75 results about "Time derivative" patented technology

The present disclosure provides a computer-implemented system for automated augmentation of differential equation models. The system stores differential equations representing mechanistic behavior of physical or computational processes and constructs a hybrid computational solver by embedding a trainable universal approximator with adjustable parameters into the differential equations, where approximator outputs augment time derivatives during numerical integration. An iterative training process adjusts parameters through numerical integration, monitors integration failures, assigns infinite penalty values to loss functions when failures occur, and computes gradients using automatic differentiation otherwise. The system computes sensitivity metrics via Jacobian matrix evaluation, classifies input / output subsets as significant based on threshold-exceeding sensitivity metrics, generates a reduced approximator operating on classified subsets, and replaces the universal approximator with the reduced version to create an optimized solver.

The invention belongs to the technical field of computational electromagnetics, and discloses a numerical calculation method for simulating electromagnetic wave propagation characteristics in time-varying plasma, which is a three-dimensional Newton-HIE-FDTD method for efficiently simulating propagation of electromagnetic waves in time-varying plasma based on a hybrid explicit-implicit finite difference time domain method and Newton's second law of motion. The method inherits the advantages of the Newton-ADE-FDTD method, the time-varying electron density is accurately represented through the time derivative, and the abundant dynamic characteristics of the time-varying plasma can be accurately captured. On the basis, the method also fuses the advantages of an HIE-FDTD method, so that the time step length of the algorithm is only restricted by the sizes of grids in two directions, and compared with other simulation methods based on time-varying plasma, the method provided by the invention is more excellent in calculation efficiency and is more suitable for large-scale popularization and application. The method is especially suitable for analysis and simulation of electromagnetic wave propagation characteristics in time-varying plasma.

The invention belongs to the technical field of power control, and particularly relates to a handheld laser welding head power control method and system based on the molten pool temperature, and the method comprises the following steps: obtaining a molten pool temperature sequence collected by a coaxial temperature sensor of a handheld laser welding head in real time; the polynomial order of a Savitzky-Golay filter is dynamically adjusted based on the second-order time derivative of the molten pool temperature sequence, the molten pool temperature sequence is filtered, and a real-time molten pool temperature measurement value is obtained; on the basis of the real-time molten pool temperature measurement value and the first-order time derivative of the real-time molten pool temperature measurement value, a preset arcing temperature threshold value, a steady-state temperature interval and a process adjustment gradient threshold value are compared, and it is judged that the current welding process is in one of the three stages of arcing, steady-state welding or arc suppression pit filling; when the steady-state welding phase is determined, the temperature deviation between the target temperature and the real-time molten pool temperature measurement value is calculated. Differential power control strategies for different process stages are achieved, and the overall quality and consistency of handheld laser welding are improved.

The invention discloses a thickener dosing control method and system, and relates to mineral processing. The method comprises the following steps: acquiring concentration values measured by an ith concentration sensor at different depths at a moment t; obtaining the turbidity T of the overflow water, the effective viscosity of the overflow water or underflow, the volume fraction of fine particles and the volume fraction of coarse particles in the overflow water, the Zeta potential of the feeding end, the Zeta potential of the overflow end, the time derivative of the Zeta potential of the overflow end, the equivalent diameter d of the particles, the density of the particles, the density of the fluid and the viscosity of the fluid; calculating the effective settling velocity of the particle swarm; carrying out online correction on the effective settling velocity by utilizing a least square method or a Kalman filtering algorithm; performing time lag correction on the concentration values at different depths by using the corrected effective settling velocity; correcting the turbidity T of the overflow water according to the corrected concentration profile; respectively calculating a flocculant dosing rate and a coagulant dosing rate; according to the invention, accurate cooperative control of the dosing rate of the flocculating agent and the coagulant is improved through the artificial intelligence model.

