19 results about "Criterion function" patented technology

The invention discloses a power prediction method for a wind power generation system based on a stacked sparse auto-encoder network Hammerstein model, and aims to solve the problems that only nonlinear mapping is modeled and dynamic characteristics of the system are neglected and parameter coupling of the Hammerstein model leads to complex identification in an existing method, the Hammerstein model is constructed, an ARMAX model is utilized to describe a dynamic linear module, and the dynamic linear module is used to predict the power of the wind power generation system based on the stacked sparse auto-encoder network Hammerstein model. A static nonlinear module is described by stacking the sparse auto-encoder network; designing a zero-mean Gaussian signal input proxy model, realizing series module decoupling based on covariance function characteristics, and eliminating parameter coupling; a self-adaptive multi-strategy grey wolf optimization algorithm is adopted to determine the number of neurons in a network hidden layer, training is performed in combination with a sparse criterion function, and the feature extraction capability is improved. According to the method, synchronous capture of static nonlinear and dynamic linear characteristics is realized, the calculation complexity is reduced, the model identification precision, prediction precision and robustness are improved, and the method is suitable for accurate prediction of the power of a wind power system.

The invention discloses an elastic prediction control method for a converter, and the method comprises the steps: constructing an output current increment prediction model which comprises an inherent dynamic item reflecting the mapping relation between the historical data of a converter system and the output current increment, and an attack item reflecting external abnormality; constructing a criterion function, calculating the gradient of the criterion function about the coefficient matrix, setting the gradient to be zero, and obtaining the estimation of the coefficient matrix at the current moment; taking the error between the reference current of the next period and the actual output current of the current period as the target output of an output current increment prediction model, rewriting the output current increment prediction model, and obtaining the control law of the voltage increment; and based on the control law of the voltage increment, substituting the coefficient matrix estimation at the current moment to obtain a voltage control increment, and selecting the switching state of the converter based on the voltage control increment. According to the method, converter prediction control without parameter dependence can be realized, false data attacks are resisted, the switching frequency is reduced, and the system robustness is improved.

The invention discloses a four-rotor aircraft data driving control method breaking through bandwidth constraint under hostile attack. The method specifically comprises the following steps: establishing a kinetic model of a four-rotor aircraft; converting the obtained kinetic model into an equivalent dynamic linearization equation by using a dynamic linearization method; designing a criterion function, and designing a data driving control method of the four-rotor aircraft; an event triggering mechanism is introduced, denial of service attack is considered, and then the final four-rotor aircraft safety event triggering data driving control method is obtained through arrangement of the obtained control method. According to the method, model-free adaptive control is applied to attitude control of the four-rotor aircraft, the advantages of PID are combined, malicious denial of service attacks are considered, an event triggering mechanism is introduced, the good flight quality of the aircraft is guaranteed, system bandwidth resources can be saved, and the working time of the aircraft is prolonged.

The application discloses a kind of aircraft global time-varying aerodynamic parameter identification method, comprising: S1. establishing aircraft rigid body dynamics model, and obtaining time-varying parameter to be identified;S2. the time-varying parameter to be identified is written as polynomial form about time;S3. state sensitivity, covariance sensitivity, gain sensitivity, filter state sensitivity and covariance sensitivity are estimated;S4. according to aerodynamic parameter characteristics or time period, carry out local subarea;S5. in current interval, obtain state estimated value, estimated covariance matrix, Kalman gain, state filter value, covariance matrix by parameter value in combination with Kalman filter;S6. according to the above obtained criterion function, when criterion function is not minimum value, parameter is updated using Newton-Raphson algorithm;S7. using moving average filter to smooth all parameters, obtain a smooth global aerodynamic data curve.The application avoids the problem that fitting is not accurate when parameter variation amplitude is too large.

