722 results about "Feature extraction algorithm" patented technology

The invention belongs to the technical field of battery monitoring, and discloses an electric vehicle power battery health condition real-time monitoring method and system, and the method comprises the steps: obtaining multi-parameter data such as voltage, current, temperature, internal resistance and the like through a battery management system, and carrying out the synchronous collection of the data through a preset sampling frequency, and obtaining a multi-dimensional time series data set; aiming at the multi-dimensional time sequence data set, adopting a feature extraction algorithm to separate dynamic change features of voltage, current, temperature and internal resistance to obtain a multi-parameter feature set; if the deviation of the battery health state output by the dynamic mapping relation model exceeds a preset threshold value, analyzing a fluctuation mode in the multi-parameter feature set through an anomaly detection algorithm, and judging whether a potential degradation risk exists or not; and according to the comprehensive representation of the battery health state, a time sequence prediction algorithm is adopted to analyze the future change trend of the multi-parameter feature set, and a short-term prediction value of the battery health state is generated.

The invention discloses a carbon emission prediction and optimization method, and the method comprises the steps: obtaining multi-source heterogeneous data including historical carbon emission data, meteorological data, economic indexes, energy consumption data, and Internet of Things sensor data, and constructing a three-dimensional feature matrix through employing an improved spatial-temporal feature extraction algorithm; based on a mixed architecture of a graph neural network GNN and a long and short term memory network LSTM, a prediction model is established in combination with an attention mechanism, and training is performed through an adaptive learning rate optimization algorithm; a prediction result is input into an improved NSGA-III algorithm, and three targets of total carbon emission, economic cost and social benefits are optimized at the same time; and establishing a feedback closed loop through reinforcement learning RL, and updating the model and the strategy on line according to real-time monitoring data. According to the method, multiple advanced technologies such as accurate data processing, dynamic prediction, multi-objective optimization and cross-domain collaboration are integrated, and a comprehensive and effective solution is provided for carbon emission management.

The invention discloses an AI-based bridge construction intelligent monitoring method, particularly relates to the field of data analysis, and comprises the steps of multi-modal sensing network construction, cross-domain characteristic parameter extraction, comprehensive state evaluation modeling and intelligent decision and regulation. According to the method, deformation, corrosion, vibration and other multi-physical field data are synchronously collected through a multi-modal sensing network, a cross-scale feature extraction algorithm is adopted to construct creep-corrosion collaborative factors and other composite indexes, the limitation of traditional single-dimensional parameter analysis is broken through, a dynamic evaluation model is fused with weighted integral and a nonlinear function, and the dynamic evaluation accuracy is improved. Precise early warning of risks such as bridge pier instability and cantilever cracking is achieved, the multi-field coupling effect quantification capacity is remarkably improved, an intelligent joint control mechanism automatically triggers instructions such as jacking reinforcement and damping tuning through a three-level emergency response system, a monitoring-analysis-regulation closed-loop system is constructed, the hysteresis of manual decision is effectively eliminated, and the safety and reliability of the system are improved. And all-weather self-adaptive safety guarantee is provided for bridge construction.

The invention provides a power transmission line inspection data asset management method and system, and the method comprises the steps: obtaining the multi-modal data of a power transmission line through a plurality of sensors disposed on the power transmission line and the surrounding environment, and sensors carried by a helicopter and an unmanned plane; and processing the multi-modal data based on the space-time correlation model to generate a fusion data set. Analyzing the fused data set by using an adaptive feature extraction algorithm, generating structured power transmission line data assets including environmental features, defect features and hidden danger features, and evaluating the possibility of triggering defects by environmental conditions based on the association of the environmental features and the defect features; according to the hidden danger characteristics and the environmental conditions, constructing a graph network model which takes a power transmission line as a node and sensor data as an edge weight and is used for analyzing a defect propagation path and predicting time and space distribution of hidden dangers; defect risk level early warning is generated based on a prediction result, a power transmission line hidden danger distribution diagram is generated in combination with environmental meteorological data, and accurate assistance is provided for patrol and maintenance plans.

