248 results about "Recurrent neural nets" patented technology

The invention relates to the technical field of production debugging control, and discloses a production debugging control method and system for a plastic container. The method comprises the following steps: arranging a plurality of different sensors in plastic container blow molding equipment, and simultaneously collecting blow molding process parameter data; performing wavelet threshold denoising and anomaly identification on the blow molding process parameter data to obtain a process parameter anomaly identification result; establishing a transfer function matrix between the process parameters and quality indexes according to the process parameter anomaly identification result, and obtaining a target process parameter set through multi-target optimization; and inputting the target process parameter set into a double-integral enhanced recurrent neural network for parameter regulation and control calculation to obtain a process parameter adjustment amount. According to the method, early detection and accurate positioning of process abnormity in the blow molding process are realized, the quality fluctuation risk and the defective product rate are greatly reduced, and the technical problem that different response characteristic parameters are difficult to coordinate is solved.

The invention relates to the technical field of data processing, and discloses an intelligent risk early warning method, device and equipment for a power distribution network, and a medium. Historical risk monitoring data of the power distribution network under multiple dimensions are fused through a graph convolutional network and a variational auto-encoder; a variational recurrent neural network and a long-short term memory network are trained in combination with historical risk fault data of the power distribution network, and an attention mechanism is introduced in the training process to generate a risk assessment model; acquiring real-time risk monitoring data of the power distribution network under multiple dimensions to extract multi-dimensional real-time fusion features and inputting the multi-dimensional real-time fusion features into the risk assessment model for processing to obtain a real-time risk assessment level so as to further process the multi-dimensional real-time fusion features through a multi-criterion decision analysis method and a fuzzy inference system; the target risk assessment level is obtained, the level is compared with the risk early warning threshold value, if the level exceeds the threshold value, early warning is triggered, and the accuracy of power distribution network risk assessment is effectively improved.

The invention discloses a multi-modal content understanding method and system based on a knowledge graph, and belongs to the technical field of multi-modal content understanding, the method comprises the steps of obtaining multi-modal input data and conducting feature decoupling, semantic information in the multi-modal data and noise and redundant information peculiar to modals can be effectively separated through the feature decoupling technology, and the multi-modal content understanding efficiency is improved. The method comprises the following steps of: establishing a space-time perception graph attention network, improving the purity and semantic expression capability of features, bridging semantic gaps among different modals through the space-time perception graph attention network, realizing cross-modal semantic alignment, enhancing the generalization capability of a model, deeply mining space-time modes, relationships and anomalies in data through space-time association reasoning, and improving the accuracy of the data. The method provides support for multi-modal data analysis in a complex scene, and combines a graph neural network and a recurrent neural network to capture semantic association and spatial-temporal dynamics and optimize the performance of an inference model.

The invention provides a third-generation semiconductor device multi-physical field coupling effect dynamic monitoring method and system, and relates to the technical field of semiconductors, and the method comprises the steps: collecting the data of a temperature field, an electric field, a magnetic field and a stress field through a complementary sensor array, constructing a feature tensor, inputting the feature tensor into a pre-trained graph neural network, and extracting a coupling effect dynamic evolution rule; on-line analysis and prediction are carried out by using an adaptive time window and a recurrent neural network, a multi-field coupling correlation degree evaluation model is established, an early warning level is determined according to the deviation between the coupling correlation degree and an early warning threshold value, and device risk evaluation and maintenance suggestions are generated, so that early warning of the failure risk of the semiconductor device is realized.

The invention relates to the technical field of the Internet of Things and artificial intelligence, and discloses an equipment maintenance fault intelligent analysis method and system based on the Internet of Things, and the method comprises the steps: representing an entity and a relation as a time function, and constructing a time sequence knowledge graph; monitoring vector change in the knowledge embedding space, detecting a concept drift phenomenon and mining an equipment performance evolution mode; constructing an equipment state transition model by using a recurrent neural network, predicting the future state of the equipment and evaluating the fault risk; collecting feedback processing knowledge conflicts and updating the model; generating multi-time-scale fault risk early warning and maintenance suggestions; according to the method, the knowledge acquisition efficiency is improved, dynamic knowledge support of the full life cycle of the equipment is provided, early recognition of gradient faults is realized, the method has adaptive knowledge updating capability, multi-dimensional fault analysis is provided, maintenance resource configuration is optimized, and the equipment management efficiency is improved.