The invention relates to the technical field of automatic control, and discloses a pelvic and abdominal muscle group cooperative training self-adaptive control system based on biological feedback, which comprises a state drift observation module, a dynamic threshold value resolving module and a self-adaptive control module, and is characterized in that the system monitors the amplitude attenuation rate of a main constraint variable in real time to update an attenuation coefficient; constructing a dynamic safety envelope containing slew rate limitation and amplitude saturation; when the first-order time derivative of the disturbance variable exceeds the limit, the controller locks the output slope of the disturbance variable, and dynamic oscillation of the time-varying coupling system caused by high-frequency pulse disturbance is suppressed by establishing a dynamic mapping mechanism of the disturbance loading rate and the main variable response bandwidth. The adaptive compensation of the parameter drift of the controlled object and the steady-state maintenance of the control precision are realized.

The invention relates to the technical field of limited space fire hazard flashover prediction. The invention provides a limited space fire hazard flashover prediction method and system based on a physical information neural network. The method comprises the following steps: acquiring sensor observation data and initial fuel distribution data; inputting the space-time coordinate vector and the initial fuel distribution data into a Mamba neural network to obtain predicted values of temperature, incident radiation and fuel mass fraction; calculating a space-time derivative of the predicted value, and constructing a physical residual term containing energy conservation, radiation transfer and fuel consumption equation residual, a boundary residual term and an observation residual term; weighted combination is carried out on the three types of residual errors to construct a loss function, and network parameters and to-be-learned physical parameters are updated through an optimization algorithm; and predicting a temperature field based on the updated network, and judging the time of detonation when the temperature reaches a detonation critical value. The problems of poor reliability and prediction deviation caused by lack of physical rule constraints of an existing data-driven fire prediction model are solved.

The present application relates to the technical field of data fusion, and specifically relates to a multi-modal sensor external parameter automatic calibration method and system, which comprises the following steps: acquiring a data frame sequence of a first sensor on a ship body and a second sensor on a mast and horizontal plane velocity data of a second sensor position, performing time derivative operation on the velocity data to obtain acceleration components and calculating a synthetic vector amplitude to identify a disturbance time period, obtaining a horizontal displacement sequence through time integration of the velocity data, combining vertical height to calculate a mast swing angle change sequence, converting the mast swing angle change sequence into a sensor space posture offset angle sequence, and finally performing coordinate transformation operation on the initial external parameter calibration parameters to obtain corrected external parameter calibration parameters. The present application can identify and compensate position offsets caused by external disturbances on sensor fixed structures in real time, and ensure the accuracy and reliability of multi-sensor data fusion.

The invention discloses a mineral resource intelligent prediction method based on a liquid neural network, and relates to the field of artificial intelligence and geological exploration cross technology, and the method comprises the steps: carrying out the time series reconstruction of a space-time coordinate observation data set, generating a multi-dimensional continuous space-time field function, and calculating a space gradient field and a time derivative field of the multi-dimensional continuous space-time field function, generating a continuous spatio-temporal data stream; and fusing the geological background static feature vector and the metallogenic dynamic feature vector, inputting the fused feature vector into a full connection layer where a liquid neural network branch and a convolutional neural network branch are jointly connected, mapping to generate a mineral resource predicted value, and meanwhile, generating a mineral resource quantity distribution diagram through spatial interpolation rendering. According to the method, the continuous spatio-temporal data flow is input into the liquid neural network branch for internal state evolution, the mineralization dynamic feature vector is generated, high-resolution capture of the dynamic time sequence mode in the mineralization process is achieved, and the accuracy and time sequence resolution of prediction of the mineralization dynamic process are improved.

The application relates to an industrial process state monitoring method based on robust space-time joint projection, which comprises the following steps: data preprocessing and standardization; data space manifold structure and time dynamic information capturing: calculating the similarity degree between samples according to neighborhood overlapping order similarity, obtaining a data similarity matrix, and thus obtaining the overall space manifold information of process data; subsequently, calculating a data time derivative matrix, extracting slow change characteristics in the data, and obtaining key dynamic information; feature extraction and monitoring model building based on robust space-time joint projection: comprehensively integrating space-time information, performing dimension reduction projection on the data, obtaining key low-dimensional characteristics for retaining the representation of system operation states, constructing monitoring statistics and monitoring thresholds based on the key low-dimensional characteristics, and building an offline process monitoring model; real-time online monitoring of the state of an industrial system.

