3048 results about "Local 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 preferred set of prices for a plurality of products, generally demand coefficients is provided. Cost data including activity-based costs is also received. A preferred set of prices that will provided a local optimum for the preferred set of prices which maximizes profit is then determined. In one embodiment, a sales model and a cost model are created. A plurality of rules is specified. The preferred set of prices is then determined based on the sales model, the cost model, and the plurality of rules.

Dynamical methods for obtaining the global optimal solution of general optimization problems having closed form or black box objective functions, including the steps of first finding, in a deterministic manner, one local optimal solution starting from an initial point, and then finding another local optimal solution starting from the previously found one until all the local optimal solutions starting from any initial point are found, and then finding from said points the global optimal solution.

The invention provides a fault diagnosis method for a rolling bearing based on a deep learning and SVM (Support Vector Machine). The method comprises using a manure learning algorithm in a deep belief network theory to complete a characteristic extraction task needed by fault diagnosis; automatically extracting the substantive characteristics of data input independent of manual selection from simple to complicate, from low to high, and automatically digging abundant information concealed in known data; in addition, classifying and identifying a test sample by adopting an SVM classification method, seeking and finding a global minimum of a target function through an effective method previously designed, so as to solve the problem that a deep belief network may be trapped into a locally optimal solution. According to the fault diagnosis method for the rolling bearing based on the deep learning and SVM provided by the invention, the accuracy and effectiveness of the fault diagnosis method for a rolling bearing can be improved, and a new effective way can be provided to solve the accuracy and effectiveness of the fault diagnosis method, therefore the fault diagnosis method can be extensively applied complex systems in chemistry, metallurgy, electric power, aviation fields and the like.

The present invention provides an indoor mobile robot vision SLAM method based on the Kinect. The method comprises the following steps: S1: acquiring color RGB data and Depth data of an indoor environment by using a Kinect camera; S2: performing feature detection of RGB data and implementing rapid and effective matching between adjacent images; S3: combining inner parameters of a Kinect camera after calibration and pixel point depth values to convert a 2D image point into a 3D space point, and establishing a corresponding relationship of 3D point cloud; S4: using the RANSAC algorithm to eliminate external points of the point cloud to complete point cloud rough matching; S5: employing an ICP algorithm with a double limit of an Euclidean distance and an angle threshold to complete fine matching of the point cloud; and S6: introducing a weight in a key frame selection, and employing the g2o algorithm to optimize a robot posture, and finally obtaining a robot moving trajectory, and generating a 3D point cloud map. The indoor mobile robot vision SLAM method based on the Kinect can solve the problems that a point cloud registration portion in a vision SLAM system is liable to local optimum and is large the matching error, and therefore the registration accuracy of the point cloud is improved.

The invention discloses a nasopharyngeal-carcinoma (NPC) lesion automatic-segmentation method and nasopharyngeal-carcinoma lesion automatic-segmentation systems based on deep learning. The method comprises: carrying out registration on a PET (Positron Emission Tomography) image and a CT (Computed Tomography) image of nasopharyngeal carcinoma to obtain a PET image and a CT image after registration;and inputting the PET image and the CT image after registration into a convolutional neural network to carry out feature representation and scores map reconstruction to obtain a nasopharyngeal-carcinoma lesion segmentation result graph. The method carries out registration on the PET image and the CT image of the nasopharyngeal carcinoma, obtains a nasopharyngeal-carcinoma lesion by automatic segmentation through the convolutional neural network, and is more objective and accurate as compared with manual segmentation manners of doctors; and the convolutional neural network in deep learning isadopted, consistency is better, feature learning ability is higher, the problems of dimension disasters, easy falling into a local optimum and the like are solved, lesion segmentation can be carried out on multi-modal images of the PET-CT images, and an application range is wider. The method can be widely applied to the field of medical image processing.

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 a facial emotion recognition method based on a deep sparse convolutional neural network. The method comprises the following steps: to begin with, carrying out emotion image preprocessing; then, carrying out emotion feature extraction; and finally, carrying out emotion feature identification and classification. The facial emotion recognition method based on the deep sparse convolutional neural network carries out optimization on weight of the deep sparse convolutional neural network through a Nesterov accelerated gradient descent algorithm to enable network structure to be optimal, thereby improving generalization of the face emotion recognition algorithm; since the NAGD has a precognition capability, the algorithm can be prevented from being too fast or too slow foreseeingly; and meanwhile, response capability of the algorithm can be enhanced, and better local optimum value can be obtained.

