472 results about "Non linear dynamic" patented technology

The invention relates to the technical field of structural health monitoring and intelligent diagnosis, in particular to a structural fatigue damage identification method based on acoustic emission and deep learning, and the method comprises the steps: collecting a structural response signal under a fatigue load through an acoustic emission sensor array, inputting the structural response signal to a CNN-BiLSTM-Attention mixed deep learning model, and carrying out the recognition of the structural fatigue damage through the CNN-BiLSTM-Attention mixed deep learning model; the model extracts local time domain features through a dynamic adaptive convolution kernel, captures long time sequence dependence by using a bidirectional long-short-term memory network, focuses key damage features through a bimodal space-time attention mechanism, divides damage stages based on a nonlinear dynamic threshold algorithm of fracture opening amount, constructs a training data set of physical-data fusion, and performs dynamic time domain feature extraction. The learning rate is optimized by adopting a gradient sensitive cosine annealing algorithm, and the robustness of the model is improved in combination with an anti-noise and anti-loss function. The method integrates physical characteristics and an intelligent algorithm, and has the advantages of adaptive noise suppression, strong cross-domain generalization ability, high real-time performance and the like.

The invention relates to an intelligent power distribution harmonic monitoring and dynamic compensation system which comprises a monitoring unit, a correction unit and a compensation unit. The monitoring unit continuously collects high-frequency harmonic voltage and current data in a distribution line at a high sampling frequency, extracts transient harmonic components through wavelet packet transformation and empirical mode decomposition, and generates low-dimensional feature vectors based on sparse representation. And the correction unit decodes the low-dimensional feature vector, recovers harmonic time-frequency features, calculates a phase drift rate, predicts a harmonic propagation path and an accumulation node by combining real-time power distribution network topology construction and adopting a nonlinear dynamic prediction model, and generates a correction instruction when abnormality is detected. And the compensation unit adopts pulse sequence density modulation to dynamically adjust a compensation current phase according to the correction instruction, and meanwhile, an inductive coupling device is utilized to transfer harmonic energy to a low-risk node, so that harmonic voltage distortion of a target node is quickly recovered to a stable level in a fundamental wave period after early warning.

A 100-meter gridded spatialization method for carbon emissions of different land use types based on multi-source heterogeneous data is provided, including the following steps: S1, fitting Luojia-1A Satellite nighttime light data year by year with defense meteorological satellite program-operational linescan system (DMSP-OLS) and national polar-orbiting partnership-visible infrared imaging radiometer (NPP-VIIRS) fused 1-kilometer gridded nighttime light data, performing additive fusion on previous light data and current light data, introducing a time inertia weight factor to improve particle swarm optimization-back propagation (BP) neural network algorithm, and forming 100-meter nighttime light data correctable on a long time series; and S2, simulating a complex nonlinear dynamic changing relationship between multilevel 100-meter gridded data of different land use types in different industries and energy carbon emissions in different industries based on the 100-meter nighttime light data, and establishing a 100-meter spatialization inversion model for energy carbon emissions of different land use types in different industries.

The invention relates to the field of transformer parameter regulation and control, in particular to a parameter optimization method and device for a coupling type transformer. The method comprises the following steps: acquiring multi-dimensional real-time working monitoring parameters and real-time working environment state parameters of the coupling type transformer; performing nonlinear dynamic analysis and global state sensing modeling on the multi-dimensional real-time working monitoring parameters so as to construct a transformer global state sensing model; performing multi-parameter combination definition on the multi-dimensional real-time working monitoring parameters, performing dynamic operation simulation based on a transformer global state sensing model, and collecting operation simulation response data of a plurality of schemes; performing multi-target dynamic balance analysis on the operation simulation response data of the plurality of schemes to obtain an optimal transformer working parameter combination; and carrying out environment dynamic parameter change analysis on the real-time working environment state parameters, and constructing a real-time environment condition distribution field. According to the invention, efficient and self-adaptive adjustment transformer parameter optimization is realized.

