572results about How to "Improve search ability" patented technology

The invention relates to a method for planning robot paths on the basis of path expansion ant colony algorithms. The method has the advantages that the ant colony algorithms are applied to the field of robot path planning, path expansion ant colony algorithm optimization strategies are proposed, the robot path optimizing efficiency can be optimized, information element distribution time-varying characteristics, information element updating strategies, path location inflection point optimization and local optimal path expansion are introduced, and location inflection point parameters and general evaluation are additionally used as evaluation standards for the paths; as verified by simulation analysis and practical experiments on the three algorithms, the method is high in robot path planning and searching capacity on the basis of the path expansion ant colony algorithm optimization strategies and is high in algorithm efficiency, and the found paths are short; phenomena that the algorithms run into local optimization can be effectively inhibited, the optimal paths of robots can be searched, and the robots can quickly avoid obstacles to safely arrive at target points.

The present invention relates to a short-term load prediction method based on a particle swarm optimization least squares support vector machine. Aiming at the deficiency of a single kernel function least squares support vector machine model, the Gaussian kernel function and the Polynomial kernel function are combined to obtain a new hybrid kernel function so as to improve the learning ability and the generalization ability of the least squares support vector machine model; the particle swarm optimization algorithm based on double populations is employed to optimize parameters of the least squares support vector machine of the hybrid kernel function, the particle swarm optimization algorithm based on double populations has advantages of good global search and local search performances, and a strategy having dynamic accelerated factors is employed so as to greatly increase the variety of particles and prevent the search from being caught in a local extremum. The short-term load prediction method based on the particle swarm optimization least squares support vector machine maximally utilizes information in computation, and in the process of selecting the optimal parameter value, the average mean square error of load data and actual data is employed as the adaptation value of the particle swarm optimization algorithm so as to improve the short-item load prediction accuracy value.

The invention discloses a charging and discharging scheduling method for electric vehicles connected to a micro-grid. The method comprises the steps of: (1) determining a system structure of the micro-grid and the characteristics of various units; (2) building a micro-grid optimal scheduling target function of considering the battery depreciation cost of the electric vehicles under time-sharing electrovalence; (3) determining constraints of various distributed power supplies, batteries of the electric vehicles and the like and forming a micro-grid optimal scheduling model by the constraints and the micro-grid optimal scheduling target function; (4) determining the number, the start-stop time, the start-stop charged states and other basic calculated data of the electric vehicles connected to the power grid under the time-sharing electrovalence; and (5) solving the micro-grid optimal scheduling model through a particle swarm algorithm and determining the charge and discharge power when the electric vehicles are connected to the power grid. The batteries of the electric vehicles are connected to the micro-grid as mobile distributed energy storage devices to achieve the peak load shifting effect; the operation safety and stability of the micro-grid in the time-sharing electrovalence environment are improved; and the energy utilization efficiency and the power grid operation efficiency are simultaneously improved.

The invention discloses a maximum-minimum ant colony optimization method and a maximum-minimum ant colony optimization system for solving a vehicle scheduling problem. The maximum-minimum ant colony optimization method comprises the following steps of acquiring address information of a customer according to delivery information in an order ticket; reading relevant information in a maximum-minimum ant colony algorithm; and performing initialization, condition termination judgment, path establishment, path improvement and information updating on the ant colony algorithm. The numerical value of pheromone polatility is changed dynamically, convergence is accelerated, a plurality of paths are searched, global searching capability of the algorithm is improved, and premature and stagnation are avoided. The maximum-minimum ant colony optimization method has the advantages that the method is easy to implement and the rapid convergence capability and the rapid searching capability are high when the method is used for solving a vehicle path problem.

The invention relates to the on-line detection technical field by utilizing machine vision and an image processing technology, in particular to an automatic on-line detection method and a device for size of automobile parts based on machine vision, aiming at solving the problems that the labor intensity is high and the detection quality is poor by adopting an artificial on-line detection method for size of automobile parts. An industrial camera is utilized for shooting a clear, complete and flaw-free standard image for the automobile part running in an automatic production line, the image is utilized as a standard image template and is stored in a computer, the precision range of detection parameters for the automobile part is set according to user requirements, the image of the on-line running automobile part, which is shot in real time by the industrial camera, is transmitted to the computer and is compared with the standard image template and is processed, the size of the automobile part can be computed, and if the precision of the part is lower than the setting requirements, the computer starts and gives an alarm, so as to prompt operational staff to treat inferior-quality products. The method and the device have high detection precision to the automobile parts and have rapid speed, so as to greatly reduce the labor intensity for artificial detection.

