340 results about "Radial basis function" patented technology

A method of constructing a digital twin physical field of a computer numerical control machine tool with double order reduction is provided. A physical field finite element simulation sample data set in a working state sampling space has an order preliminarily reduced to sparse grid node data via an improved K Nearest Neighbor (KNN) algorithm, so that the number of point sets is kept within the real-time rendering capability range of graphic rendering software. A digital twin physical field proxy model is trained using a radial basis function (RBF) to realize reconstruction of the physical field. The proxy model is iteratively optimized using a genetic algorithm to solve the problem of deviation between a proxy physical field model and a real physical model. Finally, the proxy model is deployed to a digital twin system, and the physical field distribution is solved in real time.

The invention belongs to the technical field of robot control, and particularly relates to a mechanical arm RBF network dynamic self-adaptive control method under the constraint of a time-varying mechanism, which comprises the following steps of: constructing a mechanical arm dynamic model, determining a system specified time convergence standard, combining a joint motion reference trajectory of a mechanical arm, defining a trajectory tracking error, and determining a mechanical arm dynamic model based on a dynamic nominal model. Constructing a stable robust control law of the nominal dynamical model under the specified time; and selecting a radial basis function, and designing an RBF network adaptive control law in a specified time to dynamically fit a comprehensive nonlinear disturbance term in the system. The problem that the convergence time of a traditional method is uncontrollable is solved, the RBF neural network is adopted to dynamically approach comprehensive disturbance, the network weight is updated online through the adaptive law of the time-varying gain, the anti-jamming capability is remarkably improved, a model driving method and a data driving method are combined, and the convergence time of the model driving method and the convergence time of the data driving method are greatly improved through a dynamic model decoupling and feedforward compensation strategy. And more accurate and low-delay trajectory tracking control is realized.

The invention relates to a causal effect dynamic estimation method and device and a medium. The method comprises the steps that an intervention perception convolution module is constructed through a longitudinal observation data set, weighting processing is conducted on time-varying covariables and intervention variables, and the intervention variables are embedded to generate multi-dimensional time sequence feature representation. A radial basis function is used for mapping intervention variables to generate high-dimensional feature representation, the high-dimensional feature representation is combined with time sequence features to construct a multi-layer intervention sensing module, and after feature dimension matching is adjusted, time sequence feature representation containing historical features and intervention information is output. And constructing a prediction model on the basis, predicting a result variable and a time-varying covariable of a next time step, minimizing loss by using an SAM optimization algorithm in combination with an observation value, introducing adversarial training to generate a sample, and iteratively optimizing model parameters. And performing anti-fact reasoning by using the model, generating anti-fact trajectories of each time step result variable and time-varying covariable, comparing a plurality of intervention schemes by combining different intervention variable sequences, outputting dynamic causal effect trajectory data, and realizing personalized causal effect estimation.

The invention discloses a marine water environment abnormal state secondary and derivation probability modeling and estimating method, which belongs to the field of state modeling estimation, and comprises the following steps: acquiring real-time data flow of marine environment parameters, performing segmentation processing by adopting a sliding window mechanism, and reducing data dimension by utilizing principal component analysis. Then, constructing a graph structure model based on a time sequence, and capturing correlation and a space-time dependency relationship among parameters; and performing nonlinear mapping on the graph structure model by adopting a radial basis function core, and capturing complex nonlinear characteristics among the marine environment parameters. And finally, classifying the abnormal states by using a multi-class support vector machine algorithm, and outputting secondary and derivative probability estimation results of the abnormal states in real time. According to the method, abnormal events in the marine environment can be found in time, dynamic modeling support can be provided for marine environment monitoring, and the accuracy and real-time performance of marine environment monitoring are remarkably improved.