The present application belongs to the technical field of industrial automatic linkage control, and relates to a combustion chamber nozzle regulation linkage control system, comprising: a state acquisition module, used for acquiring a controlled regulation unit displacement parameter and a physical interference carrier state parameter; a polarity phase discrimination module, used for real-time calculation of a first-order time derivative of the displacement parameter and determination of a polarity switching identifier; a matrix storage module, used for storing forward and reverse interference sub-matrices with heterogeneous weights; a compensation operation module, used for calling a sub-matrix and determining an asymmetric compensation amount when the polarity switching identifier jumps; a boundary constraint module, used for amplitude limiting processing of a compensation amount change rate; and a linkage control module, used for issuing a synchronous regulation instruction. The present application identifies asymmetric blocking characteristics of a physical response end, eliminates commutation transient compensation mismatch, and suppresses system cross oscillation in a multivariable strong coupling environment.

A computer-implemented method for estimating a health state of a solenoid valve including a solenoid for supporting a process control system. The method includes the steps of monitoring a current passing through the solenoid, determining a time period between an instant of initiating a state change of the solenoid valve and an instant when the time derivative of the current is discontinue, comparing the time period with a reference time period indicative for the health state of the solenoid valve thereby determining the health state.

This application relates to the field of burner combustion control technology and discloses a burner fuel grading control optimization method. This method calculates the background noise energy during a silent monitoring period and selects the frequency of the minimum energy value as the target micro-perturbation frequency. A sinusoidal micro-perturbation signal is generated based on this frequency and superimposed on the command of the shift fuel regulating valve. Valve displacement and combustion chamber sound pressure signals are simultaneously acquired and orthogonal decoding is performed. Electromechanical transfer gain, thermoacoustic gain, and dynamic transmission phase difference are calculated and obtained. Based on the electromechanical transfer gain, it is determined whether amplitude compensation should be performed. A two-dimensional linkage verification matrix is ​​constructed by combining the time derivatives of the thermoacoustic gain and the dynamic transmission phase difference, thereby distinguishing between pure thermoacoustic mode over-limit and physical spatial anomalies, and executing the corresponding fuel grading closed-loop regulation or safety interlocking procedure. This invention eliminates valve mechanical execution errors, accurately distinguishes combustion instability conditions under strong noise backgrounds, and improves the safety of combustion system operation.

The present application relates to the field of unmanned aerial vehicle network security, and particularly relates to a general intrusion detection method for heterogeneous unmanned aerial vehicles. The present application comprises: acquiring unmanned aerial vehicle sensor data and preprocessing; extracting timestamp disintegration features, time derivative features and periodic features of samples in the preprocessed data set; constructing a unified feature matrix; calculating feature importance according to the unified feature matrix to obtain a feature sequence; constructing a multi-layer Transformer encoder, inputting the feature sequence into the multi-layer Transformer encoder, performing aggregation processing to obtain an aggregation vector, and calculating an attack probability according to the aggregation vector; training the multi-layer Transformer encoder using a binary cross-entropy loss function; and inputting a to-be-detected sample into the trained multi-layer Transformer encoder to obtain a probability of whether it is an attack. The present application can be used between multiple UAV types, and has a cross-platform robust and practical general security detection framework.

The invention discloses a robot control method based on active disturbance observation and phase coupling control, and the method comprises the steps: collecting the current state quantity of a robot in real time, and constructing a joint space dynamic model; generating state estimation and disturbance estimation in the joint space dynamic model; a phase parameterization method is adopted to map the phase of the multi-degree-of-freedom action to an expected trajectory, and a closed-loop trajectory tracking and disturbance compensation control law is designed in combination with disturbance estimation and a sliding manifold mechanism; according to the method, a position error transformation design continuously-derivable robot auxiliary level function is introduced, the stability is analyzed by adopting a Lyapunov method, and a closed-loop trajectory tracking and disturbance compensation control law and a coupling gain adaptive law are substituted into a time derivative of a candidate Lyapunov function to complete the control of the robot. The control output can be kept smooth and continuous, instruction sudden change or attitude instability is avoided, high action success rate and landing stability can still be maintained when the environment changes, and the landing impact load peak value is effectively reduced.

