81 results about "Radial basis function network" patented technology

The invention relates to an intelligent vehicle lane change path planning method based on a polynomial and radial basis function (RBF) neural network. The intelligent vehicle lane change path planning method comprises the following steps that: the state information of obstacles and lane change vehicles in lanes are detected and determined according to a vehicle-mounted sensor, and the state information comprises positions, speed, acceleration and shapes; the lane change vehicles and the obstacles are geometrically covered, and in addition, a lane change path model using the time as the independent variable is built; boundary conditions of the lane change vehicles are obtained by the dynamic RBF neural network; the lane change path parameter is subjected to traversing in a certain range according to a certain step length, and the calculation of a polynomial method is combined to obtain the lane change path set under the specific boundary conditions; index functions for evaluating the merits of the lane change patch performance are defined, the optimal path in generated lance change paths is screened according to the index functions and is applied to the practical lane change process of vehicles; and whether the RBF neural network is updated or not is determined according to the merits of the boundary conditions of the generated lane change paths. The neural network has good self-adaption capability, so that the problem that the RBF neural network structure is oversize or undersize is solved.

The invention relates to a cutter abrasion online monitoring method based on wavelet packet analysis and a radial basis function (RBF) neural network. The method comprises the steps that shear force coefficients and cutting edge force coefficients of tangential force and radial force in different cutter abrasion states are calibrated by means of an instantaneous cutting force coefficient recognition method; and by analyzing the correlation between cutting force coefficients and cutter abrasion, the coefficients are taken as cutter abrasion characteristic parameters and input into a RBF neutralnetwork model after being subjected to normalization processing. An input layer of a RBF neutral network monitoring model training process comprises cutting force characteristics, cutting vibration characteristics, the shear force coefficients and the cutting edge force coefficients after being subjected to normalization processing; and an output layer comprises the cutter rear cutter surface abrasion capacity after being subjected to normalization processing; a hidden layer comprises neurons obtained through radial basis function iterative optimization; and it is verified that the RBF neuralnetwork monitoring model has the advantages of high response speed and high recognition precision through cutter abrasion monitoring experiments.

The invention discloses a radial basis function (RBF) neural network parameter self-optimizing-based multi-step prediction method for water quality. The method comprises the following steps of: first storing the data of each monitoring station into a database of a local server by using the remote transmission of an online water quality monitoring instrument; then performing normalization processing on a water quality sample sequence, calculating an autocorrelation coefficient to determine an input variable of an RBF neural network, and converting sample data into a standard dynamic sequence data format trained and predicted by the RBF neutral network; next searching for and determining an optimal value of a spreading coefficient spread of the RBF neural network by utilizing a differential evolution algorithm and taking a relative standard error as a target function to obtain an optimal prediction model; and finally sampling water quality data in real time, performing multi-step prediction by using the obtained optimal prediction model and adopting a single-point iteration method, and evaluating a water quality prediction result to realize an early warning function. The water quality can be intelligently warned.

The invention discloses a three-dimensional craniofacial reconstruction method based on the overall facial structure shape data of Chinese people, comprising the following steps of: (1) acquiring a thickness distribution model of a facial soft tissue based on the statistic analysis of a large amount of human head CT (Computed Tomography) data; (2) unfolding the soft tissue layer and the skull surface layer of a human head through a cylinder, and projecting the soft tissue layer and the skull surface layer to a two-dimensional flat surface, representing the soft tissue shape and the skull shape by using a two-dimensional depth map, and training a radial basis function network to realize the change between the skull to be reconstructed and the common soft tissue thickness distribution form; (3) constructing a shape subspace of local organs of the reconstructed face based on the craniofacial facial structure shape classification of human species, and learning the mapping between the craniofacial local shape and the local shape of the reconstructed face; (4) correcting the reconstructed face model by combining the integral soft tissue distribution and the local characteristic shape deformation, i.e. completing three-dimensional craniofacial reconstruction and correctness of the input skull by adding the two-dimensional depth maps of the soft tissue shape and the shape of the skull to be reconstructed; and (5) synthesizing a complete texture graph of the face through facial texture mapping by using orthogonal pictures, and rendering the skin color and the hair style of the reconstructed human picture to enhance the reality sense of the human picture. By applying the method, the problems of missing reconstruction details and lack of individual characteristics are solved, the manufacturing cost of other anthropology researches and reconstruction technologies is saved, and the working efficiency is improved. The invention has high automation degree and simple operation.