Provided is a self-adaptive identification method for nonlinear dynamic parameters of a reducer, which belongs to the design field of a reducer. The method includes: modeling a harmonic reducer corresponding to a flexible joint as a concatemer of a rigid reducer and an elastic torsion spring, and carrying out dynamic theoretical modeling and parameter variable independence processing on the concatemer to form a dynamic equation for parameter identification; giving an optimized motion trajectory to each joint of a robot and controlling the robot to act accordingly, acquiring relevant data needed for parameter identification based on a built-in torque sensor and double encoders inside the joint; using an offline identification algorithm to accurately identify a plurality of dynamic parameters of a collaborative robot considering joint flexibility and friction, and obtaining a minimum parameter set.

The invention relates to the technical field of data processing and information fusion, and provides a multi-source heterogeneous data fusion method and system, and the method comprises the steps: carrying out the multi-dimensional quality evaluation of at least three heterogeneous data sources; on the basis of a quality evaluation result, feature decoupling and cross-modal correlation analysis of the heterogeneous data source are executed, and an intermediate feature set with a space-time alignment characteristic is generated; constructing a nonlinear dynamic weight distribution model, and calculating a multi-dimensional credibility weight of each data source; performing fusion calculation on the intermediate feature set through a three-level joint optimization architecture; and dynamically correcting the fusion result by adopting a feedback type self-adaptive calibration mechanism, and outputting an optimized fusion data cube. According to the invention, the accuracy, consistency and reliability of fused data can be improved.

The invention discloses a pile foundation integrity detection method which comprises the following steps: applying a variable amplitude sound wave excitation sequence to a pile foundation structure, collecting acoustic response signals under different excitation amplitudes, and obtaining nonlinear dynamic response data reflecting material rheological characteristics; performing frequency dispersion analysis and hysteretic characteristic analysis on the nonlinear dynamic response data, extracting a stress memory dissipation coefficient and a nonlinear memory capacity index, and establishing a time-varying characteristic curve; according to an abnormal change interval and a memory capacity fading rate of the time-varying characteristic curve, determining a defect position and a defect type, and obtaining an evolution state parameter of the defect; and based on the historical change trend of the evolution state parameters, the material degradation rate and the structure damage development rate are calculated, the health state index of the pile foundation structure is predicted, and a full life cycle performance evolution curve is formed. Through stress memory activation and nonlinear dynamic response analysis, the detection method considering the rheological property of the material is established, and the performance evolution rule of the pile foundation in the whole life cycle can be accurately evaluated.

The invention relates to a self-adaptive pressure regulation vacuum pump closed-loop control system and method. The system comprises a model building module which is used for acquiring real-time data flow of a vacuum pump and building a nonlinear dynamic model to obtain a pressure-flow-power feature mapping relation; the predictive analysis module calculates a pressure-flow predictive value based on the relationship and compares the pressure-flow predictive value with the real-time power data for analysis. And generating a parameter adjustment instruction once the deviation value exceeds a preset threshold value. And the control scheme generation module corrects the control parameters according to the parameter adjustment instruction and generates an optimized power adjustment scheme. And if the data is abnormal, generating a state update value. And the control scheme updating module fuses the state updating value and the pressure-flow prediction value to obtain an optimized model parameter so as to adjust a weight coefficient of an adaptive control strategy and generate a control scheme. The system effectively improves the accuracy of vacuum pump pressure control, greatly enhances the ability of the system to deal with abnormal conditions and equipment performance changes, and ensures long-term stable operation of the vacuum pump.

The invention discloses a GIS ultrahigh frequency partial discharge abnormity early warning method and system, and relates to the technical field of power equipment fault diagnosis, and the method comprises the steps: collecting a pulse signal, carrying out the time domain normalization and leading edge detection, constructing a four-dimensional spatial-temporal feature matrix based on a detection result, and generating a structured spatial-temporal feature tensor through a coding rule; dividing the structured spatial-temporal characteristic tensor into a plurality of sub-matrixes according to a time window, reconstructing a six-dimensional phase space through an optimal embedding dimension and a time delay algorithm, and deeply fusing the reconstructed six-dimensional phase space with chaotic dynamic characteristics through a coupling equation to generate chaotic trajectory data; extracting kinetic parameters based on the chaotic trajectory data, and fusing the kinetic parameters through a deep learning model to generate a discharge anomaly risk score; according to the method, through phase-space reconstruction and chaos dynamics modeling, the nonlinear dynamic characteristics of partial discharge are accurately captured, and the prediction precision of the abnormal state is remarkably improved.