The invention discloses a use monitoring method and system for a knife gate valve, and relates to the technical field of knife gate valve monitoring, and the method comprises the steps: integrating a multi-mode sensor array at the root of a valve rod of the knife gate valve, an adjacent region of a sealing surface and in a valve cavity flow channel, and collecting multi-source signals in real time; performing dynamic fusion processing on the multi-source signal, and determining a feature extraction algorithm combination based on the current valve rod temperature and historical working condition data to extract a sealing surface damage feature, a transmission chain wear feature and a particle impact feature; constructing a dynamic anomaly judgment model, updating a clustering boundary of a vibration and torque characteristic space in real time, and performing decoupling diagnosis on a sealing surface dry friction risk, thread clearance expansion and gear wear in combination with time-frequency domain fluctuation analysis of a gear meshing frequency harmonic attenuation rate and an angular acceleration; and generating a three-level maintenance strategy according to the diagnosis result, dynamically adjusting the output torque of the execution mechanism and optimizing the switching frequency of the valve.

The invention discloses a safety risk assessment system based on slope construction, relates to the technical field of slope construction, constructs a complete system composed of a data acquisition module, a dynamic disturbance identification module, a risk assessment module and an intelligent early warning and decision-making module, and acquires multi-source data such as displacement, cracks, pore water pressure, seismic disturbance and blasting vibration at high frequency. The time sequence analysis and disturbance feature extraction algorithm is combined to realize the rapid identification of the sudden disturbance event; risk score prediction is further carried out based on a polynomial regression model, and multi-level early warning is generated through comparison with a set threshold value; and finally, by combining the construction state, the support parameters and the disturbance intensity, a safety control suggestion is dynamically generated, so that the response speed and prediction precision of the system to the sudden slope instability risk are effectively improved, and real-time perception and intelligent management and control of the risk in the slope construction process are realized.

The invention relates to the technical field of electrical engineering and sensors, and provides a high-precision current sensor electrical performance detection method, which comprises the steps of collecting an original output signal of a current sensor and performing multi-dimensional signal preprocessing; extracting multi-dimensional feature parameters from the preprocessed signals based on a dynamic feature extraction algorithm; establishing a dynamic compensation model according to the multi-dimensional characteristic parameters, and generating a compensation control signal; a compensation control signal is injected into the detected current sensor to form closed-loop feedback, and a compensated output signal is collected; calculating a sensor performance degradation parameter according to the signal difference before and after compensation; an electrical performance assessment report is generated based on the performance degradation parameter. According to the invention, the measurement precision and reliability of the sensor can be improved, the service life is prolonged, the maintenance cost is reduced, and a powerful guarantee is provided for safe and stable operation of a power system and electronic equipment.

The invention relates to the technical field of petroleum pipelines, in particular to a petroleum pipeline leakage detection method and system, and the method comprises the following steps: S1, data collection and preprocessing: collecting the detection data of a petroleum pipeline in real time through a plurality of sensors and geographic information collection equipment; s2, feature extraction: performing feature extraction on the preprocessed detection data by adopting a multi-scale feature extraction algorithm; s3, model construction: constructing a petroleum pipeline state recognition model; s4, real-time detection: inputting detection data acquired in real time into the petroleum pipeline state recognition model; s5, leakage path prediction: predicting the diffusion path and range after petroleum leakage in real time; and S6, leakage alarm: when leakage of the petroleum pipeline is detected, an alarm mechanism is triggered, and related personnel are notified to take emergency measures. According to the method, the diffusion path and range after leakage are accurately predicted, and a reliable basis is provided for emergency response.

The invention belongs to the technical field of safety monitoring of subway tunnels, and particularly relates to a subway tunnel water leakage monitoring method and system based on multi-modal data fusion, and the method comprises the steps: obtaining multi-source sensor time sequence data in a subway tunnel, carrying out the feature extraction, and extracting feature parameters related to water leakage; carrying out fusion analysis on the characteristic parameters through a data fusion algorithm, and evaluating the position and severity of water leakage, including extracting time-space correlation characteristics of data by using a dynamic time warping method; after feature extraction is performed on the data set and the space-time correlation features by using a convolutional neural network and a recurrent neural network, feature fusion is performed; and performing anomaly detection and classification on the fused high-level features by using a neural network method to obtain the position and severity of the leakage water. The advanced data fusion technology and the feature extraction algorithm are adopted, various collected data can be analyzed in real time, abnormal conditions can be found in time, and early warning is carried out.

The invention relates to an image segmentation method for a burn wound area, and the method comprises the steps: collecting burn wound images under different spectrums through a multispectral imaging device, and enabling the burn wound images to comprise a plurality of wavebands, namely visible light, infrared light and ultraviolet light; for each spectral image, analyzing reflection and absorption characteristics of a burn area under different wavebands by using optical characteristics of biological tissues, and marking a potential burn area; designing a self-adaptive algorithm, and dynamically adjusting parameters, including exposure and light intensity, of imaging equipment based on feedback of different spectral characteristics; the feature contrast of the burn area is enhanced; preliminarily delimiting the boundary of the burn region according to the enhanced spectral image through a threshold segmentation or region growing algorithm; inputting the multispectral image into a hierarchical processing model, and decomposing different tissue levels of the burn area including epidermis and dermis based on different wave band or color information; on each layering result, a feature extraction algorithm including texture analysis and edge detection is used for extracting detail features of each layer.