The application discloses a kind of hybrid energy storage auxiliary frequency modulation instruction prediction method and system of thermal power generating unit, belong to energy storage frequency modulation instruction prediction technical field, method: obtain original frequency modulation instruction sequence, carry out dynamic phase compensation;Phase reference value is calculated, and nonlinear correction is carried out;First correction signal is obtained;Information entropy gradient enhancement is carried out to sampling point;First correction signal is enhanced, and second correction signal is obtained;Chaotic time series reconstruction is carried out, and third correction signal is obtained;Chaotic time series reconstruction includes: constructing time delay embedding space to map to high-dimensional phase space, calculating local Lyapunov exponent, combining the time derivative of signal and chaotic adjustment factor to carry out dynamic reconstruction;Third correction signal is input to GRU neural network, and the output frequency modulation instruction prediction result is obtained.The application can predict the size of frequency modulation instruction in advance, let super-capacitor or battery act in advance, improve the yield value, and the degree of convenience and accuracy are high, with engineering applicability.

The invention discloses a three-phase current-based power transmission line ground fault phase identification method, system and device and a medium, and belongs to the technical field of ground fault identification, and the method comprises the steps: calculating a virtual space derivative of a zero-sequence current according to a time derivative of a three-phase current transient component and a line distributed capacitance parameter, and forming a space-time coupling tensor; performing spatial modal decomposition by adopting an intrinsic function of the zero-sequence traveling wave equation to obtain spatial modal coefficients of all orders; constructing a phase sequence leakage matrix by taking the spatial modal coefficient as a weight; performing singular value decomposition on the phase sequence leakage matrix, and extracting main singular vector feature parameters; transforming the composite mapping matrix to obtain an island vector; determining a suspected fault phase according to the projection coefficient energy ratio of the island vector; and reversely solving the distributed capacitance and calculating a theoretical value, and outputting a final fault phase when the deviation between the theoretical value and the measured value meets a condition. According to the method, accurate fault phase identification under high-resistance grounding and long-distance line working conditions is realized through virtual space derivative mapping and modal energy decomposition.

A method can include determining time derivative pressure data based on pressure data for a pump system (121; 122; 123) performing a hydraulic stimulation operation in a geological region. The method can also include determining a moving average based on the time derivative pressure data and a predetermined time window. The method can also include determining a flow adjustment for the pump system (121; 122; 123) based on the moving average, an update interval for adjusting the flow, and a predetermined flow rule. A size of the predetermined time window can be different than the update interval. The method can also include determining the time derivative pressure data using smoothed pressure data. The method can also include determining the flow adjustment for the pump system (121; 122; 123) based on the time derivative pressure data derived from the smoothed pressure data.

The invention relates to a network connection vehicle fault performance self-healing control method and system considering physical constraints in the technical field of intelligent traffic and vehicle control. The method comprises the following steps: constructing a heterogeneous networked vehicle nonlinear system model based on nonlinear dynamics of displacement, speed and acceleration, actuator fault influence and external disturbance; constructing an auxiliary dynamic variable representing the overall influence of the fault, deducing a time derivative of the auxiliary dynamic variable, designing a self-adaptive fault influence identifier, and carrying out the online identification of the system fault influence; constructing a lower definite bound parameter associated with the unknown control coefficient, designing a parameter boundary estimator, and performing unknown parameter boundary adaptive estimation; and on the basis of fault influence identification and parameter boundary estimation information, a physical constraint function of the actuator is integrated, a self-healing controller of the networked vehicle formation is designed, and fault influence compensation, physical constraint guarantee of the actuator and stable control of the networked vehicle formation are realized. And the reliability and the control precision of the networked vehicle cooperative control system under complex working conditions are improved.

