157 results about "Signal prediction" patented technology

The invention discloses an intelligent early warning method for pipeline blockage of a slurry circulation system of a slurry shield, which relates to the field of intelligent early warning, and comprises the following steps of: performing spatial-temporal feature analysis on a standardized multi-dimensional data stream, constructing a blockage feature knowledge graph based on pipeline position and time sequence correlation analysis, and generating a blockage feature vector through a graph neural network; based on the blockage feature vector, analyzing the dynamic change trend of particle distribution through a long-short-term memory network and predicting the particle blockage risk in combination with an acoustic signal, then performing adaptive judgment by fusing geological conditions and construction stage information to obtain a risk assessment result, and inputting the risk assessment result and the blockage feature vector into digital twinborn simulation to obtain the particle blockage risk. A blockage scene is predicted based on fluid dynamics and a particle sedimentation model, early warning parameters are adjusted through Bayesian optimization, and graded early warning signals are generated; according to the invention, by generating the blockage feature vector, the recognition capability of the early local abnormal propagation trend is enhanced, and a reliable basis is provided for accurately predicting the blockage risk.

The invention provides a Rowland time delay signal prediction method and system, electronic equipment, a program product and a storage medium. The method comprises the following steps: acquiring an initial Rowland time delay signal; extracting a periodic term of the initial Rowland time delay signal, and inputting the periodic term to a constructed multi-periodic term and trend term model; calculating a residual signal between the observed value of the initial Rowland time delay signal and the output of the multicycle term and trend term model; wavelet decomposition and threshold denoising are carried out on the residual signals; fusing the output of the multi-cycle term and trend term model and the denoised residual signal through an adaptive weight mechanism to obtain a predicted Rowland time delay signal; the deterministic periodic term and the long-term trend drift of the Rowland time delay signal are captured through a multi-periodic term and trend term model, and non-stationary disturbance is processed by using wavelet denoising, so that the Rowland time delay prediction precision is remarkably improved, and the method is particularly suitable for a high-precision timing scene in a complex electromagnetic environment.

The invention discloses a multi-GNSS satellite signal power abnormity real-time monitoring method. The method comprises the following steps: acquiring real-time observation data of an observation station network which is uniformly distributed globally; when the linear relation between the carrier-to-noise ratios of different frequency signals of each satellite in each observation station and the dynamic monitoring threshold value related to the elevation angle of each satellite are determined, one signal is used for predicting another signal by using the linear coefficient, and the deviation between an actual value and a predicted value is calculated; calculating a satellite elevation angle of the real-time observation data, and determining a monitoring threshold value of the current satellite at the current moment according to the satellite elevation angle; and counting an average value of the deviations of all satellites monitored by all observation stations at the current moment, and marking that the power of the current satellite at the current moment is abnormal when the absolute deviation of the current satellite is greater than a monitoring threshold value. According to the invention, on the basis of the carrier-to-noise ratio linear relation of different frequency signals and the dynamic monitoring threshold, real-time monitoring of various power abnormal scenes including natural interference, man-made interference, satellite active power adjustment and the like is realized.

The invention belongs to the related technical field of time series prediction, and particularly relates to a multi-scale autoregression time series prediction model construction method based on a Next-Scale prediction normal form, which comprises the following steps: in a training reasoning process, introducing a coarse-to-fine scale-by-scale prediction mechanism, firstly, constructing a token sequence of a preset scale through a residual signal, and then, constructing a multi-scale autoregression time series prediction model; preset-scale residual signal prediction depends on a prefix sequence, the loss of scale-by-scale weighting is calculated based on prediction and a target, advancing is carried out in sequence, the prefix sequence is kept visible when all scales are predicted, and stable global context and consistency constraints are provided for all decoding layers. According to the method, a Next-Scale Prediction normal form is introduced, multi-scale representation based on residual errors is put forward, in training, it is ensured that prediction of all scales is mutually conditional, and global and local prediction performance is improved at the same time through multi-scale loss weighted optimization.

