1367 results about "Non linear mapping" patented technology

This invention relates to a gait emotion recognition method, system, storage medium, and computer device based on spatiotemporal graph convolution. The method includes the following steps: S1, data augmentation by reversing the temporal direction of gait; S2, obtaining deep emotion features and prior emotion features respectively through a spatiotemporal graph convolutional network and prior feature statistical methods; S3, performing nonlinear mapping on the prior emotion features using a feature mapping layer; S4, inputting the fused features of the deep emotion features and prior emotion features into an emotion classifier to obtain the emotion category. The feature mapping layer of this invention achieves more effective feature fusion by performing nonlinear mapping on prior features; it also introduces causal temporal convolution to replace general temporal convolution, effectively extracting fine-grained temporal features by enhancing temporal correlation and cross-period feature fusion. Furthermore, a walking direction recognition auxiliary task is designed to accelerate the training and convergence speed of the model, enhancing the ability to extract temporal-dependent features and the performance of emotion recognition.

The invention relates to the technical field of anomaly detection, and discloses a context-aware-driven multi-dimensional anomaly detection early warning method. The method comprises the following steps: collecting real-time context data in a target monitoring scene, and generating an initial feature set containing an environment parameter sequence and a behavior pattern map; a first detection model and a second detection model matched with the scene type are constructed according to the scene types, the first model comprises a dynamic correlation function of environment indexes and abnormal probabilities, and the second model comprises a nonlinear mapping rule of behavior characteristics and risk levels; and based on the real-time context deviation degree and the characteristic fluctuation coefficient, a target model is triggered to generate a dynamic early warning instruction, and the dynamic early warning instruction is pushed to an execution module to adjust a trigger threshold of an abnormal response strategy or a priority of a risk disposal process. According to the method, multi-dimensional data is combined, the adaptability and accuracy of anomaly detection are improved through dynamic model triggering and response strategy adjustment, and the method is suitable for various monitoring scenes.

The invention discloses an aircraft surface flow field intelligent reconstruction method and system based on multi-source data fusion, and belongs to the technical field of flow field intelligent prediction. Acquiring multi-source sensor data on the surface of the aircraft, and constructing a multi-source data set; a flow field reconstruction model based on Transform is constructed; a multi-source data set is adopted to train a flow field reconstruction model; and outputting an aircraft surface flow field reconstruction result based on the trained flow field reconstruction model, and visually displaying the aircraft surface flow field reconstruction result. Based on the strong nonlinear mapping capability of the deep learning model, through training of a large amount of sensor data, high-order correlation characteristics among pressure, heat flow and friction resistance stress can be automatically extracted, through fusion of sparse discrete data, a continuous physical field of the whole surface of the aircraft can be effectively reconstructed, and the method is suitable for the aircraft. The limitation of a traditional analytical model in dealing with a strong nonlinear problem is broken through, and the precision and reliability of aircraft flow field prediction are improved.

The invention provides a soft rock tunnel surrounding rock parameter dynamic identification method and system based on data driving, and relates to the technical field of underground tunnel mechanical parameter dynamic identification, and the method comprises the steps: obtaining multi-element tunnel surrounding rock parameters, and building a joint probability distribution model of the multi-element surrounding rock parameters based on a Copula theory; performing Monte Carlo simulation, and generating a high-dimensional parameter sample library meeting physical constraints in the parameter constraint space based on the joint probability distribution model; establishing a tunnel three-dimensional numerical model and performing automatic numerical simulation to generate multivariate response data; constructing a Kriging agent model of a Gaussian kernel function based on multivariate response data training, establishing a nonlinear mapping relation between parameter input and deformation output, constructing an inversion objective function by taking the minimum root-mean-square error of multi-measurement-point displacement as an objective, and performing inversion solution by using an adaptive particle swarm optimization algorithm to obtain inversion identification parameters, and a dynamic feedback mechanism is constructed to realize adaptive tracking of the time-varying characteristics of the surrounding rock parameters.