The invention relates to a multi-target reactive power optimization method, in particular to a multi-target reactive power optimization method based on an adaptive chaos particle swarm algorithm. The method aims at solving the problem that multi-target reactive power optimization control variables are probably trapped in a locally optimal solution, and the speed for acquiring an optimal solution is low. The method includes the steps that firstly, original data of a particle swarm are input to an adaptive chaos particle swarm optimization algorithm program; secondly, first m particles are selected from the particle swarm as initial positions of the particle swarm according to fitness values in a preferred mode; thirdly, inertia weights w of the particles are acquired through calculation of inertia weight coefficients, and first M preferred particles are selected from the particle swarm for chaos optimization calculation; fourthly, the speed and the positions of the particles are updated according to the particle swarm reactive power optimization algorithm, and then iteration allowances and values of the control variables can be acquired; fifthly, whether iteration stop conditions are met or not is judged, and then the multi-target reactive power optimization method based on the adaptive chaos particle swarm optimization algorithm is finished. The multi-target reactive power optimization method is applied to the field of electric systems.

The invention provides an electric car intelligent charging system and method on the basis of a mobile device and belongs to the technical field of electric car charging positive intelligent control. The system comprises a power grid management center, a station level management server, the mobile device, a charging device and a power battery. The station level management server comprises a data input module, a data processing module, a data feedback module and a historical data memory module and is used for calculating, solving and achieving the real-time optimum order charging scheme, outputting specific charging orders to the charging device and the mobile device and feeding back the charging information. According to the method, the local optimum greedy algorithm is used for solving the real-time optimum order charging scheme, the user interaction character is achieved, and the order charging scheme of an electric car is obtained by carrying out data mining and predicting on the user data and the power grid data and carrying out performance analysis on the power battery. Under the circumstance of ensuring that battery loss is small, the electric car intelligent charging system and the method greatly meet the individual requirements of the users and achieve effective optimization of a power grid.

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 method for path planning based on an improved ant colony algorithm. Compared with the classical ant colony algorithm, the method has the following improvements: (1) a constant pheromone evaporation coefficient is adjusted to be an adaptive pheromone evaporation coefficient, and the size of the coefficient is changed adaptively along with increase in number of iterations of an ant colony method; a local optimum path is preferentially selected by adopting a rule that the number of inflection points is small on the basis that different paths are identical in length; (3) a path simplifying rule is adopted for the local optimum path, whether each passing node in the path and the starting node are neighboring nodes or not is judged, and redundant nodes on the path are eliminated; and (4) a pre-sorting rule is adopted when pheromone updating is performed on the path passing by an ant colony before, and only the top 1/3 of paths in path length sorting are updated. According to the above improvements, the method can effectively reduce the algorithm convergence time of the ant colony algorithm and improve the operating efficiency.

The invention discloses an optimization method for solving an omni-channel logistics distribution problem. In a first stage, a Lagrange relaxation technology is used to solve a LAP (Location-allocation Problem) problem. In a second stage, adaptive large-scale neighborhood search is used for solving a multi-vehicle-type vehicle path problem, a feasible solution can be searched in a large range in a solution space through one group of simple destruction and reconstruction algorithms, and a situation of falling into local optimum can be effectively avoided. Meanwhile, a simulated annealing acceptance criteria realized in the adaptive large-scale neighborhood search can guarantee the quality of a solution and the convergence of the algorithm, a result is output after the algorithm is executed for an appointed iteration number, a time constraint requirement can be met, and a good vehicle distribution scheme is solved for enterprises in limiting time. The simpleness of the Lagrange relaxation technology is combined with the efficiency of the adaptive large-scale neighborhood search, so that the integral solving efficiency of a mixed algorithm is high, and the problem of omni-channel logistics distribution can be effectively solved.

The invention relates to a mobile robot path planning method and system based on an improved ant colony algorithm. The mobile robot path planning method comprises the following steps of 1 environment modeling, 2 initial pheromone distribution and 3 optimal path searching and optimal path outputting. According to the mobile robot path planning method and system based on the improved ant colony algorithm, improvement is conducted on a previous traditional ant colony algorithm in the initial pheromone distribution aspect, ants can guide optimization of the ants at the beginning, and the early convergence speed is obviously increased; meanwhile initial parameters are reasonably selected, for instance, selection of pheromone evaluation, a result does not run into a locally optimal solution or has difficulty in forming an optimal solution, reasonable improvement is conducted on a pheromone update mode, the situation of running into the locally optimal solution can be effectively avoided, and the working efficiency and working reliability of the robot can be improved.

A method determines a global optimal solution of a system defined by a plurality of nonlinear equations by applying a metaheuristic method to cluster a plurality of search instances into at least one group, selecting a center point and a plurality of top points from the search instances in each group and applying a local method, starting from the center point and top points for each group, to find a local optimal solution for each group in a tier-by-tier manner. Then a TRUST-TECH methodology is applied to each local optimal solution to find a set of tier-1 local optimal solutions, and the TRUST-TECH methodology is applied to each tier-1 local optimal solution to find a set of tier-2 local optimal solutions. A best solution is identified among all the local optimal solutions as the global optimal solution. The heuristic method can be a particle swarm optimization method or a genetic algorithm method.