The invention relates to the technical field of fault monitoring, in particular to a power transmission line fault monitoring and positioning method, system and device and a medium. The method comprises the following steps: firstly, performing digital conversion on an original current signal to obtain time sequence data, and then identifying and classifying fault events through threshold detection and a feature extraction algorithm to obtain classification labels of fault types; then, based on the classification label, establishing a traveling wave propagation model and carrying out time difference calculation, carrying out clustering analysis on a plurality of wave head data in a preset time window, and judging whether the fault is a single-point fault or a multi-point fault through a clustering result; and finally, a positioning result is transmitted to the central server for comprehensive verification and alarm management, and a final fault response is formed. By introducing a time series data analysis and clustering judgment mechanism, the fault type can be accurately identified, single-point and multi-point fault conditions can be effectively distinguished, and meanwhile, the reliability of a positioning result is improved through comprehensive verification of the central server.

The invention discloses a VLM model intelligent decision-making-based driving method and device and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: extracting key visual features from continuous multi-frame driving scene images based on a preset visual feature extraction algorithm; inputting a user instruction and a time sequence visual Token corresponding to the key visual features into a preset VLM model for multi-modal alignment, and generating a target planning Token; inputting the target planning Token and the time sequence vision Token into a preset trajectory generation model to obtain a predicted trajectory; and converting the predicted trajectory into a control signal, and controlling the mobile device to complete a moving action based on the control signal. The problem of modal difference between a semantic space and an action space is solved.

The invention relates to a wharf sensing method and system based on data fusion of a laser radar and a camera, and the method comprises the steps: firstly employing a fisheye camera to shoot a checkerboard calibration plate at multiple angles, employing a Zhang's calibration method to calculate an internal reference matrix and a distortion coefficient of the fisheye camera, and synchronously collecting the data of the laser radar and the camera in real time; the method comprises the following steps: performing distortion removal processing on a camera image, calculating an external parameter matrix between a laser radar and a camera through a feature extraction algorithm, a feature point matching algorithm and a nonlinear optimization algorithm, and performing data fusion through an internal parameter matrix, the external parameter matrix and a bilinear interpolation method to generate fusion point cloud data with color information; and finally, identifying a key target of the wharf by marking and training a CNN model, and calculating three-dimensional parameters of the key target by adopting a specific calculation method, so that a sailor can quickly distinguish the target in the fused point cloud data, the accuracy and efficiency of wharf environment perception are remarkably improved, and accurate environment perception and decision support are provided for ship berthing and departing operation.

The invention relates to the technical field of medical diagnosis, and discloses a DCM early noninvasive analysis method based on multi-radiomics and serum markers. Collecting image data through a multi-modal medical imaging device, and collecting serum marker data through a blood detection device; respectively generating a radiomics feature set and a serum marker time sequence feature set by using a multi-scale feature extraction algorithm and a time sequence analysis model; fusing the features by adopting a dynamic weighted fusion strategy to generate a joint feature matrix; inputting the model into a pre-trained multi-task deep learning model to predict a DCM risk probability; and finally, based on a genetic algorithm, optimizing the diagnosis decision tree and outputting an early DCM diagnosis result. The method is noninvasive and accurate, and can effectively improve the early diagnosis accuracy of DCM.

The invention relates to the technical field of data processing, in particular to an accelerometer vibration rectification error analysis method, which comprises the steps of receiving multiple paths of accelerometer original current signals, processing acquired data and outputting a feature point coordinate sequence with confidence; according to the confidence and the optimization algorithm combination in the frequency band distribution characteristic dynamic scheduling knowledge base, calculating a local statistical data set; inputting the data set into a mechanical dynamics model to execute trajectory simulation, and inputting a control model reconstruction signal to compare a dual-path positioning drift distance difference to generate an error correction coefficient matrix; outputting a knowledge base updating instruction and a parameter resetting instruction by adopting a matrix reconstruction vibration rectification error quantized value; a quantized value is imported to calculate theoretical angle deviation and verify convergence, and the neural network is triggered to be retrained when the deviation exceeds a threshold value. Through a non-smooth feature extraction algorithm and a closed-loop feedback mechanism, the problem of signal distortion caused by smooth operation in the prior art is solved.