The invention discloses a diagnostic method for performance detection of a pressure sensor, and relates to the technical field of sensor equipment. Comprising the following steps: initializing a pressure sensor, sensitivity and response time under different pressures, dynamic response characteristics in a rapidly changing pressure environment, changes under different temperature conditions, anti-interference capability to external factors, long-time stability, and existence of non-linear errors and zero drift; and the overall performance of the pressure sensor is comprehensively evaluated. According to the diagnosis method, the dynamic response, the anti-interference capability, the temperature adaptability and the long-term stability of the sensor can be comprehensively quantified by setting the dynamic response characteristic model and multi-working-condition environment simulation. According to the method, neglected nonlinear dynamic behaviors in a traditional evaluation means can be captured, the potential performance problem of the sensor in a complex working environment can be effectively revealed, optimization design and application deployment are guided, and the reliability and precision of the sensor in an actual scene are remarkably improved.

The invention discloses a finite time tracking adaptive control method for a mechanical arm based on a neural network, and relates to the technical field of industrial robot control. The method comprises the following steps: constructing a kinetic model of the mechanical arm, obtaining an existence form of an unknown nonlinear term in the model, and defining a joint position tracking error and an error change rate of the mechanical arm; constructing a sliding mode dynamic equation based on the tracking error and the error change rate; a BP neural network is adopted to approach the unknown nonlinear dynamic state of the mechanical arm, and the mapping relation between a network input vector and an output vector is determined; combining a sliding mode dynamic equation with BP neural network output, and designing a finite time control method including adaptive gain; and a self-adaptive updating method of BP network weight and sliding mode gain is deduced, so that the tracking error of the mechanical arm is converged to a zero neighborhood within preset time, and self-adaptive control of the mechanical arm is completed. According to the method, high-precision trajectory tracking within the preset time can be realized, and the anti-interference capability is high.

The invention discloses a robot vision-inertia SLAM method and device and a medium, and belongs to the technical field of computer vision and robot navigation. The method comprises the following steps: synchronously acquiring images and inertial data through a robot binocular camera and an IMU, performing feature enhancement on an original image in combination with a pre-trained deep learning model, introducing an adaptive brightness compensation mechanism and designing an image light supplementing module based on a generative adversarial network (GAN), recovering low-illumination image details, and improving the image quality of a low-illumination area; an entropy-based adaptive dynamic interference rejection algorithm is provided, and dynamic interference feature points are rejected in combination with IMU (Inertial Measurement Unit) data; a low-rank approximate improved graph optimization algorithm is adopted, and global map construction and pose optimization are accelerated; and through entropy-based nonlinear dynamic smoothing coefficient adjustment, the track stability is improved. According to the method, the positioning precision and robustness in a low-light environment are improved, the calculation efficiency is improved, and dynamic interference is effectively resisted.

The invention discloses a micro-grid dynamic scheduling method based on deep learning, and the method comprises the steps: fusing industrial Internet of Things collection and GIS positioning, and constructing a multivariable original spatio-temporal data set covering multiple nodes; extracting multi-scale features through multi-resolution wavelets and Fourier transform, combining the multi-scale features with a dynamic adjacency matrix, and realizing feature adaptive distribution and nonlinear dynamic modeling by using multi-scale attention gating, graph convolution and a time sequence neural network model; the micro-grid load and state prediction accuracy, the system generalization ability and the abnormal response level can be effectively improved, and powerful support is provided for intelligent scheduling and abnormal analysis.