A method and apparatus are disclosed for classifying objects using a hierarchical object classification scheme. The hierarchical object classification scheme provides candidate classes with an increasing degree of specificity as the hierarchy is traversed from the root node to the leaf nodes. Each node in the hierarchy has an associated classifier, such as a Radial Basis Function classifier, that determines a probability that an object is a member of the class associated with the node. The nodes of the hierarchical tree are individually trained by any learning technique, such as the exemplary Radial Basis Function Network, that uses appearance-based information of the objects under consideration to classify objects. A disclosed recognition scheme uses a decision criterion based upon recognition error to classify objects.

The invention provides a power plant pulverized coal boiler combustion performance online optimizing method and system. The method comprises the steps of receiving basic data of boilers in different load work conditions, which are acquired by a Distributed Control System (DCS) and an instrument, wherein the basic data is used for establishing non-linear mapping relationship between pulverized coal boiler adjustable input variables and output variables through a radial basis function network, and the non-linear mapping relationship is used as a boiler combustion mathematic model; obtaining an optimal input combination and value of boiler combustion system adjustable variables under the corresponding expectation coal consumption and NOX emission level. By the aid of the method and the system, optimal control can be performed on boiler operation engineering, relationships among all operation parameters of the boiler are coordinated, the safety, the economy and the reliability of the system are further improved, and the boiler combustion system comprehensive performance is improved comprehensively.

The invention discloses a multi-parent genetic algorithm air source heat pump multi-objective optimization control method based on a radial basis function neural network. The method comprises the following steps that 1, input and output variables are input into a system according to user requirements; 2, creating, training and testing a radial basis function neural network; 3, performing multi-objective optimization on an air source heat pump by using a multi-parent genetic algorithm based on the trained radial basis function neural network; and 4, obtaining the parameter value of the input variable of the optimal solution according to the Pareto solution through the above steps, and transmitting the obtained input variable value to the system to adjust the control quantity of the heat pump. The multi-objective optimization of the COP heating capacity Qh or the carbon dioxide release amount m and the heating capacity Qh of the system can be rapidly realized while the precision is high.

The invention provides an RBF (radial basis function) neural network-based indoor visual environment control system and method. The system includes a data acquisition module, a data processing and control module and an output driving module; the data acquisition module is used for acquiring indoor and outdoor illuminance values; the data processing and control module is used for obtaining indoor illumination control parameters according to the illuminance values and based on an RBF (radial basis function) neural network algorithm and outputting the indoor illumination control parameters; and the output driving module is used for controlling indoor shutter blinds to rotate and/or an indoor lighting lamp to be turned on according to the indoor visual control parameters so as to realize an indoor visual environment comfortable control effect. According to the RBF (radial basis function) neural network-based indoor visual environment control system and method of the invention, the relatively reasonable indoor visual environment neural network control system is constructed, the control precision and universality of the indoor visual comfortable environment control system can be improved, defects such as instability and limitations of a traditional control system and method can be eliminated; and illumination power resources can be saved to the greatest extent with indoor visual comfort ensured.

The invention discloses a wind turbine generator set ultra-short period wind power prediction method based on an improved RBF network. A wind turbine generator set is adopted for the operation of statistic data, parameters closely influencing the output of wind power are reasonably selected, such as the wind speed, wind direction, propeller pitch angle and wind power of the previous period, and a manual neural network-a radial basis function network is utilized to establish a model of corresponding relations between related parameters and the wind power output; and the improved RBF network is utilized to modify the model, whether the node number of a current hidden layer meets a precision requirements is judged, whether the output of nodes of one hidden layer is smaller than one value in a continuous period of learning is judged, the node number of the hidden layer is modified on line in real time, and new learning samples are continuously added along with the development of prediction. The wind power prediction method is high in precision and high in speed.

The invention discloses a soft measuring system based on kernel principal component analysis and radial basis function neural network, and the system can be used to measure parameters hard to measure in a generating set or in the complex industrial process. An intelligent instrument for measuring auxiliary variables, a DCS database for storing data and the soft measuring system are included, wherein all measurable variables of the generating set are measured by the onsite intelligent instrument and stored in the DCS database, the DCS database stores all data of the set, and the soft measuring system comprises a PC used for modeling, a server for predicating a soft measurement model and a device for displaying data. The invention also discloses a soft measuring method based on kernel principal component analysis and radial basis function neural network. The system and method in the invention have high precision, generalization capability and performance, are suitable for modeling in the complex industrial process, are general and universal, can solve the problems in soft measurement of operation parameters in complex environments including high temperature, high voltage, corrosion and electromagnetic interference, and improve the system safety and reliability.