The application discloses a kind of based on model-free adaptive multi-farm machine formation path navigation-tracking control system and control method, belong to agricultural machinery navigation technical field.Main steps are:1, using sensor, real-time acquisition agricultural machinery position information, pre-look lateral deviation and area deviation.2, based on deviation information and control input constructs dynamic linear equation, constructs criterion function, minimizes tracking error in control increment, deduces control law, combines pseudo partial derivative online estimation algorithm, realizes model-free adaptive trajectory tracking.3, based on the position information of leader agricultural machinery of design, real-time control follower motion control operation, realizes agricultural machinery vehicle path tracking precision.4, based on the model-free adaptive control scheme of design pre-look deviation.The application can adapt to complex farmland environment, not dependent on accurate model and have strong adaptive ability, realizes high-precision, strong robustness collaborative operation, provides technical support for modern agricultural intelligent development.

The invention provides a method, a device and equipment for predicting the compressive strength of medium and high strength concrete based on a GA-BP neural network model, and a storage medium, and relates to the technical field of concrete strength prediction. The method comprises the following steps: acquiring a plurality of groups of concrete test samples containing cement, slag, fly ash, water, a water reducing agent, stone and sand and corresponding compressive strength measured values; a GA-BP neural network model is constructed, the node number M of an input layer of the GA-BP neural network model is consistent with the concrete component parameter type, a quadratic form error criterion function is used as a target function, a weight and threshold optimal solution is obtained through genetic algorithm optimization, and model construction is completed; performing normalization processing on the test sample, and inputting the test sample into the model for training; and normalizing to-be-predicted concrete component parameters, and inputting the normalized to-be-predicted concrete component parameters into the trained model to output a compressive strength predicted value. According to the method, accurate and stable prediction of the strength of the concrete with the complex mix proportion is achieved, and the problem that a traditional grey water ratio empirical formula is large in error is solved.

The invention discloses a data-driven prediction multi-mobile robot inclusion control method and system. The method comprises the following steps: acquiring position information of mobile robots; constructing a dynamic linearization data model, designing a multi-step prediction equation to estimate a future trajectory, minimizing a tracking error and a control increment by using a criterion function, deriving a control law, and combining a pseudo partial derivative matrix online estimation and parameter prediction algorithm to realize model-free adaptive prediction control; constructing a dynamic switching communication network based on the directed topological graph; based on a designed model-free adaptive predictive control model, an inclusion control technology is introduced, so that all followers finally enter and keep moving in a convex hull formed by a leader. The multi-robot system gets rid of dependence on a mathematical model, the controller is designed and analyzed only by using input / output data, all robots can finally enter and keep moving in a convex hull formed by a leader, the cost is effectively reduced, and the applicability of the system is improved.

A variable buffer status report configuration is transmitted from a wireless communication network node to a user equipment. The configuration may comprise one or more functions to calculate a buffer status report indication that indicates, or to calculate a table that is used to indicate, a metric related to a buffer, or related to uplink traffic stored in a buffer, of the user equipment. The configuration may comprise a function to determine a precision variable that corresponds to a step size between different criteria, or criteria functions, that are used to determine a buffer status report indication. Buffer status report indications may vary in size based on a value of the indication. A user equipment may apply different received configurations, or functions thereof, to determine buffer status report indications based on different parameters, such as traffic type, traffic Quality of Service, buffer size, or amount of buffered uplink traffic.

This application discloses a flexible predictive control method for a converter, comprising: constructing an output current increment prediction model, which includes an inherent dynamic term reflecting the mapping relationship between historical data of the converter system and the output current increment, and an attack term reflecting external anomalies; constructing a criterion function, calculating the gradient of the criterion function with respect to the coefficient matrix, and setting the gradient to zero to obtain an estimate of the coefficient matrix at the current time; using the error between the reference current of the next cycle and the actual output current of the current cycle as the target output of the output current increment prediction model, rewriting the output current increment prediction model, and obtaining a control law for the voltage increment; based on the control law for the voltage increment, substituting the coefficient matrix estimate at the current time to obtain the voltage control increment, and selecting the converter switching state based on the voltage control increment. This method can achieve parameter-independent predictive control of the converter, resist spurious data attacks, reduce switching frequency, and improve system robustness.