The invention relates to the technical field of medical information, in particular to an intelligent prediction model and method for postoperative complications of anesthetized patients, and the method comprises the steps: collecting preoperative to postoperative complete-cycle clinical data of a patient through a medical data interface; analyzing operation codes to generate risk features, extracting vital sign dynamic features, and establishing a complication probability mapping relation through a multi-modal fusion network; combining the complication probability and pharmacokinetic parameters to construct an optimization model, and solving an individualized anesthetic dosage interval by using a gradient descent algorithm; vital signs are dynamically monitored in the operation, a dose re-optimization mechanism is triggered, the infusion rate is adjusted, and a closed-loop control link is formed; and generating a visual decision report. According to the method, through deep integration of complete-cycle clinical data and multi-modal feature modeling, preoperative physiological parameters, operation coding semantic information and intraoperative vital sign dynamic modes are subjected to fusion analysis, a nonlinear mapping relation between dosage and complication probability is constructed, and the risk prediction precision and individualized adaptability are remarkably improved.

The invention discloses a sliding bearing friction wear prediction method based on fluid mechanics, and relates to the technical field of mechanical state monitoring, and the method comprises the steps: collecting single-point temperature, local pressure, vibration time domain signals and a bearing pedestal inclination angle through a sensor, and generating sensor data; performing field reconstruction based on a fluid mechanics conservation equation on the sensor data to obtain multi-field data; performing spatial alignment on the multi-field data, inputting the multi-field data into a long short-term memory (LSTM) network, and generating wear state characteristics; training a sparse correlation vector machine regression model RVM by using the historical wear data, establishing a nonlinear mapping relationship between the wear state characteristics and the wear depth, taking the wear state characteristics as the input of the vector machine regression model RVM, and outputting the predicted wear depth; sensor data and the predicted wear depth are fused in real time through Kalman filtering, and when prediction deviation exceeds a covariance threshold value, vector machine regression model RVM parameters are updated.

The invention provides a fiber-optic gyroscope drift compensation method and system fused with LMS self-adaptive filtering, and relates to the technical field of LMS self-adaptive filtering, the method comprises the following steps: synchronously collecting multi-point temperature data, temperature change rate, axial and radial gradient information and original output signals of a gyroscope shell, and calculating the multi-point temperature data, the temperature change rate, the axial and radial gradient information and the original output signals of the gyroscope shell; the original signal is separated into a temperature drift component and a non-temperature noise component through variational mode decomposition, and noise is filtered out; establishing a nonlinear mapping relation by combining the temperature field data and the drift component to generate a drift predicted value, and inputting the predicted value and the residual error of the actual drift component into an LMS adaptive filter for dynamic error compensation; and finally, superposing the compensation result and the predicted value, and outputting a corrected gyro signal. According to the invention, the drift compensation precision and stability of the fiber-optic gyroscope in a complex variable-temperature environment are improved.

The invention relates to the technical field of deep learning, in particular to an AI chip test parameter adaptive optimization method based on deep learning, which comprises the following steps: acquiring historical test data of an AI chip, and calculating correlation strength among different failure modes based on the historical test data; identifying a failure coupling matrix according to the edge weight, and converting a preset static detection parameter constraint boundary into a dynamic constraint space changing along with a failure detection state; a multi-level optimization framework is constructed, the upper layer executes failure type correlation analysis and generates constraint propagation information, the middle layer optimizes a parameter cluster based on the constraint propagation information, and the lower layer adjusts a single detection parameter and outputs a parameter optimization result; establishing a neural network mapping model, and obtaining a nonlinear mapping relationship between the detection parameters and the failure types; based on the physical state parameters, the nonlinear mapping relation is adjusted, the dynamic constraint space is updated, parameter optimization is executed again, a parameter optimization result is output, and an optimal test parameter combination is output.

