99 results about "Dynamic neural network" patented technology

The invention provides a photovoltaic station intelligent operation and maintenance simulation method and system based on digital twinning, and relates to the technical field of photovoltaic station operation and maintenance, and the method comprises the steps: constructing a digital twinning hierarchical structure through multi-modal detection signals through discrete wavelet packet transformation, tensor decomposition and a graph neural network, and determining structured data; extracting fault features by using a dynamic neural network, predicting a fault probability based on a Markov model, and triggering maintenance early warning; inputting the early warning signal into a maintenance strategy model based on multi-agent reinforcement learning, and generating a candidate maintenance time window set; the maintenance scheduling module optimizes sorting to obtain an optimal time window sequence, and the resource allocation module generates a personnel material allocation scheme by adopting a genetic algorithm; and iteratively optimizing the strategy parameters based on the maintenance cost, and outputting a final operation and maintenance implementation scheme.

Systems and methods for adaptive edge computing using artificial intelligence (AI) include monitoring real-time accuracy of a neural network by using a feedback loop configured to detect changes in inference accuracy and dynamically adjusting the structure of the neural network by adding or removing hidden layers based on monitored error rates and predetermined computational constraints. A Kalman gain computation determines neural network weight adjustments based on monitored error rates. Weight matrices undergo incremental updates derived from these adjustments. Incremental weight adjustments remain stored in memory to enable low-bandwidth model updates. The neural network stores inference results and refined weights in an inference result database. Pre-trained models periodically receive incremental updates based on stored adjustments. Predictive holistic inference logic (PHIL) applied to stored inference results improves the accuracy of the inference results.

AI neural networks are integrated with distributed ledger technology (DLT), including the integration of decentralized oracles, to enhance the functionality, security, and efficiency of systems. The integration incorporates several components and methods comprising novel neural network architectures, data preprocessing techniques, DLT integration approaches, privacy and security measures, consensus mechanisms, and others. The invention enables the development of neural smart contracts, neural consensus algorithms, dynamic neural network training, neural network optimization techniques, hybrid DLT architectures, neural network interpretability methods, and reinforcement learning for neural smart contract execution. By integrating decentralized oracles into the system, the invention has the capability to further enhance the reliability, accuracy, and diversity of data used within the DLT, improving transaction validation, consensus mechanisms, and overall system performance.

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

The invention relates to a battery charging and discharging state monitoring system, and belongs to the technical field of battery management. A battery charge and discharge state monitoring system comprises a data acquisition module, a data calculation module, an algorithm prediction module and a thermal runaway early warning module. The data acquisition module is used for acquiring the voltage, current and temperature of the current battery; the data calculation module is used for extracting electrochemical data and heat effect data of the battery in the charging and discharging process; and the algorithm prediction module is used for training the NARX dynamic neural network by using the electrochemical data and the thermal effect data. On the basis of real-time data acquisition and dynamic calculation of an electrochemical and thermal effect model, key features such as battery internal resistance, state of charge (SOC), total heat production and temperature change rate are accurately extracted, and prediction of the thermal effect state at the next moment is realized in combination with an NARX dynamic neural network; and the system can still accurately warn the thermal runaway risk in an early warning mode under the rapidly-changing working condition.

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 discloses a bearing fault diagnosis method integrated with a support vector dynamic neural network, and the method comprises the following steps: obtaining vibration data of a key position of a bearing of a rotating machine, carrying out the data preprocessing of the vibration data, and obtaining a preprocessed vibration signal data set; constructing a support vector machine model with a quadratic programming problem form based on the vibration signal data set, and designing a corresponding penalty function and a Lagrange function to simplify the support vector machine model; designing a variable parameter dynamics solving equation, and establishing a final integrated support vector dynamic neural network bearing fault diagnosis model to solve the support vector machine model; and simultaneously training a plurality of support vector dynamic neural network bearing fault diagnosis models based on a bagging classifier method, carrying out bearing state diagnosis on the vibration signal data set, and outputting a diagnosis result. According to the invention, the accuracy of the machine learning method, the convergence proof of the neural network solver and the interpretability of the intelligent fault diagnosis model are improved.

