47 results about "Dynamic neural network" patented technology

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

The invention discloses a short temporary rainfall forecasting method and system based on a dynamic neural network architecture. According to the method, training sample distribution is optimized through a space-time gradient driven resampling strategy, a time-frequency double-branch dynamic network architecture is adopted, a time domain branch extracts multi-scale space features through an encoder-decoder structure, a frequency domain branch adaptively activates an FFT calculation module through a content awareness dynamic network to capture multi-scale time features, and the multi-scale time features are obtained. And two key problems of meteorological data distribution imbalance and deep learning model optimization imbalance are solved in combination with a balance regression loss function. According to the method, adaptive computing resource allocation for meteorological events with different complexities is realized, the forecasting precision and computing efficiency of heavy rainfall events are remarkably improved, and an efficient and reliable technical solution is provided for short temporary rainfall business forecasting.

The invention relates to the technical field of industrial automation control, and discloses a mixed PID temperature control system and method based on GDNN and multi-modal prediction. The system comprises a data acquisition module, an enhanced GDNN core controller, a prediction optimization module and an actuator module. And real-time adaptive tuning of PID parameters (Kp, Ki and Kd) is realized by fusing a general dynamic neural network, a genetic algorithm optimization initial weight, a variable learning rate and an additional momentum method, and a prediction model module of a multi-layer perceptron (MLP) and a radial basis function (RBF) network. According to the system, nonlinear, time-varying and interference factors can be processed for temperature control scenes such as a high-temperature furnace and a drying system, the mean absolute error, overshoot and stabilization time are remarkably reduced, and the energy efficiency is improved. A multi-modal sensor fusion and edge computing framework is innovatively introduced, and distributed industrial application is supported. The system is suitable for the fields of high-temperature furnaces, drying systems, intelligent buildings and the like, and provides high robustness and interpretability.

Apparatuses, systems, and techniques to assign a processing resource to an inference request directed to a neural network based on an amount of information to be inferenced indicated by said request. In at least one embodiment, an AI application is deployed with a software wrapper that intercepts inference requests and dynamically distributes such requests among available processing resources such as host processor(s) and / or AI accelerator(s) to improve execution performance of said AI application.

The invention provides an electrocardiosignal anomaly detection method fused with electrocardiosignal propagation simulation. The method comprises the steps that a space diagram structure is established based on ECG data; performing spatial position mapping on each electrode and establishing a heart simulation physiological model; feature extraction is carried out on each electrode node, and a dynamic space diagram structure is constructed; based on a dynamic graph structure, through multi-layer graph convolution updating and time aggregation, global space-time feature vectors are output, electrocardiosignal detection categories are output through a classifier, a space dynamic neural network model is constructed, a total loss function is established for model optimization, the electrocardiosignal detection categories are predicted, and quantitative recognition of abnormal propagation paths is achieved. And iteratively optimizing the dynamic graph structure. According to the method, unified modeling is carried out through time dynamics and spatial relevance of physiological signals, the defect that a static graph cannot capture abnormal changes of a propagation path in a pathological state is overcome, and the accuracy of cardiovascular disease diagnosis and the effectiveness of clinical decision support are remarkably improved.

A method for online target counting on unmanned aerial vehicles (UAVs) based on a multimodal dynamic neural network includes the following steps: First, the UAV uses an onboard visible light camera and a thermal infrared camera to capture visible light and thermal infrared images, respectively. Then, the segmented images are used as input to a target counting model. The target counting model is a target counting model based on a multimodal dynamic neural network. When thermal infrared images are unavailable, the visible light images are converted into thermal infrared images using a mode conversion network. Multimodal gating analysis is performed on the scene illumination where the images are located. If the illumination is good, only the visible light mode branch of the target counting model is selected; if the illumination is insufficient, both the visible light mode branch and the thermal infrared mode branch are selected, with the thermal infrared images used as auxiliary data. A feature extraction network extracts the modal features of the selected modal branches and fuses the features from the multimodal inference flow. The features obtained in step S3 are decoded to obtain the output of the target counting model.