The invention provides a neuromorphic visual target tracking method and system based on image processing, and relates to the technical field of neuromorphic calculation, and the method comprises the steps: fusing the input of an event camera and a conventional image sensor, constructing a combined input tensor, and introducing a multi-scale convolution and synaptic event driving mechanism. Quick response and stable feature extraction of a high-speed moving target are realized, and coding block mistaken deletion and tracking loss caused by quick movement of the target are effectively avoided, so that system delay is reduced. Meanwhile, in combination with significance entropy difference evaluation and a dynamic brightness enhancement mechanism, the target judgment accuracy under low illumination and complex backgrounds is improved; redundant noise blocks are screened out through a significance weight function and confidence calculation, the redundancy calculation burden is relieved, and the lightweight characteristic of the system is guaranteed. A memory trajectory tensor and dynamic template adjustment mechanism based on a recurrent neural network is further introduced, time sequence consistency verification and self-adaptive updating are achieved, and the stability and robustness of the tracking process are enhanced.

The invention discloses a concrete internal defect quantitative detection method and system based on reflected waves, and belongs to the technical field of nondestructive testing. A reflected wave data matrix is obtained through multi-angle excitation and synchronous receiving; calculating energy characteristics of each channel, and constructing an energy response residual field; extracting waveform offset, spectrum jitter and phase change caused by defects by adopting a disturbance comparison algorithm to form a disturbance feature vector set; a defect-response function curved surface is further constructed, a defect topological structure is inversed based on gradient and curvature analysis, and defect geometric parameters are output; and finally, inputting the multi-moment defect parameters into the recurrent neural network, and predicting a defect evolution path and a failure risk. The method has high resolution and trend prediction capability, and is suitable for detection and early warning of concrete structures in bridges, tunnels and nuclear power projects.

The invention provides a hydro meteorology early warning method for an offshore oil and gas platform, and belongs to the technical field of offshore hydro meteorology. Extreme weather events are identified by adopting minimum probability abnormal event identification vectors to match abnormal characteristic parameters, and abnormal signal characteristic parameters are input into an ocean dynamics prediction model to calculate real-time sea condition parameters; calling a multi-temporal-spatial-scale early warning fusion matrix to combine with a wavelet decomposition technology and a recurrent neural network to realize multi-scale information integration, analyzing an environmental parameter change trend through a sea condition jump identification model and triggering an emergency response, dynamically adjusting system parameters according to a stability evaluation index vector, and optimizing prediction precision by adopting an early warning residual value compensation matrix. And finally, multi-level early warning information is generated and a real-time early warning notification is sent to an operator, so that the technical problem of insufficient early warning precision of an offshore oil and gas platform hydro meteorology early warning system in multi-spatio-temporal scale data fusion processing is solved.

The invention discloses an AI search recommendation method, system and device combined with commodity semantic understanding and a medium, and belongs to the technical field of commodity recommendation. The method comprises the steps that semantic vectors of commodity titles and descriptions are generated; generating a feature vector of the commodity image; fusing the semantic vector of the commodity title and description with the feature vector of the commodity image to generate a comprehensive semantic vector of the commodity; generating a user interest vector; updating the user interest vector by using a recurrent neural network based on the user interest vector; and carrying out joint modeling on the comprehensive semantic vector of the commodity and the updated user interest vector to generate a recommendation result. According to the method, a content semantic driving modeling mode is adopted, recommendation judgment can still be conducted through the deep matching relation between commodity image-text semantics and user behavior preferences even under the condition that user historical behaviors are limited or new commodities are online, good cold start adaptability is achieved, and the method is suitable for popularization and application. And meanwhile, high recommendation difference and content diversity are shown for different user groups.