Provided are a reinforcement learning (RL)-based traffic signal control (TSC) method and apparatus, a device, a medium, and a product. The TSC method includes: obtaining traffic state data of a target intersection at a current time point and a road network graph, where the traffic state data includes a quantity of lanes at the target intersection and a traffic flow of each of the lanes; inputting the traffic state data and the road network graph into a preset traffic signal prediction model, and obtaining a target phase action output by the traffic signal prediction model, where the traffic signal prediction model includes a spatiotemporal encoder and a return-based action decoder, and the traffic signal prediction model is obtained through training based on return-based contrastive learning; and controlling, based on the target phase action, a traffic light at the target intersection to execute the target phase action.

A detector system for molecular imaging of a radionuclide comprises a 3D semiconductor detector comprising a plurality of sensor stacks of sensors made of a semiconductor material having an average atomic number Z below 40. A read-out circuitry connected to the pixels is configured to output, for each interaction induced by an incident gamma ray in the detector, a signal representative of a time, a position and an energy of the interaction in the detector. The interactions in the detector belonging to a same event induced by the incident gamma ray are predicted based on the output signals and used to estimate a direction of the incident gamma ray and reconstruct an image based on the estimated directions of incident gamma rays.

Disclosed is a method by which an electronic device predicts the location of a UWB signal. The method of the present disclosure may comprise the steps of: generating an input sequence from input data for a preset number of timesteps; generating an output sequence including prediction data for a next timestep from the input sequence using a trained RNN-based model; and obtaining information about a predicted location of the electronic device at the next timestep on the basis of the prediction data in the output sequence. The input data may include UWB DL-TDoA data.

The invention relates to a hyperspectral signal prediction method based on a hyperspectral remote sensing image and pseudo label guidance, and belongs to the technical field of hyperspectral signal prediction. The method comprises the following steps: collecting remote sensing spectral data and soil spectral data, and carrying out primary preprocessing on the remote sensing spectral data; based on a designed series correction algorithm, correcting the remote sensing spectral data after the primary preprocessing by using the soil spectral data, and performing secondary preprocessing; performing imaging on the remote sensing spectrum data after the secondary preprocessing; constructing a double-branch fusion model comprising a spectrum branch and an image branch; constructing a classification pseudo label, and introducing supervised contrast loss to train the double-branch fusion model; and inputting remote sensing spectral data to be predicted into the trained double-branch fusion model to obtain a hyperspectral signal prediction result so as to realize soil content prediction. The objective of the invention is to solve the technical problems of complex noise, low quality and difficulty in guaranteeing prediction accuracy when remote sensing spectral data is acquired in the prior art.

The invention relates to the technical field of satellite navigation and positioning, in particular to a Beidou signal anti-interference method based on space-time state prediction.When the Beidou signal anti-interference method is used, time-space domain parameters, including key information such as directions and phase differences of direct and multi-path signals, of Beidou signals are extracted, and multi-path special suppression measures are combined, so that the anti-interference performance of the Beidou signals is improved; a multi-path signal spectrum peak is subjected to graded attenuation, a positioning result is calibrated in cooperation with a scene correction coefficient, finally, the urban canyon scene positioning precision is achieved, high-precision scene application such as automatic driving and precise surveying and mapping can be stably supported, meanwhile, a prediction model integrating LSTM and Kalman filtering is constructed, a multi-path signal prediction result is output in advance, and the accuracy of urban canyon scene positioning is improved. In cooperation with the rapid matching function of the interference feature library, the method can adapt to the dynamic change of multi-path signals, ensures that interference suppression measures take effect in time, and avoids signal receiving interruption or positioning deviation sudden increase.

The invention discloses a gate valve opening degree control method and device, and relates to the technical field of industrial automation control, and the method comprises the following steps: obtaining valve structure data and actuator types, reading an initial value of a valve position sensor, building a valve position zero point, and loading an initial valve position-flow mapping model; an error is calculated according to the target process variable and the current measured value, and a valve position target value is generated through an outer ring controller; querying the valve position-flow mapping model according to the valve position target value, and performing deviation correction in combination with real-time flow measurement to obtain a corrected valve position target value; the friction state is predicted according to the valve position change rate and the actuator current signal, the friction compensation amount is generated, the corrected valve position target value is corrected, and a final valve position instruction is obtained; and the final valve position instruction is compared with the actual valve position, the driving amount is calculated through an inner ring controller, an actuator is driven to act, and the actual valve position is made to approach the final valve position instruction.