The invention provides a machine tool control system and method and a storage medium, and belongs to the field of machine tool control, the machine tool control system comprises an input interface control module and an output interface control module, the input interface control module is used for constructing a standard function, and the standard function obtains multiple pieces of precondition information of machine tool operation through an input interface. According to the method, a complex fool-proof mechanism and potential collision logic of underlying hardware do not need to be concerned, the technical threshold is remarkably reduced, the working efficiency is improved, the time cost and the learning cost required by handover are greatly reduced, meanwhile, the problem of system stability caused by disordered program styles and unclear logic is effectively avoided, and the system reliability is improved. And safety risks such as equipment collision or operation faults caused by misreading of a program structure or mismodification of key control logic by maintenance personnel are effectively prevented, and the method has remarkable engineering application value and popularization prospect.

The invention discloses a unit type glass curtain wall connecting component performance evaluation system based on data analysis, and relates to the technical field of structural component testing, and the system comprises a response field generation module which is used for receiving a virtual node model, and applying a predefined load spectrum sequence to the virtual node model for numerical simulation, generating and outputting a performance response field describing continuous performance evolution; and the health degree sequence calculation module is used for receiving the performance response field, extracting features from the performance response field according to a pre-constructed degradation criterion function, and calculating and outputting a health degree scalar sequence reflecting performance evolution. According to the method, parameterized scanning and numerical simulation are carried out on the virtual node model through the response field generation module, a continuous performance response field with load amplitude and duration as independent variables and key part stress response as a dependent variable is constructed, continuous mapping of performance evolution of a component under different load working conditions is achieved, and the reliability of the component is improved. And a high-fidelity and inquirable mechanical response reference is provided for fatigue damage analysis.

Unlike conventional or otherwise known decomposition methods like standard functional decomposition, time-affecting linear pathway (TALP) decomposition, or output-affecting linear pathways (OALPs) from the decomposition of TALPs, advanced output-affecting linear pathway (A-OALP) decomposition from algorithms separate the output variables of each execution pathway such that there is only one output variable per A-OALP, converting an algorithm into a set of process groups. A-OALPs extend parallelization by combining task-like parallelism with dynamic loop parallelism. The lightweight nature of A-OALPs allows for persistent thread and code management.

The invention discloses a super-redundant series-parallel mechanical arm obstacle avoidance and trajectory planning method based on null space, and belongs to the technical field of robot motion planning. The invention aims to solve the problem that the super-redundant series-parallel mechanical arm can effectively avoid obstacles in the operation process in a complex environment. The method comprises the following steps: setting various parameters of a six-degree-of-freedom parallel mechanism module; representing the distance from a certain point to an obstacle in the working environment by adopting a pseudo distance; updating a corresponding Jacobian matrix based on the current actual mechanical arm configuration; constructing a total series Jacobian matrix of the whole mechanism through speed recursion and a vector product method; constructing a criterion function for evaluating the approaching degree of an obstacle and the mechanical arm, and constructing a criterion function for evaluating the approaching stroke limit of a joint; carrying out numerical solution and discretization integration of speed-level inverse kinematics of the whole mechanism so as to update joint variables; and solving and updating a homogeneous transformation matrix and a tail end pose of an upper hinge point coordinate system and a lower hinge point coordinate system of each module in a base coordinate system by using overall mechanism forward kinematics, and carrying out iterative calculation.

A variable buffer status report configuration is transmitted from a wireless communication network node to a user equipment. The configuration may comprise one or more functions to calculate a buffer status report indication that indicates, or to calculate a table that is used to indicate, a metric related to a buffer, or related to uplink traffic stored in a buffer, of the user equipment. The configuration may comprise a function to determine a precision variable that corresponds to a step size between different criteria, or criteria functions, that are used to determine a buffer status report indication. Buffer status report indications may vary in size based on a value of the indication. A user equipment may apply different received configurations, or functions thereof, to determine buffer status report indications based on different parameters, such as traffic type, traffic Quality of Service, buffer size, or amount of buffered uplink traffic.