The invention discloses a high-precision AI positioning method and system based on spatial multi-modal data fusion, and belongs to the technical field of fusion positioning, and the method specifically comprises the steps: collecting satellite positioning signals, inertial measurement data, visual images, laser radar point clouds, high-precision maps and other spatial multi-modal data; analyzing visual image illumination distribution, laser point cloud atmospheric particle density distribution and a satellite signal multipath reflection path to generate an environment physical attribute parameter set; inputting the original data of each modal into a correction function bound with environmental parameters, and outputting a standardized feature vector subjected to error compensation; and finally, inputting the recurrent neural network with space-time memory, and outputting the six-degree-of-freedom pose of the carrier by dynamically adjusting each modal feature fusion weight coefficient. According to the invention, through deep fusion of multi-modal data and environmental physical attributes, the problems of poor environmental adaptability and insufficient dynamic adjustment in the prior art are solved, and the precision and robustness of positioning in a complex scene are improved.

The present invention relates to urban rainfall runoff pollution prediction in urban water systems, and provides an urban rainfall runoff pollution prediction method based on integrated rolling decomposition method and deep learning algorithm. A rolling decomposition method is firstly used to decompose rainfall runoff sequence data into different sub-sequences; then decomposition is sequentially performed on added data, and future data is excluded, to prevent information leakage; a recurrent neural network is used to model and predict the sub-sequences; and finally, predicted results of the sub-sequences are summed to obtain the predicted result of rainfall runoff pollution.

The embodiment of the invention provides a barrel service life prediction method and device based on gradient enhancement and a quantile recursive network, and the method comprises the steps: collecting the multi-source sensor data of the whole life cycle of a barrel, and carrying out the preprocessing, and forming a standardized data set; constructing an XGBoost model, performing feature importance analysis on the standardized data set through the XGBoost model, screening key features based on an analysis result to obtain a data set after feature selection, and performing optimization training on the XGBoost model through gradient lifting and regularization methods; dividing the data set after feature selection into a training set and a test set; in combination with a quantile regression method, constructing a life prediction model based on a quantile recurrent neural network, training the life prediction model by using the training set, and training and optimizing model parameters through a bifurcated sequence to obtain an optimized barrel life prediction model; and inputting a test set into the model, outputting a residual service life prediction result containing a prediction value and a confidence interval, and evaluating the prediction performance.

The invention relates to the technical field of constructional engineering, and discloses a bridge hanging basket installation accurate positioning automatic operation method, which comprises the following steps of: acquiring image data of the position, the speed, the posture and the construction environment of a bridge hanging basket in real time by installing a high-precision sensor and a visual system; analyzing the acquired image data by using a deep learning model, and identifying and estimating the spatial position and angle of the hanging basket; the system comprises a high-precision sensor and an image acquisition system which are used for acquiring the position, attitude and environmental data of the hanging basket in real time; the deep learning module comprises a convolutional neural network and a recurrent neural network and is used for recognizing the position of the hanging basket in real time and predicting future deviation; and the nonlinear optimization module is used for calculating optimal control input in real time according to the optimization objective function and correcting the optimal control input. By adopting the technical scheme of the high-precision sensor and the image acquisition system, real-time accurate monitoring of the position, the posture and the construction environment of the hanging basket is achieved.

The invention relates to a multi-source disturbance perception and self-adaptive regulation and control technology in an electroplating production process, and aims to solve the problem that the process uniformity is difficult to guarantee due to diverse and dynamic changes of disturbance sources in an electroplating process. The invention provides a regulation and control method taking multi-dimensional disturbance sensing signal acquisition, preprocessing, recurrent neural network prediction, spatial distribution modeling and meta-learning reinforcement learning regulation and control as the core. The method comprises the following steps: acquiring various disturbances and auxiliary parameters such as fluid, temperature and current in real time, performing denoising, normalization and time sequence alignment processing, dynamically predicting a disturbance trend by using a recurrent neural network, and combining with process parameters to form high-expression feature input. And training the reinforcement learning regulation and control model by using a meta-learning algorithm to realize rapid adaptive optimization of the process parameters in the new disturbance scene. According to the system, through real-time feedback and dynamic self-optimization, the electroplating uniformity and the production stability are improved, and the robustness and the self-learning ability to a complex disturbance environment are effectively enhanced.

The invention provides a robot social adaptive navigation knowledge learning and migration method and system, and relates to the field of mobile robot navigation. Aiming at the problems that an existing path planner lacks time sequence memory and neglects pedestrian social intent, a man-machine co-fusion scene is constructed, a training set containing an expert demonstration path is made, and a recursive generation model is input; designing a recurrent neural network embedded RRT, generating an RNN-RRT planner, and fusing historical information and pedestrian convergence probability in training; new scene loading training parameters are finely adjusted to realize knowledge migration, loss convergence or output RNN final parameters after reaching a preset round number. According to the method, the path anthropomorphism and generalization ability are improved, and the method is suitable for complex human-computer interaction scenes.