The invention discloses a fan nonlinear load self-adaptive control method and device and a storage medium. The fan nonlinear load self-adaptive control method and device are used for efficiently achieving dynamic tracking control over fan nonlinear loads. The method comprises the steps of collecting operation state data of a fan system; constructing a dynamic neural network model containing a long short-term memory network-attention mechanism mixed structure, inputting the operation state data into the dynamic neural network model, and outputting a dynamic predicted value of the fan nonlinear load; constructing an adaptive model prediction controller based on the dynamic prediction value, and generating a control sequence; calculating a prediction residual error of the dynamic neural network model, and when the prediction residual error exceeds a standard threshold value, triggering a model updating mechanism; performing parameter updating on the dynamic neural network model by adopting an incremental learning algorithm with gradient constraint to obtain updated parameters; and the safety control quantity is output to a fan execution mechanism, and dynamic tracking control over the nonlinear load of the fan is achieved.

The invention provides a heterogeneous perception adaptive low-bit neural network deployment method, and relates to the technical field of artificial intelligence and heterogeneous computing, and the method comprises the steps: firstly obtaining the hierarchical computing feature information of each layer of a neural network and the dynamic feature parameter information of heterogeneous hardware, and forming a multi-level basic information set; and then a hierarchical efficiency association model is constructed to describe the association relationship among the calculation precision, the hardware dynamic characteristics and the layer calculation efficiency. During online operation, a hardware real-time load state and an energy efficiency constraint condition are tracked to generate a dynamic state monitoring result, and the dynamic state monitoring result and the dynamic state monitoring result are combined to generate a hierarchical deployment configuration scheme by adopting a multi-objective optimization algorithm. And finally, a lightweight runtime scheduler is called to allocate calculation tasks according to the scheme, and interlayer dependency data is loaded and executed, so that dynamic neural network deployment across hardware equipment is realized, and the deployment effect and the operation efficiency are improved.

The invention relates to the technical field of traditional Chinese medicinal materials, in particular to an intelligent detection, regulation and control method based on a traditional Chinese medicinal material planting environment, which comprises the following steps: S1, multi-modal data acquisition: acquiring environmental parameters and plant physiological parameters of a planting area in real time; s2, dynamic neural network modeling: performing space-time correlation analysis on the environmental parameters and the plant physiological parameters to generate a dynamic weight matrix; s3, fuzzy control and rolling optimization: according to the dynamic weight matrix, combining a fuzzy control algorithm to generate a multi-target cooperative regulation and control parameter; and S4, closed-loop feedback and model iteration: driving an execution mechanism to perform environment regulation and control, and correcting a dynamic weight matrix and regulation and control parameters in real time through an online feedback mechanism to form closed-loop control. According to the method, multi-mode sensing data are fused through the dynamic graph neural network, intelligent regulation and control of the traditional Chinese medicinal material planting environment are achieved, the light-temperature-water-fertilizer cooperation strategy is accurately optimized, the secondary metabolite synthesis efficiency is remarkably improved, energy consumption is reduced, and the method adapts to different medicinal material characteristics and environment changes.

The application provides a robot driving control method, device, equipment and storage medium, comprising: calculating a tracking error according to a desired trajectory and an actual running trajectory corresponding to each joint of a current time of a linkage robot; calculating the tracking error by using a sliding mode control algorithm to obtain a first input torque of the current time; taking an actual input torque of a previous time and the actual running trajectory as inputs of a dynamic neural network to predict an unknown torque in a robot dynamics model at the current time, and taking the predicted unknown torque as a second input torque of the current time; determining an actual input torque of the current time according to the first input torque and the second input torque, and controlling the linkage robot to move according to the actual input torque of the current time; and solving the problem of stability and accuracy decline of the linkage robot caused by various uncertain factors in the prior art.

