486 results about "Radial basis function neural" patented technology

A computer implemented method and system for gesture category recognition and training. Generally, a gesture is a hand or body initiated movement of a cursor directing device to outline a particular pattern in particular directions done in particular periods of time. The present invention allows a computer system to accept input data, originating from a user, in the form gesture data that are made using the cursor directing device. In one embodiment, a mouse device is used, but the present invention is equally well suited for use with other cursor directing devices (e.g., a track ball, a finger pad, an electronic stylus, etc.). In one embodiment, gesture data is accepted by pressing a key on the keyboard and then moving the mouse (with mouse button pressed) to trace out the gesture. Mouse position information and time stamps are recorded. The present invention then determines a multi-dimensional feature vector based on the gesture data. The feature vector is then passed through a gesture category recognition engine that, in one implementation, uses a radial basis function neural network to associate the feature vector to a pre-existing gesture category. Once identified, a set of user commands that are associated with the gesture category are applied to the computer system. The user commands can originate from an automatic process that extracts commands that are associated with the menu items of a particular application program. The present invention also allows user training so that user-defined gestures, and the computer commands associated therewith, can be programmed into the computer system.

The invention provides a combined wind power prediction method suitable for a distributed wind power plant. The method comprises the following steps: step 1, acquiring data and pre-processing; step 2, utilizing a training sample set and a prediction sample set which are normalized to build a wind speed prediction model based on a radial basis function neural network and predict the wind speed and variation trend of distribution fans at the next moment; step 3, building a distributed wind power plant area CFD (computational fluid dynamics) model and externally deducing the prediction wind speed of each fan in the plant area according to factors such as the terrain, coarseness and wake current influence of a distributed wind field; step 4, acquiring the power data of an SCADA (supervisory control and data acquisition) system fan of the distributed wind field; and step 5, adopting correlation coefficients. The invention firstly provides a double-layer combined neural network to respectively predict the wind speed and power. Models are respectively built through adopting appropriate efficient neural network types, and improved particle swarm optimization with ideas of 'improvement', 'variation' and 'elimination' is additionally added to optimize the neural network, so that the speed and precision of modeling can be effectively improved, and the decoupling between wind speed and power is realized.

The invention discloses a fault-tolerant sliding-mode control method for a near-space vehicle. According to the fault-tolerant sliding-mode control method for the near-space vehicle, for the situation that the order of the magnitude of external disturbance in a quick loop and slow loop system is greatly larger than the order of the magnitude of uncertain times of the system, the nonlinear disturbance observer technology is used for processing hybrid disturbance, and unknown hybrid disturbance is estimated by a disturbance observer through known system information; in order to solve the problem that saturation of the control surface of the near-space vehicle is limited, the upper bound of the deflection angle output of a steering engine is applied to design of a control law, it is guaranteed that the input is within a certain range, auxiliary variables are designed, the deflection angle output of the steering engine is automatically adjusted through the self-adaption law, and therefore the situation that when the upper bound of the deflection angle is too large, the output is too large is avoided; a compensator is established through a radial basis function neural network and is used for fault-tolerant compensation when the steering engine breaks down, and therefore the problem that the steering engine of the near-space vehicle breaks down is solved. By the adoption of the fault-tolerant sliding-mode control method for the near-space vehicle, under the conditions of system uncertainties, unknown external disturbance, limited input saturation and a fault of the steering engine, the near-space vehicle has good control performance.

The invention discloses a near space vehicle robust control method with input saturation. According to the control method, controllers are designed for a slow loop and a fast loop in a near space vehicle attitude motion system respectively; for a slow loop system, compound disturbance in a self-adaptive processing system is adopted to design the controller based on a dynamic sliding mode method, and further the problem of buffeting of the controller is solved; for a fast loop system, considering that order of magnitude of external disturbance is far higher that that of uncertain items of the system, the compound disturbance is processed by the aid of a nonlinear disturbance observer technique, the controller is designed based on a normal sliding mode method of a double-power reaching law, meanwhile a compensator is constructed by the aid of radial basis function neural networks to perform saturation compensation on the designed controller, and further the problem of limitation to saturation of a control plane of a near space vehicle is solved.