The invention discloses an efficient refrigerating machine room air conditioner energy-saving intelligent control system and method, and relates to the field of air conditioner intelligent control. The method comprises the steps that air conditioner operation parameters, machine room equipment operation data and machine room environment data are collected and preprocessed; building a deep neural network by using a deep Q-learning reinforcement learning algorithm to obtain a thermal load demand of the machine room; introducing a nonlinear dynamic compensation function to calculate an air-conditioner dynamic energy efficiency coefficient and air-conditioner refrigeration power, and calculating the rotating speed of an air-conditioner compressor by referring to air-conditioner operation parameters; a PID (Proportion Integration Differentiation) controller is used for carrying out primary frequency conversion on a machine room air conditioner, and a multi-stage adjusting mechanism is used for correcting a primary frequency conversion result in real time according to machine room equipment operation data, machine room environment data change and frequency conversion conditions. According to the air conditioner energy-saving control method, efficient air conditioner energy-saving control is achieved by combining the deep Q-learning reinforcement learning algorithm, the nonlinear dynamic compensation function and the PID controller.

The invention belongs to the technical field of crossing of environmental engineering and ocean dynamics, and particularly relates to a tidal dynamics prediction method and control device for a seawater desulfurization system, and the method comprises the steps: constructing a time-space coupling prediction model fusing multi-source hydrological observation data, and introducing a nonlinear dynamic weight distribution mechanism; the influence of terrain constraint, wind stress disturbance and upstream runoff on tidal propagation is quantified in real time, and a rolling prediction sequence of tide level phase, flow velocity gradient and salinity disturbance in the next three hours is output; the prediction result drives the scheduling of a desulfurization pump set, the adjustment of spraying density and the matching of aeration intensity, and the model weight is corrected on line based on the actually measured feedback of desulfurization efficiency to form closed-loop control. By means of the technical scheme, accurate cooperation of the operation parameters of the desulfurization system and tidal dynamics is achieved, meaningless energy consumption is reduced while the desulfurization efficiency is guaranteed, and the utilization rate of the desulfurization agent and the stability of the system are improved.

The invention discloses a grid-connected inverter parameter optimization method based on an improved genetic particle swarm algorithm. The grid-connected inverter parameter optimization method comprises the following steps: constructing a target function; performing population position initialization; calculating a fitness value of each particle at an initial moment, recording an optimal solution, and storing initial global optimal particle and individual optimal particle information; random disturbance is added to the speed and the position of the particles; updating the speed and the position of the particle; performing multi-point crossover and mutation operation; according to the current optimal solution, carrying out local domain search by adopting a fine search mode based on Laplacian distribution and carrying out global neighborhood search by adopting a search mode based on Cauchy distribution; and checking convergence conditions, if convergence occurs, outputting an optimal solution, and obtaining optimal parameters of the grid-connected inverter system. The method has the remarkable effects that by optimizing three key parameters in a control system and utilizing a nonlinear dynamic strategy to enhance the global search capability and the convergence speed of the algorithm, various defects in the prior art can be overcome.

The invention relates to a time synchronization maintaining method assisted by temperature sensing, and belongs to the technical field of time synchronization. The method comprises the following steps: for a network communication scene in which synchronous information interaction cannot be carried out between equipment due to a main clock fault or communication link interruption, considering the characteristic that the output frequency of an equipment clock crystal oscillator presents nonlinear dynamic time varying due to environment temperature change; constructing a time sequence prediction model based on the TimeNet neural network and suitable for the non-external connection; training the model by using clock parameter data and temperature information which are historically recorded; using the trained model to take the environment temperature information as the input of the model, and predicting the clock frequency offset of the slave node; and the clock phase offset of the slave node is calculated by using the predicted clock frequency offset and a frequency offset autoregressive state transition equation, and the slave node corrects a local clock and realizes clock self-holding with the master node by using the clock frequency offset and a clock phase offset value.