The invention relates to the field of breeding industry, and discloses a pig behavior-based pig health condition analysis method and system, and the method comprises the steps: carrying out the comprehensive monitoring of pig behaviors, capturing the gait, feeding mode, excretion behavior and activity range of a pig in real time based on a behavior feature extraction algorithm, and obtaining a behavior state video stream sequence; multi-dimensional time sequence correlation analysis is carried out on the behavior state video stream sequence, and historical behavior data, pig weight changes and physiological parameters are combined; based on the dynamic time sequence feature vector, dynamically identifying a change track of pig behaviors by applying a self-adaptive behavior identification algorithm; performing correlation analysis on the detected abnormal behavior pattern and the potential health risk of the pig, fusing the environmental factors, group behavior data and health history of the pig, and identifying a potential health problem; and based on a risk early warning result, automatically adjusting environmental parameters and feeding management strategies, and providing intervention measure suggestions. The pig health management system has the advantage of improving the efficiency and accuracy of pig health management.

The invention relates to the technical field of agricultural information, and discloses a visual analysis method and system based on an agricultural big data model. According to the system, crop growth time sequence data are processed by using a multi-scale feature extraction algorithm combining a recurrent neural network and wavelet transform, and key conversion points of a crop growth stage are automatically identified by using a deep learning architecture combining a variational auto-encoder and a hidden Markov model. A standard growth track model and a multi-dimensional deviation measurement index are constructed to evaluate the abnormal growth condition of crops, a dynamic threshold model based on reinforcement learning is applied to realize early warning of abnormal growth, and a multi-dimensional visual interface based on a clock metaphor is designed to visually display crop growth information. The crop growth stage recognition precision and early warning timeliness are improved, and the agricultural production management efficiency is remarkably enhanced.

The invention relates to a method and device for optimizing the click effect of an advertisement platform based on artificial intelligence, and belongs to the technical field of advertisement platform click effect optimization, and the method comprises the steps: carrying out the feature extraction of an image advertisement material and a text advertisement material through a feature extraction algorithm, and obtaining an image feature vector and a text feature vector; the classification algorithm classifies the image advertisement material and the text advertisement material according to the image feature vector and the text feature vector to obtain a classification result; acquiring historical behavior data of the user on the advertisement materials, and analyzing preferences of the user on different types of advertisement materials through a deep learning algorithm to generate a user preference model; acquiring real-time behavior data, and adjusting the display frequency and sequence of the advertisement materials according to the real-time behavior data and the user preference model; and adjusting the advertisement material display frequency, display position and material content according to the user preference model and the classification result. According to the method, the advertisement material click rate, the personalized recommendation effect and the advertisement material putting efficiency are remarkably improved.

The invention provides a high-precision positioning method and system based on multi-source information fusion. The high-precision positioning method comprises the following steps: acquiring the omm positioning information of the pose of an unmanned aerial vehicle in real time based on a visual inertial navigation unit; a global feature extraction algorithm is combined with a similarity algorithm, and a target satellite image matched with the airborne image of the unmanned aerial vehicle is selected from a satellite image library; using a local feature matching algorithm to combine with the geographic coordinates of the target satellite image to obtain GPS predicted positioning coordinates; fusing the odom positioning information and the GPS predicted positioning coordinates by using a global fusion technology to obtain preliminarily fused odom positioning information; according to the method, secondary fusion is carried out on the basis of GPS positioning data obtained by a real GPS sensor in combination with the preliminarily fused odom positioning information to obtain final odom positioning information, and through a double fusion strategy, the advantages of a multi-source positioning technology are fully integrated, and the positioning accuracy is improved.

The invention provides an intelligent inspection and diagnosis system, method and device for a photovoltaic power station unmanned aerial vehicle and a medium, and the system comprises a heterogeneous perception fusion module which is used for constructing digital mirror image mapping of a power station global physical field through multi-mode sensor space-time coding and electromagnetic fingerprint matching; the group intelligent decision module is used for realizing autonomous task negotiation and anti-fragile path evolution of a multi-unmanned aerial vehicle cluster based on a dynamic Bayesian game model; the embedded diagnostic kernel module is used for running a quantization feature extraction algorithm at an edge computing node to realize component-level defect subsurface-level diagnostic reasoning; the superbody self-evolution module is used for continuously reconstructing a diagnostic knowledge graph by means of a genetic programming framework to realize Darwin asymptotic optimization of a system cognitive architecture; the problems that in unmanned aerial vehicle inspection, fault type judgment and accurate geographic positioning cannot be conducted online, photovoltaic array arrangement changes and sudden shielding scenes cannot be self-adapted, and transmission bandwidth limitation and analysis lag are likely to happen in a 5G weak coverage area are solved.