The invention relates to the technical field of equipment health state prediction, in particular to a multi-source sensing driven equipment health prediction method and system. The method comprises the following steps: synchronously acquiring equipment temperature, vibration, current and acoustic data through a multi-source sensor, carrying out denoising and standardization processing, dynamically distributing each signal weight to adapt to an equipment operation stage, generating a high-dimensional dynamic feature vector, and embedding a historical smoothing mechanism to realize continuous updating; performing standardization and nonlinear mapping on the features, constructing a dynamic coupling factor matrix to quantify a cooperative relationship between the features, fusing interaction information and adaptively enhancing abnormal features; three-layer progressive health prediction from a local part, a middle-layer subsystem to global equipment is implemented based on coupling characteristics, a trend consistency verification mechanism is introduced, global and middle-layer prediction differences are quantified through residual errors, weights are adaptively corrected, and the equipment health state evolution trend and the risk level are output. According to the method, the multi-working-condition adaptability, the feature coupling sensitivity and the prediction result reliability are remarkably improved.

The invention relates to the technical field of metasurface antennas, and provides a metasurface antenna parameter optimization method and system based on a convolutional neural network, and the method comprises the steps: collecting metasurface sample data; extracting a comprehensive electromagnetic feature set, and establishing a nonlinear mapping relation model; constructing an antenna performance comprehensive evaluation function, inputting the nonlinear mapping relation model and the antenna performance comprehensive evaluation function into a hybrid optimization algorithm to generate a parameter candidate set, and performing local optimization on the parameter candidate set by using a particle swarm algorithm to obtain a metasurface antenna parameter combination; and extracting electromagnetic characteristics of the metasurface antenna parameter combination, iteratively adjusting the height parameter of the resonant cavity until the height parameter meets a threshold value to obtain an electromagnetic simulation verification result, and feeding back the electromagnetic simulation verification result to the deep Q neural network model for parameter updating to obtain an optimal metasurface antenna parameter combination. According to the method, the optimization of antenna parameters is realized, the design efficiency of the metasurface antenna is improved, and the consumption of electromagnetic simulation calculation resources is reduced.

The invention belongs to the technical field of brain-computer interfaces, and particularly relates to a brain-computer interface driven emotion recognition and self-adaptive regulation and control system which comprises a multichannel nerve-peripheral coupling module, an emotion intensity probability mapping module and a closed-loop nerve regulation and control current module. The multi-channel nerve-peripheral coupling module is used for realizing overall quantification of central and peripheral emotional physiology; the emotion intensity probability mapping module is used for generating continuous emotion probabilities ranging from 0 to 1 through normalization and nonlinear mapping by utilizing emotion energy and combining eye movement fatigue and electroencephalogram entropy; and the closed-loop nerve regulation and control current module is used for dynamically adjusting the transcranial electrical stimulation intensity within the safety current upper limit according to the difference value between the emotion probability and the expected target. According to the invention, the recognition precision, the response speed and the use comfort are obviously improved.

The invention provides a geophysical gravity and magnetic anomaly source model construction and rapid forward and reverse modeling method, and relates to the technical field of intelligent three-dimensional geological modeling and simulation. According to geological information of a research area, source body modeling parameters of a gravity and magnetic anomalous field are set for the research area, and a three-dimensional model matrix M capable of describing a plurality of underground anomalous bodies is obtained; constructing a fast forward modeling network, establishing nonlinear mapping from the three-dimensional model matrix to the simulated abnormal data through the fast forward modeling network, and calculating forward modeling response of the three-dimensional model matrix; and constructing an inversion network based on a concurrent module CFTBlock and combining a CNN and a Transform, and establishing nonlinear mapping from the gravity and magnetic abnormal data to a three-dimensional model matrix. The method has the advantages of fast and accurate forward modeling, high-resolution inversion and the like, and is suitable for better interpretation of actually measured gravity and magnetic data.

The invention discloses a power system net load prediction method based on regular decomposition and double-branch prediction, and the method comprises the steps: obtaining a historical net load sequence of a target power system and corresponding environment parameters, constructing a target function fusing fitting precision and trend smoothness through employing a regularization optimization method, extracting a long-term trend sequence of a net load, and carrying out the calculation of the long-term trend sequence. And a short-term disturbance sequence is separated. Constructing a trend prediction sub-network based on series connection of a Transform encoder and a long-short-term memory network, and learning a trend evolution rule; meanwhile, a regression prediction sub-network based on environmental parameters is constructed, and a nonlinear mapping relation between disturbance and environmental factors is modeled. And utilizing the two types of sub-networks to respectively predict future trend and disturbance components and superpose the future trend and disturbance components to obtain a multi-time-step net load prediction result. According to the method, the problem that a traditional model is insufficient in trend and disturbance modeling capacity is effectively solved, and the accuracy and stability of load prediction are improved.