The invention relates to the technical field of communication, in particular to an anti-interference satellite signal capturing antenna suitable for a complex environment. Comprising an environment perception and digital twinning module, a multipath signal prediction and separation module, a synthetic array signal processing module, a beam forming control module, an incremental learning module, a radiation unit module, a temperature compensation module and a multi-system data interface. A direct signal and a characteristic multipath signal can be actively predicted and separated, so that the physical limitation of a traditional antenna is broken through, an anti-interference synthetic wave beam is formed in a polarization domain and a space domain in a combined manner, the wave beam can accurately point to a target satellite, and meanwhile, depth null is generated in a shielding area and an interference source direction; therefore, stable and high-gain acquisition of satellite signals is realized in a complex environment, the antenna system can continuously optimize the model according to real-time signal quality feedback, and the adaptive capability, the anti-interference performance and the long-term reliability of the antenna in a changing scene are improved.

The embodiment of the invention provides an ultrasonic distance measurement chip, an ultrasonic distance measurement device and a self-adaptive threshold generation method. The ultrasonic ranging chip comprises an echo signal processing module, a near-field threshold generator and a near-field decision device, and the echo signal processing module is configured to receive a target echo signal generated by an ultrasonic transducer and generate a near-field echo envelope signal based on the target echo signal; the near-field threshold generator includes a filter configured to obtain a model configuration parameter for the filter, generate an adaptive threshold using the filter based on near-field echo envelope signal prediction, where a gain of the filter is adaptively adjusted based on the model configuration parameter and the near-field echo envelope signal; the near-field decision device is configured to generate first alarm information according to the near-field echo envelope signal and an adaptive threshold. According to the embodiment of the invention, self-adaptive threshold generation during near-field target detection is realized, the false alarm rate and the missed alarm rate of the decision device are reduced, and accurate detection of the near-field target is realized.

The invention provides a medium-voltage grounding fault positioning method and device, a medium and terminal equipment, and relates to the technical field of power grid fault positioning, and the positioning method comprises the steps: obtaining a time sequence traveling wave interference signal based on a historical original voltage signal, and forming a sample data set; based on the sample data set, constructing an interference signal prediction model through an evolutionary algorithm; determining a real-time line mode voltage traveling wave signal, and determining a traveling wave interference prediction signal by using an interference signal prediction model; determining a real-time pure traveling wave signal based on a difference value between the real-time line mode voltage traveling wave signal and the traveling wave interference prediction signal; determining whether a medium-voltage grounding fault occurs or not; and under the condition that the occurrence of the medium-voltage grounding fault is determined, determining the occurrence position of the medium-voltage grounding fault by using the real-time pure traveling wave signal. Through the method provided by the invention, fault traveling waves can be accurately restored, fault detection and positioning are carried out according to the fault traveling waves, the anti-interference capability of medium-voltage grounding fault detection and positioning is improved, and the accuracy of detection and positioning is improved.

The invention discloses a runoff prediction method and device for a target drainage basin, equipment and a medium. The method comprises the following steps: collecting historical multi-source time series data to obtain a standardized input matrix containing meteorological and hydrological characteristics; simulating a natural runoff sequence based on meteorological characteristics and basin physical parameters, and calculating a difference value with actually measured runoff to obtain a regulation and control signal; combining the standardized input matrix and the regulation and control signal into time sequence comprehensive data, dividing the time sequence comprehensive data according to a fixed time length, and inputting the time sequence comprehensive data into an original prediction model for iterative training; setting a dynamic characteristic threshold value by calculating version model parameter variation; removing and testing the sub-features one by one, and reserving target features with an error super-dynamic threshold value to form an optimal feature subset; inputting the control signal and model parameters into a prediction model to obtain a control signal prediction value, and superposing the control signal prediction value with a natural runoff sequence to obtain an actual runoff prediction result. According to the embodiment of the invention, the method achieves the precise prediction of the actual runoff in the designated drainage basin, and can adapt to the runoff non-stationarity caused by human activities.