The invention discloses a high-temperature surface contact thermal resistance elimination method based on double thermocouple compensation, and belongs to the technical field of material thermal property characterization and testing. The method comprises the following steps: synchronously acquiring double-thermocouple temperature, and obtaining a temperature difference signal through filtering calibration and environment correction; calculating the real-time heat flux density according to the corrected temperature difference, the Seebeck coefficient and the dynamic correction factor; establishing a nonlinear dynamic coupling model containing contact thermal resistance parameters, and performing temperature interval division; identifying a contact thermal resistance parameter on line by adopting a self-adaptive recursive least square algorithm, and generating a dynamic thermal resistance compensation value; and applying the compensation value to a double-thermocouple signal according to the weight, and outputting accurate high-temperature surface temperature. According to the method, data acquisition and preprocessing, dynamic heat flow correction, nonlinear segmented modeling, self-adaptive online identification and refined compensation output strategies are adopted, the influence of high-temperature surface contact thermal resistance can be effectively eliminated, and the accuracy and reliability of temperature measurement in the high-temperature environment are remarkably improved.

The invention relates to the field of remote monitoring, in particular to a stem cell culture process monitoring method based on the Internet of Things. Comprising the steps that environmental parameters are collected, sensor data are obtained, the sensor data are verified through a median filtering algorithm, and whether the sensor data are abnormal or not is judged; based on the sensor data marked as normal, calculating by using a nonlinear dynamic coupling analysis algorithm to obtain an environment state index; based on the environment state index, using a non-linear state monitoring prediction algorithm to predict and obtain an environment state index at a future moment; based on the predicted environmental state index of the future moment, using an intelligent early warning trigger algorithm based on environmental state prediction to obtain an early warning state, and generating an early warning signal according to the early warning state; and based on the early warning signal, a dynamic feedback adjustment algorithm is used to automatically generate a control signal. The technical problem that normal operation is interfered due to the fact that a wrong early warning signal is easily triggered by misjudgment when the environment state changes critically is solved.

The invention relates to the technical field of oral health monitoring, and discloses an oral detection method based on an intelligent tooth socket. The method comprises the following steps: acquiring an original oral cavity pressure time sequence and frequency domain characteristics through an intelligent tooth socket, determining an optimized decomposition parameter, and performing multi-scale decomposition on an original signal to generate a multi-scale oral cavity signal component; nonlinear dynamic features are extracted, a component complexity index is obtained, and key signal components related to oral health are screened out; generating a personalized physiological response frequency in combination with the user oral cavity baseline features, the real-time occlusion state and the component complexity index; reconstructing an oral cavity physiological feature sequence based on the key signal component and the personalized physiological response frequency, and separating a low-frequency component and a high-frequency component through modal decomposition; identifying oral cavity abnormity categories according to the two components, establishing a mapping relation with a diagnosis result, and generating an oral cavity health detection instruction. According to the method, convenient and comprehensive oral cavity detection can be realized, the detection adaptability and precision are improved, and support is provided for oral cavity health management.

A method and system are provided for identifying time-varying suspension characteristics of heavy-load vehicles. The method includes collecting sequential control state data of a mining truck using sensors, predicting parameter-related factors through a deep learning network, estimating suspension stiffness and damping coefficients via a linear dynamic model considering longitudinal-vertical coupling, and predicting future system states through a nonlinear dynamic model based on the estimated parameters and learned factors. According to the method, a deep learning network is integrated into a physical model of the mining truck, an accurate longitudinal-vertical dynamical model of the mining truck is established, accurate suspension parameters are identified, the stiffness damping time-varying characteristics of the suspension of the mining truck are given through a physical model-data driving method, and the model has certain interpretability and generalization; the rigidity and damping of the four suspensions can be obtained only through sprung information.

The invention relates to the technical field of smart power grids, and discloses a hierarchical safety early warning method based on smart power grid analog simulation, and the method comprises the following steps: S1, collecting the operation data of a smart power grid, including the real-time monitoring data of voltage, current, power factor and temperature, and processing the collected operation data; s2, optimizing estimation of a power grid state by using an extended Kalman filtering algorithm; s3, establishing a nonlinear dynamic model of the smart power grid, and predicting the health state of the power grid according to the dynamic behavior of the power grid; and S4, constructing a Bayesian network model, evaluating the risk of the power grid through probabilistic reasoning, and judging the health condition of the power grid. According to the invention, through combination of intelligent power grid analog simulation, deep reinforcement learning and adaptive optimal control, intelligence, adaptive adjustment and real-time response capability of the power grid early warning system are realized, and stability and emergency response efficiency of the power grid in a complex environment are improved.

