95 results about "Nonlinear prediction" patented technology

The invention discloses a method for intelligently regulating and controlling production parameters in a fruit concentrated juice production process, which comprises the following steps of: acquiring multi-dimensional process parameters such as temperature, pressure, flow, concentration, equipment state and the like in real time through a multi-channel sensor network, and forming a standardized data sequence after filtering, normalization and drift correction; extracting stage features by using technologies such as a sliding window and Fourier transform, and inputting the stage features into the lightweight classification model to realize production stage identification; in combination with an identification result, dynamically calling a corresponding multi-target optimization sub-model, and realizing nonlinear prediction and optimal solution selection of process parameter setting by adopting an LSTM and a multi-target genetic algorithm; on the basis of real-time feedback, the performance of the model is automatically evaluated, self-adaptive adjustment and optimization of the optimization algorithm are achieved through reinforcement learning and an incremental updating mechanism, multi-target collaborative optimization, self-adaptive adjustment and model switching in the production process can be achieved, and the consistency of production efficiency and product quality is improved.

The invention discloses a PINN-based magnetic levitation vehicle nonlinear predictive control method and device and a medium, and relates to the field of rail transit, and the predictive control method comprises the following steps: S1, constructing a dynamic model; s2, learning and approaching unknown dynamic and time-varying parameters in the dynamic model by adopting a physical information neural network; s3, designing an optimization cost function meeting system input and output constraints based on the unknown dynamic state of the dynamic model predicted by the physical information neural network; and S4, constructing a step-by-step variable terminal constraint set to process input time lag. In a controller design and theoretical analysis process, a non-linear dynamic form of a system is completely reserved, and a stepping variable terminal constraint set suitable for input time delay is constructed, so that the controller can still maintain stability and dynamic performance under the condition that a system state obviously deviates from a balance point. According to the method, the operation safety and the control precision of the maglev vehicle under complex working conditions such as parameter drift and time lag disturbance are effectively improved.

The invention belongs to the field of automatic control of hydroelectric generating sets, and particularly discloses a primary frequency modulation optimization control method and system based on power opening nonlinear prediction.The method comprises the steps that frequency deviation is converted into primary frequency modulation power variable quantity, the power variable quantity and a basic power set point of a set are added, and a dynamic power target is obtained; integrating the power deviation signal to obtain a power integration opening reference instruction; taking the dynamic power target and the unit water head as input of a feed-forward model, and obtaining a feed-forward dominant opening instruction; the opening degree deviation value is input into a PID controller, and a feedback opening degree correction instruction is generated; and a guide vane opening given value is obtained based on the feed-forward dominant opening instruction and the feedback opening correction instruction and serves as a given signal of a guide vane position control loop. According to the invention, through nonlinear prediction and a unique feedback structure, high self-adaption to the working condition change of the unit is realized, and the rapidity, consistency and robustness of the primary frequency modulation response of the unit are remarkably improved.

The invention relates to the technical field of market trend prediction, and discloses a market trend prediction system driven by macroeconomic indicators. An index acquisition module of the system dynamically acquires core economic indexes such as GDP growth rate, CPI, PMI and currency supply; the data preprocessing module is used for carrying out layered noise reduction processing on the multi-source heterogeneous data; the feature engineering module constructs a market sensitive feature set through spatio-temporal feature fusion; the prediction model building module is used for building a multi-layer nonlinear prediction model based on a deep belief network; the dynamic adjustment module adopts reinforcement learning to optimize a decision threshold value and combines a Markov chain to carry out state transition planning; and the feedback iteration module analyzes and predicts deviation through Bayesian filtering and realizes strategy updating. According to the method, deep learning and reinforcement learning technologies are creatively fused, the prediction precision is remarkably improved through a dynamic calibration mechanism, and the method can be widely applied to the macroeconomic analysis fields of financial investment, industrial planning and the like.