The invention relates to a method for optimizing combustion of a boiler. The combustion optimization of the prior boiler mainly depends on debugging stuffs to do experiments, thereby taking time and labor and obtaining limited parameter combinations. The method includes the following steps: collecting working parameters of the boiler and corresponding indexes characterizing the combustion characters of the boiler and building a real-time database; adopting an integrated modeling method supporting a vector machine to carry out modeling under the condition that the real work load is 60 percent smaller than the design load of the boiler and adopting a radial basis function neural network integrated modeling method to carry out modeling under the condition that the real work load is60 percent larger than or equal to the design load of the boiler to build boiler combustion models with different indexes; and utilizing the particle swarm optimization algorithm and combining with the built models to optimize the combustion parameter setting of the boiler according to different combustion indexes or index combinations of the boiler. The invention improves the predictive ability of the integral model, greatly improves the predictive ability of the models, and carries out one-line optimization and off-line optimization.

A soft measurement method of industrial production melt index on PP polymerization includes selecting nine variables influencing variation of melt index as input variables of soft measurement mode, using master element analysis to pick up main composition from input variables for eliminating off relativity between variables, applying radial based function neuro-network to set up nonlinear model between input and output as well as simultaneously utilizing fuzzy genetic algorithm to carry out optimum selection on model parameter.

The invention discloses a deep neural network multitask hyper-parameter optimization method. The method comprises: firstly, a data training set of each task being subjected to model training to obtaina multi-task learning network model; secondly, predicting all points in an unknown region, screening candidate points from a prediction result, finally evaluating the screened candidate points, adding the candidate points and target function values of the candidate points into the data training set, and establishing a model, predicting, screening and evaluating again; and so on, until the maximumnumber of iterations is reached, finally selecting a candidate point corresponding to the maximum target function value from the data training set, that is, the hyper-parameter combination of each task in the multi-task learning network model. According to the method, the Gaussian model is replaced by the radial basis function neural network model, and the radial basis function neural network model is combined with multi-task learning and is applied to the Bayesian optimization algorithm to realize hyper-parameter optimization, so that the calculation amount of hyper-parameter optimization isgreatly reduced. The invention further discloses an electronic device and a storage medium.

The identification of Hammerstein models relates to a computerized method for identifying Hammerstein models in which the linear dynamic part is modeled by a space-state model and the static nonlinear part is modeled using a radial basis function neural network (RBFNN), and in which a particle swarm optimization (PSO) algorithm is used to estimate the neural network parameters and a numerical algorithm for subspace state-space system identification (N4SID) is used for estimation of parameters of the linear part.

The method for the identifying of multiple input, multiple output (MIMO) Hammerstein models that includes modeling of the linear dynamic part of a Hammerstein model with a state-space model, and modeling the nonlinear part of the Hammerstein model with a radial basis function neural network (RBFNN).

The adaptive superconductive magnetic energy storage (SMES) control method and system control a SMES device connected to a power generation system. A radial basis function neural network (RBFNN) connected to the controller adaptively adjusts gain constants of the controller. A processor executes an improved particle swarm optimization (IPSO) procedure to train the RBFNN from input-output training data created by the IPSO, and thereafter generate starting weights for the neural network. Tests carried out show that the proposed adaptive SMES controller maintains the DC capacitor voltage constant, thus improving the efficiency of wind energy transfer. The power output (reactive and real) of the SMES device improves the voltage profile following large voltage dips and provides added damping to the system.

The embodiment of the invention discloses a neural network adaptive robust trajectory tracking method and a controller applied to the technical field of robot trajectory tracking control, so as to solve the problems of poor stability and poor control effects of the prior robot trajectory tracking control technology. The method comprises steps: a proportion-derivative (PD) controller is acquired, and according to the acquired PD controller, a nominal part of the trajectory tracking system is acquired; on the basis of a radial basis function neural network, uncertain items of the trajectory tracking system are acquired; an adaptive robust controller is acquired, and the uncertain items of the trajectory tracking system are adjusted via the adaptive robust controller; and according to the nominal part, the uncertain items and an uncertain upper limit value of the uncertain items, total control input is acquired, and according to the total control input, an actual output trajectory is acquired.