The application belongs to the technical field of image processing, and discloses an image processing method and device based on an event camera, equipment and a medium. The method comprises the following steps: acquiring event data of a blurred image collected by an event camera; constructing an initial PINN model, embedding an event generation equation in the initial PINN model; inputting the event data into the PINN model to obtain a predicted luminance value, performing self-supervision of a time derivative based on the predicted luminance value and an actual luminance value, introducing a Tikhonov regularization constraint condition to optimize the PINN model, and determining an optimized PINN model; inputting event data of an image to be processed into the optimized PINN model to obtain log luminance values of three color channels of the image to be processed; and converting the log luminance values into a reconstructed image frame by using tone mapping. The method can reduce noise and artifacts of the reconstructed image and improve the quality of the model reconstructed image.

The application belongs to the technical field of computational electromagnetics, and discloses a numerical calculation method for simulating electromagnetic wave propagation characteristics in time-varying plasma, which is a three-dimensional Newton-HIE-FDTD method for efficiently simulating electromagnetic wave propagation in time-varying plasma based on a mixed explicit-implicit finite-difference time-domain method and Newton's second law of motion. The method inherits the advantages of the Newton-ADE-FDTD method, accurately represents the time-varying electron density through the time derivative, and can accurately capture the rich dynamic characteristics of the time-varying plasma. On this basis, the method also integrates the advantages of the HIE-FDTD method, so that the time step of the algorithm is only restricted by the grid size in two directions. Compared with other simulation methods based on time-varying plasma, the method is more efficient in calculation, and is particularly suitable for the analysis and simulation of electromagnetic wave propagation characteristics in time-varying plasma.

The present application relates to the technical field of confined space fire flashover prediction. A confined space fire flashover prediction method and system based on physical information neural network are provided. The steps are as follows: obtaining sensor observation data and initial fuel distribution data; inputting the space-time coordinate vector and the initial fuel distribution data into the Mamba neural network to obtain temperature, incident radiation and fuel mass fraction prediction values; calculating the space-time derivatives of the prediction values, constructing physical residual terms containing energy conservation, radiation transfer and fuel consumption equation residuals, and boundary residual terms and observation residual terms; combining the three types of residuals by weighting to construct a loss function, updating the network parameters and the physical parameters to be learned through an optimization algorithm; and determining the flashover occurrence time when the temperature reaches the flashover critical value based on the updated network prediction temperature field. The present application solves the problems of poor reliability and prediction deviation caused by the lack of physical law constraints in existing data-driven fire prediction models.

The application discloses a kind of regional network supply load prediction method, equipment, storage medium and product, the prediction method includes obtaining the historical data of target area before prediction;History data is analyzed and sorted, constructs time derivative feature;According to historical network supply load and historical meteorological data, select the meteorological parameter with high correlation degree with historical network supply load, and then according to historical meteorological data and selected meteorological parameter constructs meteorological derivative feature;According to the daily historical peak power consumption and historical valley power consumption of each user extracted, user derivative feature is constructed;Load and distributed energy output prediction model are constructed, and historical data and time derivative feature, meteorological derivative feature and user derivative feature are used to train and verify load and distributed energy output prediction model, obtain target prediction model;Regional network supply load prediction is carried out using target prediction model.The application improves the prediction accuracy of network supply load.

The application belongs to the technical field of temperature measurement and relates to a temperature dynamic monitoring system in a glass melting process, which comprises the following steps: a data acquisition unit converts an original signal into a measured temperature sequence; a high-order differential state observation unit calculates first and second time derivatives of the measured temperature; a boundary condition dynamic identification unit extracts an amplitude decay rate at commutation to determine a thermal response time constant variation value; a dynamic inverse convolution compensation unit uses an inverse inversion operator to decouple the time derivative and the variation value to generate a correction signal; and a system instruction output unit outputs a fuel control instruction according to the correction signal and a temperature control line deviation. The application implements dynamic hedging and error calibration on the inherent thermal inertia and large lag of a contact type temperature sensor, reconstructs and outputs a real temperature measurement signal of a melt in real time, eliminates the combustion overshoot phenomenon caused by temperature measurement lag through inverse inversion, suppresses temperature fluctuation of a melt liquid surface during commutation, and ensures long-term stability of thermal field state observation.