The invention provides a target detection method and system based on a dynamic neural network, and the method comprises the steps: firstly carrying out the improvement of a YOLOv7 model, replacing a high-efficiency layer aggregation module in a backbone network through a multivariate convolution fusion module, and introducing a bidirectional feature pyramid into a head network. And finally, taking the two improved YOLOv7 models as basic models, and combining an intelligent router to construct a dynamic target detection model. Different from a conventional static target detection model, the dynamic target detection model provided by the invention can adaptively adjust the network structure according to the picture complexity, the simple picture is detected by using a single network to ensure the detection speed, and the complex picture is processed by two networks to improve the detection precision. Compared with a traditional target detection method, the method has higher precision and better flexibility, and the higher precision can be kept under the condition that the speed is not lost.

The invention discloses a rapid water quality detector and a water quality detection method. The detector comprises a digestion tube, a quantitative liquid feeding unit, a heating unit, a cooling unit, a temperature measuring unit, a colorimetric detection unit and a control unit, the quantitative liquid feeding unit quantitatively inputs liquid into the digestion tube; the heating unit and the cooling unit are respectively used for heating or cooling the digestion pipe; the temperature measuring unit is used for detecting the liquid temperature and the environment temperature in the digestion tube in real time; the colorimetric detection unit is used for detecting the absorbance of liquid in the digestion tube; and the control unit integrates a dynamic neural network temperature compensation algorithm and a temperature-sensitive adaptive multi-target particle swarm optimization algorithm to respectively realize accurate temperature control and detection value optimization. According to the invention, high-precision temperature control is realized through a dynamic neural network temperature compensation algorithm, and the detection error rate is reduced in combination with a multi-target particle swarm optimization algorithm; the liquid feeding precision is guaranteed through the design of the double quantitative loop pipes, and multi-parameter detection is supported; the incremental learning mechanism ensures long-term stability of the system and adapts to wide-temperature-range environment requirements.

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.

The invention discloses a vehicle-mounted multi-target classification and detection method based on multi-teacher distillation and dynamic reasoning, and the method comprises the steps: collecting an image through a vehicle-mounted image collection device, taking the image as the input through a dynamic neural network, and outputting the classification and bounding box regression of multiple targets. The dynamic neural network is composed of a multi-teacher network and a student network. The multi-teacher network is composed of a plurality of teacher models; a dynamic weight distribution system based on an attention mechanism is introduced into the multi-teacher network, and different weights are distributed to each teacher model according to the characteristics of the current input scene; a confidence coefficient threshold value is set in a multi-teacher network, and regional knowledge possibly containing a target is only taught to a student network. The student network is composed of a strategy network and a detection network, and the detection network is a two-stage target detection network obtained by integrating a feature extraction network and a target positioning network; the strategy network adaptively extracts task features according to knowledge provided by the multi-teacher network; and the detection network dynamically selects a route according to the policy network decision vector.

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 discloses an edge-end cooperative task division and resource allocation method based on model segmentation, relates to the field of edge computing video analysis, and integrates CNN channel pruning, bilinear sampling and affine quantization multi-dimensional compression of intermediate transmission feature data; a parameter-shared dynamic neural network is trained based on a sandwich rule and a knowledge distillation technology, and real-time switching of characteristic data compression amplitude is realized; modeling user reasoning performance indexes in edge-end cooperative task division, and constructing an optimization problem of maximizing reasoning accuracy meeting user performance demand constraints and edge resource constraints; a solution algorithm based on dynamic programming is adopted, optimal configuration such as model break points and intermediate feature compression parameters is selected for users, and edge communication resources and computing resources are efficiently allocated, so that the reasoning accuracy under the multi-user condition is improved.

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 present application discloses a spatiotemporal omics image processing method and device based on a spatial dynamic neural network, the main purpose of which is to solve the problem that an effective tissue gene representation map cannot be generated in the existing method. It includes obtaining spatial node graph data of tissue genes and cell-to-cell communication pairs based on spatiotemporal omics images; performing convolution processing on the spatial node graph data based on the node layer in the spatial dynamic neural network that completes model training, and performing convolution processing on the cell communication pairs based on the edge layer in the spatial dynamic neural network, and the propagation between the node graph after the convolution processing of the node layer and the edge graph after the convolution processing of the edge layer is updated alternately; the output representations of the node layer and the edge layer are integrated through the attention mechanism to generate the representation map of the tissue genes.

