724 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.

The present invention discloses a facial emotion recognition method based on a depth sparse self-encoding network. The method comprises the steps of 1, acquiring and pre-processing data; 2, establishing a depth sparse self-encoding network; 3, automatically encoding / decoding the depth sparse self-encoding network; 4, training a Softmax classifier; and 5, finely adjusting the overall weight of the network. According to the technical scheme of the invention, sparseness parameters are introduced. In this way, the number of neuronal nodes is reduced, and the compressed representation of data can be learned. Meanwhile, the training and recognizing speed is improved effectively. Moreover, the weight of the network is finely adjusted based on the back-propagation algorithm and the gradient descent method, so that the global optimization is realized. The local extremum and gradient diffusion problem during the training process can be overcome, so that the recognition performance is 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 provides a method and a device for planning a route of an electric car, which are used for providing a global optimum route to the running of the electric card, and can get ready for the next travelling after the electric car arrives at the destination. The method comprises the following steps: determining the position information of each candidate charging station and each candidate charging station sequence according to acquired predetermined starting position information, destination position information, charging facility information of the destination and initial electric quantity; aiming at each candidate charging station sequence, respectively calculating the route parameters from the starting point, through the candidate charging stations included in the candidate charging station sequence in sequence and to the destination point, and selecting the optimal route according to the route parameter of each candidate charging station sequence and a predetermined route selection rule.

The invention discloses an automatic inspection method of a significant object sequence based on studying videos. In the method of the invention, static significant features are firstly calculated, and then dynamic significant features are calculated and self-adaptively combined with the static significant features to form a significant feature restriction; the space continuity of each image of frame is calculated; the time continuity of significant objects in neighboring images is calculated. The similarity between all possible significant objects is calculated by the method; a significant object sequence obtained through the former calculation is utilized to calculate the overall subject model and calculate corresponding energy contribution; the overall optimum solution is solved by dynamic planning so as to obtain the overall optimum significant object sequence; the iteration is continued for solving if a convergence condition is not satisfied, otherwise a rectangle box sequence is outputted as the optimum significant object sequence. The method of the invention can effectively settle the choosing of the static and dynamic significant features, the optimum integration of various restraint conditions and the high effective calculation of target sequence inspections.

The invention discloses a method for finding an optimal path for an AODV (ad hoc on-demand distance vector) protocol in an Adhoc (self-organized) network based on an improved genetic-ant colony algorithm. Due to continuous changes of an Adhoc network topological structure, the performances of an existing routing protocol are very difficult to meet the needs of the network. In order to overcome the defects of being low in convergence rate, long in searching time, easy to get in locally optimal solution and incapable of reaching global optimum of a normal routing algorithm, the invention provides a method for finding an optimal path for an AODV protocol by taking the improved genetic-ant colony algorithm (IGAACA) as a core. The method comprises the following steps: firstly, finding a relatively optimal solution by utilizing global searching ability of a genetic algorithm; then, converting the relatively optimal solution into an initial information element of the colony algorithm; finally, adopting the advantage of quick converge of the colony algorithm, finding the routing global optimal solution. The algorithm can be adopted to quickly and effectively find the optical path, so that the network performances are improved.

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 method for autonomous navigation using a geomagnetic field line map. Firstly, a plurality of characteristic quantities of the geomagnetic filed on a path of an aerial vehicle are measured continuously according to a preset frequency, and measurement data are used to build a matched line map of the corresponding characteristic quantities in a sliding window mode with fixed-point number; and a matched line map of the plurality of characteristic quantities is matched and compared with a reference map by using an algorithm for fining global optimum according to a matching similarity rule and a matching result fusion rule to acquire the position information of the aerial vehicle. The technology makes full use of the characteristics of the plurality of characteristic quantities of the geomagnetic field to calculate the accurate position of the aerial vehicle, avoids navigation accumulated error under a condition of long flight period, is particularly suitable for navigation in environments without typical geomorphic features such as ocean and plain, can meet requirements of future cruise missiles, unmanned aerial vehicles, submarines and the like for passive, all-sky time, all-weather and all-terrain navigation, and also can be used in civil area.

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.

The invention relates to a digitizing detection method of a complicated curved face. The method comprises the following steps: (1) extracting the geometric data of a CAD model of the complicated curved face, establishing an NURBS theoretical model of the complicated curved face, measuring a part object with the curved face by a three-coordinate measuring machine, digitizing the surface of the partto obtain the parameter of a measuring point; (2) establishing a binary nonlinear mathematical model with the minimum distance from the measuring point to an isoparametric line areas of the curved face by searching two groups of isoparametric line areas with isoparametric line structure proximate to the measuring point on the CAD curved face; and (3) calculating the shape error of the complicatedcurved face by a genetic algorithm to realize the error estimation of the complicated curved face. Compared with the prior art, the invention establishes an accurate curved face theoretical model, enhances the searching efficiency, can ensure the acquisition of a globally optimal solution and lightens the measuring intensity.

A method for synchronizing multi-carrier signals in an orthogonal frequency division modulation (OFDM) data transmission system is disclosed which provides maximum likelihood estimation of timing offset and frequency offset. The estimates are able to compensate the estimation error over an entire span of observed data samples. The method requires no training sequence thus enabling blind frequency compensation. The method provides a joint probability density function for the estimates which consists of two terms; one generated from observed data received during a first interval and one generated from observed data received during a second, following, interval. The estimates provided by the method are therefore maximal likelihood over the entire span of observed signals and are a significant improvement over estimates provided by methods based only observations during the first interval. The method is mathematically robust and computationally and statistically efficient. Comparison studies generated by computer simulation graphically display the improved estimates provided by the invention over previous estimation techniques.

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 an underwater vehicle three-dimensional route planning method based on a cuckoo search algorithm and belongs to the technical field of underwater vehicle three-dimensional route planning. In detail, according to the problems existing in underwater vehicle three-dimensional route planning, the method includes the five basic steps of modeling, initializing the cuckoo search algorithm, updating the positions of cuckoo nests, selecting the global optimum position, judging an end condition and outputting the optimum route. According to the method, simplicity, high efficiency and global searching capacity of the cuckoo search algorithm are utilized well. Compared with a traditional underwater vehicle route planning method, the underwater vehicle three-dimensional route planning method is higher in intelligence and adaptability and is higher in flexibility and easier to implement compared with other intelligent optimization algorithms; the process of route planning is performed in a three-dimensional environment, a planned route is higher in practicability compared with a route planned in a two-dimensional environment, and the navigation requirements of an underwater vehicle can be met very well.

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.