The invention discloses a method for solving a logistic transport vehicle routing problem with soft time windows. According to the method, for the purpose of solving the problem of the logistics transport vehicle routing problem with the soft time windows on the basis of real-time traffic information, a time window punishment mechanism is employed and a mathematic model is established; and the model is solved by use of a self-adaptive chaotic ant colony algorithm, and the searching optimization capability of the algorithm is improved through self-adaptive updating of algorithm information elements and chaotic self-adaptive adjustment of algorithm parameters. According to the invention, the method better matches logistics distribution in realistic production life, the problem is solved by use of the self-adaptive chaotic ant colony algorithm, the optimization search capability is better, a search process is effectively prevented from partial optimum, the diversity of solutions and the global searching optimization capability are improved, the global updating strategy is improved, an elite strategy is introduced, and positive feedbacks of information elements released by high-quality ants are properly improved; and the upper limits and lower limits of the information elements and the information element increments are arranged so that overlarge differences of the information elements on a path are reduced, and the classic vehicle routing searching optimization problem is solved by use of the self-adaptive chaotic ant colony algorithm.

The invention provides a cooperative air combat firepower distribution method based on an improved multi-target leapfrog algorithm and belongs to the technical field of computer simulation and method optimization. The method comprises the steps that firstly, required data information is obtained through a cooperative air combat formation command and control system; secondly, a multi-target optimization module of cooperative air combat firepower distribution is established; then a multi-target quantum leapfrog algorithm based on a self-adaptive mesh method is carried out, and a Pareto non-inferior solution of firepower distribution problem is solved; finally, rules can be selected independently according to the optimal distribution scheme, and the optimal firepower distribution scheme is selected from the non-inferior solution. The cooperative air combat firepower distribution method based on the improved multi-target leapfrog algorithm has the major functions that weapons on a fighter aircraft on an attack mission are distributed to multiple targets according to the optimal firepower distribution scheme, the formed cooperative air combat is enabled to realize the optimal cooperative attack effect, and the maximum operational effectiveness is obtained.

The invention provides a variable neighborhood search algorithm for solving multi depot vehicle routing problem with time windows. The variable neighborhood search algorithm is characterized in that in a local searching progress, an or-opt and 2-opt mixed operator is utilized for local searching; a Metropolis rule in a simulated annealing algorithm model is introduced into a basic frame of VNS (variable neighborhood search) algorithm for accepting partial poorer solutions under a certain condition, so that the possibility that the algorithm is trapped into local optimization is reduced; in this way, the reliability of the algorithm is improved; and a rear optimization progress is added into the algorithm framework, as a result, both the solving quality is improved and the convergence speed of the algorithm is increased in a way.

The invention discloses an RBF neural network optimization algorithm based on an improved sparrow search algorithm. RBF initial parameters are optimized through the improved sparrow search algorithm,so that the sea clutter prediction precision is further improved, and the purpose of suppression is achieved. An elite reverse learning strategy is introduced, a current optimal solution is selected as an elite individual, and a reverse solution of the elite individual is generated, so that the global search capability of the algorithm is enhanced. Self-adaptive Gaussian variation is adopted to perform variation on an optimal solution and perform greedy selection, and in addition, a position updating mode for sparrow investigation early warning is also improved. And the population is promotedto evolve towards the optimal solution direction, so that the problem that sparrows are easy to fall into local optimum in the convergence process of low fitness in the sparrow search algorithm is avoided to a certain extent. The ability of the improved sparrow search algorithm to jump out of the local optimum is enhanced, and the convergence speed and precision of the RBF network optimized by theimproved sparrow search algorithm are further improved.