The invention discloses a transient wind tunnel total pressure control method based on a dynamic neural network and fuzzy control, and relates to the field of wind tunnel test, and the method comprises the steps: S1, constructing a preset opening table of a pressure regulating valve; s2, the fuzzy controller and the pressure controller are disconnected in the wind tunnel starting stage, and the pressure regulating valve opening PI controller is adopted to control the opening of the pressure regulating valve; s3, total pressure is collected in real time to determine whether the coarse adjustment stage of pressure regulating valve opening control is completed or not, if not, valve opening control continues to be conducted, and if not, the fine adjustment stage of S4 is executed; s4, the gas source pressure II collected in real time and the known target total pressure I and the target Mach number I are substituted into a neural network preset opening controller, and fine adjustment of the PI controller on the opening of the pressure regulating valve is completed; and S5, judging whether the fine adjustment stage is ended or not based on the total pressure difference. The invention provides a transient wind tunnel total pressure control method based on a dynamic neural network and fuzzy control, which can effectively save the total pressure adjustment time and reduce the test energy consumption.

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 invention relates to the technical field of data model analysis, in particular to an old people living behavior analysis method for intelligent old people care. Comprising the following steps: acquiring multi-modal data of living behaviors of old people to obtain synchronized multi-modal data; preprocessing the synchronized multi-modal data, and performing feature extraction and optimization on the preprocessed multi-modal data to obtain comprehensive feature data; acquiring historical living behavior data of old people to obtain historical comprehensive feature data; and based on the historical comprehensive feature data, constructing a hierarchical time sequence dynamic neural network model to obtain a trained and verified hierarchical time sequence dynamic neural network model, and processing the comprehensive feature data through the trained and verified hierarchical time sequence dynamic neural network model to obtain an old people living behavior analysis result. The technical problems that the multi-modal data feature extraction of the living behavior is not accurate enough and the sensitivity of an analysis model is low in the aged living behavior analysis are solved.

The invention discloses a dynamic neural network compiling execution method and device, equipment and a medium. Comprising the following steps: calculating an optimal fusion slice corresponding to each dynamic fusion fragment according to chip parameters in a compiling stage; static fusion fragments matched with the corresponding dynamic fusion fragments are obtained according to the optimal fusion slices, and all the dynamic fusion fragments and the matched static fusion fragments form a fusion unit; and in the execution stage, the cyclic scalar control logic of the dynamic neural network is obtained, and the fusion unit is dynamically called based on the cyclic scalar control logic. The optimal fusion slice, suitable for the hardware cache size, of each dynamic fusion fragment is obtained under the condition of not depending on shape information, the dynamic fusion fragments are converted into static fusion fragments based on the optimal fusion slices so as to eliminate related computing nodes of dynamic shapes, dynamic scheduling planning can be conducted on the static fusion fragments in the execution stage, and therefore the dynamic fusion fragments can be dynamically scheduled and planned. And the execution efficiency of the dynamic neural network is greatly improved.

The invention provides a temperature monitoring method, an over-temperature protection method, a server, a vehicle and a product, the method is applied to the technical field of vehicles, and the method comprises the following steps: obtaining historical operation data of each vehicle; extracting temperature related parameters and temperature measured values of the wet clutch in the historical operation data; generating a training data set according to the temperature related parameters and the temperature measured values of the wet clutch of each vehicle; and training by using the training data set to obtain a temperature simulation model of the wet clutch, and monitoring the current temperature of the wet clutch based on the trained temperature simulation model. According to the method, the temperature of the wet clutch can be accurately monitored in real time based on an artificial intelligence dynamic neural network model; according to the method, the faults such as ablation damage of clutch hardware caused by overhigh temperature can be effectively avoided, so that a protection method for overtemperature of the wet clutch and a control method for reducing the temperature of the wet clutch are formed, and the safety of vehicle driving and the smoothness of gear shifting are improved.

The invention discloses a method for constructing a correction system and a category weight system of a neural network model, and relates to the technical field of deep learning, and the method comprises the steps: firstly copying an original neural network model to obtain an initial model, then mixing new and old data samples, importing the new and old data samples into the initial neural network model in batches, and carrying out the dynamic training; during each batch of training, if an old data sample is encountered, a weight correction mode is started, a correction coefficient is calculated by comparing predicted mean differences of the original model and the dynamic model for the old data sample, and the weight updating strength of the old data sample in the dynamic model is adjusted according to the positive and negative values and the size of the correction coefficient; therefore, a new dynamic neural network model is obtained by accumulatively updating according to batches, so that the adaptive capacity of the model to new and old data is improved by dynamically adjusting the weight updating strength of the old data sample, and the stability and generalization capacity of the model are enhanced.