The invention discloses a digital twin system architecture of a vertical shaft and a structural performance monitoring method. The method comprises the following steps: constructing a five-dimensional digital twin system framework suitable for a vertical shaft based on a shaft operation mechanism and performance monitoring requirements; establishing a shaft digital twinborn model with dynamic characteristics; a finite element proxy model is constructed through a virtual-real mapping technology in combination with a grid dimensionality reduction finite element analysis method, and rapid generation of the digital twinborn body is realized. According to the system, a three-dimensional operation platform is constructed based on a Unity 3D virtual engine, and efficient mapping and bidirectional interaction between twin and finite element simulation data are realized by adopting a radial basis function (RBF) proxy model. And real-time acquisition and online prediction are carried out on structural performance parameters in the shaft operation process. And dynamically updating the twinborn model according to a prediction result, and constructing a high-precision and light-weight digital twinborn evolution model, thereby realizing real-time observation of the stress change of the shaft and intelligent monitoring of the structural performance. The method can be widely applied to the fields of shaft safety assessment, maintenance decision making, intelligent mine construction and the like.

The invention relates to the technical field of gas steel cylinder pressure control, in particular to a gas steel cylinder multi-stage pressure control method based on a self-adaptive threshold value, which can dynamically correct the influence of ambient temperature on a pressure reference value through a constructed pressure-temperature compensation function, eliminate measurement errors caused by temperature drift, and improve the accuracy of pressure control. A pressure fluctuation entropy value is calculated in real time based on a sliding window algorithm, a self-adaptive threshold value adjustment coefficient alpha is generated in combination with historical working condition database matching, a control threshold value is dynamically adjusted along with gas flow velocity fluctuation and equipment aging degree, and the pressure over-limit risk is reduced; according to the method, fuzzy neural network control is introduced in a critical adjustment stage through a multi-stage pressure adjustment strategy, an improved radial basis function dynamic updating mechanism can adapt to a pressure sudden change mode online, the control response speed is increased, and the steady-state error is controlled within + / -1.5%.

The invention provides a digital twinning application-oriented electrical equipment electromagnetic heat flow coupling rapid calculation method, and belongs to the technical field of electrical digital data processing.The method comprises the steps that firstly, a three-dimensional model of electrical equipment is acquired and preprocessed, and a full-order electromagnetic heat flow coupling calculation model is established and verified through a temperature rise test; generating an experimental point matrix by using a Latin hypercube sampling method, and constructing a current temperature power density relational data set; performing regional division on the power density field by applying a K-means clustering algorithm, and constructing an electromagnetic response surface model through a radial basis function; establishing a heat flow field order reduction model based on an intrinsic orthogonal decomposition technology, and extracting a dominant mode primary function; bidirectional coupling of an electromagnetic field and a heat flow field reduced-order model is achieved, an improved Lagrange multiplier method and a fixed point iteration method are adopted for processing the nonlinear coupling problem, finally, a software development kit supporting an open platform communication unified architecture protocol is packaged, and the electromagnetic heat flow coupling rapid calculation capacity needed by digital twinning application is achieved.

The invention discloses an ML-based rear subframe structure lightweight and modal optimization target design method, which comprises the following steps: (1) through three-dimensional modeling, statics analysis and modal analysis, constructing a mathematical model corresponding to the weight of a rear subframe and first-order inherent frequency simulation; (2) generating a population based on a Maximin criterion and a Latin hypercube, and establishing a radial basis function machine learning model; (3) generating candidate offspring individual vectors by adopting a Pbest-driven DPM evolutionary strategy based on an Eplison function; (4) constructing a minimum and maximum Pareto front lifting function to screen real offspring individual vectors; and (5) performing simulation evaluation on a real offspring individual vector, adaptively switching the reference vector type based on a reverse generation distance updating condition, returning to the step (3) until an optimization target meets a design requirement, and outputting an optimal optimization design parameter value. According to the method, the evolution direction is adaptively adjusted according to the population simulation result, and the optimization design effect on the two targets of lightweight and modal optimization is good.

The invention relates to the technical field of intelligent power grids, in particular to a grid-connected control method for an improved RBF (Radial Basis Function) network construction type converter with active support capability. The method comprises the following steps: firstly, taking a group of initial values in a VSG system virtual inertia and equivalent damping coefficient parameter value range; determining an initial angular frequency according to the initial value and a swing equation; a VSG secondary control system is improved, an improved phase self-tracking pre-synchronization method without a phase-locked loop is added, a voltage deviation signal is responded, a frequency phase is compensated, and the rotational inertia and the damping coefficient of the system are adjusted in real time to respond to the change of the system state. According to the neural network, the virtual inertia, the damping coefficient and the angular velocity compensation amount are adaptively adjusted, and whether parameters accord with criteria is compared, so that the input parameters are corrected, the influence of disturbance on the system frequency and the output active power is reduced, the dynamic response process of the system is improved, and the stability of the system is improved. And system output power distribution errors and overshoot caused by a rotor motion equation are reduced.