The invention provides a multi-neural network control planning method for a robot path in an intelligent environment. The method comprises the steps that 1 a global map three-dimensional coordinate system is constructed for the carrying area of a carrier robot to acquire a walkable area coordinate in the global map three-dimensional coordinate system; 2 a training sample set is acquired; 3 the global static path planning model of the carrier robot is constructed; and 4 starting and ending coordinates in a transportation task are input into the global static path planning model based on a fuzzy neural network to acquire the corresponding optimal planning path for the carrier robot. According to the invention, the global static path planning model and a local dynamic obstacle avoidance planning model are separately established; the nonlinear fitting property of the neural network is used to find the global optimal solution quickly; and the problem of falling into a local optimum in common path planning is avoided.

The present invention discloses a non-feature extraction dense SFM three-dimensional reconstruction method, comprising: inputting n images about a certain scenario, n≧2; establishing a world coordinate system consistent with a certain camera coordinate system; constructing an objective function similar to optical flow estimation by taking a depth of a three-dimensional scenario and a camera projection matrix as variables; employing a from coarse to fine pyramid method; designing an iterative algorithm to optimize the objective function; outputting depth representing the three-dimensional information of the scenario and a camera projection matrix representing relative location and pose information of the camera; and realizing dense projective, similarity or Euclidean reconstruction according to the depth representing the three-dimensional information of the scenario. The present invention can accomplish dense SFM three-dimensional reconstruction with one step. Since estimation of dense three-dimensional information is achieved by one-step optimization, an optimal solution or at least local optimal solution can be obtained by using the objective function as an index, it is significantly improved over an existing method and has been preliminarily verified by experiments.

The invention, which belongs to the technical field of mobile robot navigation, provides a mobile robot obstacle avoidance method based on a DoubleDQN network and deep reinforcement learning so that problems of long response delay, long needed training time, and low success rate of obstacle avoidance based on the existing deep reinforcement learning obstacle avoidance method can be solved. Specialdecision action space and a reward function are designed; mobile robot trajectory data collection and Double DQN network training are performed in parallel at two threads, so that the training efficiency is improved effectively and a problem of long training time needed by the existing deep reinforcement learning obstacle avoidance method is solved. According to the invention, unbiased estimationof an action value is carried out by using the Double DQN network, so that a problem of falling into local optimum is solved and problems of low success rate and high response delay of the existing deep reinforcement learning obstacle avoidance method are solved. Compared with the prior art, the mobile robot obstacle avoidance method has the following advantages: the network training time is shortened to be below 20% of the time in the prior art; and the 100% of obstacle avoidance success rate is kept. The mobile robot obstacle avoidance method can be applied to the technical field of mobilerobot navigation.

The invention discloses a random convolutional neural network-based high-resolution image scene classification method. The method comprises the steps of performing data mean removal, and obtaining a to-be-classified image set and a training image set; randomly initializing a parameter library of model sharing; calculating negative gradient directions of the to-be-classified image set and the training image set; training a basic convolutional neural network model, and training a weight of the basic convolutional neural network model; predicting an updating function, and obtaining an addition model; and when an iteration reaches a maximum training frequency, identifying the to-be-classified image set by utilizing the addition model. According to the method, features are hierarchically learned by using a deep convolutional network, and model aggregation learning is carried out by utilizing a gradient upgrading method, so that the problem that a single model easily falls into a local optimal solution is solved and the network generalization capability is improved; and in a model training process, a random parameter sharing mechanism is added, so that the model training efficiency is improved, the features can be hierarchically learned with reasonable time cost, and the learned features have better robustness in scene identification.

The invention discloses an improved ICP object point cloud splicing method for fusing fast point characteristic histogram. The method comprises the steps of projecting a standard sinusoidal digital grating onto the surface of the object to be measured, photographing stripe images of the surface of the object projected with the standard sinusoidal digital grating from different angles of view by aCCD camera, and obtaining photographing point clouds from multiple angles of view; for two image point clouds that need to be stitched together, building a k-D tree and interpolate to obtain that interpolated point cloud; for the two interpolated point clouds to be spliced, computing the fast point feature histogram, and obtaining the point cloud by random sampling consistent transformation; usingthe improved iterative nearest point method to obtain the first interpolated point cloud which is precisely registered; overlaying point cloud and mesh to realize the mosaic of two different angles of view of the shooting point cloud. The invention has low requirement for the initial position of the splice point cloud, the robustness is remarkably improved, the local optimization is not easy to fall into, the splice accuracy is improved, and the precise splicing of the point cloud under multi-view angles is realized, so that the practical industrial application requirements can be met.