723 results about "Global optimum" patented technology

The invention relates to a flight path planning method based on a sparse A* algorithm and a genetic algorithm and belongs to the technical field of flight path planning of an unmanned aerial vehicle (UAV). According to the characteristics of flight path planning, the method comprises the following steps: planning an initial reference flight path by the utilization of the sparse A*search (SAS) algorithm, wherein constraint conditions are combined into algorithm search, so that useless nodes in a search space can be effectively deleted and the search time is shortened; and when emergent threat occurs during real-time flight of the UAV, performing real-time flight path planning by the utilization of the genetic algorithm and generating a flight path with local optimum or approximate optimum until the threat disappears and the UAV returns the original global optimum reference flight path and continues flying. The method provided by the invention has high real-time performance and rapidity; the searched flight path is closer to the actual UAV optimal flight path; and the method can be applied to the technical fields of robot path planning, urban vehicle path planning and the like under complex environments.

A method for the estimation of the state variables of nonlinear systems with exogenous inputs is based on improved extended Kalman filtering (EKF) type techniques. The method uses a discrete-time model, based on a set of nonlinear differential equations describing the system, that is linearized about the current operating point. The time update for the state estimates is performed using integration methods. Integration, which is accomplished through the use of matrix exponential techniques, avoids the inaccuracies of approximate numerical integration techniques. The updated state estimates and corresponding covariance estimates use a common time-varying system model for ensuring stability of both estimates. Other improvements include the use of QR factorization for both time and measurement updating of square-root covariance and Kalman gain matrices and the use of simulated annealing for ensuring that globally optimal estimates are produced.

The invention discloses a three-dimensional formation reconfiguration method for multiple unmanned aerial vehicles based on particle swarm optimization and genetic algorithm. The method considers the position of the unmanned aerial vehicle in the ground coordinates and the speed, track angle and course angle of the unmanned aerial vehicle when establishing a formation model, carries out subsection linear disposal of the control input of each flying unit in the unmanned aerial vehicle, replaces the approximate subsection linear control input with the continuous control input, then carries out global search by the genetic algorithm, subsequently carries out partial searching by the particle swarm optimization algorithm, on the base thereof, the particle swarm optimization is used to guide the genetic algorithm to search a global optimum solution so as to figure out the subsection linear control input. Compared with the traditional method, the method provided by the invention has good real-time performance and rapidity and can be used for solving the formation reconfiguration problem of multiple space robots under complex and dynamic environment.

The invention relates to an autonomous integrated navigation system which belongs to the technical field of navigation systems. The SINS (Strapdown Inertial Navigation System)/SAR (Synthetic Aperture Radar)/CNS (Celestial Navigation System) integrated navigation system takes SINS as a main navigation system and SAR and CNS as aided navigation systems and is established by the following steps: firstly, designing SINS/SAR and SINS/CNS navigation sub-filters, calculating to obtain two groups of local optimal estimation values and local optimal error covariance matrixes of the integrated navigation system state, then transmitting the two groups of local optimal estimation values into a main filter by a federal filter technology for fusion to obtain an overall optimal estimation value and an overall optimal error covariance matrix, and finally, performing real-time correction on the error according to the overall optimal estimation value so as to obtain an optimal estimation fusion algorithm of the SINS/SAR/CNS integrated navigation system. The autonomous integrated navigation system, disclosed by the invention, is less in calculation amount and high in reliability, is applicable to aircrafts in near space, aircrafts flying back and forth in the aerospace, aircrafts for carrying ballistic missiles, orbit spacecrafts and the like, and has wide application prospect.

The invention provides an integrated navigation method and equipment based on multisource information fusion. The method comprises the following steps: obtaining multisource navigation information, namely obtaining navigation related information from one or more of a global satellite navigation system GNSS, an inertial navigation system INS, a multimode region difference augmentation system MLDAS, a pressure altimeter and timekeeping equipment, which are arranged on an aircraft; performing fusion treatment on multisource information by using a federal wave filter, wherein the federal wave filter comprises a main wave filter and a plurality of local wave filters connected with the main wave filter, and each kind of the multisource navigation information and a reference signal are jointly input to one local wave filter; triggering the local wave filters to respectively calculate local estimation values and error covariance matrixes; triggering the main wave filter to perform wave filtering on the reference signal, and performing optimal infusion on the wave filtering results of the reference signal according to output results of the local wave filters and the local wave filters, so as to obtain a global optimum estimation value. Therefore, the availability and the integrity of on-board navigation equipment are improved.