The invention relates to the technical field of data analysis, in particular to a newborn health data analysis system which comprises a physical sign data construction module, a trend recognition module, a weight distribution module, a nonlinear modeling module and a prediction curve output module. According to the method, the growth cycle of the newborn is subdivided into continuous stages with different physiological meanings, the change rates of the sign data between the adjacent stages are deeply calculated and compared, the dynamic trends such as acceleration, stability or slowing down of body weight and height changes can be accurately recognized, and then quantitative weights are given to the different growth trends; according to the method, the positive growth situation is more evaluated in subsequent analysis, the growth and slowdown situation is correspondingly adjusted, a nonlinear prediction model is constructed on the basis, the non-uniform-speed natural law of growth and development of the newborn can be fit, the staged trend can be dynamically fused into long-term change track prediction, and the prediction accuracy of the growth and development of the newborn is improved. And the health conditions of the newborn in different developmental window periods are disclosed.

The invention relates to the technical field of automatic control, and discloses a suction force self-adaptive adjusting method based on a suction cup base, comprising the following steps: collecting current attitude disturbance information of to-be-adsorbed objects including a lamp, glass, a steel plate, a plastic box body and a wood material plate, the attitude disturbance information comprises a pitch angle, a roll angle, an angular velocity and a vertical acceleration; estimating the offset of the gravity center of the to-be-adsorbed object relative to the center of the sucker array based on the attitude disturbance information; according to the offset, target adsorption force of the object to be adsorbed is determined, and distribution is carried out according to a set load distribution weight; the invention further discloses a suction force self-adaptive adjusting system based on the suction cup base. The system comprises a posture sensing module; an offset calculation module; an adsorption force distribution module; and an adsorption control module. According to the invention, dynamic coordination and accurate tracking control of multi-sucker adsorption force are realized by fusing attitude sensing, adsorption modeling and nonlinear predictive control.

The application relates to the technical field of intelligent control of refrigeration equipment, and discloses an intelligent energy-saving control method and system for a refrigeration display cabinet. The method comprises the following steps: collecting temperature distribution and passenger flow data in the refrigeration display cabinet through a multi-parameter sensor network, inputting the data into an ARIMA model after sliding average filtering processing, and predicting a refrigeration load fluctuation trend; a dynamic energy efficiency ratio indicator is established based on the ratio of compressor power to the predicted value of the load, and the energy-saving effect is quantified; the compressor frequency and the fan rotating speed are adjusted in combination with a nonlinear prediction control algorithm, and a cooperative control instruction is generated; the influence of the instruction on the system load is analyzed through a refrigerant flow tendency function, the defrosting cycle is optimized synchronously, an energy-saving control strategy is formed, and the strategy is executed. The application improves the predictability and cooperativeness of energy efficiency management of the refrigeration display cabinet.

The invention relates to an integrated state estimation and motion control method for an automatic driving vehicle, and the method comprises the steps: building an implicit mapping function between a vehicle-mounted sensor measurement signal and a longitudinal lateral vehicle speed, determining the input and output of a state estimator based on a long short-term memory network, and constructing a state estimation loss; establishing a nonlinear prediction model for trajectory tracking control, and depicting a trajectory tracking control optimization problem under a rolling time domain framework; the control quantity output by the model prediction controller based on the long-short-term memory network is projected to a constraint space, the control quantity meeting constraints acts on the nonlinear prediction model oriented to trajectory tracking control, a state quantity in a prediction time domain is obtained, and optimization target loss is constructed; and constructing a joint loss function to carry out integrated training, deploying on a real vehicle platform after training is finished, and carrying out state estimation and motion control on the automatic driving vehicle. Compared with the prior art, the method has the advantages that estimation precision and trajectory tracking performance are both considered, and safety and reliability are high.

