363 results about "Neural net architecture" patented technology

The invention relates to the technical field of exception prediction, in particular to a storage cabinet exception trend prediction system based on time series data analysis, which comprises a state monitoring module, an interval sensing module, a path reconstruction module, a symptom activation module and an evolution prediction module. According to the method, the state vectors including the temperature, the voltage, the current and the door lock state are constructed and combined with the timestamp information to form the time sequence data sequence, and the dynamic expression mode of state change is established; a jump characteristic is analyzed by using a ratio of a time interval to a state change amplitude, a short-time disturbance path and a trend evolution path are distinguished by combining a jump rate statistical index, and an evolution activation signal is identified based on trend maintenance and non-fallback characteristics. On the basis, a neural network structure with long-time dependent learning ability is introduced to capture an aperiodic thermal anomaly trend in a state sequence, and the accuracy and timeliness of anomaly recognition are improved through multi-dimensional parameter cooperative processing and path construction logic.

The invention discloses a lithium battery residual life prediction method and system and terminal equipment, and relates to the technical field of lithium battery health management. The method comprises the following steps: receiving a battery capacity attenuation sequence as an original input sequence, detecting and filtering abnormal data by adopting a 3 sigma criterion, and carrying out noise suppression processing on the battery capacity attenuation sequence through a Dropout mask; and carrying out normalization processing on the preprocessed battery capacity attenuation sequence, dividing the battery capacity attenuation sequence into a training set, a verification set and a test set through a sliding window algorithm, and generating a time sequence characteristic matrix and a corresponding residual service life label. According to the method, a neural network structure fusing trend prior perception and dynamic attention regulation is constructed, a multi-scale capacity modeling strategy is introduced to separate a degradation trend, fluctuation disturbance and high-frequency noise, and compared with a traditional time sequence neural network or a single attention model, pseudo fluctuation characteristics caused by capacity regeneration can be more effectively recognized, and the method is more efficient and more reliable. And the judgment accuracy of the model in a complex degradation scene is improved.

The invention relates to the technical field of industrial robot control, and discloses an industrial robot trajectory optimization control method based on an intelligent algorithm. The method comprises the steps that joint position information, tool center point coordinates and a motion time sequence when a robot executes multiple tasks are collected and stored in a track database; after cleaning and screening data, extracting a feature set containing a path point sequence, speed distribution and an acceleration contour; constructing an intelligent optimization algorithm model of a neural network structure, and training by using the feature set to learn a trajectory optimization strategy; analyzing a target position coordinate and a motion constraint condition of the current task to obtain an initial track parameter; and inputting the initial parameters into the trained model, outputting an optimized track sequence containing a path point list and a speed curve, and generating a control instruction to drive the robot to move. The method can adapt to different tasks, improves track rationality and motion stability, and fits industrial production practice.

The invention discloses a microseismic source positioning method, device and system, and a storage medium. The method comprises the following steps: dividing a microseismic data sample data set into a training set and a test set; according to the training set, constructing a microseism inversion subnet containing a Swin Transform encoder, and according to the training set, constructing a microseism inversion subnet containing a Swin Transform encoder; the micro-seismic forward modeling subnet realizes seismic wave field continuation by inputting a micro-seismic source position and a speed model and utilizing a recurrent neural network structure and a convolution operator, and establishes a forward modeling subnet based on a wave equation; constructing an inversion-forward modeling closed-loop neural network according to the micro-seismic inversion subnet and the forward modeling subnet based on the wave equation; and inputting the test set into the inversion-forward closed-loop neural network to carry out micro-seismic source positioning. By adopting the technical scheme of the invention, the limitations on physical constraint, feature modeling and anti-noise capability in the prior art are overcome.

The invention discloses a low-sample neural network structure reliability evaluation system and evaluation method, and relates to the technical field of engineering structure safety monitoring, and the evaluation system comprises a cloud server which is used for constructing a recurrent neural network model containing a static variable embedding mechanism, completing model training and converting a model format; the edge calculation terminal is used for receiving and preprocessing real-time data of the sensor, executing multi-step prediction to output a future time period response sequence, and calculating a future failure probability through virtual Monte Carlo simulation; the sensor assembly is used for collecting structure state time sequence data; and the communication module is used for realizing data interaction and alarm signal transmission operation. According to the method, collaborative modeling of time-varying and static uncertainty is realized by adopting a static variable embedded recurrent neural network model, failure probability distribution is generated at an edge computing terminal in combination with a virtual Monte Carlo technology, failure risk prediction in a future time period is supported, and real-time and accurate reliability early warning can be realized in a resource limited scene.