The invention discloses a micro reactor transient multi-physical field rapid prediction method based on a reduced-order model, and the method comprises the steps: taking a reactor core parameter change and a time change in a transient process as all discrete parameter points in a parameter space, and building a response matrix of the reactor core power, the reactor core reactivity, the reactor core temperature and the matrix expansion rate, which serve as target information; reducing the order of the response matrix into a low-dimensional matrix by utilizing intrinsic orthogonal decomposition (POD); in a new parameter point input in real time in an online stage, a radial basis function is used to establish a relationship between the parameter point and a response vector, and rapid prediction is performed through a low-dimensional matrix, so that a result with relatively high calculation precision is obtained at low calculation cost. According to the method, transient multi-physics field coupling simulation is carried out on the reactor starting process of the micro reactor based on an intrinsic orthogonal decomposition radial basis function (POD-RBF) method, so that the calculation efficiency is remarkably improved, and meanwhile, relatively high prediction precision is ensured. A traditional high-fidelity simulation method usually faces high calculation cost when multi-physics coupling calculation is carried out, and the calculation amount is remarkably reduced on the premise that the precision is guaranteed.

The invention belongs to the technical field of structure optimization, and particularly discloses a geometric nonlinearity-considered parameterized level set porous structure topological optimization method, which comprises the following steps of: constructing a level set function to implicitly describe a structure boundary, and performing spline interpolation by adopting a tightly-supported radial basis function to obtain a parameterized level set function; establishing an equilibrium equation of geometric nonlinear topological optimization, and solving structural response under the condition of large deformation through geometric nonlinear finite element analysis; approximating and simplifying local volume constraint through a local constraint domain and a p norm function; establishing a topological optimization model based on geometric nonlinear porous filling rigidity maximization; performing sensitivity analysis through an adjoint method, and calculating a partial derivative of an objective function of the topological optimization model to an expansion coefficient so as to determine an optimization direction of each finite element in geometric nonlinear porous filling stiffness maximization; and carrying out iterative optimization to obtain an optimized topological structure. According to the method and the device, porous filling topological optimization under geometric nonlinear conditions can be realized.

The invention discloses a heat effect and stripe noise synchronous progressive correction method based on an RBF curved surface. The method comprises the following steps: acquiring a degraded image; performing gray processing on the degraded image to obtain a gray degraded image; performing guided filtering processing on the gray scale degraded image to obtain a filtered thermal radiation effect estimation image; constructing an RBF kernel matrix according to the thermal radiation effect estimation image and the RBF kernel function, and solving a weight coefficient in combination with a pixel gray vector of the thermal radiation effect estimation image; multiplying the solved weight coefficient by the RBF kernel matrix to generate an RBF thermal radiation effect curved surface; estimating stripe noise through a stripe operator based on the degraded image and the RBF thermal radiation effect curved surface; according to the RBF thermal radiation effect curved surface and the stripe noise, a potential clear image is restored through a synchronous progressive correction optimization algorithm. According to the invention, the thermal radiation effect and possibly accompanied stripe noise of the image can be simply and efficiently removed.

The invention belongs to the technical field of environmental science, and provides an ozone forecasting method based on multi-dimensional meteorological factors and variables, which comprises the following steps: S1, collecting and sorting the multi-dimensional meteorological factors, and calculating change variables of each element; s2, taking all processed multi-dimensional meteorological factors as forecast factors, and carrying out standardization processing; s3, screening all processed forecasting factors by adopting a stepwise regression method to obtain an optimal forecasting factor combination; s4, performing model training on historical data by adopting a multi-layer perceptron machine learning method according to the screened forecast factors; s5, checking and evaluating the trained perceptron learning model, and comparing and evaluating the trained perceptron learning model with a linear regression model and a radial basis function model; s6, predicting the ozone pollution process in different time periods and different weather backgrounds; according to the invention, the accuracy and timeliness of ozone forecasting can be obviously improved, and more reliable data support is provided for weather and environment management departments.