The invention relates to a method for rapidly detecting adulteration of olive oil, particularly relating to a method for detecting the adulteration of the olive oil by combing a near-infrared spectroscopy with a principal component analysis-radial basis function neural network method, and mainly being used for solved the technical problems that the suitable detection method does not exist at home and abroad, the detection time is too long and the detection process is cockamamie. The detection method of the invention comprises the following detecting steps: putting a sample in a 5mm-detection cell and carrying out spectrum acquisition by the near-infrared transmission spectroscopy, wherein the scanning range is 12000cm-1-3700cm-1, the resolution ratio is 4cm-1, and the number of times of the scanning is 32; taking the average value after each sample is repeatedly detected for 5 times; selecting the spectrum wave band within 12000 to 5390cm-1 to carry out pretreatments of baseline correction and vector standardization on the original spectrum; extracting the principal components for the pretreated spectrum data by a principal component analysis method; establishing a model of a radial basis function (RBF) neural network after the principal component is extracted; and acquiring the near infrared spectrum of a sample to be detected and carrying out forecasting by the established model. By using the detection method of the invention, the olive oil can visually distinguished from the adulterated olive oil.

The invention discloses a neural network-based subway train fault diagnosis device and a neural network-based subway train fault diagnosis method. A lower computer classifies acquired subway train state information according to a functional unit, concentrates and summarizes data, and sends the data to an upper computer; the upper computer receives, processes and stores the subway train state data summarized by the lower computer; the upper computer comprises a data acquisition module and a neural network module; the data acquisition module finishes the classification of the acquired subway train state data; the lower computer acquires real-time data information of a subway train; and when the subway train fails or is to fail, the neural network module of the upper computer performs corresponding judgment and pre-judgment according to the output of a radial basis function neural network established during training and outputs fault information to a fault diagnosis result module. By the embodiment of the invention, the technical problems of insufficient acquired and analyzed data volume, low data processing efficiency and a complicated calculation process in the prior art can be well solved.

The invention discloses a real-time prediction method of mine gas concentration in short and medium terms based on radial basis function neural network integration. The method comprises the following steps of: taking mine gas concentration data as a chaotic time series to construct a plurality of prediction sub-models of radial basis function (RBF) neural networks, and taking a weighted mean of synchronous prediction results of all prediction sub-models as an integrated prediction value to realize prediction model initializtion of RBF neural network integration; then realizing prediction of the gas concentration in the range of from a short term to a medium term through setting an integrated capacity parameter (the integrated capacity parameter is also equal to an RBF network prediction step-length); and obtaining a new prediction sub-model by utilizing an incremental training mode aiming at the characteristics that gas concentration information is continuously collected, and realizing updating of the RBF neural network integration according to a first in first out queue sequence so as to improve real-time prediction precision of the gas concentration, therefore, a proper compromise can be obtained between prediction range and prediction precision requirements, and the technical requirement on a mine gas information management system is satisfied.

The invention provides a combination automatic control method with a single-joint manipulator under mixed suspension microgravity environments. The combination automatic control method comprises the following steps of 1, enabling a combination to be equivalent to an underwater robot, and establishing a kinematics equation and a dynamics equation; 2, approximating the dynamics equation of the combination by a radial basis function neural network, so as to obtain control force and control torque corresponding to the radial basis function neural network; 3, using a sliding mode control method, so as to obtain control force and control torque corresponding to sliding model control; 4, synthesizing the control force and control torque corresponding to the neural network and the control force and control torque obtained by the sliding model control method, and distributing thrust, so as to obtain a general vector which consists of thrust and joint torque of each propeller; approximating the thrust deviation of the corresponding thruster through the radial basis function neural network, so as to obtain the estimation value of the thrust deviation; 5, combining the results obtained in step 2, step 3 and step 4, obtaining the general vector consisting of the thrust and the joint torque of the corresponding propeller, and further obtaining the thrust and the joint torque of the corresponding propeller, so as to realize the automatic control.

