234 results about "Neural network analysis" patented technology

The invention provides a space field game behavior dynamic evolution and strategy deduction optimization method and system, and relates to the technical field of space field game behavior optimization, and the method comprises the steps: analyzing historical behavior data through a deep neural network, constructing a dynamic relation graph of participants, inputting a multi-agent reinforcement learning model, and outputting a game behavior model. Then, a multi-layer game scene evolution tree is constructed, the instant income and the long-term risk are calculated in combination with a dual neural network, dynamic updating is performed by using a search algorithm of a hierarchical attention mechanism, and candidate evolution paths are generated; and finally, evaluating the candidate paths by using a strategy evaluation model constructed by a space-time diagram neural network, selecting an optimal strategy path, and generating a strategy deployment scheme implemented by stages in combination with a knowledge inference engine. According to the method, the evolution trend of the game behavior in the space field can be effectively predicted, a feasible strategy deployment scheme is provided, and the scientificity and effectiveness of strategy decision are improved.

The invention relates to the technical field of power battery packs, and discloses a power battery pack state evaluation method and system, and the method comprises the steps: collecting an operation characteristic data set of a power battery pack under various working conditions, and constructing a hybrid evaluation model; performing parameter configuration on the double-extended Kalman filter to obtain an improved filter; acquiring real-time voltage, current and temperature data, and inputting the real-time voltage, current and temperature data into the improved filter for state calculation to obtain a charge state value and an internal parameter value; inputting the charge state value and the internal parameter value to perform multi-branch adversarial neural network analysis to obtain a fault mode type and a fault severity; according to the method, the multi-factor health index is calculated, particle swarm optimization fitting is carried out on the degradation curve of the power battery pack, the residual service life prediction value is obtained, more accurate residual service life prediction is further achieved, the precision in a wide temperature range is remarkably improved, and the difference between monomers in the power battery pack can be effectively processed.

The invention provides an intelligent high-performance collaborative welding robot system, which belongs to the technical field of welding robots and comprises a multi-degree-of-freedom welding robot body, an intelligent control system, a high-performance welding power supply and auxiliary equipment. A welding process control module firstly obtains three-dimensional information of a workpiece based on visual inspection to construct a welding path; then selecting matched process parameters according to material characteristics and welding seam shapes; establishing a welding error matrix to monitor the welding process in real time; constructing a parameter error adjustment matrix for dynamic adjustment; analyzing parameter fluctuation by adopting a neural network to identify molten pool characteristics; the pre-trained neural network is used for evaluating the welding seam quality; and finally, a multi-robot collaborative welding strategy is integrated to achieve efficient operation, and the technical problem that in the prior art, welding process parameters in a welding robot are difficult to adjust accurately in real time so as to adapt to complex working condition changes is solved.

The invention relates to a fault diagnosis method for a server. Efficient fault positioning and processing are achieved by constructing a multi-dimensional intelligent diagnosis system. Constructing a server virtual model at each node and establishing a connection relationship, and collecting various data and mapping the data to the virtual model; performing weighted fusion on the data through correlation analysis, and extracting fault features including time and space correlation by using a bidirectional long-short-term memory network; fault probability distribution is obtained by means of a dynamic fault knowledge graph and graph neural network reasoning, and a fault evaluation result is visualized in combination with a virtual model; and finally analyzing the behavior deviation through a neural network and generating a processing strategy. Real-time processing of multi-source data, intelligent extraction of fault features and dynamic deduction of fault propagation are achieved, the accuracy, the real-time performance and the automation level of server fault diagnosis are effectively improved, and predictive maintenance and intelligent decision making of a complex server system are achieved.

The invention discloses a 3D printing process intelligent control method and system based on real-time feedback, and relates to the technical field of 3D printing, a data acquisition module collects a printing layer surface image and printing data in real time, constructs an image data set and a printing data set, and performs cleaning and standardization processing on the data in a preprocessing module; the image analysis module analyzes surface defects of a printing layer by using a convolutional neural network, generates a defect score D, compares the defect score D with a preset defect score threshold D1, evaluates the state of the printing layer and triggers early warning, and the comprehensive evaluation module calculates a crack generation probability Z by combining printing data and the defect score; and the intelligent control module compares the crack generation probability Z with a preset crack generation probability threshold value Zl, evaluates the printing state and feeds back and controls printing parameters according to a result, so that crack and structure defects in the printing process are effectively prevented and reduced, and the printing precision and the finished product quality are improved.