The invention belongs to the technical field of multi-body dynamics analysis, and discloses a wind driven generator transmission chain rigid-flexible coupling multi-body dynamics analysis method based on dynamic mode decomposition, and the method comprises the steps: firstly, enabling multi-degree-of-freedom time series data to be non-linearly embedded into a high-dimensional feature space through an encoder neural network; extracting a dominant mode by utilizing intrinsic orthogonal decomposition (POD), and constructing a low-dimensional feature space; parameterized dynamic mode decomposition and radial basis function regression are adopted, a mapping relation between system parameters and Koopman operators is established, and accurate prediction of dynamic characteristics under variable working conditions is achieved; and finally, reconstructing a physical response through a decoder, and optimizing model parameters in combination with an error driving mechanism. The problems that a traditional method is low in calculation efficiency, poor in nonlinear adaptability and difficult in multi-parameter coupling prediction are effectively solved, the efficiency and precision of transmission chain dynamic analysis are remarkably improved, and reliable technical support is provided for state monitoring and service life prediction of the wind turbine generator.

The invention discloses a dual-band InSar and GNSS fused high-precision three-dimensional deformation adaptive monitoring method, and the method comprises the following steps: constructing a dual-band observation equation, and decomposing the dual-band observation equation to obtain a dual-band InSAR resolving residual error; calculating the comprehensive weight of each GNSS observation point through an entropy weight method, selecting a plurality of GNSS observation points with high comprehensive weights as an optimal GNSS reference point combination, and converting the three-dimensional deformation observed by the optimal GNSS reference points into an LOS direction; expanding a two-dimensional radial basis function to a three-dimensional radial basis function, optimizing the number and distribution of the three-dimensional radial basis function according to the residual drop rate in the expansion process, and performing basis function encryption on the key area by combining the LOS direction result of the reference point; an original two-dimensional state equation in a Kalman filtering algorithm is expanded to be three-dimensional, meanwhile, a GNSS three-dimensional observation value serves as a strong constraint condition of the Kalman filtering algorithm, and a final three-dimensional deformation rate field is output through iteration and 3D-Va analysis.

Examples described herein generally relate to alerting metric baseline behavior change. The examples include performing at least one of a radial basis function (RBF) kernel procedure and an autoencoding procedure for a time-series data; determining whether one or more change points occur in a seasonal pattern of the time-series data based on at least one of the RBF kernel procedure and the autoencoding procedure; and transmitting, to a user, an alert indicating the one or more change points based on a determination that the one or more change points occur in the seasonal pattern of the time-series data.

The invention discloses a Raman spectrum fluorescence baseline correction method and device, and the method comprises the steps: collecting a time domain signal of a to-be-detected sample, and obtaining an IRF function of a to-be-detected sample collection system; pre-processing the time domain signal, and carrying out deconvolution on the pre-processed time domain signal and an IRF function to obtain a deconvolution result; fitting the second half data of the deconvolution result by using a support vector regression model to obtain a fitted curve; wherein a radial basis function is adopted as a kernel function, and hyper-parameters of the support vector regression model are optimized through a grid search and cross validation method; performing difference operation on the deconvolution result and the fitting curve to obtain a Raman attenuation curve; and windowing the Raman attenuation curve and averaging to obtain a Raman spectrum. According to the method, a fluorescence attenuation model and parameters thereof do not need to be preset, the IRF deconvolution result is processed and the time domain baseline is predicted by utilizing the characteristics of the time domain signal data and the support vector regression model, the signal-to-noise ratio of the extracted Raman signal can be greatly improved, a good effect is achieved, and the method is suitable for practical application.