The invention discloses a livestock and poultry health state intelligent evaluation method based on multi-sensor fusion and an AI prediction model, and belongs to the technical field of livestock breeding, and the method comprises the following steps: setting multiple types of sensors in a livestock and poultry breeding area, collecting multi-source data such as temperature, humidity, carbon dioxide concentration, ammonia gas concentration, illumination intensity, weight and current, and carrying out the analysis of the data; wherein the weight data is obtained through the weighing platform, and the current data is used for sensing the operation state of drinking, ingestion, ventilation or lighting equipment; various types of sensors such as temperature and humidity sensors, carbon dioxide sensors, ammonia gas sensors, illumination sensors, weight sensors and current sensors are deployed in livestock and poultry breeding areas, all-directional data acquisition of environments and behavior states is realized, and dynamic modeling and feature extraction of key behavior nodes are realized by introducing a deep neural network structure of a gating circulation unit and an attention mechanism.

The invention discloses a low-voltage power distribution network line loss prediction method, a model training method and a related device, and the model training method comprises the steps: (1) employing a neural network structure combining a time sequence feature extraction module and a multi-scale feature extraction module, and capturing the long-term trend of photovoltaic output and load fluctuation, line loss change modes under different time scales are effectively modeled; (2) a deep feature extraction module introduces a deep feature extraction mechanism with mutually different architectures, and the expression ability and generalization performance of the model to a complex nonlinear relationship are improved; (3) a crown porcupine optimization algorithm is adopted to perform joint optimization on model parameters and structures, efficient search can be realized in a high-dimensional non-convex space, local optimum is avoided, and prediction precision and stability are improved; based on the line loss prediction model, the line loss prediction method provided by the invention can be directly used for power distribution network operation situation evaluation and energy efficiency analysis, and has good engineering application value under the background of wide distributed photovoltaic access.

The invention relates to the field of numerical reservoir simulation, and provides a proxy modeling method for embedding a coarse grid simulator, so as to solve the problems of poor space-time extrapolation performance and unstable long-term prediction. According to the method, a coarse mesh numerical simulator is used as a physical prior module to be embedded into a multi-resolution fusion neural network structure (MNN), and a complex nonlinear relation in the physical prior module is captured by means of a Fourier neural operator (FNO), so that efficient, long-time-sequence and stable prediction of multiple physical fields such as pressure, oil saturation and gas saturation is realized. According to the method, a coarse mesh numerical solution is used as an intermediate drive, multi-scale physical information is fused through a modular MNN network, and the physical consistency and the space-time generalization ability of the proxy model are remarkably improved. In the model, the FNO is utilized to extract global frequency domain characteristics of a coarse grid simulation result field, and through verification of multiple cases, the model shows good space-time extrapolation performance under various coarsening scales and well control conditions. The method has the robustness of numerical simulation and the high efficiency of deep learning.

The invention belongs to the technical field of artificial intelligence, particularly relates to the technical field of reinforcement learning, and particularly relates to an unmanned system autonomy evaluation method based on reinforcement learning, which can be applied to intelligent unmanned aerial vehicle manufacturing, and comprises the following steps: constructing an unmanned aerial vehicle autonomy evaluation index system; constructing an unmanned system autonomy scoring model based on reinforcement learning; and training an autonomous scoring model of the unmanned system. According to the method, a three-level index system taking the autonomy of the unmanned aerial vehicle as a root node is established, a double neural network structure based on reinforcement learning is designed, and an autonomy score is calculated. A multi-head attention mechanism is embedded in the value network, and adaptive learning of each leaf index weight is realized. According to the method, the importance weights of different evaluation dimensions are dynamically adjusted, and accurate and adaptive autonomy scores are provided. According to the method, the problems of fixed weight and lack of adaptability in a traditional evaluation method are solved, and the evaluation strategy can be dynamically optimized according to actual task requirements.