The invention discloses a flexible load resource aggregation method based on an improved dynamic neural network, and relates to the technical field of flexible load resource aggregation and regulation, and the method comprises the steps: carrying out the analysis of the composition and adjustment characteristics of a flexible load, and obtaining a flexible load resource adjustable capability quantitative index, a generalization mathematical model is constructed based on the flexible load resource adjustable capability quantitative index, the generalization mathematical model comprises an electric vehicle model and an energy storage model, clustering analysis is carried out on the generalization mathematical model, a flexible resource pool model is formed through coupling, and the flexible resource pool model is optimized to obtain a flexible load resource aggregation optimization model; according to the flexible load resource aggregation optimization method based on the improved dynamic neural network, the adjustable potential of flexible loads such as electric vehicles and energy storage is accurately evaluated, and the problem that multi-type load collaborative optimization is insufficient in a traditional method is effectively solved; and high-precision resource support is provided for scenes such as peak regulation and frequency modulation.

The application provides a heterogeneous-aware adaptive low-bit neural network deployment method, and relates to the fields of artificial intelligence and heterogeneous computing technology. First, hierarchical computing feature information of each layer of a neural network and dynamic characteristic parameter information of heterogeneous hardware are acquired to form a multi-level basic information set. Then, a hierarchical performance correlation model is constructed to describe the correlation between computing accuracy, hardware dynamic characteristics and layer computing performance. During online operation, real-time hardware load state and energy efficiency constraint conditions are tracked to generate dynamic state monitoring results. A multi-objective optimization algorithm is used in combination with the two to generate a hierarchical deployment configuration scheme. Finally, a lightweight runtime scheduler is called to allocate computing tasks, load inter-layer dependent data and execute according to the scheme, thereby realizing dynamic neural network deployment across hardware devices and improving deployment effect and operation efficiency.

The present invention discloses a method for edge collaborative task division and resource allocation based on model segmentation, which relates to the field of edge computing video analysis, and integrates CNN channel pruning, bilinear sampling and affine quantization to multi-dimensionally compress intermediate transmission feature data; a parameter-sharing dynamic neural network is trained based on the sandwich rule and knowledge distillation technology to realize real-time switching of the feature data compression amplitude; user reasoning performance indicators in edge collaborative task division are modeled, and an optimization problem for maximizing reasoning accuracy that meets user performance requirement constraints and edge resource constraints is constructed; a solution algorithm based on dynamic programming is used to select the optimal model segmentation point and intermediate feature compression parameter configuration for the user, and at the same time, edge communication resources and computing resources are efficiently allocated to improve its reasoning accuracy under multi-user conditions.

The present application relates to the field of intelligent recommendation. In particular, it relates to a product recommendation method and system based on state updating. The method comprises obtaining product state time series data and consumer preference state time series data, inputting them into a recommendation model based on a double-state dynamic neural network, outputting product feature vectors and consumer preference feature vectors, and obtaining a pre-sale product recommendation list using a collaborative filtering method. According to the pre-sale product recommendation list, a corresponding adoption product is selected. After the product growth process is completed, the product state time series data and the consumer preference state time series data of the product that has not been adopted are input into the recommendation model based on the double-state dynamic neural network, real-time product feature vectors and real-time consumer preference feature vectors are output, and a formal product recommendation list is obtained using a collaborative filtering method. The present application can take into account the whole process of agricultural products and dynamically adjust the recommendation content according to the state of agricultural products.

The invention provides a gas turbine state intelligent early warning method and system based on a dynamic neural network. The method comprises the steps of gas turbine historical operation data acquisition, characteristic parameter screening, neural network prediction model construction and training, gas turbine real-time data acquisition, gas turbine key operation state characteristic parameter prediction and analysis, dynamic updating of a gas turbine historical database and a neural network prediction model and the like. And real-time monitoring and early warning of the running state of the gas turbine are realized. According to the method, through boundary condition-operation state characteristic parameter classification and neural network prediction model dynamic modeling and training, the problems of limitation of single-parameter early warning in traditional gas turbine state monitoring, lack of prediction model updating mechanisms and the like are solved, and a technical means can be provided for intelligent operation and maintenance of the gas turbine.