The invention discloses an MDCK cell low-serum culture medium construction method based on KAN modeling and Bayesian optimization and application thereof.The MDCK cell low-serum culture medium construction method comprises the steps that firstly, key influence factors are screened out from numerous nutrient components through multi-factor experimental design, and then a high-precision nonlinear prediction model between the key factors and cell performance is established through KAN; based on the model, a Bayesian optimization algorithm is adopted for rapid optimization, and the optimal concentration of each component is determined. The cell line culture medium has universality and can be migrated and applied to culture medium development of other cell lines. According to the MDCK cell low-serum culture medium constructed through the method, the adding amount of fetal calf serum (FBS) is only 2%-4% (v / v), the formula is systematically optimized, efficient growth of cells can be directly supported, and pre-domestication is not needed. The culture medium has obvious effects on promoting MDCK cell proliferation, improving virus (such as influenza virus) titer and reducing production cost, and is suitable for large-scale production of vaccines.

This application relates to a real-time power load forecasting method and system based on a hybrid model. The method includes: acquiring current cycle load data and combining it with historical load data to form a load sequence, and acquiring corresponding weather data; performing timestamp alignment, anomaly processing, and normalization on the load sequence and weather data to obtain a standardized input sequence; determining the order parameters of the linear forecasting model and the set of hyperparameters to be optimized, consisting of the network structure and training parameters of the nonlinear forecasting model, and optimizing them through a combined optimization algorithm to update the training configuration of the two models; outputting the first and second forecast sequences for the next cycle in the current cycle, respectively, and using the second forecast sequence as a trend term to compensate the first forecast sequence to obtain a fused forecast sequence; acquiring the fused forecast sequence for the current cycle from the previous cycle, constructing a residual sequence with the current cycle load data and determining the deviation term, calibrating the current cycle fused forecast sequence online, and outputting the calibrated load forecast result.

The invention discloses an S-type pitot tube calibration coefficient prediction method based on CFD, and the method is realized through the following steps: S1, carrying out CFD numerical simulation based on parametric modeling, and obtaining a calibration coefficient set of an S-type pitot tube under different installation angle deviations, flow velocity range conditions and environmental parameters; s2, integrating simulation data, and constructing a feature vector data set of the key influence parameters; s3, dividing the data set into a training set and a test set; s3, based on an RBF algorithm, constructing a high-precision nonlinear prediction model by using the training set; and S4, verifying the performance of the model by using the test set, and judging whether the prediction accuracy meets the expectation or not. A CFD simulation technology and a machine learning algorithm are integrated, the problem that a traditional real flow calibration device is limited in capacity and cannot reproduce on-site complex conditions is solved, and a solution is provided for high-precision prediction and correction of calibration coefficients under on-site complex installation conditions and a non-uniform flow field.

The invention discloses a safe real-time monitoring system and method for lifting and lowering a drilling barrel of a heavy slurry cap in pressure control drilling, and the method comprises the steps: collecting the real-time data of the shaft in a drilling process, and calculating the pressure change trend of the shaft, the density fluctuation range of drilling fluid and the thickness attenuation condition of the heavy slurry cap in a future preset time period through a multivariable coordination nonlinear prediction algorithm; in combination with a calculation result, the drilling fluid density is dynamically adjusted by utilizing a drilling fluid density self-adaptive adjustment algorithm, and the sealing performance, the pressure transmission efficiency and the anti-pollution capacity of the heavy slurry cap are evaluated by virtue of a heavy slurry cap action efficiency evaluation algorithm; and the adjusting parameters and the evaluation result are input into a heavy slurry cap pressure control intelligent analysis engine to calculate pressure control parameters and generate a control instruction, the state of the shaft is monitored in real time according to the control instruction in combination with the safe real-time monitoring parameters of the drilling barrel, and data closed-loop updating is formed. According to the invention, multi-parameter collaborative management and control and precise evaluation of the efficiency of the heavy slurry cap are realized, and the safety monitoring precision of the shaft is improved.