The invention discloses a grain condition data prediction method and device, and relates to the technical field of grain, and the method comprises the steps: carrying out the data cleaning processing of original grain condition data, so as to generate a grain condition data optimal attribute set; training the grain condition data optimal attribute set through a radial basis function (RBF) neural network to generate a grain condition data prediction model; and outputting predicted grain condition data within a specified time step length through the grain condition prediction optimal attribute set and the grain condition data prediction model, and performing early warning according to a comparison result of the predicted grain condition data and a preset safe grain storage critical value. According to the invention, the future development or change trend of the grain condition is predicted through the multi-type grain condition data, so that early warning is carried out on the possible dangerous grain condition to ensure the grain storage safety.

The invention discloses a multi-disaster-type disaster internet-of-things time sequence adaptive anomaly detection method and system, and relates to the field of internet of things, and the method comprises the steps: S1, constructing an anomaly detection model; s2, acquiring a training data set; s3, training an anomaly detection model; s4, acquiring to-be-detected data; s5, analyzing the reconstruction structure of the to-be-detected data; s6, analyzing an abnormal score; the emergency disaster early warning system comprises an acquisition unit, a storage unit, a calculation unit and an early warning unit. A multi-scale time convolutional network and a self-adaptive spectrum feature module are fused, the characteristics of time sequence data in a time domain and a frequency domain are deeply mined, a gating memory mechanism is introduced, normal time-frequency features in the data can be accurately captured and enhanced, and the recognition capability is improved; by adding the radial basis function layer, the detection capability of the model on tiny anomalies is remarkably improved, so that the model can detect tiny abnormal changes more accurately.

The invention discloses a river model flow velocity intelligent measurement method and device, and belongs to the technical field of river model test measurement, and the method specifically comprises the steps: obtaining a model flow field image sequence, and carrying out the preprocessing; automatically identifying and marking tracer particles by using an image identification algorithm; calculating the instantaneous speed of the tracer particle according to the displacement information of the tracer particle in the continuous time period in combination with an image acquisition frame rate and a model scale; reconstructing a three-dimensional flow velocity field by using a radial basis function; according to the method, non-contact and high-precision measurement of the flow field of the river model is achieved, errors and interference possibly caused by a traditional physical contact measurement mode are avoided, and the automation degree and efficiency of measurement are improved; according to the method, the instantaneous speed of the tracer particles can be accurately calculated by utilizing the displacement information and the image acquisition frame rate of the tracer particles in combination with a river model scale, and a three-dimensional flow velocity field is reconstructed through spatial interpolation and a radial basis function, so that the accuracy and the efficiency of a river model test are improved.

The invention relates to the technical field of ship energy consumption prediction, and discloses a ship energy consumption interval prediction method and system based on a Gaussian quantile regression model.The method comprises the steps that firstly, a ship navigation historical data set is preprocessed, a model input feature set is screened, a Gaussian process quantile regression model with a radial basis function as a kernel is constructed, and hyper-parameters are optimized; and after the prediction performance of the subset evaluation point is verified through the model, an upper quantile prediction model and a lower quantile prediction model are respectively established according to a target confidence level, and finally a prediction interval is synchronously output and an evaluation report is generated. According to the method, through combination of Gaussian process processing nonlinear relation and quantile regression estimation condition distribution, high-precision point prediction is provided, meanwhile, prediction uncertainty can be quantized, an energy consumption prediction interval corresponding to a target confidence level is output, and more comprehensive and reliable information support is provided for ship energy efficiency management and operation decision making.

The invention discloses a PMSM (permanent magnet synchronous motor) AC servo system speed control method based on improved particle swarm optimization optimization RBF (radial basis function) fuzzy neural network PID control, the system is composed of a speed outer ring and a current inner ring, and the current ring adopts a PI regulator. A speed loop is designed to be an RBF fuzzy neural network PID speed controller, an RBF fuzzy neural network is optimized by improving a particle swarm optimization algorithm, and optimal parameters kp, ki and kd suitable for the PID controller are output. Simulation analysis and experiment results show that compared with a common PID control strategy, a BP algorithm optimization fuzzy neural network PID control strategy and a particle swarm algorithm optimization RBF fuzzy neural network PID control strategy, the particle swarm algorithm optimization RBF fuzzy neural network PID control strategy based on the improved particle swarm algorithm has optimal control performance; the method has the advantages of being high in dynamic response speed, good in control stability, resistant to load disturbance and high in robustness, and the excellent speed control effect of the PMSM alternating current servo system can be achieved.