The invention discloses a coagulant self-adaptive adding control method and system based on a physical constraint neural network, and relates to the technical field of water treatment automatic control, and the method comprises the steps: collecting water quality data; preprocessing the water quality data to obtain a standardized water quality sequence; inputting the standardized water quality sequence into a pre-trained time sequence dynamic neural network model, and predicting future dosage and future effluent turbidity; at the end of each control period, based on a model prediction control mechanism, performing rolling optimization on the pre-trained time sequence dynamic neural network model by taking the optimization objectives that the future effluent turbidity predicted by the time sequence dynamic neural network model does not exceed the standard and the future dosing amount is minimum, and solving an optimal medicament dosing sequence; and converting the optimal medicament feeding sequence into a control signal to drive a dosing pump to feed medicaments. The problems that a traditional control method is weak in self-adaptive capacity, poor in predictability and high in medicine consumption when facing complex and changeable raw water quality are solved, and stable standard reaching of the effluent quality and accurate optimization of the coagulant adding amount are achieved.

The application discloses a motor driving sudden change friction characteristic modeling and feedforward compensation method, which realizes decoupling and independent description of non-sudden change characteristics and sudden change characteristics of friction, and constitutes a dynamic neural network friction model with a width neural network structure which integrates the width neural network structure characteristics and the dynamic recurrent neural network structure characteristics; and the motor control system feedforward control compensation based on the friction model: the motor rotation angle is used as the input signal of the friction model, the friction model obtains corresponding friction torque prediction and estimation, the output of the motor controller is corrected through the feedforward control compensation, and the influence of internal friction on the motor execution precision is offset.

An automatic driving target detection method based on self-distillation assisted dynamic neural network, the collected image is used as the input of the target detection model to realize target classification. The target detection model is based on a self-distillation assisted dynamic neural network, which is composed of a strategy network, a detection network and a hybrid distillation network. The detection network is composed of a series of multi-branch residual blocks. The detection network takes the collected image as the input and outputs the target classification result. The strategy network generates corresponding routing vectors for different inputs to determine the opening and closing of the residual blocks in the detection network. The hybrid distillation network includes two subnetworks. The two subnetworks are differentiated from the detection network in the initial training stage and are randomly initialized. The subnetworks after hybrid distillation are fused into a fusion network. Through knowledge distillation, the knowledge of the fusion network is compressed and migrated back to the detection network, completing a closed-loop optimization.

The application discloses a kind of bionic dynamic neural network, the neural network can form behavior state relation net by learning, and can be received when setting target task, state transfer and behavior activity control are carried out according to current state and the behavior state relation net formed, directly complete the target task.The bionic dynamic neural network provided in the embodiment of the application imitates the neural circuit topological structure and dynamic characteristics of biology, realizes the control to state transfer, so that state transfer and action control form the behavior state relation net with causal relationship, more in line with the way of human brain processing problem, improve the decomposition ability of complex task and the efficiency of reinforcement learning, so that reinforcement learning can be more realistically used in actual robot task.The bionic dynamic neural network of the embodiment of the application can be applied in reinforcement learning model, for building the reinforcement learning algorithm model with higher learning efficiency capable of decomposing task.

Apparatuses, systems, and techniques to assign a processing resource to an inference request directed to a neural network based on an amount of information to be inferenced indicated by said request. In at least one embodiment, an AI application is deployed with a software wrapper that intercepts inference requests and dynamically distributes such requests among available processing resources such as host processor(s) and / or AI accelerator(s) to improve execution performance of said AI application.

The invention provides a real-time speech enhancement method and system based on an adaptive deep neural network, and belongs to the technical field of speech signal processing. The method comprises the following steps: collecting multiple paths of voice signals through a multi-microphone array, and suppressing environmental noise by using a beam forming algorithm; processing the voice signal by adopting a hybrid noise reduction method of wavelet transform and adaptive filtering; constructing a dynamic neural network model, dynamically adjusting the network weight according to the noise environment classification result, and enhancing the voice signal; frequency band energy compensation is carried out on the enhanced voice in combination with a psychological acoustic model, and auditory fatigue is reduced; and finally, reconstructing a time domain voice signal through inverse short-time Fourier transform, and carrying out post-processing to output a final enhanced voice. The method has the advantages of being high in adaptability, high in real-time performance, good in voice quality and the like, and is suitable for various scenes such as voice communication, voice recognition, intelligent voice assistants and the like.