The application discloses a voltage stability margin calculation method considering a control mode of a photovoltaic power station, and adds modeling consideration of a reactive power-voltage control mode of the photovoltaic power station in voltage stability margin calculation. In a continuous power flow calculation process, parameterized power flow equations are obtained by extending node voltage with the fastest voltage drop. Meanwhile, in a prediction link in the continuous power flow calculation process, a hybrid prediction method is adopted. In the case that voltage margin is large, nonlinear prediction is adopted to accelerate the calculation speed. In the case that voltage stability limit is approached, linear prediction is adopted. The voltage stability margin calculation method fully considers the influence of the control mode of the large-scale photovoltaic power station on voltage stability, and improves the calculation efficiency and the calculation precision.

The invention belongs to the technical field of integrated circuits, and particularly relates to a high-precision low-overhead runtime on-chip digital power meter. The power meter comprises a bit-level agent flipping detection module, a lifting binary tree prediction module, a weight score read-write module, a weight score accumulation module and an average power consumption calculation module. By detecting the activity of the proxy net in the deployed target design, the method adopts binarized input characteristics and a lightweight nonlinear prediction model, and can avoid high-precision redundant calculation while keeping high-precision prediction of dynamic power consumption, thereby accelerating the calculation period and reducing the area overhead. The method has the characteristics of high precision and low overhead, and can monitor the on-chip real-time dynamic power consumption by using efficient hardware resources.

The invention discloses a circuit breaker actuation time prediction method and system, a storage medium and electronic equipment. The method comprises the following steps: constructing a multi-parameter nonlinear prediction model of a nonlinear relationship between multiple characteristics of a circuit breaker and actuation time; determining a key feature based on a rate of change of each of the plurality of features of the circuit breaker; constructing a grid on a plane based on the key features, and performing prediction by using a multi-parameter nonlinear prediction model based on feature data corresponding to each point on the grid so as to determine an action time prediction value corresponding to each point on the grid; calculating a partial derivative based on the action time predictor to determine a gradient corresponding to each point; and obtaining target key feature data, and based on the target key feature data, the motion time prediction value corresponding to each point on the grid and the gradient corresponding to each point, performing motion time prediction by using a two-point cubic Hermite interpolation algorithm, and obtaining a motion time prediction value corresponding to the target key feature data.

The application relates to a rotor airfoil optimization method and system based on deep reinforcement learning, and belongs to the field of airfoil design. Through a large number of interactive learning between an intelligent agent and an environment, an optimization strategy is obtained, a new airfoil with better performance can be obtained by dynamically optimizing a target airfoil, and the optimization process corresponding to the optimization strategy has physical interpretability; an agent model for predicting a rotor airfoil aerodynamic force hysteresis loop is established by using a deep neural network, and the agent model has better nonlinear prediction capability.

The invention relates to the technical field of manhole cover monitoring, in particular to a manhole cover comprehensive environment monitoring system based on the Internet of Things, which is characterized in that a manhole cover displacement value is calculated point by point in a time window and is subjected to weighted stacking with a preorder trend curve to form a fusion sequence, and then the fusion sequence is input into a long short-term memory network to complete nonlinear prediction; an output result is compared with a threshold value interval section by section, it is ensured that abnormity judgment is achieved in a continuous fragment, through combination of time sequence prediction and nonlinear learning, unified modeling is achieved on displacement trend change and environment trend, the continuity and accuracy of abnormity judgment are improved, the displacement and the inclination angle of the well lid are synchronously judged in a trend set, and the safety of the well lid is improved. According to the method, the initial signal is triggered, the signal and the gas sudden change difference value are accumulated, features are extracted through the convolutional neural network, matching is completed, and the high-risk signal is output, so that sensitive capture of sudden abnormity is enhanced, the probability of missing report is reduced, and the response timeliness under the sudden situation is improved.