The invention provides a substation self-adaptive inspection method based on equipment health degree dynamic evaluation. The substation self-adaptive inspection method based on equipment health degree dynamic evaluation comprises the steps of S1, collecting electrical parameters, mechanical vibration parameters and environmental parameters of substation equipment in real time through a multi-source sensor network, and S2, performing data cleaning and time synchronization on the electrical parameters, the mechanical vibration parameters and the environmental parameters, and performing subset dynamic normalization processing. According to the substation self-adaptive inspection method based on equipment health degree dynamic assessment, electrical, mechanical and environmental parameters of the equipment are acquired in real time through the multi-source sensor network, and the real-time performance and accuracy of equipment health degree assessment are remarkably improved by combining dynamic normalization processing and real-time anomaly detection. And the LSTM neural network is used for analyzing the change trend of the equipment health index, so that the residual life of a key component can be predicted, and differentiated inspection and resource optimization allocation can be realized.

Disclosed herein is an artificial neural network-based medical image analysis apparatus for analyzing a medical image based on a medical artificial neural network. The artificial neural network-based medical image analysis apparatus includes a computing system, and the computing system includes at least one processor. The at least one processor is configured to acquire or receive a first analysis result obtained through the inference of a first artificial neural network from a first medical image, to input the first analysis result to a second artificial neural network, to acquire a first evaluation result obtained through the inference of the second artificial neural network from the first analysis result, and to provide the first evaluation result to a user as an evaluation result for the first medical image and the first analysis result.

The invention discloses a charging pile intelligent heat dissipation method and device based on heat conduction line optimization and a medium, belongs to the technical field of charging pile heat dissipation, and aims to solve the technical problem of how to avoid the defects of high thermal resistance, response lag and large energy consumption in a traditional charging pile heat dissipation scheme and improve the heat dissipation efficiency and operation reliability of a charging pile. According to the technical scheme, a heat conduction structure is optimized; deploying a thin film thermocouple and constructing a three-dimensional temperature field model through infrared thermal imaging; establishing a thermal resistance-flow-power transfer function model by adopting a fuzzy PID (Proportion Integration Differentiation) and model predictive control hybrid algorithm; historical charging data are analyzed based on an LSTM neural network, a power peak value is predicted 300 ms ahead of time, and heat dissipation equipment is pre-started.

The invention relates to the technical field of cross-border e-commerce storage, in particular to a deep learning cross-border e-commerce storage management system, which comprises a data acquisition processing unit, a space-time diagram neural network analysis unit, an alliance management scheduling decision unit and an equipment execution feedback unit, a data acquisition and processing unit acquires and preprocesses storage data, a space-time diagram neural network analysis unit constructs a space-time diagram and predicts task requirements and equipment states, an alliance management scheduling decision-making unit constructs a dynamic alliance and generates a scheduling instruction, and an equipment execution feedback unit receives the instruction and autonomously adjusts a strategy. The problems of unreasonable equipment scheduling, poor collaboration and resource waste in traditional cross-border e-commerce warehouse management are solved, intelligent scheduling and collaborative operation of the warehouse equipment are realized, and the warehouse management efficiency and the resource utilization rate are improved.

The invention relates to the technical field of power system monitoring, in particular to an electric energy meter and concentrator data fusion monitoring system and method. Comprising the steps that data of an electric energy meter are periodically collected, integrity verification is conducted on the data, noise interference in the data is removed, then the data are fused to construct a power network diagram structure, and the power network diagram structure comprises node information and edge weight information; a graph convolutional network is used for modeling, a power network graph structure is used as the input of a graph neural network model, an adaptive learning rate adjustment algorithm is combined with an early stop method to prevent overfitting and deep training of the model, and space-time association between nodes is captured through multi-layer space-time graph convolution operation. According to the method, the power network graph structure is constructed by fusing the data of the electric energy meter through the concentrator, nodes and edges are analyzed by using the graph neural network, key nodes and potential fault points are identified, and the network health state is evaluated in real time, so that comprehensive monitoring and optimal management of the power system are realized, and the overall performance and reliability of the power system are improved.