The invention discloses a bearing-free asynchronous motor RBF neural network self-adaptive inverse decoupling control and parameter identification method. An SVPWM module, a voltage inverter, a bearing-free asynchronous motor and a load of the bearing-free asynchronous motor form a whole serving as a composite controlled object. Two radial basis function neural networks are adopted to achieve inverse control and parameter identification conducted on the composite controlled object. A self-adaptive inverse controller is formed by using an RBF neural network through learning, and is serially connected in front of the composite controlled object, errors of a feedback signal and a given signal are input into an inverse controller, and accordingly closed-loop control is formed, then a self-adaptive parameter identifier is formed by using one RBF neural network through learning and identifies output quantity speed and displacement of the composite controlled object, speed-less and displacement-free sensor control is achieved, online learning of an estimation signal is aided by means of a learning algorithm, and non-linear dynamic decoupling control of the bearing-free asynchronous motor is achieved. The bearing-free asynchronous motor RBF neural network self-adaptive inverse decoupling control and parameter identification method is high in control speed and higher in identification accuracy, and a control system is excellent.

The invention discloses a bearing temperature model based wind turbine fault prediction method. The method includes the following steps: 1) selecting a bearing according to a fault monitoring target of wind turbines; 2) analyzing SCADA operation data, and selecting modeling parameters of a bearing temperature model by using principal component analysis; 3) establishing an LRRBF prediction model ofbearing temperature in healthy state according to historical healthy state operation data on the basis of a radial basis function neural network and a linear regression analysis method; 4) calculating a predicted value of the bearing temperature in an actual operation state according to the present operation data on the basis of the LRRBF prediction model; and 5) calculating a residual error between the predicted value of the bearing temperature and an actual operation value, and analyzing the residual error by using a sliding window method. If a mean value of the residual error exceeds a preset confidence interval, the fault monitoring target is judged to have a fault, and so the fault prediction of the wind turbines is realized. The fault of the wind turbines is predicted through the bearing temperature, which is economical and efficient.

The invention discloses a self-adaptive robust control method for a nonlinear bilateral teleoperation system. For a communication time delay problem of the bilateral teleoperation system, by online estimating a non-power environmental parameter of a slave end via a radial basis function neural network model and transmitting the non-power environmental parameter back to a master end to reconstructan environmental force, the passivity of the teleoperation system as well as the balancing problems of stability and transparency is prevented. For problems of nonlinearity and uncertainty of the bilateral teleoperation system, a track generator, and a nonlinear self-adaptive robust controller based on a radial basis function neural network are respectively provided at the master and slave ends, and based on a Lyapunov theory, a self-adaptive rate for online adjusting a neural network parameter is designed, so that the system is guaranteed to have good asymptotic stability and convergence. Theself-adaptive robust control method can guarantee the global robust stability of the nonlinear bilateral teleoperation system well, implements the position tracking of a robot at the slave end, and provides a vivid force feedback for an operator.

The robust controller for nonlinear MIMO systems uses a radial basis function (RBF) neural network to generate optimal control signals abiding by constraints, if any, on the control signal or on the system output. The weights of the neural network are trained in the negative direction of the gradient of output squared error. Nonlinearities in the system, as well as variations in system parameters, are handled by the robust controller. Simulation results are included in the end to assess the performance of the proposed controller.

The invention provides an oil field output prediction method based on a dynamic radial basis function neural network. The method comprises the steps that 1, factors which affect the output are determined according to oil field situations, and historical data are obtained and divided into a training data set and a test data set; 2, unitization processing is conducted on the data sets through a deviation standardization method; 3, an RBF neural network structure is adjusted in a dynamic mode through a sensitivity method, and a temporary RBF neural network prediction model is established; 4, a model error is corrected through a state transition probability matrix, and a stable RBF neural network oil output prediction model is obtained; 5, verification is conducted on the model through the test data sets obtained in the first step to judge whether the model meets expectations or not; 6 oil field output prediction is conducted through the output prediction model which meets the expectations and obtained in the fifth step. According to the oil field output prediction method based on the dynamic radial basis function neural network, the problem that the hidden layer neurons are too many or too small is avoided. and the obtained model has an adaptive adjustment function; second correction is conducted on a prediction error, and the prediction result is more accurate and reasonable.