The invention relates to the technical field of large model algorithms, in particular to a knowledge distillation-based field large model lightweight adaptive method and system, and the method comprises the steps: obtaining knowledge distillation parameters and student model performance parameters, and building a nonlinear mapping relation between the knowledge distillation parameters and the student model performance parameters; the optimal parameter combination is optimized and solved based on the mapping relation, and target knowledge distillation parameters are generated; issuing the target parameters to a training engine, monitoring performance deviation in real time and triggering re-optimization; in the reasoning process, performance fluctuation is monitored, and model characteristics are managed and controlled; target domain data characteristics are collected, a mapping relation is corrected in combination with big data analysis, and the domain adaptation capacity is improved; a knowledge base and a case base of historical distillation data are constructed, a standardized adjustment scheme is formed, and self-adaptive matching is achieved. According to the scheme, through precise modeling, dynamic optimization, real-time monitoring and knowledge reuse, the knowledge distillation efficiency, model robustness and field adaptability are remarkably improved, and systematic technical support is provided for large model lightweight.

The invention discloses an HPLCamp (High Performance Liquid Chromatography) based on deep learning. The invention discloses an HRF dual-mode communication adaptive coding modulation and anti-noise method. The method comprises the following steps: acquiring an optical radio frequency signal amplitude-phase change rate and synchronously sampling and normalizing; calculating a node amplitude-phase residual error to generate a nonlinear mapping coefficient; monitoring coherent change to solve a drift trend, adjusting a modulation coding optimization scheme, compensating distortion and outputting an anti-noise result. According to the method, the instantaneous amplitude and phase of the optical radio frequency dual-mode signal are extracted, a multi-dimensional amplitude-phase characteristic matrix is formed in combination with time domain synchronization and a normalization template, differential residual modeling and nonlinear mapping coefficient calculation are carried out between impedance nodes, and dynamic compensation of amplitude-phase mismatch and envelope offset is achieved. A drift trend quantity is generated based on coherent offset parameter differentiation, feedback is provided for modulation format and coding strategy optimization, amplitude equalization and phase correction are completed, the signal synchronization degree and amplitude-phase consistency are improved, and the steady-state response and anti-disturbance performance of a transmission link are enhanced.

The invention relates to the technical field of supply chain risk early warning, in particular to a supply chain risk early warning method based on deep learning, and the method comprises the steps: obtaining supply chain data, extracting a material circulation relation between supply chain nodes, constructing a node relation graph, and employing a graph neural network to achieve the aggregation of the features of the nodes and adjacent nodes. And space correlation characteristics in the global network are extracted, and a multi-stage transmission and diffusion path of the risk is effectively modeled. And then, splicing node space features and historical time sequence features, inputting the spliced features into a long-short-term memory network, dynamically capturing the evolution trend of node risks along with time, identifying periodic fluctuations and sudden anomalies, and improving the prediction precision of the risk trend. And finally, a multi-layer perceptron is adopted to carry out nonlinear mapping and feature fusion on risk time sequence features output by the long-short-term memory network, node risk scores are generated, real-time early warning of high-risk nodes is realized accordingly, and the accuracy and timeliness of supply chain risk monitoring are greatly improved.

The invention discloses a subway depot upper cover building vibration response prediction method based on deep learning, and the method comprises the steps: constructing a feature library containing vibration signals and working condition data, generating enhanced data through a mechanical model, and fusing the enhanced data into a data set; a mixed deep learning model embedded with physical prior is constructed, and training and dual-objective parameter optimization are carried out; a prediction result is output after working conditions of real-time data are recognized through the lightweight model; parameters are finely adjusted through regular incremental learning, and transfer learning adaptation is carried out when working conditions suddenly change; verifying precision and rationality, and adjusting the weight of a regular term or suggesting to add a sensor; according to the method, measured data sparseness is made up by enhancing data fusion; the double-branch architecture overcomes the deep nonlinear mapping problem, and physical constraints are prevented from violating physical rules; the incremental learning reduces the cost, and the transfer learning solves the time-varying vibration capture problem; precision is improved through closed-loop verification, accurate real-time prediction of vibration response is achieved, and safety and comfort of a building are guaranteed.