The invention provides a high-precision electric energy metering and fault diagnosis method adaptive to multiple working conditions, and the method comprises the following steps: carrying out the multi-rate synchronous sampling of an electric parameter through a double-AD parallel sampling architecture, collecting a fundamental wave voltage / current signal through a low-speed AD module at a sampling rate of 4kHz, capturing a high-frequency harmonic wave and a transient signal through a high-speed AD module at a sampling rate of 256kHz, and carrying out the fault diagnosis of the high-frequency harmonic wave and the transient signal; a sampling mode is dynamically switched according to the load harmonic content; a sliding window mechanism is adopted to carry out multiple times of repeated detection on the same electric parameter, five times of independent measurement are completed in a 200ms time window, an outlier is eliminated based on a Pauta criterion, then a weighted mean value of a signal-to-noise ratio is calculated, AD reference voltage is calibrated in real time through a PT100 temperature sensor, and the accuracy of the AD reference voltage is improved. Carrying out nonlinear dynamic compensation by combining a cubic spline interpolation method of a pre-stored load characteristic curve; and constructing a composite electric energy calculation model, summing the fundamental wave electric energy and the harmonic electric energy weighted according to the standard to generate a total electric energy value, and comparing a metering result with a theoretical value in real time by using a digital phase-locked loop.

The invention provides a robust high-precision tracking control method based on a dynamic sliding mode surface. The method comprises the following steps: 1, constructing a driver model; 2, introducing a nonlinear dynamic function term, a high-order error term and an integral term of a displacement error into the dynamic sliding mode surface; and 3, constructing a robust high-precision tracking sliding mode controller based on the dynamic sliding mode surface and the driver model obtained in the step 2. 4, inputting the displacement error of the driver into the sliding mode controller; and the sliding mode controller outputs a voltage signal to the piezoelectric actuator. The nonlinear dynamic function term, the high-order error term and the integral term of the displacement error are introduced into the dynamic sliding mode surface, the transient response speed of the sliding mode surface is improved through the integral term, and the steady-state error of the sliding mode surface is reduced; the nonlinear dynamic function improves the response speed and robustness of the sliding mode surface; the high-order error term enables the sliding mode surface to be more sensitive to error changes.

The invention provides a self-adaptive algorithm and system for improving frequency measurement precision and response speed of a speed regulator. The method comprises the following steps: Step 1, signal acquisition and preprocessing; step 2, dynamically adjusting filtering parameters, and suppressing power grid signal noise; 3, extracting frequency characteristics in real time, and improving the frequency measurement resolution; 4, a synchronous clock is adopted as a reference frequency source, a clock reference value is periodically and automatically corrected, and long-term drift is eliminated; 5, a nonlinear dynamic model of the hydroelectric generating set is constructed, the nonlinear relation between the valve opening degree and output of the speed regulator is compensated in real time, and the frequency modulation precision is improved; and step 6, outputting the instantaneous frequency. According to the scheme, through the self-adaptive frequency measurement algorithm, high-precision clock calibration, a hardware acceleration mechanism and a nonlinear compensation strategy, a multi-dimensional optimization system is constructed, high-precision frequency measurement is carried out, a rapid effect can be achieved, and a hydroelectric system has long-term stability and high adaptability.

The invention discloses a shape adaptive planning and control method for a deformable unmanned aerial vehicle, and the method comprises the steps: carrying out the searching based on an occupied grid map of a scene through employing a variable-size kinematics A * path planning algorithm, and obtaining an initial path; by taking the initial path as an initial condition, shape-adaptive trajectory optimization in a continuous space-time space is carried out to obtain an optimized trajectory, and in the trajectory optimization process, the mass center position and deformation parameters of the unmanned aerial vehicle are optimized at the same time; and based on the optimized trajectory, on the basis of a nonlinear model predictive controller and by combining an incremental nonlinear dynamic inverse algorithm, calculating and compensating external force disturbance and external torque disturbance caused by deformation of the unmanned aerial vehicle and a load, so as to realize shape adaptive control of the deformable unmanned aerial vehicle.