The application provides a kind of Loran time delay signal prediction method, system, electronic equipment, program product and storage medium, the method comprises: obtaining initial Loran time delay signal;Periodic term of the initial Loran time delay signal is extracted, and input to the multi-periodic term and trend term model constructed;Residual signal between the observation value of initial Loran time delay signal and the output of the multi-periodic term and trend term model is calculated;Wavelet decomposition and threshold denoising are carried out on residual signal;The output of the multi-periodic term and trend term model and the denoised residual signal are fused by adaptive weight mechanism to obtain predicted Loran time delay signal;The certainty periodic term and long-term trend drift of Loran time delay signal are captured by multi-periodic term and trend term model, and non-stationary disturbance is handled using wavelet denoising, which significantly improves the prediction accuracy of Loran time delay, especially suitable for high-precision timing scene in complex electromagnetic environment.

Systems, methods, apparatus, and computer program products for predicting uplink reference signals are provided. One method may include: receiving a probe reference signal (SRS) configuration from a network entity, the SRS configuration including at least one of the following: a first time window during which a first set of one or more SRS transmissions to the network entity will be performed; a first SRS resource set on which the first set of one or more SRS transmissions will be performed; a second time window during which the first set of one or more SRS transmissions will be suspended; or a second SRS resource set to be indicated by an SRS indication from the network entity; performing the first set of one or more SRS transmissions during the first time window; and receiving from the network entity an SRS indication of one or more resources indicating the second SRS resource set.

The application discloses a method for expanding random telegraph noise (RTN) based on a storage neural network, and the signal expansion process is realized based on an artificial neural network of a novel storage unit. According to partial RTN measured signals as a learning set, the expansion process of signal prediction reasoning can realize expansion of the signals with an arbitrary time length, and accelerates extraction of the time parameters of the RTN. The method has important significance for development of a physical unclonable function (PUF) technology based on the RTN and information data security.

The invention discloses an intelligent shared battery replacement cabinet battery management method and system, and relates to the technical field of intelligent Internet of Things, and the method comprises the steps: obtaining a battery state, a user demand and a power grid signal in real time, and forming global state sensing data; constructing a dynamic graph network prediction model, and outputting a battery demand prediction value and a power grid price signal prediction value of each network node in a future preset time period; calculating a power constraint envelope of a corresponding area of each intelligent battery changing cabinet through a layered multi-agent weighing algorithm, and dynamically weighing a target weighing factor corresponding to user waiting time, battery life loss and power grid cost; generating a real-time charging power distribution list of each battery in the battery replacement cabinet by combining the real-time state of the corresponding battery replacement cabinet and the prediction result; and issuing the information to the corresponding intelligent battery changing cabinet. The invention aims to solve the problem that the user waiting time, the battery life loss and the power grid cost cannot be optimized at the same time through a traditional or single-dimension optimization method.

Various embodiments relate to a method and related device and computer-readable storage medium for evaluating a cardiac monitoring device including one or more of the following: receiving an EGM signal from a cardiac monitoring device inserted in a patient, predicting a plurality of potential cardiac episodes experienced by the patient based on the EGM signal, and analyzing the plurality of potential cardiac episodes to evaluate a state of the cardiac monitoring device. For example, the method may include characterizing a health state (e.g., device performance) and / or determining whether a change in device settings may be warranted, based on the predicted cardiac episodes.

The invention discloses an exoskeleton closed-loop stepping control system based on electromyographic signal prediction, which is characterized in that a multi-mode sensing module collects angles of shoulder and elbow joints and electromyographic / force signals of a user in real time, a physical information neural network inference engine is deployed in a microcontroller chip internal memory, receives a state vector constructed by sensing signals, and sends the state vector to a processor; predicting gravity and friction force compensation torque required by each joint in real time; and the flexible power-assisted control unit fuses the predicted compensation torque with the processed user intention torque to generate a total driving torque instruction, and a motor driving module drives a joint motor according to the total driving torque instruction to form high-response closed-loop control. Accurate and real-time fitting of a kinetic model is achieved through the embedded lightweight PINN, the problems that a traditional exoskeleton system is complex in modeling and lagged in response and has a dragging feeling are effectively solved, and low-delay and high-transparency flexible assistance experience is achieved on a single chip.