The invention provides an L1-L4 lumbar vertebra segment-oriented multi-feature fusion diagnosis system and method, and the system comprises an image preprocessing module which is used for receiving a lumbar vertebra CT image sequence of a patient; a centrum anatomy partition module; the multi-dimensional image feature extraction module is used for extracting four types of quantitative features from each sub-region; the clinical multi-modal data coding module is used for independently acquiring and processing three types of clinical data: a multi-modal graph attention fusion network; and the segment-level diagnosis output module outputs diagnosis results of three levels. Through a parallel processing architecture and an optimized feature extraction algorithm, the whole diagnosis process only needs 45 seconds from data input to report generation, time is saved compared with manual film reading, and the consistency of diagnosis results is remarkably improved.

The invention provides an engineering test method and system for a storage chip and a medium, and belongs to the technical field of semiconductor packaging. The method comprises the following steps: acquiring read-write operation data, temperature data and voltage data of a storage chip in real time through a distributed sensor network, performing dimension reduction and segmentation processing on test data by using a multi-dimensional feature extraction algorithm, extracting statistical features and correlation features, inputting a fault prediction model constructed based on a deep learning algorithm, and performing fault prediction. Fault type and probability prediction is realized; and judging whether the chip has a fault by combining a preset threshold value, if the chip has the fault, accurately positioning a fault area by adopting a dynamic probe test technology, determining a fault time point and a trigger condition through time sequence analysis, and finally generating a fault diagnosis report and providing a repair suggestion. According to the invention, the accuracy and efficiency of fault detection of the storage chip can be effectively improved.

Provided are a method for training a transformer fault detection model, a fault diagnosis method, and a related device. The method includes: obtaining an initial voiceprint signal of a transformer and a fault type corresponding to the initial voiceprint signal; preprocessing the initial voiceprint signal to obtain an input signal, and establishing an input signal dataset; performing feature extraction on a first input signal in the training dataset based on a preset feature extraction algorithm to obtain a first voiceprint feature; training an initial detection model based on the first voiceprint feature and a first fault type corresponding to the first input signal to obtain a first training result; determining a loss function based on the first training result and the first fault type; and iteratively adjusting a weight value of the initial detection model until the loss function converges to obtain a fault detection model.

The invention discloses a network fault diagnosis and simulation method and device of a power grid system and a medium, belongs to the technical field of cloud computing networks and smart power grids, and aims to solve the technical problem of how to monitor, diagnose, effectively simulate and accurately predict various faults possibly occurring in the operation of a power grid in real time. In order to improve the self-healing capability, stability and reliability of a power grid and ensure the continuity and safety of power supply, the adopted technical scheme is as follows: analyzing fault scenes and types, identifying fault scenes possibly encountered by the power grid and classifying the fault scenes; deploying a real-time monitoring system, and uninterruptedly collecting power grid operation data; key features related to the fault type are extracted by adopting a feature extraction algorithm; a fault diagnosis model is constructed by using a machine learning or deep learning technology, and automatic identification of fault types is realized; and creating a power grid digital twinborn model, simulating physical characteristics and behaviors of the power grid, and developing a data analysis tool to perform statistics and trend analysis on a simulation result.

The disclosure provides a transformer fault detection model training method, a fault diagnosis method, and a related device. The method comprises: obtaining an initial voiceprint signal of a transformer, and a fault type corresponding to the initial voiceprint signal; preprocessing the initial voiceprint signal by using a wavelet packet analysis method, so as to obtain an input signal, and according to the input signal and the fault type, establishing an input signal data set; according to a preset feature extraction algorithm, performing feature extraction on a first input signal in a training data set to obtain a first voiceprint feature; using the first voiceprint feature and a first fault type corresponding to the first input signal to train an initial detection model, so as to obtain a first training result; according to the first training result and the fault type, determining a loss function; on the basis of the loss function, using a back propagation algorithm to iteratively adjust weight values of the initial detection model, until the loss function converges, so as to obtain a fault detection model. In the present disclosure, accurate transformer fault detection is realized by utilizing the obtained fault detection model.