A method for tracking objects in a scene being viewed by a sequence of digital images comprises: separating a region of interest in the digital images into a plurality of spatially smaller, overlapping modules, and defining a hidden Markov model for each module. The method further comprises observing detections of positions of possible objects at different times, considering a set of states at a point of time (t₁) such that the set of states comprises a state having a global optimum probability, and backtracking through the sequence of digital images for each hidden Markov model to shrink the set of states that are possible for earlier parts of the sequence of digital images, such that a single optimal state is found for an earlier point of time (t₂<t₁), whereby tracks of detected objects through the scene are determined up to the earlier point of time (t₂).

The invention discloses a slope stability analysis slice method based on global optimization and belongs to the field of slope stability analysis. The method includes that a slope slip mass is divided into vertical strip blocks or inclined strip blocks, acting force (including normal force and shearing force) on the bottom faces of the strip blocks and acting force (including normal force and shearing force) between the strip blocks are utilized as unknown variables, stable safety coefficient of the slope is utilized as a target function, and a balance equation of the strip blocks, the yield condition of the bottom slip face of the strips blocks, the yield condition of contact face between the strip blocks and other constraint conditions are combined to build a nonlinear mathematical planning model for slope stability analysis, and an optimization algorithm is utilized to solve the global optimum maximum stable safety coefficient. By means of the method, the performance that the slope safety coefficient has a floor solution can be achieved. The method has the advantages of being clear in conception, high in calculation accuracy and the like and can be applied to stability analysis of soil slopes or rock slopes.

The invention discloses a cloud data center load prediction method based on LSTM (Long Short-Term Memory), and aims to solve the problem that optimal utilization can not be obtained by the limited calculation resources of a cloud data center. The method comprises the following steps that: taking the mass historical records of the cloud data center as a basis to manufacture a training sample and atesting sample; in addition, constructing a neural network connected by LSTM units; continuously inputting training samples on batch to obtain an output value. A neural network optimization algorithmadopts a new adaptation moment estimation method, parameters in each unit are continuously updated through iterative training, and global optimum is realized after training is finished, only the testing sample needs to be input into the network to obtain the next prediction value of a sample sequence; and if an input sequence is continuously updated by the prediction value, a prediction value sequence in one future period of time can be obtained.

The invention relates to a plug-in hybrid electric vehicle energy optimization management method realizing real-time working condition adaption. The plug-in hybrid electric vehicle energy optimization management method includes the steps of (1), acquiring real-time working condition information of each section of each path; (2), setting the optimization target of minimizing accumulated equivalent fuel consumption of each section of each path, building the plug-in hybrid electric vehicle energy optimization management strategy based on the dynamic planning by taking the speed limit of each section of each path, the traffic flow velocity and the limit of power battery working current; (3), acquiring corresponding target economical speed of each section of each path and sending the same to a vehicular controller; (4), by the vehicular controller, acquiring demanded torque sequence of each moment within a predicted time scale; (5), taking the minimum accumulated equivalent fuel consumption within the predicted time scale as the target, and tracking the target economic speed in real time. Compared with the prior art, the method has the advantages of combining the global optimum and the real-time optimum of the plug-in hybrid electric vehicle energy consumption according to the real-time working condition information, and the like.

The invention discloses a mobile robot path planning method based on an ant colony algorithm under a dynamic environment. The method comprises the following steps of 1, modeling the environment by using a grating method; 2, building local diffusion information pheromone tau''rs; 4, computing a transition probability; 5, adding a feasible node S into a tabu table; 6, completing paths; 7, acquiringthe shortest path via path information recorded in the tabu table; 8, updating pheromone matrix elements; and 9, finding the optimal path via iteration, that is to say an algorithm ending condition ismet, and outputting a final result. According to the ant colony algorithm based on a potential field method provided by the invention, the faster convergence speed and optimizing ability are provided, the local diffusion information pheromone has relative good smoothness, the collaboration ability of individual ants is further enhanced, the local cross paths are reduced, the quantity of lost antsis reduced, and thus the ant colony algorithm is converged to the global optimum with the faster speed, and meanwhile also achieves the diversity of learning, and the defect that an artificial potential field method is easy to trap in the local optimum is overcome.

The invention discloses a mixed path planning method and system based on a grid map. The method comprises steps of according to an original grid map model, using a searchable neighborhood in the A*searching algorithm to acquire local obstacle potential field function of idle grid nodes; according to the obtained local obstacle potential field function, acquiring a cost function; using the A*searching algorithm to process the original grid map model so as to obtain passing cost of all target grid nodes; successively adding 0,1 to a weight factor mu and repeating above steps until the value of the mu is 10; finding a weight factor mu corresponding to the minimum value from the obtained passing cost; connecting all the corresponding target grid nodes to form a global passing cost smallest path; extracting all turning points in the global passing cost smallest path to serve as local target points; using the DWA algorithm to process the local target points; and connecting the processed results to form a local track meeting the global optimum.