The invention provides a bearing small sample data expansion method and system based on a variational auto-encoder, and belongs to the field of deep learning and data enhancement. The problems that a traditional generation model has limitation in bearing small sample data, feature fuzziness and distortion are prone to occurring, and the data set quality is poor are solved. According to the method, a deep VAE framework is constructed, and a dimension reduction module, a data expansion module and a dimension raising module are used in a potential space; dimensionality reduction is performed on high-dimensional data by adopting a UMAP algorithm, so that the topological structure of the data is effectively reserved, and the extraction efficiency and quality of data features are improved; a Gaussian mixture model combining regularization and particle swarm optimization optimization is used for fitting distribution of scattered small sample data, new data with fusion features are expanded through sampling, and data diversity is increased; a radial basis function is used for nonlinear data dimension raising, new data can be ensured to be accurately mapped back to a high-dimensional space, meanwhile, the relation between features is reserved, and defect data with fusion features is reconstructed through a decoder.

The invention discloses a mining area roadway stability intelligent classification and support scheme design method, and the classification method comprises the steps: carrying out the denoising through employing a denoising method based on statistical deviation, constructing a weight distribution frame based on a random forest algorithm, carrying out the feature importance evaluation of each feature variable through employing a decision tree integration method, and carrying out the design of a support scheme. Quantifying the influence proportion of each characteristic variable on the stability of the mining roadway, and generating a weight matrix containing the influence proportion of each characteristic; and constructing a mining area roadway stability intelligent classification model based on a support vector machine, adopting a radial basis function as a kernel function to map a feature variable to a high-dimensional space, adjusting a model classification boundary by iteratively optimizing penalty parameters, and training the model by using historical data to obtain an optimized mining area roadway stability intelligent classification model. Accurate evaluation and intelligent classification of the stability of the roadway in the roadway mining area are achieved, the supporting effect and the roadway safety are effectively improved, and technical support is provided for safe and efficient mining of the mine roadway.

The invention relates to the field of dam effect quantity monitoring, in particular to a dam monitoring effect quantity prediction method based on mechanism and data dual drive, which comprises the following steps of: performing noise reduction preprocessing on monitoring data by adopting a wavelet noise reduction method; constructing a monitoring effect quantity long-term prediction model; constructing a short-time proximity precise prediction model; a Newton-Raphson optimization algorithm (NRBO) is used for optimizing network hyper-parameters of a physical constraint radial basis function (PIRBF) to construct an inversion agent model of finite element model parameters, a finite element calculation result is calibrated, and finally a hybrid model is constructed to realize long-term prediction of monitoring effect quantity. A deep learning model is constructed through an aurora optimization algorithm (PLO), a Transform architecture and a gated cycle unit network (GRU) to correct a long-term prediction model error, a deep learning model result is coupled to construct a short-term approaching prediction model, and short-term approaching accurate prediction of the effect quantity is realized.

The invention belongs to the technical field of life state monitoring and maintenance management of a pantograph carbon contact strip, and particularly discloses a pantograph carbon contact strip full-life cycle data management system, which comprises a multi-level gradient feature library, a pseudo edge filtering technology, multi-scale feature extraction and radial basis function classification, full-scale identification of defects such as cracks is realized, and the microcrack detection accuracy is improved; multi-source data collaborative acquisition and three-dimensional coordinate mapping are adopted, and self-adaptive sliding window analysis is combined, so that data integrity and timeliness under different working conditions are ensured; through impact energy parameter integration, pressure fluctuation index calculation and a thermal expansion correction coefficient, a partition life prediction model is established, and the wear prediction error of a key area is reduced; high-risk area automatic marking and maintenance work order generation are realized, the RFID tracing technology is combined, the maintenance efficiency is improved, and the service life is prolonged. According to the method, the defects of a traditional method in the aspects of defect detection, dynamic monitoring and service life prediction are effectively overcome.