The invention discloses a method for determining an electrical fire risk assessment weight index coefficient, and relates to the technical field of risk assessment, and the method comprises the steps: deploying a plurality of types of sensors to collect original environment data streams including historical fault data, environment parameter data and communication network data in real time, carrying out the preprocessing of the original environment data streams, and carrying out the calculation of the original environment data streams; forming a preprocessed feature data set; performing sparse optimization on the preprocessed feature data set by using an Elastic Net regression function, optimizing regularization parameters in the regression function through a cross validation method, and finally obtaining an optimized feature set and a preliminary weight vector; and processing the time evolution sequence of the preliminary weight vector by using a convolution mode to generate a convolution feature tensor, and carrying out nonlinear mapping on the convolution feature tensor by using a ReLU activation function to obtain a predicted weight sequence. Effective fusion of multi-scale features is realized through a dynamic segmentation strategy of an adjustable time window in combination with a high-frequency signal analysis and long-term trend extraction technology.

The invention discloses a commercial building energy monitoring and intelligent control method and device and a storage medium, and belongs to the technical field of building intelligent control, and the method comprises the steps: collecting data, building a nonlinear mapping relation, and generating an energy consumption demand prediction tensor; injecting an adversarial disturbance sample, and evaluating the robustness of the prediction model; in combination with the energy consumption baseline, performing cross confirmation and correction on the prediction data exceeding the threshold value; performing attribution analysis on the corrected energy consumption sequence to generate an energy consumption attribution map; adjusting the solution of a multi-objective optimization function according to the atlas, and generating an optimal cooperative control strategy; and the comprehensive efficiency is used as a reinforcement learning reward, strategy parameters are iteratively updated, and a control knowledge base is formed. According to the method, a closed-loop control framework integrating robust demand prediction, dynamic attribution analysis, collaborative optimization decision and a self-evolution strategy is adopted, intelligent regulation and control of building energy consumption can be realized, and the long-term adaptive optimization capability is improved.

The invention discloses a BMI-driven 3D organ obesity visualization system based on multi-modal fusion, and relates to the technical field of medical science, the system comprises a BMI-driven prediction model, the BMI-driven prediction model is used for establishing a quantitative mapping model of a BMI index and three-dimensional organ fat deposition, and the quantitative mapping model is used for establishing a BMI index and three-dimensional organ fat deposition. The BMI driving type prediction model comprises a multi-modal data fusion unit, a model mapping unit and a residual compensation unit. By installing the BMI driving type prediction model, precise nonlinear mapping of the BMI index and organ fat deposition is achieved, the problem that traditional single-mode prediction is large in deviation is solved, and organ fat volume prediction precision and individual difference adaptability are improved.

The invention belongs to the technical field of high-performance composite materials, and discloses a carbon fiber reinforced thermoplastic composite material performance database, a construction method and application thereof, and the method comprises the following steps: S1, database structure construction; s2, experimental sample collection and data standardization; s3, feature engineering and variable reduction; s4, training a machine learning model; s5, constructing and verifying an adaptive model; and S6, data expansion and feedback optimization. According to the method, material performance prediction and formula parameter reverse design under target performance are realized through systematic acquisition and normalization processing of three types of data of material components, preparation process and performance characterization and building of a nonlinear mapping model among a material structure, a process and performance through a machine learning method. The database can be used for intelligently recommending a high-performance composite material combination scheme, is suitable for rapid screening and customized development of various thermoplastic composite materials, effectively reduces the research and development cost and development cycle, and improves the material design efficiency.