The invention discloses a multisource disturbance actuator saturation integrated spacecraft relative attitude control method. The method includes: starting from spacecraft relative attitude kinematicand kinetic equations to perform characteristic analysis and classification of multisource disturbances in a system; then, estimating disturbances with different characteristics by taking advantages of estimation performances of a disturbance observer, a radial basis function neural network and an extended state observer; next, designing an anti-saturation compensator to avoid damages caused by saturation upper limit exceeding of a spacecraft execution mechanism; finally, designing a composite controller according to a backstepping method on the basis of multisource disturbance observation values and anti-saturation compensation items. Therefore, adverse effects of multisource disturbances on the system are avoided, system robustness is improved, accurate spacecraft relative attitude control in a saturation range is guaranteed by the execution mechanism, and smoothness in space operation task completion is guaranteed.

Through designing a radial basis function neural network compensator to estimate coupling between channels, a model uncertainty part and external interference, a pole-placement method is used to determine a gain initial value of a fractional order proportional differential controller, the control performance is further improved by the fine adjustment of a fractional order differential order number, the flexibility of a system is enhanced, finally a feedback linearization controller is designed to obtain a control amount, and the stable attitude control with strong anti-interference for a four-rotor unmanned aerial vehicle is realized. The invention has the advantages that an unmodeled part of the system, the coupling effect between the channels and the external interference are considered, and the universality of an attitude control method is improved. Through designing a radial basis function neural network estimator to estimate the unmodeled part of the system, the coupling effect between the channels and the external interference for compensation, the system has good anti-interference ability. On the basis of traditional proportional differential control, fractional order differential is introduced to improve the control performance and flexibility of the system.

The invention discloses a dissolved oxygen control method based on a dynamic radial basis function neural network, which adopts the following steps of: determining a control object; designing a dynamic RBF neural network topology structure used for a dissolved oxygen DO controller during sewage treatment; correcting sample data; training a neural network by using part of the corrected data, controlling dissolved oxygen (DO) by using the trained RBF neural network, and taking an error between anticipant DO concentration and actually output DO concentration and an error change rate as the input of the RBF neural network, wherein the output of the RBF neural network is the input of a frequency transformator, and the frequency transformator achieves the purpose of controlling a blower by adjusting the rotating speed of an electromotor so as to finally control aeration rate. The output of the whole control system is the actual DO concentration; the control effect of the controller is improved; the dissolved oxygen meets the anticipant requirements quickly and accurately; and the problem of poor self-adaptive capability based on switch control and PID control is solved.

The invention provides a large-size wind turbine feedback linearization power control method based on a radial basis function (RBF) neural network, and relates to the field of wind turbine power control. The control method comprises the steps that 1, on the basis that a wind turbine state space is built, an affine nonlinear model of a variation paddle controller is put forward, and the feedback linearization control law is designed; 2, an affine nonlinear model of a torque controller is built, and the feedback control law is designed; 3, on the basis of analyzing blade force vibration and tower vibration, the threshold value definition of a dual-loop controller is put forward for serving as the basis of controller transformation; and 4, the RBF neural network is designed to serve as a compensation control method for controlling errors. According to the dual-loop controller based on feedback linearization provided by the invention, the constant power control problems that the wind speed change is large, small, and fast after the rated wind speed is exceeded can be solved, the control precision is also improved through error compensation, and the robust performance of the system is improved.

The invention discloses an aero-engine thrust estimation algorithm through an adaptive RBF neural network. According to the algorithm, an improved particle swarm optimization algorithm is utilized tooptimize centers, width, connection weights and other neural network parameters of all nodes of the radial basis function (RBF) neural network, and meanwhile the network scale is optimized, so that the neural network is compacter under the condition of meeting a precision requirement. The algorithm can be used for medium and small-scale data regression and can be applied to estimation of thrust and other parameters in terms of aero-engine. Through the algorithm, the adaptive RBF neural network is provided based on the particle swarm optimization algorithm; in the improved particle swarm optimization algorithm, according to different network hidden layer node numbers, locally optimal solutions in the same number as types of the hidden layer node numbers are set; and the algorithm provides anew thought for aero-engine thrust estimation and is easy to understand, simple in parameter adjustment, easy to realize, high in applicability and capable of realizing high-precision thrust estimation.