The application relates to a connected vehicle fault performance self-healing control method and system considering physical constraints in the technical field of intelligent transportation and vehicle control. The method comprises the following steps: constructing a heterogeneous connected vehicle nonlinear system model based on displacement, speed, nonlinear dynamics of acceleration, actuator fault influence and external disturbance; constructing an auxiliary dynamic variable representing the overall influence of the fault, deriving its time derivative, designing an adaptive fault influence identifier, and performing online identification of the system fault influence; constructing a lower bound parameter associated with unknown control coefficients, designing a parameter boundary estimator, and performing adaptive estimation of the unknown parameter boundary; based on the fault influence identification and parameter boundary estimation information, integrating the actuator physical constraint function, designing a connected vehicle formation self-healing controller, and realizing fault influence compensation, actuator physical constraint guarantee and connected vehicle formation stable control. The reliability and control accuracy of the connected vehicle cooperative control system under complex working conditions are improved.

For the operation of the electrochemical energy converter, a control object (Σ p The model-based actuation of the control variable (y(k)) is determined and the control object (Σ p (·)) extended object model (Σ m,aug (·)) to determine the time derivative of the controlled variable y(k) (equation (I), (I), equation (II), (II),..., y(n)) up to the system dimension (n) of the controlled object (Σ p (·)) actuator (Σ a (·)) actual adjustment amount (u act (k)) is determined; and depending on the determination, the compensation and / or correction required (dr eq (k)).

The invention discloses a viscoelastic scalar P-wave equation construction and wave field numerical simulation method, and belongs to the field of deep sea oil and gas field exploration and development. In order to solve the problems that an existing scalar acoustic equation is insufficient in physical completeness, a multi-component elastic wave equation is high in calculation cost, and a constant Q model viscoelastic equation is difficult to fully reflect the dynamic characteristics of a wave field, a frequency dispersion relation based on a constant Q model is established; according to the method, a viscoelastic multi-component wave equation containing a fractional order space differential operator and a time derivative coupling term is constructed, then a dual projection operator is introduced to realize modal decoupling of a P wave and an S wave, a viscoelastic scalar equation only describing the P wave is obtained, and numerical simulation is performed by adopting a pseudo-spectral method and a finite difference method. According to the method, propagation dynamic behaviors of seismic waves in a strong attenuation medium can be described more accurately, amplitude attenuation and phase dispersion effects are effectively decoupled, and a reliable theoretical and calculation tool is provided for high-precision seismic data processing and imaging.

A computer-implemented method for determining an operating condition of a reciprocating compressor, the method comprising the steps of: a. receiving (100) time-series sensory data (1) of the reciprocating compressor; b. creating (101) a dataset (3) comprising at least one of: a time derivative of the time-series sensory data (2) as a function of the time-series sensory data (1); and time-delay embeddings of the time-series sensory data; c. extracting (102) a set of data features from the dataset (3); d. performing (103) an analysis on the set of extracted data features to determine and operating condition of the reciprocating compressor.

Method for detecting a risk of a motor vehicle tipping over, wherein the risk of tipping over is the risk of the motor vehicle tipping over sideways, in which - the time derivative of the lateral acceleration (Day) is determined and - depending on the time derivative of the lateral acceleration (Day), the presence of the risk of tipping over is detected, characterized in that - the temporal derivative of the lateral acceleration (Day) in a form weighted at least with the lateral acceleration (ay) is included in the detection of the risk of tipping over (101) and that the time derivative of the lateral acceleration (Day) is included in the detection of the risk of rollover in a form weighted at least additionally with the time derivative of the steering angle (DLw).

A data correction device 400 includes: an acquisition section 410 that acquires measurement data from a measurement device 100 capable of periodically measuring a distance while moving at least one of (i) a subject 10 to be measured or (ii) at least a part of the measurement device 100, in which first measurement results of the distance are arranged in a time series, and second measurement results obtained by measuring the distance when the subject 10 to be measured and the measurement device 100 are in a stationary state are arranged at a head or a tail of the first measurement results; and a correction section 430 that corrects an error included in the measurement data by applying the measurement data to a recursive formula based on a time derivative of a measurement result of the measurement device.