The invention discloses a hybrid particle swarm optimization algorithm in combination with a genetic algorithm. The advantages of strong global search capability of a particle swarm optimization (PSO)algorithm and high local convergence speed of the genetic algorithm (GA) are integrated. Firstly, global search is performed by virtue of the characteristic of the strong global search capability ofthe PSO algorithm, and when iteration is performed for a specified algebra and is close to a globally optimal solution, at the moment, a whole population enters a neighborhood of the globally optimalsolution; and secondly, local quick search is performed in the neighborhood of the globally optimal solution by utilizing an improved genetic algorithm, so that the globally optimal solution is reached finally.

The invention relates to an overlay network layered multicast optimal resource allocation method for a scalable video stream, and provides a new measurement standard for the multicast performance, namely layer extensity which is used for measuring end-to-end time delay of video layers during data distribution aiming at layered multicast communication of the scalable video stream in the overlay network. In order to realize the overall minimization of the layer extensity, the method carries out the combined optimization on the network code of relay nodes, the receiving end driven flow control, and multi-path route strategy, and adopts a linear programming method to establish a layered multicast resource optimum allocation model for the overlay network. On one hand, the method adaptively matches the interlayer dependency of the scalable video code; on the other hand, the method allows a receiving node to decide and regulate the required video quality of own accord. In addition, the invention also provides a distributed heuristic algorithm which has low complexity, approaches the globally optimal solution and is applied to the construction of a scalable video flow distribution network.

The invention discloses a cascade hydropower station group optimized dispatching method based on an improved quantum-behaved particle swarm algorithm. The problems that local optimum happens to the quantum-behaved particle swarm algorithm at the later iteration period due to premature convergence for the reason that population diversity is decreased, and an obtained hydropower station group dispatching scheme is not the optimal scheme are mainly solved. The hydropower station group optimized dispatching method based on the improved quantum-behaved particle swarm algorithm is characterized by comprising the steps that first, power stations participating in calculation are selected, and the corresponding constraint condition of each power station is set; then, a two-dimensional real number matrix is used for encoding individuals; afterwards, a chaotic initialization population is used for improving the quality of an initial population, the fitness of each particle is calculated through a penalty function method, the individual extreme value and the global extreme value are updated, an update strategy is weighed, the optimum center location of the population is calculated, neighborhood mutation search is conducted on the global optimum individual, the positions of all the individuals in the population are updated according to a formula, and whether a stopping criterion is met or not is judged. The hydropower station group optimized dispatching method based on the improved quantum-behaved particle swarm algorithm is easy to operate, small in number of control parameters, high in convergence rate, high in computation speed, high in robustness, reasonable and effective in result, and applicable to optimized dispatching of cascade hydropower station groups and optimal allocation of water resources.

Aiming at the disadvantages of a basic particle swarm algorithm on the solving of the coverage optimization problem of a wireless sensor network, in combination with a maximum coverage algorithm, the invention provides a particle swarm-based coverage optimization method of a wireless sensor network mobile node. The algorithm takes a mobile node position vector quantity as an input parameter, and a network coverage rate as a target function, and the positions among nodes can be adjusted by a far module and a near module mentioned in the maximum coverage algorithm, the nodes are enabled to be far away if being distributed densely; and the nodes are enabled to be near if being distributed loosely. In combination with the position adjustment and the particle swarm algorithm, the positions of the nodes and the nearest node can be adjusted in a particle swarm algorithm speed updating formula, and the particle can be guided to be evolved, so that the coverage range of the nodes can be preferably expanded, and the capability of the particle swarm algorithm for searching the globally optimal solution can be enhanced, i.e. the network coverage rate can be improved. Finally, the wireless sensor network coverage optimization problem can be solved by the position adjustment-based particle swarm algorithm.

The invention relates to the technical field of unmanned surface vehicle path planning, in particular to an unmanned surface vehicle path planning method based on a neighborhood intelligent water drop algorithm. The method comprises the steps of 1, performing environment modeling on unmanned surface vehicle path planning; 2, performing off-line global path planning in an operation area grid matrix by utilizing the intelligent water drop (IWD) algorithm according to a known unmanned surface vehicle operation area static obstacle, an advancing goal and path evaluating function so as to obtain a global off-line optimum path. The problem that the method is stagnated and low in convergence rate caused by the fact that a basic IWD method is easily caught in local optical solution is improved, and an optical solution adjacency expansion mechanism and a global optimum stressing mechanism are introduced on the basis of the basic IWD method to obtain an NIWD method, so that prematurity caused by the fact that the method is caught in local optimum is avoided, and the optimizing convergence rate of the method is improved.