The invention belongs to the field of fine control, and particularly discloses a soil water and fertilizer fine control system based on machine learning, which comprises a soil water and fertilizer data real-time acquisition module, a soil water and fertilizer content prediction module and a soil water and fertilizer fine control module. According to the method, the dynamic neural network model is constructed, and Bayesian regularization training, a back propagation technology and a gradient descent algorithm are combined to optimize the model, so that high-precision dynamic prediction of the water and fertilizer content of the soil is realized; pID (Proportion Integration Differentiation) control parameters are dynamically generated by adopting an elitism strategy genetic algorithm with a memory bank, a method for synchronously optimizing valve opening, harmonic suppression and water and fertilizer loss indexes by combining a multi-target genetic algorithm is combined, self-adaptive optimization and multi-target collaborative optimization of parameters of the water and fertilizer controller are realized, and dynamic adjustment is performed by combining real-time monitoring data. And the PID parameters are ensured to be always in an optimal state.

The application provides a small-thrust trajectory optimization method and system based on a structure adaptive neural network, and relates to the technical field of spacecraft trajectory optimization. The application trains and verifies a structure adaptive neural network based on a small-thrust trajectory data set of a spacecraft, and obtains a dynamic neural network model. The structure adaptive neural network comprises an initial neural network, a performance stagnation monitor and a deep neural network capacity heuristic adjustment module. The deep neural network capacity heuristic adjustment module is used for hierarchical regulation and control of the capacity of the structure adaptive neural network. When trajectory data with new features are accumulated, the application adaptively adjusts the network structure, can absorb new knowledge through incremental evolution of the network structure, and does not need to retrain from the beginning. On the basis of fully trained knowledge, the model can accommodate and learn new small-thrust trajectory optimization rules through structure growth, and can effectively solve the fundamental problem that the learning potential of a fixed structure model is limited when facing new data.

The application provides a component abnormal sound diagnosis method based on a nonlinear dynamics neural network, and belongs to the technical field of acoustics, vibration signal processing and artificial intelligence, and comprises the following steps: constructing a multi-dimensional vibration-sound state feature vector according to collected three-axis acceleration of an excitation source and microphone sound pressure signals of a response source, and inputting the multi-dimensional vibration-sound state feature vector into a double-branch neural network, wherein the neural network comprises an abnormal sound mechanism classification branch neural network based on a deep nonlinear physical constraint loss function, which is used for analyzing the type of abnormal sound; and a material feature decoupling branch neural network based on fractional calculus, which is used for analyzing the material producing the abnormal sound.The application can solve the technical problem that the BSR abnormal sound AI automatic diagnosis scheme based on deep learning in the prior art has poor accuracy in abnormal sound identification and is difficult to guide component abnormal sound rectification work.

The invention discloses a dynamic neural network tree continuous learning method and device oriented to edge computing, and the method comprises the steps: (1) a domain adaptation stage: enabling the features of new task data to be aligned with a target domain through a self-adaptive horizontal extension domain adaptation (DA) module, so as to eliminate the influence of domain difference; (2) class perception learning stage: inputting the features after domain alignment into a neural network tree, and performing interpretable tree structure growth through a greedy strategy based on confidence so as to learn a newly appearing class; (3) a knowledge forgetting suppression stage: during model training, effectively consolidating old knowledge only by replaying a small number of samples of a single reference domain by utilizing the characteristic of domain alignment and adopting a memory-friendly playback strategy; and (4) an efficient reasoning stage: during reasoning, dynamically and selectively loading model branches related to input data, and minimizing memory occupation. According to the method, the learning process is decoupled into domain adaptation and class learning, so that the problem that the model is difficult to adapt to complex continuous learning of simultaneous change of domains and classes on edge equipment with limited resources is solved, and the learning efficiency, the accuracy and the resource utilization rate of the model are remarkably improved.