The invention discloses an edge calculation optimization and compression algorithm based on distributed optical fiber sensing data, and the algorithm achieves the full-section continuous monitoring of an embankment through the layering burying of a distributed optical fiber network along the axis of the embankment, and eliminates the blind area of a conventional point sensor. Strain data and temperature data are analyzed by using Brillouin scattering and Raman scattering, time sequence characteristics are analyzed through an LSTM neural network, and piping and crack hidden dangers are identified. External environment parameters such as water level and rainfall are fused to construct a multiple regression model, and the seepage risk level is evaluated. Through combination of BIM three-dimensional modeling and a seepage simulation algorithm, hidden dangers are accurately positioned, and spatial distribution of the hidden dangers is visualized. Based on edge calculation optimization, a data compression technology is adopted to reduce transmission requirements, a self-repairing material injection and high-pressure plugging scheme is triggered through a grading early warning system, closed-loop management from monitoring to repairing is formed, the real-time performance and accuracy of hidden danger recognition are improved, and efficient and reliable monitoring support is provided for dike engineering.

The invention provides a thermal imager intelligent temperature measurement method based on a neural network, and relates to the technical field of thermal imaging temperature measurement, and the method comprises the steps: firstly collecting an infrared image and a visible light image of a target object, and environment temperature and humidity data; then, the infrared image is preprocessed; then calculating an initial temperature value through a temperature compensation formula, correcting energy attenuation by utilizing humidity data, and processing an abnormal heating signal in combination with the visible light image and the humidity data; and finally, related data are analyzed by means of a neural network, and a corrected temperature value is output. According to the method, a temperature compensation formula combining heat exchange and atmospheric radiation difference is constructed, correction factors are adjusted according to humidity and atmospheric pressure, a visible light image is used for identifying the dirt accumulation level, infrared image features are analyzed in combination with a neural network, and multi-source data fusion and environmental factor dynamic compensation are achieved. The interference of environmental factors on the temperature measurement of the thermal imager is effectively overcome, and the temperature measurement precision and the equipment defect detection accuracy in a complex environment are improved.

The invention belongs to the technical field of bridge engineering, and particularly discloses a proxy model and finite element fusion method and system for bridge safety early warning. Comprising the following steps: simulating a real load of a bridge by adopting a structural multi-scale finite element model to calculate a bridge structural response, constructing a finite element agent model, and training the finite element agent model by adopting a data set to extract a relationship between weight matrix analysis and output items of a neural network; and in the refined grid division part, considering the damage directly observed by the structure, dividing the model parameters extracted from the monitoring point by the model parameters directly corrected by the damage to obtain a final corrected model. According to the method, sensor signal processing, model correction and finite element calculation are closely combined together through neural network analysis, a method basis is provided for dynamic evolution of a digital object fusion model, and technical support is provided for subsequent bridge structure safety evaluation and health early warning.

The invention discloses a digital station building equipment state intelligent monitoring system and method. The system comprises a data acquisition module, a multi-dimensional data processing module, an LSTM neural network analysis module and a state evaluation module. The data acquisition module acquires multi-modal time series data through a multi-type sensor group; the multi-dimensional data processing module performs space-time alignment and feature fusion on the data to construct a composite feature vector; the LSTM neural network analysis module adopts an attention gating mechanism to fuse dual-scale features, and outputs equipment state probability distribution and a residual life prediction value; and the state evaluation module updates the posterior probability of the health state of the equipment based on the dynamic Bayesian network so as to realize graded early warning and maintenance decision. According to the invention, the accuracy and predictability of equipment state monitoring are improved, the requirements of the digital station building for accurate monitoring and predictive maintenance of the equipment state are met, and the intelligent level of operation and maintenance management is improved.

The invention discloses a cervical lesion intercellular relation modeling and analysis system based on a graph neural network, and the system comprises a medical image collection module which is used for collecting a digital image of a cervical tissue pathological section or a cervical TCT slide; the cell detection and segmentation module is used for extracting spatial position information and morphological characteristics of cells; the cell feature extraction module is used for extracting and fusing the spatial position, morphology, texture and biological marker features of the cells; the cell relation graph construction module is used for constructing a heterogeneous cell relation graph with cells as nodes and inter-cell relations as edges; the graph neural network analysis module is used for carrying out feature learning and modeling on the heterogeneous cell relation graph; the intelligent auxiliary diagnosis module is used for generating auxiliary diagnosis suggestions; and the data management and automatic control module is used for realizing automatic control and case data management of the whole process of the data. The intelligent and automatic level of cervical lesion cell analysis can be comprehensively improved, and the accuracy and efficiency of diagnosis are improved.