A method for counting drone image targets based on a parameter-adaptive dynamic neural network, the steps of which include: 1) An aerial photography device on the drone collects ground images; 2) The collected images are preprocessed; 3) A feature extraction network is used to detect targets in the processed images; 4) The detected targets are counted. In step 2), the scale is dynamically divided and the image is segmented according to the flight altitude and shooting depression angle of the drone; in step 3), a feature extraction network with enhanced spatial information is used for the input feature map to extract the position information of the targets. The dilation rate parameter of the convolution in the receptive field selection module after the feature extraction network is determined according to the segmented image. A dilation rate parameter adaptive strategy is designed to calculate the scale range and segment the image according to the flight state, and to adjust the dilation rate parameter in the receptive field selection module. This method significantly reduces the inference latency, improves the MAE and MSE, and also has excellent counting accuracy.

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 present invention proposes a method, device, medium and product for predicting COD of sewage treatment effluent based on a dynamic LSTM neural network, which relates to the field of data processing technology. The method includes: pre-treating the inlet and outlet water data of the biochemical pool of the sewage plant; creating a dynamic LSTM neural network model, designing a gate weight dynamic adjustment algorithm, dynamically adjusting the weight ratio of the model input gate and the forget gate, realizing accurate prediction of the output index of the sewage plant, reducing the prediction time, and reducing the sewage treatment cost; initializing the dynamic neural network model and setting the model training parameters, calling the particle swarm algorithm to optimize the hyperparameters of the gate weight dynamic adjustment algorithm, and training the model based on the stochastic gradient descent method until the curve of the loss function converges; calling the pre-processed test data set as the model input, obtaining the prediction result of the standardized processing output, calculating the accuracy of the prediction result according to the preset target variable, and providing guidance for increasing or decreasing the aeration amount or the dosage.

The present invention discloses a wireless communication network resource allocation algorithm for dynamic adjustment on demand, which specifically includes the following steps: Step 1: Quantitatively describe the characteristics of tasks in the wireless communication network and represent them as input vectors of fixed dimensions #imgabs0# Step 2: Construct a high-reliability and low-latency resource allocation model based on a dynamic neural network with variable widths; Step 3: For the said model, give an optimization objective and a knowledge-driven solution; Step 4: Establish a knowledge base regarding the deployment environment and the optimal inference model; Step 5: Obtain the optimal model from the knowledge base to get the resource allocation scheme. The technical effect of the invention is to divide the network resource allocation problem into two stages: First, determine the optimal width of the decision network according to the task characteristics and the user's computing power; then, input the task characteristics into the optimal decision network to obtain the optimal resource allocation scheme.

The invention discloses an RSSI (Received Signal Strength Indicator) indoor positioning and ranging method based on neural network learning, relates to the technical field of indoor positioning and ranging, and remarkably improves RSSI ranging robustness in complex scenes such as underground parking lots and the like through multi-modal fusion and a dynamic neural network architecture. A double-flow neural network is adopted to separate modeling signal long-term attenuation and instantaneous abrupt change characteristics, the RSSI distortion problem caused by dynamic shielding is effectively relieved, and dependence of a traditional model on a uniform signal environment is avoided; an expansion rate and moving speed dynamic binding mechanism is introduced, a convolution receptive field is adjusted in a self-adaptive mode, time sequence information loss caused by low-speed sampling is compensated, and accumulated errors under high-speed moving are restrained; meanwhile, on the basis of a pre-training strategy of the generative adversarial network, diversified shielding scene data is synthesized through physical constraints, and the generalization ability of the model to multipath reflection and metal interference is enhanced.

The invention discloses a petrochemical engineering reaction process intelligent regulation and control method based on a dynamic neural network, and relates to the technical field of petrochemical engineering process control, and the method comprises the following steps: obtaining temperature distribution data of a catalyst bed layer, and fluid flow velocity field data, component concentration gradient data and stirring frequency data of a reactor in real time; and inputting the temperature distribution data and the stirring frequency data into a first branch of a dynamic neural network, and outputting an activity attenuation index of the catalyst bed layer. According to the scheme, by fusing the temperature standard deviation, the stirring dominant frequency component and the by-product weighted value, the dynamic relevance of mass transfer and heat transfer on the surface of the catalyst can be captured, meanwhile, the nonlinear influence of a side reaction path on activity attenuation is considered, the abnormal activity of the catalyst is warned in advance, and a more accurate input basis is provided for regulation and control of the reaction process.