This invention discloses a distributed data-driven control method for high-speed train groups under fault saturation. Specifically, it involves: establishing a dynamic model of the high-speed train group using Newton's laws, followed by discretization and normalization; using pseudo-partial derivatives and the mean value theorem to linearize the nonlinear model; establishing criterion functions for the system data model parameters and control signals, and preliminarily obtaining a distributed data-driven control scheme for the train group based on optimization conditions; establishing a model for intermittent actuator faults and nonlinear input saturation during high-speed train operation, introducing multi-agent theory and parameter reset algorithms to obtain a data-driven distributed anti-saturation robust control method for high-speed train groups; testing and verification on a numerical simulation platform, and then porting it to a high-speed train automatic operation system. This invention eliminates the dependence on train models, has a simple structure, is easy to implement, and can improve the utilization rate of inter-station lines and the transportation efficiency of high-speed trains.

A kind of finger vein and finger knuckle print dual-mode identification method based on canonical correlation analysis, comprising: Daubechies wavelet pre-processing is carried out to the finger vein image and finger knuckle print image for training, to obtain the low-frequency image of finger vein image and finger knuckle print image respectively, K-L transform is used to extract features from two groups of low-frequency images respectively, then correlation criterion function between two groups of feature matrices is established, two sets of canonical projection vectors are obtained according to criterion function, finally the canonical correlation characteristics are fused by given feature fusion strategy and applied in classification identification.The beneficial effects of the present application are: the present application obtains the feature information of two modes by dimension reduction, reduces the recognition calculation amount, improves the recognition accuracy, introduces more class information into the criterion function more fully, not only reaches the purpose of information fusion, but also effectively eliminates the redundant information between features, and makes the classification performance greatly improved.

An analyzing method includes preparing measured position information that is position information of a plurality of measured-parts formed on a substrate, and fitting a reference function, which is a sum of at least one function obtained by multiplying a criterion function expressed using a first type Bessel function by a proportional coefficient, to the measured position information and calculating an optimum value of at least one of the proportional coefficient.

This invention belongs to the field of low-frequency transformer magnetic field optimization technology, and discloses a method, system, device, and medium for constructing a low-frequency transformer surrogate model based on physical feature guidance and Bayesian active learning to solve the problem of prediction distortion in key performance areas. The method includes: constructing a global parameter space; establishing a multi-physics finite element model; defining high-risk performance areas based on low-frequency physical laws; constructing an initial Kriging surrogate model using Latin hypercube sampling; setting penalty weights based on whether unresolved sample points are located in high-risk areas and introducing a point-addition criterion function to solve for the optimal sampling points; calling the finite element model to calculate the true response value and updating the surrogate model; determining whether the prediction accuracy of high-risk areas meets the convergence condition; if it does, outputting the current surrogate model; otherwise, continuing the iteration.

The application discloses a method for identifying aerodynamic parameters of a UAV based on improved maximum likelihood estimation, and is implemented as follows: an initial aerodynamic coefficient table is generated by using DATCOM, a mathematical expression of the aerodynamic parameters is obtained by using a nonlinear least square polynomial fitting method, and a modeling difficulty of measured data is solved; a modeling process is simplified by combining a confidence interval and aerodynamic physical constraints, and complexity and interpretability of the model are balanced; a high-order coupling term of a polynomial is used to represent system uncertainty, iterative calculation is simplified, a gradient and a Hessian matrix are solved, an LM algorithm is introduced, and problems of covariance singularity, low efficiency and unstable convergence of traditional MLE in processing high-dimensional aerodynamic parameters are solved. The method is improved from three dimensions of aerodynamic model construction, optimization criterion function reconstruction and iterative algorithm optimization, is suitable for identifying aerodynamic parameters of a UAV under high dynamic maneuvering states, and has a 14 times higher calculation efficiency and a relative error of less than 7% compared with traditional MLE.