The invention relates to a quay crane RTK positioning precision evaluation method and system and a storage medium, and the method comprises the steps: L1, when an unmanned container truck carries out the container loading and unloading operation under a quay crane, the quay crane RTK feeds back the positioning value of a vehicle according to a fixed frequency, and obtains the data information of the positioning value of the vehicle within a fixed time; l2, based on the data information of the positioning value of the vehicle within the fixed time, predicting the positioning value of the vehicle by adopting an improved ELMAN dynamic recurrent neural network prediction algorithm optimized based on a particle swarm optimization algorithm to obtain the data information of the predicted positioning value of the vehicle; and L3, based on the predicted data information of the positioning value of the vehicle, optimizing the positioning value of the vehicle by adopting a zebra optimization algorithm of a self-adaptive dynamic learning factor based on global search to obtain the optimized data information of the positioning value of the vehicle. The alignment success rate of the unmanned container truck can be increased, and harbor area operation can be prevented from being affected.

The invention relates to the technical field of computer vision and multi-sensor data fusion, in particular to a multi-sensor image fusion obstacle real-time detection and tracking system, which comprises the following steps of: firstly, fusing data of a camera, a millimeter wave radar and a laser radar, and extracting and fusing multi-modal features; performing multi-target tracking based on a recurrent neural network: generating a target state through space-time modeling, associating a target with a historical track by using an attention mechanism, and maintaining track consistency; and the system performs semantic classification and interaction analysis on the obstacle, predicts the movement track of the obstacle, realizes deep semantic understanding, and finally outputs the identity label and the complete historical track of the obstacle.

The invention discloses a Fourier sequence diagram learning method and system for cross-cycle power load prediction, and relates to the technical field of power system prediction, the system comprises a feature extraction module, a spatial relationship modeling module and a data processing and feature fusion module, and multi-scale Fourier transform belongs to the feature extraction module. Parallel graph attention network expansion belongs to a spatial relation module, joint optimization framework perfection belongs to a data processing and feature fusion module, multi-scale Fourier transform comprises dynamic spectrum reconstruction and multi-resolution spectrum fusion, the dynamic spectrum reconstruction is based on a recurrent neural network and variants thereof, and the multi-resolution spectrum fusion is based on the recurrent neural network. According to the method, the future change trend is predicted according to the fluctuation mode in the historical data, the frequency domain features are dynamically adjusted, and the dynamic change of the data is captured, and the method has the advantages that the power load is predicted more accurately by using the multi-scale Fourier transform and the parallel graph attention network.

The invention relates to the technical field of photoelectric pod target tracking, and discloses a multi-mode target automatic identification tracking method and system based on a photoelectric pod. A multi-modal data acquisition module of the system integrates visible light, infrared thermal imaging and laser ranging sensors based on a photoelectric pod, acquires target multi-modal sensing data and completes time-space synchronous calibration; the dynamic feature extraction module adopts a multi-scale convolutional neural network to process multi-modal data, generates a target multi-level feature map and performs significance region labeling; the adaptive tracking decision module deploys a recurrent neural network to predict a target motion trajectory according to a labeling result, and generates a tracking control instruction through an optimization algorithm; the execution control module drives the photoelectric pod holder mechanism and adjusts the orientation of the sensor to realize target tracking; the feedback optimization module monitors the tracking state in real time, calculates a tracking deviation index, and generates a strategy adjustment parameter to dynamically optimize the tracking strategy.

The invention discloses a student state real-time analysis method and device based on deep learning, and the method comprises the steps: obtaining and preprocessing image data of students in a classroom, and carrying out the multi-scale face detection and facial feature extraction of the preprocessed image data; expression features are extracted based on standardized facial feature data, fusion is carried out in combination with attention indexes and attitude features, a time sequence feature sequence is constructed, a heavy-tailed recurrent neural network is applied to carry out time sequence modeling, an evaluation standard is established, evaluation parameters are adjusted through a self-adaptive threshold value, and finally a student state evaluation result is obtained. Through the heavy-tailed recurrent neural network and a slow transition mechanism to low-dimensional chaos, subtle changes and long-term trends of student states can be accurately captured, and the technical problems that a traditional student state monitoring method is poor in real-time performance, limited in coverage and insufficient in individuation are solved.