The invention discloses a short-term tourist traffic and trend prediction system based on streaming data extraction. The system comprises a client terminal and scenic zone data terminal acquiring data; a database is established for multi-dimensional statistics; input variable parameters are acquired by converting a computation formula; a prediction model is established through a radial basis function neural network. On the basis of the system, the adopted data resource includes data acquired by an intelligent terminal, scenic zone operation and business platform backstage data and the like, the model established according to the radial basis function neural network can be used for real-time traffic prediction, and the auxiliary determination effect is achieved.

The invention proposes a motor temperature rise forecast method based on a radial basis function (RBF) neural network. According to the method, a motor temperature rise parameter of a modern car window is forecasted by building the RBF neural network, and meanwhile, the parameter forecasted by the neural network is substituted into a built motor temperature rise mathematic model so as to achieve real-time forecast on the motor temperature. The RBF neural network selected by the invention is an optimal network in a forward network, and is higher in algorithm speed than an ordinary back propagation (BP) neural network algorithm, the classification ability is high, the convergence rate is high during the studying process, and the problem of local optimum of a studying method is also avoided.

The invention relates to a multi-robot cooperation time sequence predictive n control method. The method includes the following steps that: a radial basis function network is adopted to establish an environmental quality parameter model; an environmental quality parameter optimization problem is established based on the environmental quality parameter model; an environmental monitoring task is represented by a linear time sequence logic method, and a finite state transfer system is established; and finally, a multi-robot cooperation control optimization problem is established, and based on ideal optimal movement trajectories of robots, an actual optimal control sequence of the robots is generated through adopting a predictive control method, and first control in the actual optimal control sequence is inputted to the robots so as to control the movement of the robots. With the multi-robot cooperation time sequence predictive control method of the invention adopted, deficiencies of traditional control can be made up, and environmental regions can be explored sequentially with a multi-robot tracking environmental quality parameter optimal value ensured, and collision avoidance of multi-robot movement can be maintained, and the velocity differences of the multi-robot movement are bounded.

The invention relates to a genetic algorithm and Kalman filtering based RBFN (Radial Basis Function Networks) combined training method which comprises the following five steps: I, setting a random initialized population according to parameters to code central values: v11, v12,..., v1m, v21,..., and vcm; II, calculating adaptive values of individuals in the population and storing the optimal adaptive value, wherein the target of training RBFN is to minimize an output error E and a fitness function is set as follows: Fit(fi)=1/E; III, if set evolutionary algebra is realized or a current optimal individual satisfies the condition, returning network parameters and skipping to the step IV, otherwise, skipping to the step II after selection, crossing and genetic variation operation; IV, correcting the network parameters in a self-adaptive manner by a Kalman filtering algorithm, wherein the network parameter value optimized by a genetic algorithm is taken as the network initial parameter of the Kalman filtering algorithm; and V, ending a program when the maximum iterative time limitation is realized or the current network error meets the requirement, otherwise, skipping to the step 4 to operate continuously.

The invention discloses a mars probe onboard autonomous orbit calculation method, which is a calculation method based on radial basis function neural network curve fitting. The method includes the following steps: building a three-layer radial basis function network model; getting orbit prediction data of a mars probe within a period of time according to ground orbit determination, and training the radial basis function network model by taking the data as a training sample; and finally, uploading the trained radial basis function neural network model as an onboard orbit prediction model to the mars probe. There is neither need for establishment of a complex dynamic model on a satellite nor need for ephemeris calculation. The prediction precision is almost equal to the ground orbit prediction precision. The method is also suitable for engineering implementation. The method not only can satisfy the engineering precision constraints of the recursion result, but also can satisfy the constraints of limited resources of onboard computers.

The invention discloses a remote-sensing estimation method for chlorophyll of apple leaves. The remote-sensing estimation method comprises synchronously acquiring hyperspectral reflectivity and corresponding chlorophyll relative content of the apple leaves by virtue of an SVC HR-1024i type hyper-spectrometer and an SPAD-502 chlorophyll meter, carrying out relevant analysis on original spectral reflectivity and a first-order derivative derivative spectrum so as to extract spectrographic red edge parameters of the apple leaves, and optimizing an artificial neural network by virtue of a traditional univariate regression algorithm, a BP neural network and a radial basis function network, and establishing a chlorophyll content inversion model. Compared with a traditional univariate model, the regression precision of an artificial network model is obviously increased, and the radial basis function network is high in study speed and precision and has a relatively reliable fitting result; and the artificial network model is the chlorophyll content inversion model which is worthy of being popularized.