The invention discloses a machine room equipment energy-saving regulation and control method and system based on load prediction, and belongs to the technical field, and the method specifically comprises the steps: collecting multi-dimensional operation data in a machine room in real time, inputting the operation data to a pre-trained multi-modal prediction model, dynamically predicting the load demand of the machine room in a future time period, and calculating the load demand of the machine room in the future time period. The multi-modal prediction model combines an emergency disturbance factor, generates a non-linear prediction curve, performs multi-stage grouping on equipment in a machine room based on a load demand prediction result, determines a differential start-stop strategy and an operation power distribution scheme based on a group response speed and an energy efficiency ratio, and improves the power distribution efficiency while meeting the current load demand. The load evolution trend of a future time period is simulated in advance, the running state of the equipment is balanced in a cross-time mode, and starting and stopping of the equipment are regulated and controlled through a virtual buffering mechanism.

The invention provides a nonlinear predictive control method for a Novolens polypropylene process, and relates to the technical field of nonlinear predictive control of a chemical process, and the method comprises the following steps: S1, building a mechanism model corresponding to a controlled loop according to the internal reaction mechanism of the Novolens polypropylene process, and obtaining the real-time gain of the process; s2, obtaining a time constant and a lag time parameter of the controlled Novolens polypropylene process model; s3, constructing a corresponding mechanism state space model through the real-time gain, the time constant and the delay time; s4, on the basis of the mechanism state space model, state prediction of the controlled Novolens polypropylene process is obtained; s5, an objective function is introduced, and the optimal control input increment of the controlled Novolens polypropylene process is obtained; and S6, performing calculation according to the optimal control input increment to obtain optimal control. The method is used for accurately realizing optimization control of the Novolens polypropylene process.

The invention discloses a chemical data missing process fault detection method and system, and the method comprises the steps: converting two-dimensional data into a three-dimensional tensor through employing MDT, and carrying out the linear prediction and nonlinear prediction of an incomplete value through employing linear smooth CP and CP-SAE, and carrying out the reconstruction of normal data. And extracting a residual error and a feature space of the data in the data missing process through CP-SAE. And combining features extracted by smooth CP-decomposition and CP-SAE, and establishing three statistical magnitudes to realize fault detection. According to the method, the MDT and smooth CP decomposition method is used for solving the problems of data missing and time delay of data sample sampling, and the timeliness is high. The CP-SAE feature extraction robustness is high, and compared with a conventional linear method, the precision is high, and the response speed is high. The method is simple to operate, does not need repeated operation, and can extract the key features of the data while reconstructing the complete data set only by operating on the incomplete data set. The missing data can be effectively supplemented, the process monitoring requirement can be met, and the precision is high.

The application relates to the field of ethylene industry diagnosis, in particular to an ethylene furnace tube coking thickness prediction method and system.The method comprises the following steps: collecting ethylene furnace tube parameter time sequence data, extracting time sequence convolution features, obtaining bidirectional time sequence features through bidirectional time sequence dependence processing, and obtaining time sequence pooling features through attention pooling; linearly mapping the features to obtain a furnace tube coking thickness linear prediction value, combining a learnable nonlinear transformation with the linear prediction value to obtain a furnace tube coking thickness nonlinear prediction value; finally, fusing historical furnace tube coking thickness prediction error features, the furnace tube coking thickness linear prediction value and the furnace tube coking thickness nonlinear prediction value to calculate the furnace tube coking thickness prediction value of the ethylene furnace tube.Compared with the prior art, the linear behavior and the nonlinear behavior are combined, and the fusion strategy is adaptively adjusted based on the historical prediction error, so that the ethylene furnace tube coking thickness can be effectively predicted.