The invention discloses a fruit and vegetable juice production line equipment fault tracing method, which comprises the following steps of: acquiring parameters such as temperature, pressure, vibration, rotating speed and motor current in real time through a multi-channel sensor, and establishing a working condition characteristic database by combining filtering, normalization, statistics and frequency domain characteristic extraction; based on a support vector regression algorithm, a nonlinear mapping model of working condition features and anomaly detection thresholds is constructed, and dynamic threshold adaptive output and real-time anomaly judgment for different working conditions are realized; according to a detection result, a fault signal is automatically triggered, a model is continuously incremented and trained, the adaptability to new working conditions is improved, the accuracy, intelligence and stability of equipment anomaly detection are effectively improved, misinformation and missing information can be reduced, and the automatic operation and maintenance level of a production line is enhanced.

The invention discloses a dynamic DEM spatial interpolation method which comprises the following steps: performing depression filling, flow direction analysis and confluence cumulant calculation on DEM data, and extracting a natural sub-basin unit by adopting a minimum catchment area threshold method; constructing a topographic feature matrix, performing refined second-level classification on the first-level drainage basin through an improved self-organizing mapping network, generating a hydrological response unit through boundary processing, and establishing a hydrological attribute library; fusing multi-source data, supplementing attribute interpolation such as underlying surface and rainfall, and constructing an interpolation auxiliary parameter system; a drainage basin is divided into regular grids as neurons, a dynamic neural network containing dynamic states and static attributes is constructed, and nonlinear mapping of DEM correction parameters is achieved through optimization of a dynamic activation function and a loss function. The method overcomes the defects that a traditional interpolation algorithm does not consider hydrological boundary constraints, a neural network model topological structure is fixed and the like, and the DEM interpolation precision and the hydrological simulation effect of the complex terrain area are improved.

The invention relates to the technical field of numerical control programming, in particular to a five-axis machining path planning method and system based on data driving, and the method comprises the following steps: obtaining real-time coordinates of each axis of a machine tool, calculating linear velocity and angular velocity components to construct a Jacobian matrix, executing singular value decomposition, and calculating a conditional number ratio by using maximum and minimum singular values; and inputting a nonlinear mapping function to calculate a dynamic penalty factor, generating a rotating shaft weighted item in combination with a rotating shaft identifier, constructing a weighted damping least square objective function, calculating a five-axis motion increment, and accumulating the five-axis motion increment with a real-time coordinate to generate a target absolute position coordinate. According to the method, the pose singularity degree is quantified by monitoring the machine tool pose condition number ratio and converted into the dynamic penalty factor to apply the self-adaptive constraint to the rotating shaft, the severe sudden change of the rotating shaft in the singularity area is inhibited, the tool nose track following error is minimized, and meanwhile smooth distribution of the motion increment is achieved; and the dynamic stability and the surface quality of five-axis linkage machining are improved.

The invention relates to the technical field of food and beverage, in particular to a food and beverage network sales trend prediction model construction system and method based on multi-source data fusion and deep learning. Comprising a data acquisition unit; a data processing unit; the model construction unit is used for constructing a deep learning prediction model, and an improved LSTM-Transform fusion algorithm is adopted to realize nonlinear mapping modeling of the food and beverage sales trend by integrating time sequence feature modeling and a global dependency relationship analysis technology; a model training verification unit; and a prediction output unit. According to the method, multi-source data such as network sales platform data, social media emotion texts, weather information and industry information are integrated, cross-correlation features such as time dimension features, text emotion features and price elasticity-weather influence are extracted in combination with a feature engineering technology, influence factors of food and beverage sales are comprehensively covered, and the sales quality is improved. The problem that a traditional scheme is single in data dimension is solved.

The invention discloses a dynamic digital compensation method for the metering error of wide-temperature-interval electric energy meter equipment, and the method comprises the steps: collecting the metering error data of the equipment at different temperatures through a temperature sensing module, so as to construct a historical temperature-error relation library; training an adaptive compensation model based on a historical temperature-error relation library to establish a nonlinear mapping relation between the temperature and the error; in the real-time operation process of the equipment, the current equipment temperature is collected through a temperature sensing module, and the current equipment temperature and the real-time load rate are input into the self-adaptive compensation model to obtain error correction; and the metering result is dynamically adjusted in real time according to the current equipment temperature and the error correction amount so as to output a compensated accurate metering value. According to the method, a temperature sensor does not need to be newly added, dynamic error correction is realized only by utilizing the existing temperature sensing capability of equipment, the metering precision and stability in a wide-temperature environment can be improved, the comprehensive cost is reduced, and the high-precision metering requirements in special environments such as extremely cold and high temperature environments are met.