The invention discloses a gastrodia elata quality detection method based on a computer vision technology, relates to the technical field of intelligent detection, and is used for solving the problems of low detection efficiency and poor recognition accuracy in traditional gastrodia elata detection. According to the invention, synchronous acquisition and preprocessing of multi-source data are carried out through an industrial camera, an infrared imager, a 3D scanning device and a spectrometer, a multi-scale feature extraction algorithm is utilized to generate quality feature vectors containing forms, textures, colors and defects, and a cross-modal three-dimensional characteristic spectrum is constructed. The deep learning model is combined to realize automatic quality evaluation and grading; when the reject ratio exceeds a threshold value, main influence factors of unqualified products are analyzed, and an interpretable quality evaluation report is generated; the precise detection of the quality of the gastrodia elata is realized; and the detection efficiency and the identification accuracy are effectively improved.

The invention relates to the technical field of design and application of two-dimensional materials, and discloses a design and simulation method of a two-dimensional semiconductor nanometer transistor, which comprises the following steps: collecting multi-source data of design and simulation of the two-dimensional semiconductor nanometer transistor, and screening through a data quality evaluation model to obtain a layered data structure; constructing and training a Bayesian neural network model; key influence parameters are identified through a multi-scale feature extraction algorithm and a parameter correlation analysis algorithm, and an attention algorithm is applied to pay attention to an important parameter combination; meanwhile, the uncertainty is predicted, a sampling point with the most information content is generated, and a prediction confidence interval is provided; through active learning feedback optimization circulation, high-value data points are selected based on prediction uncertainty for verification, and the model is updated until preset precision or resource constraint is achieved; according to the method, through multi-scale feature representation and parameter correlation analysis, invalid parameter exploration is reduced, and meanwhile, the model interpretability is improved through integrated physical constraint and uncertainty quantification.

The invention discloses a golf motion simulation method and system based on digital twinning, and the method comprises the steps: obtaining an original data set containing a timestamp and a space coordinate from the cooperative motion of a plurality of parts and equipment of an athlete body through a sensor network technology in combination with a high-speed image capture device, and obtaining a preliminary multi-source motion information record; aiming at the initial multi-source motion information record, correcting time synchronization deviation and space matching error by adopting a data preprocessing module, and determining a corrected unified data framework by comparing timestamps and coordinate mapping relationships of data sources; according to the corrected unified data framework, a feature extraction algorithm is used for separating and marking the action analysis details and key parameters at the ball hitting moment, and a feature vector set containing the body posture and the equipment state is obtained. According to the invention, a highly vivid virtual environment support is provided for exercise training and match analysis, and the simulation precision and application value of a virtual exercise scene are effectively improved.

The invention discloses a driving motor fault diagnosis method and device based on an artificial intelligence technology, and relates to the technical field of fault diagnosis, and the method comprises the steps: arranging a multi-modal sensor at a preset part of a driving motor, and obtaining a multi-dimensional data signal collected by the multi-modal sensor; performing real-time filtering, amplification and noise reduction processing on the multi-dimensional data signal, and performing feature extraction on the multi-dimensional data signal by using a feature extraction algorithm to obtain a plurality of key feature parameters; based on a preset dynamic weighted fusion algorithm, fusing the plurality of key feature parameters to obtain fused key feature parameters; and establishing a hybrid deep network architecture consisting of a long-short term memory network and a convolutional neural network, and inputting the fusion key feature parameters into the pre-trained hybrid deep network architecture to obtain corresponding fault information of the driving motor. The problem of low fault diagnosis accuracy of the driving motor in the prior art is solved.

The invention provides a neurosurgery tumor patient personalized nursing intervention method based on big data. The neurosurgery tumor patient personalized nursing intervention method comprises the steps that physiological parameters, tumor characteristic data, behavior data and environment data of a patient are collected through a multi-mode sensor and an electronic medical record system; preprocessing the data to generate a standardized data set; extracting dynamic time sequence features and spatial correlation features based on a multi-modal fusion feature extraction algorithm; calculating an intensity parameter, a frequency parameter and a priority parameter of nursing intervention through a personalized intervention parameter generation algorithm according to the features; generating a personalized nursing intervention scheme in combination with the nursing rule base; a dynamic adjustment scheme is fed back through real-time data, and intervention parameters are corrected through a feedback compensation mechanism; and outputting the corrected intervention scheme to the nursing terminal equipment for execution. Accurate personalized nursing intervention can be achieved, the nursing scheme is dynamically adjusted, and the nursing effect and rehabilitation quality of neurosurgical tumor patients are improved.