The invention discloses a fast calculation method for dynamic characteristics of a contactor based on a radial basis function neural network. The method comprises the following steps of: 1, acquiringthe size of each structure of the contactor, the rated voltage of the contactor, the resistance of a coil, the number of turns of the coil, the mass of an armature and the material for each structureof the contactor according to the drawing of the contactor; 2, establishing a finite element model of the contactor; 3, simulating the finite element model of the contactor; 4, establishing a radial basis function neural network model of flux linkage of the contactor and a radial basis function neural network model of electromagnetic force of the contactor; 5, setting an initial state of dynamic characteristic calculation of the contactor, and determining the step length of calculation time and the total calculation time; 6, solving a dynamic characteristic equation of contactor by using a fourth-order Runge-Kutta method; and 7, aligning the solved data with the time to obtain the dynamic characteristics of the contactor. The method takes both calculation efficiency and calculation precision into account, provides a basis for the optimal design of the contactor, and has very good practical application value.

The invention discloses a small current grounding system multicriteria fault line section method based on a radial basis function (RBF) network. For small current grounding system fault line section,zero sequence current signals under different fault conditions are adopted, a fundamental wave characteristic component, a fifth harmonic characteristic component, an active component and a transientstate component are extracted, the components are input into an RBF neural network, and structure parameters of the RBF network are trained by utilizing a differential evolution (DE) algorithm, thus optimal parameters of the RBF neural network are obtained. Test results show that the RBF network trained by virtue of the DE algorithm is high in convergence rate and small in output error, and a built line selection model has high accuracy and is not influenced by various fault conditions.

The invention discloses an SVI prediction method based on a peak self-organizing radial basis function neural network, not only belong to the field of control science and engineering, but also belongs to the field of environmental science and engineering. In order to solve the problems that the sludge bulking kinetics characteristic is complex and key parameters are difficult to measure in the sewage disposal process, the method achieves accurate prediction of sludge bulking. As the prediction method adjusts the structure and connection weight of the radial basis function neural network at the same time, the information processing capacity of the neural network is improved, and the prediction precision of the SVI is improved; an experimental result shows that the intelligent prediction method can accurately predict the SVI and promote the efficient and stable operation of the sewage disposal process.

A method provided by the invention directs at the photovoltaic power of a designated power station, a power station photovoltaic power prediction model structure based on a simplified indirect causality radial basis function network is proposed, and a main meteorological factor ''solar radiation intensity'' that influences the power station photovoltaic power is reasonably hidden. Similar records are screened out from historical meteorology and photovoltaic power records according to a mahalanobis distance from a meteorological factor at a prediction time point, and a primary selection sample set with similar indirect influence factors is built, then a carefully selected sample set with similar indirect influence factors and results are selected according to a mahalanobis distance from the primary selection sample population, and then the carefully selected sample set is used to determine undetermined parameters in the prediction model structure, thereby realizing short-term power station photovoltaic power prediction modeling and prediction. The method not only simplifies a prediction model and is easy to realize prediction based on existing weather forecast information, but is also more accurate in principle, and the problem that existing power station photovoltaic power prediction methods are either not easy to realize or not accurate enough in principle is solved.

The invention discloses a novel network structure and parameter identification method for an RBF-AR model. An RBF-AR (Radial Basis Function Network-Style Coefficients Auto Regressive) model is converted into a novel generalized RBF neural network containing two hidden layers according to the structure characteristics of the model. In view of the problem that an SNPOM (Structured Nonlinear Parameter Optimization) method is of low RBF-AR model identification accuracy at low noise-to-signal ratio, a self-organization state space model of the RBF-AR model is built and an adaptive particle filter algorithm with parameter optimal initial value and parameter driving noise statistical characteristic estimation as the core is employed to identify the parameters of the RBF-AR model. The noise-containing data modeling precision and prediction precision of the RBF-AR model can be improved effectively. Online estimation and real-time control of the RBF-AR model are realized. A novel method is provided for parameter identification of the RBF-AR model.

The present invention discloses a radial basis function (RBF) interpolation-based fluid-solid coupling interface data transfer method considering load uncertainty. The method considers the fluid domain uncertainty input in the fluid-solid coupling interface data transfer, the interval representation of load uncertainty is constructed, and the radial basis function with uncertainty is established.Based on the radial basis function (RBF) interpolation, the definite solution conditions of the coefficients to be solved are constructed. Furthermore, the uncertain undetermined coefficients are solved by the definite solution conditions of the physical quantities in the fluid domain of the fluid-solid coupling interface. Finally, based on the relationship between physical quantities and undetermined coefficients, the mathematical expression of the data transfer matrix is derived, and the reliable prediction of the load range and upper and lower bounds in the solid domain is completed, so asto realize the effective transfer of the load uncertainty data of the fluid-solid coupling interface.