An example three-dimensional (3D) structure prediction device includes a first encoder, a second encoder, and a feature vector generator. The first encoder generates a first feature map based on two-dimensional (2D) image data corresponding to a target object. The second encoder generates a second feature map based on spectrum data corresponding to the target object. The feature vector generator receives the first feature map and the second feature map, and output a feature vector corresponding to a 3D structure of the target object based on a deep machine learning model.

The embodiment of the invention provides an automatic gain control system and method based on a casing coupling positioning signal. The system is applied to the field of petroleum perforation engineering and comprises an analog front end, a prediction module, a master control module and a bus, and the analog front end comprises an over-temperature protection circuit, an over-current protection circuit, a level translation circuit, a buffer, a programmable amplification circuit and a filter circuit; wherein the level translation circuit is used for converting a bipolar signal into a unipolar signal; the buffer is used for isolating front-stage and rear-stage circuits; the programmable amplification circuit is used for adjusting a gain coefficient; the filter circuit is used for suppressing noise signals; the prediction module is used for pre-judging the voltage amplitude of the casing coupling positioning signal according to the real-time falling speed of the perforating gun; and the main control module is used for processing the falling speed data of the perforating gun, calling the prediction module to output a pre-judgment voltage value, matching an optimal gain coefficient according to the pre-judgment voltage value, and outputting a control instruction to the programmable amplification circuit through a bus, so that the quality of perforating data is improved.

The invention discloses a non-invasive-minimally invasive electroencephalogram signal recording method for deep brain region activity, which comprises the following steps: acquiring a deep electroencephalogram real signal and a first superficial electroencephalogram signal collected by a subject in a first time period and in a minimally invasive state; the second superficial layer electroencephalogram signals are collected by the tested body in a second time period and in a non-invasive state; performing model calibration on the initialized electroencephalogram signal prediction model according to the deep electroencephalogram real signal and the first superficial electroencephalogram signal to obtain a calibrated electroencephalogram signal prediction model; inputting the second superficial layer electroencephalogram signal into the calibrated electroencephalogram signal prediction model for deep prediction to obtain a deep layer electroencephalogram prediction signal of the subject in a second time period; and obtaining deep electroencephalogram record data according to the deep electroencephalogram real signal and the deep electroencephalogram prediction signal. According to the method, the integrity and safety of deep electroencephalogram signal recording can be effectively improved. The invention relates to the technical field of electroencephalogram signal processing.

This application discloses a closed-loop stepping control system for an exoskeleton based on electromyography (EMG) signal prediction. A multimodal sensing module collects real-time shoulder and elbow joint angles and EMG / force signals from the user. A physical information neural network inference engine, deployed in the microcontroller's on-chip memory, receives state vectors constructed from sensor signals and predicts in real-time the gravity and friction compensation torques required for each joint. The compliant assist control unit fuses the predicted compensation torque with the processed user-intended torque to generate a total driving torque command. The motor drive module then drives the joint motors accordingly, forming a high-response closed-loop control. Accurate and real-time fitting of the dynamic model is achieved through embedded lightweight PINN, effectively solving the problems of complex modeling, lag, and dragging sensation in traditional exoskeleton systems. This results in a low-latency, high-transparency compliant assist experience on a single chip.

A control method, an electrical device, and a storage medium (200). The control method comprises: on the basis of a plurality of actual zero-crossing signals of an alternating current of an electrical device, predicting an occurrence period of future zero-crossing signals of the alternating current, and establishing a virtual clock (01); during the operation of the electrical device, performing zero-crossing signal correction on the alternating current on the basis of the virtual clock, so as to obtain a corrected zero-crossing signal (04); and on the basis of the corrected zero-crossing signal, controlling the electrical device to operate (05).

The application provides a multi-directional stress prediction method, device and equipment in a milling cutter milling process and a storage medium. It relates to the field of numerical control machine tool processing digital twin technology. The method comprises: obtaining small sample experimental data based on an orthogonal test method, time-frequency decomposition of the milling force test signal, and extraction of multi-dimensional features of the milling force dynamic characteristics; analyzing the correlation between the processing parameters and the features, screening the key features, establishing a physical mapping model of the process parameters to the key features and solving the cutting coefficients; constructing a time-varying signal prediction model based on a recurrent neural network, predicting the multi-directional dynamic milling force of the milling cutter with the key features in the small sample test data; and based on the cutting coefficient, designing an adaptive filter to post-process and optimize the predicted signal and inverse normalize it, and output the final prediction value. Based on small sample data, the application can accurately predict the multi-directional dynamic stress of the milling cutter only with the process parameters, and effectively improve the virtual-real mapping and dynamic optimization capability of the processing process.