The invention provides a device and method for predicting the risk of Pierre Robin syndrome by using audio, and the device comprises an audio collection module, a signal preprocessing module, a feature extraction module, a deep neural network analysis module and a result output module, and forms a complete processing link from signal collection to risk prediction. A continuous mapping function from a high-dimensional acoustic feature space to a low-dimensional risk assessment space is constructed mathematically, the problem of association between nonlinear time-frequency features and pathological states is solved, full-process automation from audio acquisition to risk prediction is realized, the accuracy and accessibility of PRS early diagnosis are improved, and the PRS early diagnosis efficiency is improved. Precious time is won for clinical intervention, the occurrence rate of PRS-related complications is expected to be remarkably reduced, the life quality of sick children is improved, and meanwhile, a new way is opened up for non-invasive acoustic screening of other diseases.

The invention relates to the field of network security, and particularly discloses a network security defense strategy optimization method based on machine learning, and the method comprises the steps: aggregating isolated security events into attack activity clusters through causal association analysis, constructing a dynamically evolved global attack graph, and improving a defense perspective from a discrete event to a full combat view. In order to realize foresight, a graph neural network is utilized to analyze a graph to identify attack tactics and predict the next intention. A hierarchical reinforcement learning framework is innovatively introduced in the decision-making stage; an upper-layer strategic agent formulates a macroscopic defense target based on a global situation; and the lower-layer tactical agent focuses on the related attack sub-graph under the strategic guidance, and selects and executes the specific tactical action which can reach the target most. The strategy and tactical separated decision-making mode ensures that each defense action serves a long-distance target, so that strategic passivity caused by only taking care of previous threats is avoided.

The invention provides an intelligent pod control method and system for an unmanned aerial vehicle. According to the method, multiple frames of thermal radiation images are obtained through an infrared imaging module of an unmanned aerial vehicle pod, a dynamic temperature field atlas is generated through heat source decoupling, and spatial relevance between heat sources is analyzed through an atlas neural network. Damping torque matched with wind disturbance is generated based on the temperature gradient vector, filtering parameters of the magnetofluid holder are optimized, and meanwhile the interference intensity between energy transmission paths is calibrated. A threat propagation path is generated by combining thermal diffusion characteristics, and the pod deflection angle is dynamically adjusted, so that the center of an optical view field is synchronized with the threat centroid, and accurate tracking and anti-interference control are realized. The method is used for intelligent pod control of the unmanned aerial vehicle. Through intelligent heat source analysis and adaptive adjustment, accurate and stable tracking of a threat target by the unmanned aerial vehicle pod is realized.

The invention relates to the technical field of clinical nursing, in particular to a clinical nursing system for interventional operations, which can accurately identify and predict potential complications by performing deep neural network analysis in combination with preoperative medical history, intraoperative real-time physiological data and operation types. It is ensured that a nursing scheme can be finely adjusted based on individual differences of patients, complex physiological data can be processed through a deep neural network, key physiological data are recognized from the complex physiological data, the scheme is dynamically adjusted in the nursing process through a long-short-term memory network, and the nursing accuracy is improved. The change trend of data in the operation is deeply mined, the fluctuation of physiological indexes is tracked, the abnormity is timely identified, the potential risk is predicted, the nursing decision and the physiological state of the patient can be synchronously updated, the working efficiency of nursing personnel is optimized, and the postoperative recovery effect and comfort of the patient are improved.

The invention relates to the technical field of robot control, in particular to a cross-modal perceptual driving body robot compliance control system which comprises the steps that a sensor is adopted to synchronously collect environment information, multi-source data bias is eliminated through a space-time alignment algorithm, a radial basis function neural network is adopted to analyze multi-modal fusion features, and a multi-modal model is obtained; human operation intention probability distribution is extracted to decompose a task into a path planning layer and a motion control layer, a collision-free trajectory is generated through an RRT algorithm, a high-fidelity physical engine is adopted to construct a virtual interaction scene, and robot learning results are shared through federal learning. According to the method, the problems of inaccurate perception, incoordination between intention recognition and interaction control, difficulty in control strategy verification, slow new task adaptation and difficulty in multi-robot learning result sharing caused by multi-source data deviation and large multi-modal semantic difference of the body robot in a complex environment are solved.