The invention discloses a voiceprint characterization method and system for resisting voice conversion and voice synthesis based on deep learning. Relates to the field of speech recognition and biological feature security. Comprising the steps of 1, acquiring an input voice sample signal in an automatic speaker verification system, and extracting an FBANK feature of the voice sample signal; 2, performing depth feature extraction on the FBANK features by using a convolutional neural network (CNN) to obtain a depth feature vector; 3, processing the depth feature vector by using a recurrent neural network (RNN), and generating a forged identity vector of the voice; and 4, classifying the counterfeit identity vectors by using a linear discriminant analysis (LDA) module, and outputting a judgment result. According to the invention, the accuracy of counterfeit detection can be effectively improved in both clean and noise environments.

The invention provides a power grid data anomaly detection method and system based on a hybrid deep learning model, and belongs to the technical field of power grid data processing. According to the method, a convolutional neural network is combined with a recurrent neural network, a gating circulation unit, a long-short-term memory network and an attention model to carry out hybrid modeling, an initial detection model is obtained, and meanwhile, a model collaborative optimization mechanism is adopted to carry out distributed parallel training on the initial detection model; constructing an adaptive optimizer through an adaptive optimization algorithm, and dynamically updating model parameters and a model structure by using the optimizer and a dynamic training mechanism to obtain a hybrid detection model; and inputting the real-time data stream of the power system into the hybrid detection model for anomaly detection, and executing an active security protection operation on the power system according to the detected abnormal data and potential attack behaviors according to a preset defense strategy. According to the invention, accurate detection and real-time early warning can be carried out on complex abnormal behaviors of the power system.

The invention discloses a low-altitude large-speed small-radius maneuvering control method for an unmanned aerial vehicle. The method comprises the steps of data acquisition and preprocessing, establishment of an accurate unmanned aerial vehicle model, design of a model prediction controller, sensor fusion, real-time control and the like. Flight state data is collected and preprocessed through various sensors, dynamics and kinematics models considering aerodynamic nonlinearity are established, a model prediction controller is designed by using a recurrent neural network and a particle swarm optimization algorithm, sensor fusion is performed by using an extended Kalman filtering algorithm, and a model prediction model is established. Accurate control of the attitude and track of the unmanned aerial vehicle is realized. Meanwhile, the functions of environment perception and obstacle avoidance, fault diagnosis and fault-tolerant control, real-time controller parameter adjustment, target optimization and the like are added, the maneuvering performance, adaptability and safety of the unmanned aerial vehicle are improved, and the unmanned aerial vehicle can be widely applied to the fields of military reconnaissance, logistics distribution, film and television shooting and the like.

The invention discloses a laser welding control method and system based on machine vision, and relates to the technical field of laser welding, the system collects operation data and welding image data of laser equipment in real time by integrating a sensor group and an industrial camera, and preprocesses the operation data and the welding image data to ensure the accuracy and the reliability of the data; the deep learning module identifies related features in the image data by using a convolutional neural network CNN and a recurrent neural network RNN, and performs feature extraction; the data analysis module processes the extracted features to obtain a light spot shape distortion index SSD, a pulse characteristic index MCT and a fusion depth index WPD; the comprehensive analysis module calculates the indexes to obtain a comprehensive welding quality index CWQI; and the welding evaluation control module evaluates, regulates and controls the welding quality by utilizing a historical standard welding quality fusion depth interval and a preset quality threshold value, so that the welding quality is controlled by collecting welding piece data and collecting welding laser in real time.

The invention belongs to the technical field of aircraft control, particularly relates to a range extender control system for an unmanned aerial vehicle and a controller, and aims to solve the problems of limited endurance, poor flight stability and the like caused by discontinuous energy supply and power response lag. The system comprises a range extender power source module, an electric energy conversion and distribution module, a flight state sensing module, a load power prediction module, a multi-target optimization scheduling module and a closed-loop feedback execution module. Through flight state real-time perception and load power prediction based on a recurrent neural network, an optimal power generation instruction is generated in combination with multi-target optimization scheduling, and precise rotating speed tracking is realized through adaptive PID control. A fuel consumption, power supply smooth switching and battery health combined cost function is introduced, dynamic weighting is carried out according to task types, and the cruising ability and the system robustness are improved; the system has the functions of fault emergency response, power battery hot plug and model online updating, and safety and maintainability are enhanced.