The invention discloses an active distribution network dynamic topology reconstitution method based on mixed artificial intelligence. Multiple improved artificial intelligence methods are adopted for optimizing solving, the superiority of various algorithms can be integrated, meanwhile the various artificial intelligence methods are improved during the process of combining various optimization algorithms, furthermore the astringency of the algorithms is improved, the defects such as locally optimal solution are avoided, three object functions are integrated in the optimization process, three different optimization objects are considered, and a corresponding Pareto optimal solution set is solved out; Since measurements of indexes such as on-off operation times and power supply volume are not constant, in order to establish a unified measurement model, all the indexes are converted into loss indexes according to respective conversion relations, and finally a dynamic analytic hierarchy process is adopted for deciding solutions in the Pareto optimal solution set, so that the optimal solution representing an optimal distribution network structure is obtained.

The invention provides a method of reconstructing a power distribution network containing a distributed power supply. A network topology adjusting module considering various load modes is established according to actual operation conditions of the power distribution network and has good practical value. Meanwhile, topological adjusting is performed by means of a binary particle swarm optimization algorithm according to features of network topology adjustment; a dynamic inertial weight adjusting mode is provided; better coordination with global convergence speed and local convergence precision is provided; optimizing effect is better; the topological adjustment results and analysis of an IEEE-33 node typical distribution system show that the method is effective and practical.

The invention belongs to the technical field of robot navigation, automatic control and pattern recognition, and discloses an application method of adaptive ant colony algorithm (AACO) in mobile robotpath planning. The method comprises steps of constructing a point-to-point adaptive path selection strategy to select the best path point by the transfer optimization mode in the segmentation combination state; using an obstacle avoidance planning strategy to identify the nature of the obstacle, and selecting different local obstacle avoidance points to avoid obstacles; and applying a mixed deadlock processing strategy in the deadlock environment, and counting deadlock point and its fallback path point distribution information to guide ants to jump out of the deadlock environment. The data inthe embodiment shows that the AACO described in the present invention has better optimization ability than the basic ant colony algorithm (ACO), has better overall performance than the ACO, and can be effectively applied to the global process of robot path planning.

The invention discloses a sea target detecting system of an adaptive radar, which comprises a radar, a database, and an upper computer connected in order; the radar is used for irradiating the detected sea area and storing radar sea clutter data in the database; the upper computer comprises a data pre-processing module, a Robust prediction model modeling module, an adaptive swarm intelligent optimizing module, a target detecting module, a model updating module and a result displaying module. The invention further provides a sea target detecting method of the adaptive radar. The invention provides a sea target detecting system of the adaptive radar and a method thereof with adaptive parameter, good optimization effect and high prediction efficiency.

The invention provides an unmanned aerial vehicle route planning method based on an improved Salp algorithm, belonging to the technical field of unmanned aerial vehicle route planning. The method comprises the following steps: firstly, determining a start point position, a destination point position and a threatening area range; establishing a route planning cost model through path cost and threatening cost; performing optimizing for the established cost model, on the basis of a basic Salp algorithm, updating the position of a population with a sinusoidally varying iterative factor, embeddingan adaptive genetic operator to improve optimizing capability of the algorithm; after upper limit of iteration is reached, obtaining an optimal individual position, namely unmanned aerial vehicle optimal route points from the start point to the destination point; smoothening a connection line of the obtained optimal route points, obtaining the optimal route, and realizing route planning. The method provided by the invention can plan the optimal route from the start point to the destination point and avoid that the route is in the threatening area, the method has flexible, simple and fast calculation processes, and the method solves a problem that the existing route planning optimization algorithm has relatively low convergence speed and is very liable to be caught in local optimum.

The invention provides a distributed-power-source-contained power distribution network reactive power optimization method based on mixed integer cone optimization. According to the probability density function of wind speed, the output power characteristics and the random outage rate of a draught fan, the probability density function of the output power of the draught fan is derived, and the multi-state discrete probability model of the output of the draught fan is established; according to the network topology, the line parameters, the node load level, the injected wind turbine generator capacity, the reference voltage and the reference power of a power distribution network, a power distribution network branch tide equation is established, and second-order cone relaxation processing is carried out on the tide equation; the economic benefits brought by installing a capacitor serve as an objective function of reactive power optimization, tide second order cone relaxation equation constraints, voltage constraints and capacitor capacity constraints are taken into consideration, and a power distribution network reactive power optimization model with intermittent energy is established. According to the distributed-power-source-contained power distribution network reactive power optimization method based on mixed integer cone optimization, the optimizing capacity is high, it is guaranteed that the obtained solution is optimal, and practicability is high.