A generalized framework is disclosed in which a wide variety of propagation models can be cast in a matrix-based format using arbitrary matrix coefficients (e.g., real numbers, integers, etc.). Casting propagation models in the matrix-based framework enables efficient computer implementation and calculation, ease of tuning, admissibility (i.e., the tuned parameters of a linear matrix model are guaranteed to be the global optimum), and aggregating multiple propagation models into a single matrix-based model. Matrix-based propagation models based on transmitter-receiver azimuth orientation, transmitter antenna height, terrain elevation, and clutter are also disclosed. The propagation models can be used in conjunction with automated data acquisition from information sources such as topographic maps, clutter maps, etc.

The invention aims at providing a positioning and map establishing method and system. A global optimum route from a starting point to a destination is determined in a grid map, determined according tomilemeter data and laser data, of a current environment to complete a navigation task of a mobile device; word bag data of a current image is extracted based on a re-positioning request, and key frames corresponding to historical word bag data having the similarity with the word bag data of the current image in a preset range is retrieved through a lexicographic tree; feature matching is performed based on the key frames to determine the posture and position of the current image in a world coordinate system, and the posture and position of the mobile device under world coordinates are determined according to the posture and position of the current image in the world coordinate system and the installing posture and position of an image sensor in the mobile device to complete re-positioning. Accordingly, the mobile device can perform map establishing, positioning and navigation tasks in an unknown environment, makes global re-positioning easy to achieve and can be used for navigation and obstacle avoidance tasks of mobile devices.

The invention provides a method and system for recognition of a GIS ultrahigh frequency partial discharge signal. The method for recognition of the GIS ultrahigh frequency partial discharge signal comprises the following steps of (1) carrying out preprocessing on the GIS ultrahigh frequency partial discharge signal to obtain a three-dimensional spectrogram, (2) carrying out projection on the three-dimensional spectrogram to form a two-dimensional spectrogram, respectively extracting discharge characteristic parameters which describe shape difference of the two-dimensional spectrogram, and discharge characteristic parameters which describe difference between a positive semi-circle outline and a negative semi-circle outline of the two-dimensional spectrogram to obtain a sample to be detected, and (3) carrying out defect recognition on the sample to be detected according to an ABC-BP model which is built in advance. The method for recognition of the GIS ultrahigh frequency partial discharge signal can carry out rapid convergence to obtain the global optimum, and improves efficiency and accuracy of fault recognition of GIS partial discharge.

The invention discloses an image segmentation method based on immunity spectrum clustering, which includes: 1. extracting texture characteristic of the input image, representing each pixel point in the image with an eigenvector to obtain a characteristic set; 2. mappings the characteristic set to a linear measure space by spectrum clustering to a mapping set; 3. dividing the category number according to the given image, accidentally selecting the corresponding number of data from the mapping set as the initial clustering center, executing cloning, variation, selection and judgement in sequence, to find out a optimum clustering center with the same category number with the initial clustering center; 4. dividing all pixel points of the characteristic set to an optimum clustering center nearest to the pixel points, and giving each pixel point a category mark according to the category of optimum clustering center where the pixel point locates to complete the image segmentation. Compared with the prior technology, the invention has advantages of insensitivity to initialization, quick convergence to global optimum and high specification accuracy, which can be used in the image segmentation of SAR image processing and computer visual sense field.

The invention discloses a short-term electric load prediction method based on improved genetic algorithm for optimizing extreme learning machine. A hill climbing method is used to perform preferentialselection again in the progeny population, an initial individual is selected, another individual in a close area is select, their fitness values are compared, and one individual which has good fitness values is leaved. If the initial individual is replaced or a better individual cannot be found in several iterations, iteration is stopped, the search direction of the genetic algorithm through thehill climbing method is optimized, obtaining an optimal weight value and a threshold value, a network optimization prediction model are obtained, a network optimization prediction model is obtained, the network optimization prediction model and prediction results of BP network and the extreme learning machine are comparative analyzed, including selection of input and output of the prediction network model, algorithm of improved genetic algorithm for optimizing extreme learning machine, and analysis of prediction results. The short-term electric load prediction method based on improved geneticalgorithm for optimizing extreme learning machine has faster training speed and more accurate prediction results, and is suitable for modern short-term electric load prediction with plenty of influence factors and huge data volume.