The invention provides a transformer substation residual current intelligent monitoring method and device based on multi-parameter fusion, and relates to the technical field of power system monitoring, and the method comprises the steps: collecting the residual current value of each loop through a residual current sensor, and collecting environment parameters at the same time; performing dynamic confidence fusion on the residual current values of the plurality of residual current sensors through a confidence function and the consistency factor to obtain a fused residual current value; calculating self-adaptive weights of the environmental parameters, and calculating a dynamic threshold value through the nonlinear mapping function of the environmental parameters and the self-adaptive weights; calculating a multi-parameter fusion evaluation index, combining the fusion residual current value, the dynamic threshold value and the multi-parameter fusion evaluation index, calculating a comprehensive fault risk index through a fault membership function, and obtaining a fault diagnosis result according to the risk index value; and outputting early warning information according to the fault diagnosis result. According to the invention, intelligent monitoring and fault early warning of the residual current of the transformer substation can be realized, and the monitoring precision and the reliability of fault diagnosis are improved.

The invention relates to the technical field of power grid data analysis, in particular to a power consumer anomaly detection and risk assessment method, system and device based on spatial-temporal feature fusion and a storage medium. The method comprises the following steps: acquiring multi-source power consumption data of various power consumers, constructing a space-time correlation feature extraction model, and establishing a user behavior space-time coupling relationship through time sequence analysis and spatial distribution characteristic analysis; constructing a multi-dimensional risk mapping model based on a long short term memory network and a convolutional neural network, establishing a nonlinear mapping relation from feature information to a risk assessment result, and identifying an abnormal power consumption behavior; establishing a distributed node credibility evaluation system, and performing credibility quantitative analysis on the data nodes in combination with a fuzzy comprehensive evaluation method; and based on an abnormal detection result and credibility evaluation, intelligent analysis and dynamic early warning of the electric charge management and control risk are realized. The time-space coupling characteristic of power consumption data can be fully mined, and high-precision identification of abnormal power consumption behaviors and accurate detection of non-technical power loss are realized.

The invention relates to a clinical psychological treatment effect evaluation method and system based on machine learning, and the method comprises the steps: obtaining biological signals, behavior patterns and psychological state data of a patient during treatment, constructing a three-dimensional tensor structure with aligned timestamps, and carrying out the standardization of the three-dimensional tensor structure to generate a multi-dimensional data matrix; dimensionality reduction, reconstruction and verification are carried out on the matrix through a deep auto-encoder network, and unified feature vector representation is output; utilizing an improved support vector regression algorithm to establish a nonlinear mapping model of the feature vector and the curative effect score; according to the method, the curative effect score is predicted in real time, when the score is abnormal or fluctuation exceeds a threshold value, a personalized treatment scheme optimization mechanism based on the knowledge graph is triggered, deep fusion of multi-source heterogeneous data is achieved, evaluation precision and treatment adaptability are improved through a dynamic optimization mechanism, and intelligent decision support is provided for clinical psychological intervention.

The invention discloses a self-adaptive visual admittance control method fusing fluid characteristics and multi-modal perception, which comprises the following steps: designing a self-adaptive Bingham-shear thickening fluid virtual damping coefficient through nonlinear mapping based on sigmoid, and combining a threshold triggering behavior of a Bingham fluid and a sudden stiffening characteristic under the impact of the shear thickening fluid; the flexibility is enhanced under the action of small force, and the anti-interference capability is improved under impact. Besides, a force auxiliary function based on force amplitude is introduced, an anisotropic compliance strategy is combined, rigidity and damping are dynamically adjusted by identifying the main force direction, and the mechanism can reduce sensitivity to noise of a micro sensor and ensure stability and accuracy in the task execution process. Meanwhile, an environment attraction domain model is established in a feature space, Lyapunov analysis shows that the system has consistent final boundaries, stable convergence is ensured, and secondary correction is supported.