The invention discloses a method and a system for production scheduling based on improved particle swarm optimization and a heuristic strategy. The method comprises the following steps: proposing constraint conditions; defining an objective function, namely, a fitness function; carrying out particle swarm initialization; randomly initializing swarm particles, including position and velocity; carrying out iterative optimization: updating the velocity and position of particles, and finding out an optimal solution; setting the maximum number of iterations as an iteration termination condition, judging whether the iteration termination condition is satisfied, and outputting a global optimal solution if the iteration termination condition is satisfied; if iteration termination condition is not satisfied, jumping to the previous step to continue to find out an optimal solution. The beneficial effects are as follows: the computing speed of the algorithm is increased by using a novel particle encoding method; the problem of local optimum in the process of the traditional particle swarm optimization algorithm can be solved; the phenomenon of infeasible solutions is avoided to a great extent; and efficient and optimal production scheduling is realized.

The invention discloses a human face recognition method based on a local binary value and a PSO BP neural network. The method comprises the steps that first, all kinds of human face images in a known human face library are divided into a training sample set and a testing sample set in a non-overlapped mode, and normalization and local binary preprocessing are conducted on the images; second, two-dimensional discrete wavelet transformation is conducted on the preprocessed images, the influence of diagonal line component is removed, weight fusion is conducted on other three frequency band components, then two-dimensional discrete cosine transform is conducted on the fused images, and a zigzag scanning mode is used for extracting a main transformation coefficient matrix; then, the initial weight value and the threshold value of the PSO BP neural network are used for conducting network training; at last, the data of the testing sample set are sent to the trained BP neural network for testing, and the recognition rate is calculated. According to the human face recognition method based on the local binary value and the PSO BP neural network, high computing efficiency and high recognition capacity are achieved, and the method is suitable for human face recognition systems.

The invention relates to a scheduling graph optimizing method based on a multi-target genetic algorithm. The scheduling graph optimizing method comprises the steps of: scheduling graph simulation model, scheduling graph generalization, the realization form of the multi-target genetic algorithm NSGA-II (nondominated sorting genetic algorithm II): NSGA-II (nondominated sorting genetic algorithm II) algorithm, the generation of an initial population, and the cross heteromorphosis method. In the scheduling graph optimization, the scheduling graph optimizing method adopts the multi-target genetic algorithms, such as the NSGA-II algorithm. The NSGA-II algorithm is known as the algorithm having the best multi-target optimizing effect. The NSGA-II algorithm adopts a rapid domination-free stratified sorting and eliminating mechanism, and introduces in an elite retention strategy, so that the diversity of the results can be ensured so as to make the results widely and uniformly adjacent to the optimal leading edge of Pareto. The multi-target genetic algorithm is relatively nature and stable, which can present stronger optimizing ability no matter in the theoretical test function or the actual production problem. The multi-target genetic algorithm does not need to coordinate a plurality of targets, and moreover, the multi-target genetic algorithm can directly search the non-inferior solutions and provide a mixed coding method. The multi-target genetic algorithm has wide application and strong expandability.

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 discloses a particle swarm optimization method for an air combat decision, comprising the following steps of: firstly, acquiring the current situation of a battlefield from a command control center; secondly, acquiring a threat factor among aircrafts according to the current situation of the battlefield; thirdly, setting the particle swarm scale and the maximum iterations of the particle swarm; fourthly, initializing all particles of the particle swarm; fifthly, acquiring the threat degree of an enemy party on a first party after weapon attacks of the first part according to an empirical formula; sixthly, constructing a BP (Back Propagation) neural network; seventhly, updating the historical optimal position of the particle swarm and the individual historical optimal position of the particles; eighthly, continuously searching an air combat decision scheme until the maximum iterations of the particle swarm are achieved; and ninthly, determining the historical optimal position coordinate of the particle swarm as the obtained air combat decision. By processing the input and the output of the BP neural network, the decision method can move in a set solution space and has favorable search capability on the optimal solution.