The invention discloses a traditional Chinese medicine plant combination anti-hair loss and hair growth formula optimization method based on a neural network algorithm, and the method comprises the following steps: S1, collecting hair health data of a user, and building a personalized health file; s2, based on the health record, analyzing the physiological and psychological states of the user in real time, and establishing an emotion-hair growth feedback mechanism to evaluate the risk of alopecia; s3, analyzing the health archive by using a deep neural network, predicting an alopecia trend and generating a personalized alopecia prevention and hair growth scheme; s4, matching optimal plant components and proportions through a neural network optimization model, and dynamically adjusting a pharmacodynamic model; s5, adaptively adjusting the plant formula proportion through a quantum neural adaptability learning mechanism; s6, simulating different formula effects through the virtual test platform, optimizing the formula and feeding back to the health file; and S7, forming a closed-loop feedback mechanism through continuous user feedback and physiological monitoring results, and regularly optimizing the formula. Through personalized analysis and dynamic adjustment, an accurate anti-hair loss and hair growth solution is provided.

Functional activation-based analysis of deep neural networks uses a structured set of inputs (e.g., input datasets corresponding to different knowledge or datatype domains) are sequentially provided to a pretrained neural network (e.g., according to a block-sequence). The output values for each node in the neural network are recorded and stored as a time-series of layer output values. A statistical analysis of the time-series of layer output values may be fit as a function of the structured set of inputs to generate neural network analysis data that indicate activations of layers within the neural network based on the inputs.

The invention discloses a boiler operation state intelligent monitoring method and system, and the method comprises the steps: collecting multi-source heterogeneous data in a boiler operation process, carrying out the cleaning and normalization processing of the multi-source heterogeneous data, extracting key features through wavelet transform, and obtaining standard multi-source heterogeneous data; modeling time series data in the standard multi-source heterogeneous data on the basis of an LSTM (Long Short-Term Memory) network, capturing a dynamic change trend of boiler operation to obtain time series characteristics, analyzing a hearth flame image and an infrared thermal image by using a CNN (Convolutional Neural Network), and extracting combustion state characteristics and thermal distribution characteristics; and based on the comprehensive state vector, a confidence interval of each feature dimension is calculated through a GMM Gaussian mixture model, an operation state deviation degree is analyzed and evaluated in combination with an entropy value, and when the deviation degree exceeds a preset threshold value, graded early warning is triggered. And the accuracy of boiler operation state intelligent monitoring is improved.

The invention discloses an intelligent greenhouse environment control method and system, particularly relates to the technical field of greenhouse control, and is used for solving the problem that the layering phenomenon is difficult to identify in the existing greenhouse carbon dioxide concentration monitoring. Modeling and identifying carbon dioxide concentration and gas flow distribution data in the greenhouse based on a clustering analysis algorithm to judge whether a carbon dioxide layering phenomenon exists or not; when a layering phenomenon exists, airflow velocity field characteristics are extracted through an optical flow method, a velocity field image is analyzed in combination with a convolutional neural network, and airflow vortex morphological characteristics of a local area of the greenhouse are identified; calculating the information entropy of the concentration change in combination with Shannon entropy, analyzing the diffusion path in combination with a dynamic programming algorithm, and evaluating the complexity of the diffusion path of the layered region; further identifying an eddy current risk area; the chlorophyll distribution characteristics of crops are analyzed through a spectral analysis algorithm, the growth abnormality is evaluated by combining carbon dioxide concentration data, and the abnormality is used as an auxiliary condition to precisely regulate and control ventilation and carbon dioxide supplementation.

The invention relates to the technical field of power grids, in particular to a power distribution network fault processing method. Comprising the following steps: carrying out fault detection by comprehensively considering various factors such as current, voltage, temperature and humidity through a multi-parameter detection method; through an intelligent algorithm, machine learning and a neural network, detection data are analyzed, and the accuracy and reliability of fault detection are improved; the single-phase earth fault positioning method mainly comprises the following steps of zero-mode traveling wave extraction, S transformation time-frequency matrix construction, fault feature extraction and a fault positioning algorithm. Through an automatic recovery system, according to a preset recovery strategy and remote control, rapid recovery of a fault is realized; through the intelligent scheduling system, the recovery path and sequence are optimized, and the recovery efficiency and safety are improved. The power distribution network fault processing method provided by the invention has the advantages of accurate fault detection, accurate fault positioning, high fault recovery efficiency and small influence of environmental factors.