The invention discloses a low-coherence interference demodulation method based on modal decomposition and a radial basis function neural network, and the method comprises the steps: carrying out the empirical mode decomposition of a filtered low-coherence interference signal, extracting the effective time-frequency domain features of each IMF and the mathematical statistics time domain features of the low-coherence interference signal, and forming a low-coherence interference signal feature data set; constructing and training a radial basis neural network, establishing a nonlinear model between low-coherence interference signal features and pressure, setting an input layer to correspond to a fusion feature vector, setting a hidden layer to adopt a radial basis function as an activation function, realizing nonlinear mapping by using a Gaussian kernel function, and outputting a layer to correspond to a pressure value; the network is trained through the feature data set, a mean square error is used as a loss function, a gradient descent method is adopted to optimize the weight and threshold of the network, and iterative training is carried out until the error converges; and inputting a low-coherence interference signal acquired by an optical fiber Fabry-Perot pressure demodulation device, and demodulating the signal through the trained radial basis function neural network model to obtain a corresponding pressure value.

The invention discloses a J-A model parameter identification method, system, equipment and medium based on RBF and an improved brownish bear algorithm, and belongs to the technical field of power system optimization, and the method comprises the steps: building a Jiles-Atherton hysteresis reverse model of a current transformer, determining a to-be-identified parameter vector, and building a model with a root-mean-square error between actually measured magnetic field intensity and simulated magnetic field intensity as a target function, training a radial basis function neural network model, expanding data through linear interpolation processing, obtaining a predicted magnetic induction intensity value, inputting an objective function and radial basis function prediction data into an improved brownish bear optimization algorithm, and iteratively optimizing model parameters through hierarchical population position updating and fitness evaluation until convergence conditions are met. And outputting an optimal parameter identification result. According to the method, high-precision and high-efficiency identification of hysteresis model parameters is realized, the generalization capability and robustness of the system are improved, and reliable technical support is provided for hysteresis characteristic analysis of a complex physical system.

The invention relates to a method and device for predicting online open course learner satisfaction and electronic equipment, and the method comprises the steps: predicting the online open course satisfaction of students through an MLP and RBF neural network model by using a virtual learning environment of a large-scale online teaching and learning platform and combining learning behavior data in a learning management system (LMS); the model comprises a data acquisition and processing module, a multilayer perceptron (MLP) module, a radial basis function (RBF) neural network module, a classification tree module and a control block, the data acquisition and processing module is used for generating a training and testing data set, and the MLP and RBF neural network model predicts the satisfaction degree of a learner. The MLP model carries out feature extraction through a multi-layer perceptron structure and different activation functions, the RBF model measures the distance between input data and a center by using a radial basis function to realize feature extraction, the classification tree is used for judging a prediction model to which a data point belongs, the control block integrates features from the MLP and RBF neural network models, and the RBF model is used for determining a prediction model to which the data point belongs. Experimental results show that the prediction accuracy of low-satisfaction-degree learners and high-satisfaction-degree learners can be improved at the same time through the combination scheme of the MLP and the RBF, the method can be applied to learner satisfaction degree prediction of various online open courses, an educational institution is helped to know the satisfaction degree condition of students in time, course design and teaching strategies are optimized, and the teaching efficiency is improved. And important support is provided for teaching reform and optimization in the field of online education.

The invention discloses a machine learning driven vehicle frame lightweight design method, which comprises the following steps: (1) performing vehicle frame parametric modeling in CATIA, constructing a vehicle frame modal analysis model and a stiffness analysis model in ABAQUS, and deducing a mathematical model of vehicle frame lightweight design; (2) performing Latin hypercube sampling and discrete Gaussian sampling on continuous and discrete parameters to generate a frame population, and establishing a database; (3) designing a variable type driven hybrid variation mechanism to obtain a candidate frame population; (4) constructing a radial basis function machine learning model, and deducing a comprehensive minimum statistical lower limit function to screen an optimal candidate frame; and (5) performing parametric modeling and simulation analysis on the optimal candidate frame, updating the frame population and the database, returning to the step (3) until the optimal frame meets the design requirement, and outputting the optimal frame. According to the method, adaptive variation strategies and screening functions are designed according to the vehicle frame parameter characteristics, and the vehicle frame lightweight design effect is good.