The invention discloses an addressing and capacity configuration method used for a UPFC. A UPFC addressing and capacity configuration model with transient stability constraints is established, a difference evolution algorithm serves as a framework, and the installation position and the capacity of the UPFC are optimized; in addition, a centrality correction interior point method is adopted for carrying out optimization and fitness assessment on continuous variables of each difference evolution unit. The difference evolution algorithm is simple in operation, high in searching capability, fewer in adjusting parameters and suitable for mixed optimization, and the interior point method is good in convergence and strong in robustness, so that the provided mixed algorithm can well solve the problems of UPFC addressing and capacity configuration, the method is highly efficient and convenient, and the application prospect is good.

The invention discloses a network intrusion detection method. The network intrusion detection method includes: searching network data to construct a test network data set; performing feature extraction on the test network data set by utilizing a kernel principal component analysis method; constructing a training data set, putting the training data set into a support vector machine classifier for training; obtaining feature datasets, obtaining an optimal feature subset from the feature data set by using a genetic algorithm; utilizing a firefly swarm optimization algorithm to obtain the overalllocal optimal feature subset and the optimal support vector machine parameters from the optimal feature subset, processing the training data set according to the overall local optimal feature subset,and inputting the training data set into a support vector machine classifier for classification modeling to obtain a network intrusion detection model. According to the method, the simplicity and convenience of the algorithm are improved, abnormal data can be more effectively found from samples, the detection accuracy of network intrusion is effectively improved, the missing report rate and the false report rate are reduced, and the overall performance of network intrusion detection 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 discloses a measurement and control resource scheduling distribution method based on Multi-Agent and a DNN, and the method comprises the steps: designing three big types of intelligent agents of a measurement and control resource dynamic scheduling problem; carrying out the initial arrangement of the measurement and control tasks and measurement and control resources based on a Multi-Agent negotiation distribution mechanism of the game theory; creating a measurement and control task knowledge base, carrying out the repeated training of the measurement and control task knowledge base through a DNN (depth neural network) algorithm with a deep learning structure, and eliminating a problem of mutual conflict between the measurement and control tasks; generating a measurement andcontrol task dynamic factbase after deep learning, and distributing tasks to each measurement and control station for accurate execution according to a generated optimal measurement and control task execution sequence. The method optimizes the measurement and control resource planning and scheduling through the Multi-Agent cooperation technology based on the game theory and the DNN technology. Through the deep learning process of the DNN algorithm, the measurement and control task knowledge base is continuously improved, thereby improving the dynamic adjustment and intelligent execution of themeasurement and control resource scheduling management.

An SVR antifriction bearing performance degradation prediction method based on a krill-herd algorithm belongs to the field of functional approximation rotating machinery prediction methods. The method comprises the following steps: firstly analyzing time domain, frequency domain and time-frequency domain feature indexes, and proposing a feature extraction method based on combination of CEEMD and wavelet packet half-soft threshold noise reduction to perform fault diagnosis of an antifriction bearing; performing comprehensive evaluation of the fault degradation feature of the antifriction bearing for multiple feature parameters, and proposing a method of combining the LLE nonlinear feature dimension reduction method with the fuzzy C mean value; and finally, introducing the basic theory of the support vector regression machine, and proposing the prediction model of multivariable support vector regression machine based on the krill herd algorithm, optimizing parameters of the SVR, and selecting the optimal C, [sigma] parameters. The method is advantaged by high prediction precision, short calculation time, and good feature value prediction effect after clustering. The degradation process of the antifriction bearing can be precisely predicted through the abovementioned three steps.

The invention discloses a Dynamic service resource scheduling method based on A genetic-ant colony fusion algorithm. The method comprises the following steps: S1, establishing a service task, and determining a dynamic service resource set; s2, selecting a genetic operator, and carrying out solving on the basis of the genetic operator to obtain an optimized solution with a high fitness value; s3, selecting an ant colony operator, carrying out transition on the genetic operator and the ant colony operator, and converting an optimization solution solved by the genetic operator into initial pheromone distribution of the ant colony operator; and S4, obtaining a scheduling scheme of the dynamic service resources based on the initial pheromone distribution. According to the method, the ant colonyalgorithm and the genetic algorithm are fused and then applied to the scheduling problem of the dynamic service resources, the utilization rate of the dynamic service resources is increased, the resource use time, cost and the like are reduced, and the production efficiency is improved. The method provided by the invention has relatively high optimization solving capability, and the iterative convergence is better than that of other algorithms and tends to be relatively high in stability. The utilization rate of resources can be improved, and the economic benefits of enterprises are increased.