The invention relates to the technical field of the Internet of Things, and discloses a biological material component analysis method and system based on the combination of the Internet of Things and a neural network, and the method comprises the steps: obtaining material sample data of a to-be-detected biological material and environment state data of an environment where the to-be-detected biological material is located, and extracting an intrinsic attribute index of the to-be-detected biological material from the material sample data, calculating the basic substance content of the biological material to be detected; calculating the characteristic absorption rate of the to-be-detected biological material so as to analyze the characteristic absorption intensity of the to-be-detected biological material; constructing a spectral line graph corresponding to the to-be-detected biological material, and re-extracting fingerprint spectral information of the to-be-detected biological material from the spectral line graph; and inputting the fingerprint spectrum information into a biological detection unit of a preset Internet of Things, outputting a corresponding induction signal sequence by using the biological detection unit so as to identify molecular configuration information of the to-be-detected biological material, and analyzing the material composition of the to-be-detected biological material by using a trained neural network. The accuracy of biological material component analysis can be improved.

The invention discloses a GIS equipment fault identification method based on a double-domain neural network, and relates to the technical field of power equipment fault diagnosis, and the method comprises the steps: extracting time domain critical features and frequency domain critical features of a health state and a fault state of GIS equipment, and forming a fault evolution feature library; calculating a time domain characteristic gradient and a frequency domain characteristic gradient by using a double-domain neural network, and measuring a difference value; and fusing the difference values through nonlinear mapping to generate a comprehensive feature vector, and identifying the GIS equipment fault type according to the matching degree of the comprehensive feature vector and a preset fault type feature. According to the method, the fault evolution feature library is created to record the fault critical features, the gradient difference between the real-time operation data and the critical features is analyzed by using the double-domain neural network, and the difference features of different domains are fused through nonlinear mapping for comprehensive matching, so that the accurate recognition of the GIS equipment fault is realized; the technical problem that a traditional single-domain method cannot effectively recognize early weak faults is solved.

The invention relates to the field of fractional calculus and partial differential equation solving, and discloses a novel fractional sub-equation neural network analysis solver, which comprises the following steps: constructing a full-connection neural network model, and substituting the formula into a fractional partial differential equation to obtain a fractional sub-equation neural network analysis solver; and a Riemann-Liouville fractional derivative is corrected by utilizing Jumarie which meets a chain rule, so that the problem is converted into an algebraic equation form. Unknown variables and coefficients of the integer order partial differential equation are extracted by using a symbol calculation tool, an overdetermined nonlinear algebraic equation set is generated, and the weight and bias of the neural network are obtained by solving the equation set. And finally, optimizing the preliminary analytical solution in combination with a special solution of a fractional order Riccati equation, and generating a final analytical solution comprising a generalized fractional order hyperbolic function, a generalized fractional order trigonometric function and a Mittag-Leffler function form. According to the method, the analytic solution efficiency is improved, the expression range of understanding is expanded, and meanwhile, the mathematical characteristics of fractional derivatives are reserved.

The invention discloses a supply chain full-process intelligent monitoring and dynamic scheduling optimization method based on the Internet of Things and digital twinning, and the method comprises the following steps: constructing a lightweight twinning body for a supply chain physical entity, binding the twinning body with a sensor corresponding to the entity, and storing the basic data of the entity; carrying out local data processing on each twinborn body through an edge computing node, and constructing a distributed training network by utilizing federated learning; the twinborn body monitors sensor data through a self-diagnosis module, and when data drift is detected, calibration parameters are generated and sensor output is corrected; according to the method, local anomaly detection and self-calibration of sensor data are realized through lightweight twin and edge computing node deployment: a data feature space is constructed by using a variational auto-encoder to identify drift, and spatial correlation of adjacent nodes is analyzed in combination with a graph neural network to realize data mutual verification, so that centralized monitoring dependence is broken through; the problem of data distortion caused by faults of a single sensor is solved.