Embodiments of the present disclosure provide an ultrasonic ranging chip, an ultrasonic ranging device and a self-adaptive threshold generation method. The ultrasonic ranging chip comprises an echo signal processing module, a near-field threshold generator and a near-field decision maker. The echo signal processing module is configured to receive a target echo signal generated by an ultrasonic transducer and generate a near-field echo envelope signal based on the target echo signal. The near-field threshold generator comprises a filter configured to obtain a model configuration parameter for the filter, and use the filter to predictively generate a self-adaptive threshold based on the near-field echo envelope signal, wherein the gain of the filter is adaptively adjusted based on the model configuration parameter and the near-field echo envelope signal. The near-field decision maker is configured to generate first alarm information according to the near-field echo envelope signal and the self-adaptive threshold. The embodiments of the present disclosure realize adaptive threshold generation in near-field target detection, reduce the false alarm rate and the missed alarm rate of the decision maker, and realize accurate detection of near-field targets.

The invention relates to a method and a device for deducting frequency drift of a hydrogen atomic clock. The method comprises the following steps: acquiring a historical frequency signal which is output by the hydrogen atomic clock and traces first time forward from a current moment; performing wavelet decomposition on the historical frequency signal to obtain a plurality of component signals; performing long-term stability analysis on each component signal, taking the component signal with the worst long-term stability as a long-term component signal, and taking the other component signals as general component signals; predicting a component signal corresponding to the long-term component signal in a future second time; predicting a component signal corresponding to each general component signal in a second time in the future; coupling the predicted component signals in the second time in the future to obtain predicted frequency signals in the second time in the future; determining a predicted frequency deviation sequence in a second time in the future; and in the second time in the future, performing frequency drift deduction on the frequency signal output by the hydrogen atomic clock based on the predicted frequency deviation sequence in the second time in the future.

The invention discloses an extreme cold event prediction method based on a multi-time-scale climate oscillation signal, and relates to the technical field of meteorological prediction. The method comprises the following steps: acquiring climate oscillation signal prediction data of multiple time scales; carrying out initial judgment according to the ENSO index: if the ENSO index is greater than or equal to 0, judging the risk as a 0-level risk, and outputting a code 000; if the ENSO index is less than 0, entering a PDO index judgment step; respectively entering a positive PDO sub-process or a negative PDO sub-process according to positive and negative PDO indexes; judging whether the MJO is at the second or third phase and the amplitude of the MJO is Agt in each sub-process by combining an MJO index; the method comprises: 1, determining a final risk level and an output code; the output result includes a risk level and an output code representing a trigger condition. The Taiwan strait extreme cold event prediction method can predict the Taiwan strait extreme cold event in China according to the three different time scale climate oscillation signals of the PDO phase, the ENSO phase and the MJO activity, and the prediction precision is improved.

The invention provides a method and device for predicting multidirectional stress in the milling process of a milling cutter, equipment and a storage medium. Relates to the technical field of numerical control machine tool machining digital twinning. The method comprises the following steps: acquiring small sample experimental data based on an orthogonal test method, performing time-frequency decomposition on a milling force test signal, and extracting multi-dimensional characteristics of milling force dynamic characteristics; analyzing the correlation between the processing technological parameters and the features, screening key features, establishing a physical mapping model from the technological parameters to the key features, and solving a cutting coefficient; constructing a time-varying signal prediction model based on a recurrent neural network, and predicting the multidirectional dynamic milling force of the milling cutter under small sample test data by using the key features; and designing an adaptive filter based on cutting coefficient constraint to perform post-processing optimization and inverse normalization on the predicted signal, and outputting a final predicted value. According to the method, based on the small sample data, the multi-directional dynamic stress of the milling cutter is predicted in a high-precision mode only through the technological parameters, and the virtual-real mapping and dynamic optimization capacity in the machining process is effectively improved.