The invention discloses a design method for a nonlinear system controller of an aero-engine. The method is directed at control problems of the affine nonlinear system of the aero-engine within a large deviation range. The method comprises the following steps: linearizing the nonlinear system of the aero-engine based on the theory of exact linearization, adopting the variable structure control in designing a non-linear sliding mode controller, changing a control structure with a purpose by using a linearized state variable to enable the linearized state variable to move based on the designed sliding mode track so as to offset parameter perturbation and exterior interference, finally directed at the key problem of designing non-linear controller parameters, adopting the artificial bee colony algorithm in adjusting the controller parameters, and calculating the optimal parameter to optimize the control effect. According to the invention, the method is directed at the problem of designing complex controller parameters, and obviates the need for tedious manual debugging and repeated verification. By using the bee colony algorithm in designing a reasonable target performance function, the method enables an automatic calculation of the optimal controller parameters and enables the non-linear controlling system of the aero-engine to have a satisfied dynamic performance and robust stability.

The invention discloses a face recognition method based on a particle swarm optimization BP network. The method includes that an image is preprocessed to eliminate external disturbance; information of the preprocessed image is projected to a feature space by means of mapping transformation and by selecting different feature extraction modes; in the training or recognition process of neural networks, each feature corresponds to one input node of each neural network, output nodes are equal to classes in number, and one output node corresponds to one class. Therefore, a fully-connected BP network is designed, wherein the number of neurons in an input layer corresponds to the number of the features of the image, the number of neurons in an output layer is the number of swarm classes, the number of neurons in a hidden layer is set as the following formal, network weight is initialized as a random value between 0 and 1, and each particle corresponds to one neuron network. According to adaptive values of the particles and variable quantities of the adaptive values, inertia weight of each particle is regulated in real time, a global optimal solution can be rapidly found out, and efficiency and accuracy of face recognition are improved finally.

The invention discloses an optimal configuration method for an electric automobile charging pile. The method comprises the following steps: predicting the charging power demand of a planning area by a Monte Carlo simulation method on the basis of analysis of various electric automobile behavior characteristics; building a bi-level planning model of charging station investment profit and user perception effect under the consideration of constraint conditions such as a power grid, a charging station and an investor budget; and introducing a KKT (Karush-Kuhn-Tucker) condition to realize equivalent conversion of a double-layer model and a single-layer model, and solving by adopting a variable neighborhood search-particle swarm mixed algorithm with a convergence polymerization degree. Through adoption of the method, the problem of premature convergence of particles is avoided effectively; population diversity is increased; the optimization capacity of the particles and the convergence speed of the algorithm are improved and increased remarkably; the calculation speed and the calculation accuracy of optimal configuration of the charging station are increased; and important references are provided for investors to plan and build the charging station under an enterprise-dominant pattern.

The invention discloses a multi-language hybrid input method used on an embedded touch screen virtual keyboard. Each key on the virtual keyboard maps three to four characters respectively; a display region of a touch screen is provided with a virtual keyboard region, an editing region and a candidate region; the touch screen also comprises a pop-up amplifying and selecting region; the method particularly comprises the following steps of: performing keystroke operation; dynamically displaying Chinese information, numerical information and foreign information related to the key at the candidate region; selecting the candidate region where a target item is positioned, popping up the amplifying and selecting region, and amplifying the row in which the target item is positioned in the candidate region by the amplifying and selecting region; and clicking or downwardly sliding the target item and selecting and displaying input Chinese information, numerical information or foreign information at the editing region in real time to finish the input. By the method, rapid hybrid input of Chinese, number, English and other foreign languages is realized, the efficiency of inputting written information is greatly improved, and the operation is intuitive and the compatibility of the method is good.