operations on a protein module which is formed preliminarily, iterating in a circulative manner and searching a most optimal global solution; and at last, carrying out post processing process. The method disclosed by the invention can keep the diversity of a group in the optimization searching process, thereby avoiding getting into local optimization; the global optimization module division is obtained, and the protein complex with remarkable biological enrichment is obtained.

The invention relates to a fish swarm algorithm-based cucumber seedling stage carbon dioxide optimization regulation and control model. A model formula is put forwards with temperature T and photon flux density PFD adopted as independent variables and with carbon dioxide concentration corresponding to a maximum photosynthetic rate adopted as a dependent variable; the establishment and application of the model are also disclosed. Multi-dimensional data are acquired by using a photosynthetic rate multiple-factor nested experiment; a photosynthetic rate multivariable nonlinear regression model is constructed; a fish swarm algorithm-based carbon dioxide model optimization method is designed; carbon dioxide saturation points under different temperature and different photon flux density are obtained; and the cucumber carbon dioxide optimization regulation and control model with the carbon dioxide saturation points adopted as target values can be built. As indicated by model verification test results, the fish swarm algorithm-based cucumber seedling stage carbon dioxide optimization regulation and control model of the invention can dynamically obtain the carbon dioxide saturation points under different temperature and different photon flux density, the determination coefficient of the actually-measure values and calculated values of the carbon dioxide saturation points is 0.98, and the maximum relative error of the actually-measure values and calculated values of the carbon dioxide saturation points is lower than 3%, and the model has high precision and is of great significance for the improvement of the carbon dioxide environmental regulation and control efficiency of facilities.

The invention discloses a CodonPlant system used for plant exogenous gene modification, and a modification method thereof. The CodonPlant system comprises an input module, a processing module and an output module, wherein the input module is used for a user to input a gene sequence, a codon use frequency sorting table and a group number n; and the processing module is used for receiving input codon information contents and codon use frequency sorting table information contents, carrying out effective processing on the basis of the number n of groups input by a user and outputting a corresponding result through the output module. By use of the system, parameters, including a shearing site, mRNA (Messenger Ribonucleic Acid) and the like, are subjected to fixed point mutation and put in a genetic algorithm to keep the diversity of populations in an evolution process, an exclusion mechanism is increased to make up the deficiencies of low astringency efficiency of the genetic algorithm, theoptimal solution searching ability of the algorithm can be improved, and the system is high in practicality.

The invention discloses a parallel type genetic Elman neural network-based source driving 235U concentration recognition method, which mainly comprises the following steps: establishing a neural network model, wherein the neural network model is structurally divided into three layers which are a data allocation layer, a sub-network layer and a comprehensive decision-making layer respectively; preprocessing an acquired neutron pulse signal auto-correlation function; inputting a processed signal auto-correlation function sample into the data allocation layer of a parallel type genetic Elman network and adopting a cyclic random multi-point sampling method to allocate the data of the sample; inputting the allocated data into each genetic Elman sub-network in the sub-network layer respectivelyfor recognition and giving recognition results; and performing comprehensive processing on the recognition results of the plurality of sub-networks by the comprehensive decision-making layer to obtain a final 235U concentration recognition result. Through the method, relatively better 235U concentration recognition effect is obtained due to relatively higher data utilization ratio and a novel network structure.

The invention discloses a motion estimation method based on genetic search and template matching, belonging to the technical field of video compression coding. The method comprises the following steps: adopting multiple methods to predict blocks to be coded in a frame to be coded so as to obtain multiple predicted motion vectors; respectively searching a point directed by each predicted motion vector in a search window, adopting three termination strategies to judge, and if the three termination strategies are met, finishing the search; using an initial template to carry out population initialization, and copying, intersecting and selecting population cycles until genetic termination conditions are met; on the basis, searching adjacent points so as to obtain matched blocks to code the blocks to be coded; and traversing a complete frame image, and coding the complete frame image. In the method, the statistic characteristics of the motion vectors are combined to set the three termination strategies, and the template matching is combined with the genetic search algorithm for use, thus ensuring the coding quality and greatly reducing the time of the motion estimation at the same time.