This invention relates to the field of artificial intelligence-based educational assessment, and discloses a cognitive diagnostic model and method based on knowledge text. The model includes a text feature extraction module for extracting and generating knowledge point association vectors representing the degree of association between questions and preset knowledge points; a knowledge proficiency embedding module for mapping knowledge proficiency vectors; a question attribute embedding module for mapping question knowledge difficulty vectors and question discrimination scalars; a knowledge association attention module for adjusting attention weights and generating weighted knowledge representations; and an adaptive nonlinear prediction module containing a multi-layer KANLinear structure composed of B-spline basis functions and outputting the prediction probability of correct student answers. This invention solves the problem of fragmented internal module functions in existing models and features high interpretability and independence from manual annotation.

The application discloses a molecule property prediction method based on a chemical element knowledge graph and a functional group prompt, and comprises the following steps: collecting chemical knowledge including chemical elements and their chemical attributes, functional groups and their chemical attributes, and constructing a chemical element knowledge graph according to the chemical knowledge; enhancing an original molecule graph according to the chemical element knowledge in the chemical element knowledge graph to obtain a molecule enhanced graph; pre-training a graph encoder in a comparative learning mode according to the original molecule graph and the molecule enhanced graph; constructing a functional group prompt according to the functional group knowledge in the chemical element knowledge graph, adding the functional group prompt to an input molecule graph, and fine-tuning the pre-trained graph encoder and a nonlinear predictor by using the input molecule graph added with the functional group prompt; and the fine-tuned graph encoder and the nonlinear predictor constitute a molecule property prediction model; and the molecule property prediction model is used to predict the molecule property, so that the accuracy of the molecule property prediction is improved.

The present application relates to the technical field of drilling operation, and particularly relates to a PDC bit residual life prediction method based on torsion time series data, which comprises the following steps: collecting torsion data of the bit to construct torsion time series data; extracting wear modal components by using a variational mode decomposition algorithm containing a frequency band bandwidth constraint term and a time domain sparsity constraint term; calculating the logarithmic energy features and multi-scale spectrum entropy of the wear modal components and weighting fusion to obtain a composite degradation index; calculating the ratio of the composite degradation index to the cumulative running time, multiplying by a preset wear acceleration factor to obtain an instantaneous degradation rate, and combining with a preset failure threshold to obtain the residual life. The present application effectively extracts the wear modal components by introducing the time domain sparsity constraint term, and constructs a nonlinear prediction model in combination with the wear acceleration factor, thereby improving the accuracy of the PDC bit residual life prediction.

This invention belongs to the field of traditional Chinese medicine (TCM) extraction technology, and particularly relates to a method and system for cross-scale dynamic control of TCM extraction processes. The method involves collecting process parameters and corresponding quality attributes of several batches of TCM preparations under small-scale, pilot-scale, and large-scale production conditions during extraction. A multivariate analysis model, a dynamic control standard identification model, a cross-scale nonlinear prediction model, and a multi-scale coupled dynamic simulation model are then trained sequentially. Real-time process parameters are input into the trained cross-scale nonlinear prediction model and multi-scale coupled dynamic simulation model to obtain predicted real-time key quality attributes. This invention achieves real-time prediction and dynamic control of key quality attributes through the coupling of the multivariate analysis model, the dynamic control standard identification model, the cross-scale nonlinear prediction model, and the multi-scale coupled dynamic simulation model, enabling timely adjustment of process parameters to stabilize production and ensure the stability of TCM extraction processes at large-scale production levels.

The invention relates to the technical field of data processing, and particularly discloses a big data management-based substation maintenance operation positioning and safety early warning method, which comprises the following steps of: fusing an unstructured operation task book, real-time SCADA (Supervisory Control And Data Acquisition) equipment state data and GIS (Geographic Information System) spatial data; and a safe operation area and a danger warning area which are completely matched with the field electrical state are automatically and dynamically constructed for each operation, so that the accuracy and scenario of warning are realized from the source. On the basis, in order to overcome the hysteresis of a traditional alarm, the dynamic geofence is abstracted into an environmental potential field providing gravitational force and repulsive force in the scheme, and high-precision nonlinear prediction is carried out on a future trajectory through fusion of personnel motion inertia and environmental potential field force. According to the mechanism, the system can pre-judge an imminent danger approaching behavior in advance, and the fundamental conversion from post-event response to pre-warning is realized, so that the safety risk is actively solved.