The invention discloses a method and device for generating animation data. A specific implement mode of the method comprises the following steps: obtaining a target motion parameter of at least one target animation segment in target animation to be generated; after mapping the target motion parameter to be vector matched with input of a pre-trained radial basis function neural network model, inputting to the radial basis function neural network model; identifying each component in the vector output by the radial basis function neural network model as fusion weighting coefficient of each sample animation segment in the sample animation segment sequence; according to the fusion weighting coefficient, using animation data of each sample animation segment in the sample animation segment sequence to execute the fusion, and obtaining the animation data of the target animation segment; and based on the animation data of at least one target animation segment, generating the animation data of the target animation. The implement mode is capable of realizing the automatic generation of the animation data.

The invention discloses a dissolved oxygen model prediction control method based on a self-organization radial basis function neural network, not only belongs to the field of control, but also belongs to the field of water treatment. Aiming to the characteristics of high nonlinearity, strong coupling, time varying, large lag, serious uncertainty and the like in a sewage disposal process, the control method improves the disposal capability of the neural network by automatically adjusting a neural network structure, builds a prediction model of the sewage disposal process, carries out control through a prediction model control method, and therefore improves a control effect, and enables dissolved oxygen to achieve expected requirements fast and accurately. The method solves the problem that current methods based on a switch control and a proportion integration differentiation (PID) control are poor in adaptive ability. Experimental results show that the method can control dissolved oxygen concentration fast and accurately, has strong adaptive ability, improves the quality and the efficiency of sewage disposal process, reduces sewage disposal cost, and promotes a sewage treatment plant to run efficiently and stably.

The invention relates to a greenhouse wireless sensor network control node device for intensive aquiculture by using a wireless measurement and control method, which is installed in a wireless measurement and control network of intensive aquiculture. The device is arranged in a culturing farm of an intensive aquiculture region, a collection node is used for collecting the parameters of water quality environment sensors, and the data collected by the sensor group is preprocessed by combining a rule base and an information fusion algorithm. A radial basis function neutral network algorithm (RBF algorithm) and the fuzzy computing technology are adopted as an algorithm model of information fusion, the collected data is subject to field level data fusion, and a ZigBee wireless module is used for sending fused abnormal water quality environment state and environment parameter data to a convergent node. The convergent node uploads the data to a monitoring center, and the monitoring center can monitor the growth conditions of cultured organisms, environmental conditions, control device operating conditions and the like of a plurality of culturing farms within a monitoring range in real time. The collection node can also receive the feedback information of the convergent node and the monitoring center and adjusts the parameters of the information fusion algorithm. The device is an information collection device for a wireless sensor network, has high efficiency, reliability and convenient operation, and is used for solving the difficulties of data real-time collection for culturing environment and filed level data fusion in the intensive aquiculture process by using the wireless sensors.

The invention discloses a self-learning inverse model control method of an electronic throttle. The control method comprises two parts: 1) taking a radial basic function neural network as a recognizer to create the non-linear model of the electronic throttle; 2) taking another RBF neural network to serve as an inverse model controller to obtain an appropriate control amount. The two RBF neural networks adopt a self-learning strategy which comprises an off-line learning step and an on-line learning step. In off-line learning, the two RBF neural networks adjust and optimize network weighting parameters according to on-site sample data; after the off-line learning is completed, an on-line learning algorithm is adopted to adjust and optimize the network weighting parameters of the two RBF neural networks, and then the control performance can meet the requirements. The invention can overcome the difficulties of nonlinearity, time varying and the like in electronic throttle control and improve the control effect and performance.

A system and method for performing Automatic Target Recognition by combining the outputs of several classifiers. In one embodiment, feature vectors are extracted from radar images and fed to three classifiers. The classifiers include a Gaussian mixture model neural network, a radial basis function neural network, and a vector quantization classifier. The class designations generated by the classifiers are combined in a weighted voting system, i.e., the mode of the weighted classification decisions is selected as the overall class designation of the target. A confidence metric may be formed from the extent to which the class designations of the several classifiers are the same. This system is also designed to handle unknown target types and subsequent re-integration at a later time, effectively, artificially and automatically increasing the training database size.