The invention relates to the field of cold-chain transportation, and discloses an aquatic product cold-chain quality monitoring and tracing method, which comprises the following steps: acquiring multivariable environmental data in cold-chain transportation; based on the multivariable environment data, constructing a dynamic coupling model of a cold chain environment for representing a nonlinear dynamic relationship among environment variables; performing real-time estimation on the cold chain environment state by using a dynamic monitoring algorithm, and predicting the future change of the cold chain environment state; constructing a target function, and optimizing the operation parameters of the cold chain equipment according to the dynamic change of the cold chain environment; constructing a mapping model between the cold chain environment and the aquatic product quality, and dynamically evaluating the quality index of the aquatic product according to the historical change of the environment; and generating a traceability report based on the evaluation result, wherein the traceability report comprises a dynamic record of the cold chain environment and an aquatic product quality change curve. Dynamic monitoring, quality tracing and system optimization of the whole cold-chain transportation process can be realized, and the stability of the cold-chain environment and the aquatic product quality guarantee capability are improved.

The invention relates to the field of power transmission line channel risk hidden danger monitoring, and provides a data fusion power transmission line channel risk hidden danger monitoring method and system, and the method comprises the steps: collecting the multi-modal sensing data of a power transmission line channel, and generating a multi-modal data flow of a unified time-space coordinate; constructing a three-dimensional space point cloud through a phase unwrapping and stereo matching fusion algorithm, and fusing multi-modal data to generate a space probability tensor; extracting risk semantic latent variables, constructing a Bayesian network and identifying potential risks; performing tensor product on the potential risk and the environmental data to generate a dynamic risk enhancement feature matrix, and constructing a nonlinear dynamic threshold curved surface through quantum annealing and Gaussian process regression; a mechanical equation is constructed, Gaussian kernel density estimation and numerical simulation are combined, the evolution trajectory of the risk in the space-time dimension is predicted, and a risk thermodynamic diagram and early warning information are generated; and generating a structured risk early warning report by adopting a natural language processing method. And the accuracy of power transmission line channel risk hidden danger monitoring is improved.

The invention discloses a sea surface temperature prediction method and device based on a multivariable time series, and belongs to the field of meteorological ocean data processing and prediction.The sea surface temperature prediction method comprises the steps that sea surface temperature and meteorological factor data are collected from multi-source observation data of a target area, the collected data are preprocessed, and cleaned time series data are obtained; building a sea surface temperature prediction model based on a multivariable time sequence, wherein the sea surface temperature prediction model comprises a variable embedding layer, a lag feature embedding layer, a Transform encoder, a linear modeling layer, an output layer and a RevIN module for performing normalization and de-normalization processing on non-stationary data; training the established sea surface temperature prediction model by using the preprocessed data; and predicting the day-by-day sea surface temperature of the future 30 days by adopting the trained sea surface temperature prediction model. According to the invention, the nonlinear dynamic change of the sea surface temperature can be effectively captured, and the prediction precision of the sea surface temperature is significantly improved.

The invention discloses a lithium battery recession track dynamic prediction system based on deep learning, and the system comprises a data collection module which is used for collecting the related data of a lithium battery; the feature extraction module is used for performing multi-dimensional feature fusion on the related data of the lithium battery, obtaining a fusion feature vector and sending the fusion feature vector to the trajectory prediction module; the trajectory prediction module is used for receiving the fusion feature vector, inputting the fusion feature vector into a prediction model, and performing decline trajectory prediction on the lithium battery through the prediction model; the updating module is used for dynamically updating prediction model parameters by utilizing an incremental learning algorithm; and the visualization module is used for carrying out dynamic mapping based on decline trajectory prediction and lithium battery related parameters, and generating an interactive decline trajectory thermodynamic cloud picture and a residual service life probability distribution curved surface. According to the method, the residual service life probability distribution is output by capturing the nonlinear dynamic change and the long and short term dependency relationship in the lithium battery recession process, and quantitative analysis of prediction uncertainty is realized.