This application relates to the field of turbocharger efficiency prediction technology, and discloses a turbocharger efficiency evaluation method and device based on variable structure turbine data. The method first establishes a reliable radial turbine numerical model through high-precision three-dimensional simulation and experimental verification; then, it uses sensitivity analysis and Latin hypercube sampling to screen key impeller geometric parameters and construct an efficient sample dataset; the core is the application of a neural network algorithm to establish a nonlinear prediction model with turbine reduced speed and key geometric parameters as input and turbine efficiency as output, thereby quickly and accurately obtaining the variable structure turbine efficiency characteristics under all operating conditions; finally, by dynamically identifying the real-time operating conditions of the turbocharger, and combining the turbine efficiency predicted by the neural network with the compressor efficiency calculated by actual measurements, an accurate and efficient evaluation of the overall efficiency of the variable structure turbocharger is achieved, effectively solving the problems of high prediction difficulty and low accuracy of traditional methods.

The application discloses a kind of considering nonlinear subgrade soil resilience modulus estimation method and estimation method, comprising: obtaining measured data under different compaction degree, moisture content and stress state by oedometer;According to the influence law of experimental result analysis normal stress, compaction degree and moisture content factor pair, determine the relationship with normal stress, compaction degree and moisture content respectively;The estimation model is constructed as the function of exponential form with physical constraint, and the model parameters in the estimation model are expressed as the polynomial of compaction degree and moisture content;Based on the estimation model, the static octahedral shear stress is calculated, so as to calculate the resilience modulus of subgrade soil.The application takes normal stress as the core and considers physical state, constructs the static soil pressure coefficient estimation model with clear physical meaning, measurable engineering parameters, and can be directly embedded into roadbed dynamic response analysis, and is used for subgrade soil resilience modulus estimation, simple, fast, improves calculation efficiency and accuracy.

The invention discloses a Bluetooth sound equipment intelligent sound effect adjusting system based on adaptive noise reduction, and relates to the technical field of audio processing, and the system obtains an environment noise signal and an original audio signal, calculates an initial anti-phase sound wave signal based on the environment noise signal, and obtains an initial anti-phase sound wave signal based on a parameterized large-signal nonlinear model; the bottom layer electrical feedback parameter is converted into the transient physical displacement state of the current loudspeaker diaphragm, and the parameterized large signal nonlinear model takes the force factor, the mechanical stiffness coefficient and the voice coil inductance of the loudspeaker changing along with the displacement as physical constraints to generate a theoretical composite excitation signal; inputting the theoretical composite excitation signal and the transient physical displacement state into a loudspeaker nonlinear prediction network to obtain a pre-judgment result, when the pre-judgment result is that a physical limit threshold value is broken through, constructing a reverse distortion compensation waveform, and superposing the reverse distortion compensation waveform into a mixed signal of an attenuated initial reverse sound wave signal and an original audio signal to obtain the loudspeaker nonlinear prediction network. And outputting the final audio signal.

The application discloses a method for dynamic error prediction correction of an electromagnetic positioning system, which unifies multiple data points collected at different time points in a measurement period to a same target timestamp by establishing a dynamic prediction model to generate a correction data frame with completely aligned timestamps, and uses the correction data frame for pose solution. The application provides various implementation manners, including a prediction method based on linear extrapolation of historical data frames, a nonlinear prediction method based on polynomial function fitting, a method of directly predicting by taking measurement values as states and using a standard Kalman filter, and a hybrid prediction method of inversely solving theoretical measurement values by a forward model after predicting future poses by taking sensor poses as states and using an extended Kalman filter. The application covers various prediction schemes by a unified framework, and significantly improves the accuracy and robustness of the electromagnetic positioning system in a dynamic scene.