The invention provides a robot driving control method and device, equipment and a storage medium. The robot driving control method comprises the steps that tracking errors are calculated according to expected trajectories and actual moving trajectories corresponding to all joints of a connecting rod robot at the current moment; calculating the tracking error by adopting a sliding mode control algorithm to obtain a first input torque at the current moment; taking the actual input torque at the previous moment and the actual moving track as the input of a dynamic neural network, predicting the unknown torque in the robot dynamic model at the current moment, and taking the predicted unknown torque as the second input torque at the current moment; the actual input torque at the current moment is determined according to the first input torque and the second input torque, and the connecting rod robot is controlled to move according to the actual input torque at the current moment; the problem that in the prior art, stability and accuracy of a connecting rod robot are reduced due to various uncertain factors is solved.

This invention discloses a dynamic neural network event-triggered control method for motor load frequency under external disturbances and internal coupling, relating to the field of motor control technology. The method includes the following steps: obtaining the system matrix parameters of the motor system; establishing a motor state-space model to obtain discrete states; based on the discrete states, representing external disturbances and internal coupling in the motor system as a common disturbance term, and estimating the common disturbance term online using a neural network to obtain disturbance estimates; obtaining the trigger update time of the control signal based on the state deviation between the discrete states and their most recent trigger state; constructing a dynamic neural network state feedback controller at the trigger update time; substituting the dynamic neural network state feedback controller into the motor system model, establishing linear matrix inequalities, and implementing dynamic event-triggered control by solving the linear matrix inequalities, which can better cope with unknown disturbances and reduce communication burden.

The invention discloses a motor load frequency dynamic neural network event trigger control method under external disturbance and internal coupling, and relates to the technical field of motor control, and the method comprises the following steps: obtaining system matrix parameters of a motor system, building a motor state space model, and obtaining a discrete state; based on the discrete state, uniformly representing external disturbance and internal coupling in the motor system as a common disturbance term, and performing online estimation on the common disturbance term through a neural network to obtain a disturbance estimation value; based on the state deviation between the discrete state and the last trigger state, obtaining a trigger update moment of the control signal; constructing a dynamic neural network state feedback controller at a trigger updating moment; a dynamic neural network state feedback controller is substituted into a motor system model, a linear matrix inequality is established, dynamic event trigger control is implemented by solving the linear matrix inequality, and the control effects of better coping with unknown disturbance and reducing communication burden can be achieved.

The invention discloses a step-by-step field effect transistor modeling method and system based on neural network space mapping, and belongs to the technical field of microwave circuit and device modeling. Three types of core models are constructed in stages: a static neural network space mapping model and a dynamic neural network space mapping model are established as intermediate modeling; constructing a dynamic neural network model containing more hidden layer neurons as a final target model; and the direct current data, the small signal S parameter data and the large signal harmonic balance data are respectively adopted to carry out targeted training on the model in each stage, and finally a high-precision transistor large signal model is obtained. A constraint condition formula is introduced in the training process, and it is ensured that training in the subsequent stage does not change the training result achieved in the early stage. According to the method, one-stop modeling of the transistor large signal model of the field effect transistor is realized, the modeling efficiency and the model precision are effectively improved, and an efficient and reliable solution is provided for transistor modeling in microwave circuit design.

A method and system for detecting armed personnel and equipment based on a dynamic neural network is disclosed. The method includes the following steps: acquiring images of armed personnel at different distances using a high-resolution camera with variable zoom; labeling personnel and equipment in each image to form an equipment detection dataset; constructing a dynamic neural network model, which includes a first sub-network and a second sub-network, wherein the first sub-network is used to detect humans in the image; when the first sub-network detects humans in the image, extracting the human ROI and transmitting it to the second sub-network; the second sub-network is used to detect equipment using classifiers at different network depths according to different image resolutions; training the dynamic neural network model based on the equipment detection dataset to obtain a trained armed personnel and equipment detection model; and inputting the image to be detected into the armed personnel and equipment detection model to obtain the armed personnel and equipment detection result of the image to be detected.