The invention relates to a multi-granularity interest point recommendation method based on a geography-time mixed tree structure. The method comprises the following steps: collecting sign-in data of each user; clustering the geographic positions of the sign-in points to obtain a clustering result containing a plurality of geographic clusters, dividing each piece of sign-in data into each geographic cluster, and distributing corresponding geographic cluster labels; segmenting time, counting geographic clustering labels of all sign-in points in all time periods to obtain a track-level geographic hierarchical structure, and organizing the track-level geographic hierarchical structure into a tree structure to obtain a geographic tree and a time tree; a multi-level recurrent neural network is adopted to establish a recommendation model, geographic features and time features are obtained based on the geographic tree and the time tree, the input of the recommendation model is the geographic features and the time features, and the output of the recommendation model is a prediction result of interest point recommendation; inputting the spatio-temporal information of the current user into the trained recommendation model, and outputting the predicted next potential interest point by the recommendation model; and a more accurate interest point recommendation result is obtained.

The present invention relates to proteomics, and techniques for predicting de novo sequencing of chains of amino acids, such as peptides, proteins, or combinations thereof. Particularly, aspects of the present invention are directed to a computer implemented method that includes obtaining a digital representation of a mass spectrum, the digital representation including a plurality of container elements, encoding, using an encoder portion of a bidirectional recurrent neural network of long short term memory cells and gated recurrent unit cells, each container element as an encoded vector, decoding, using a decoder portion of the bidirectional recurrent neural network, each of the encoded vectors into a sequence of amino acids; and recording the sequence of amino acids as a multi-dimensional data set of amino acids types and a probability of each of the amino acid types in each position of the complete amino acid sequence.

The invention discloses a time-varying and time-lag multi-CSTR system adaptive control method and system based on a neural network, and the method comprises the steps: collecting key operation parameters of a multi-CSTR system in real time, constructing a time-varying and time-lag dynamic model through a recurrent neural network, and updating a time-lag parameter estimation value. And designing a hierarchical neural network structure comprising an upper global coupling model and a lower local compensation model, designing an adaptive algorithm based on a stability theory to adjust the weight of the neural network, and generating a control instruction to drive an execution mechanism. The system correspondingly comprises a data acquisition layer, a time-varying time-delay estimation module and the like. According to the scheme, the problems of time varying, time lag and coupling of the multi-CSTR system are solved, and stable operation of the system is guaranteed.

Provided is an underwater acoustic target recognition (UATR) method based on a recurrent neural network (RNN) structure and differential learning rate (LR) retraining, which is specifically aimed at identification and classification issues of ship underwater acoustic targets. Specific implementation steps include: 1. A ship underwater acoustic signal is preprocessed. 2. A UATR depth model is constructed based on a pre-trained model. 3. Retraining configuration. 4. The model is retrained to implement migration to a target domain. 5. A high-performance classification model for UATR is trained. In a model structure of this application, the pre-trained model is combined with the newly added RNN structure and a classification layer, so that a model obtained after retraining can more accurately identify an underwater acoustic target.

The invention discloses a Tokamak temperature diagnosis reconstruction method and device based on a data-driven model, and belongs to the technical field of machine learning and nuclear fusion physical crossover, and the method comprises the steps: firstly, carrying out the training of a data-driven model based on the fusion of a recurrent neural network and a self-attention mechanism through the large-scale Tokamak experiment data, and carrying out the reconstruction of the Tokamak temperature diagnosis. The complex correlation between various diagnosis signals and electronic temperature diagnosis is learned; secondly, an efficient data processing mode is provided, tokamak original signals are divided into equal-length sub-data in a window division mode, and the data are packaged and stored in an array form after being subjected to data processing so that the data can be directly used for further processing, reading, training and reasoning of subsequent machine learning; finally, the model can be seamlessly integrated into an existing Tokamak data management system by excluding a control reference signal. According to the invention, relatively accurate electronic temperature diagnosis reference can be provided.