The invention provides a personalized federal learning method and system for multi-device heterogeneous data, and the method comprises the steps: transmitting a neural network structure to all clients, so as to enable all clients to carry out local model training; receiving the trained model parameters of each client, and dividing the trained model parameters of each client into non-BN layer parameters and BN layer parameters; all the non-BN layer parameters are aggregated; calculating distribution similarity among the clients according to all the BN layer parameters to obtain a similarity matrix; clustering the clients according to the similarity matrix by adopting an affinity propagation algorithm to obtain a client group with similar feature distribution; performing intra-group aggregation on the BN layer parameters corresponding to each group of clients; sending the aggregated non-BN layer parameters to all the clients, and sending the aggregated BN layer parameters in the groups to the clients in the corresponding groups; therefore, the training stability and the prediction precision in a multi-device heterogeneous environment are improved.

The invention relates to the technical field of electrolytic aluminum monitoring and control, and provides an automatic control method and system for an aluminum electrolysis cell in the electrolytic aluminum process, and the method comprises the steps: A, collecting the operation parameters of the electrolysis cell in real time through a multi-source sensing array; b, constructing a dynamic material balance-heat balance coupling model, and inputting the operating parameters of the electrolytic cell into the dynamic material balance-heat balance coupling model for outputting alumina blanking rate data; c, according to the aluminum oxide blanking rate data change rate, temperature-polar distance cooperative control of the electrolytic cell is synchronously executed, and the optimal polar distance compensation amount is calculated according to the operation parameters; and D, constructing an electrolytic cell resistance change rate prediction model based on the LSTM neural network, and inputting the aluminum oxide blanking rate data change rate into the LSTM neural network structure model for outputting an aluminum oxide concentration compensation strategy. The change condition of the aluminum electrolysis cell in the aluminum electrolysis process can be rapidly and accurately monitored, and real-time control is provided.

The invention relates to the technical field of audio signal processing and biomedical signal analysis, and still has a further optimized space for the recognition of anti-noise requirements, signal individual differences and complex pathological modes in a noise environment. The invention provides a double-path CNN heart sound classification method based on time-frequency and double-spectrum fusion features, and the method comprises the steps: carrying out the preprocessing of an original heart sound signal of a data set which is classified into a normal heart sound and an abnormal heart sound, and obtaining a to-be-recognized heart sound signal; based on dynamic continuous wavelet transform, adaptively selecting parameters to extract time-frequency characteristics, introducing bispectrum analysis, capturing nonlinear characteristics, generating a dual-channel characteristic pattern, and efficiently storing the dual-channel characteristic pattern in an HDF5 format; and based on a designed double-path convolutional neural network structure, respectively processing the extracted time-frequency and double-spectrum features, performing classification after fusion, and training a model in combination with category weighted loss and an optimization strategy to obtain a heart sound classification result. The heart sound recognition accuracy can be improved.

The invention discloses a bone injury detection method based on ultrasonic guided waves and a multi-branch convolutional neural network, and the method comprises the steps: firstly collecting UGW signals of bone tissues, and carrying out the standardization preprocessing of the UGW signals, so as to eliminate the amplitude difference between different samples; then, data enhancement strategies such as Gaussian noise disturbance and amplitude scaling are adopted, a finite sample set is effectively expanded, and the robustness and generalization ability of the model are improved; a multi-branch convolutional neural network (TB-CNN) structure is constructed, the network designs independent branches for time domain, frequency domain and time-frequency domain input, deep features are automatically extracted from the respective branches, and feature splicing and multi-level information integration are realized in a fusion module; finally, regression prediction of the bone injury depth is realized through a full connection layer, so that continuous value output is obtained, and the severity of the bone injury can be reflected more finely.

The invention provides a whole vehicle manufacturing coating resource scheduling method based on multi-agent deep reinforcement learning, and belongs to the technical field of artificial intelligence and intelligent manufacturing. The method is characterized by comprising the following steps: firstly, deeply analyzing whole vehicle manufacturing coating production characteristics and dynamic resource attributes in a cloud environment, and constructing a three-stage coating resource scheduling model considering manufacturing energy consumption and completion time; on the basis, through a multi-agent dynamic interaction mechanism in the cloud platform, a multi-agent near-end strategy optimization (MAPPO) algorithm is adopted to solve the whole vehicle manufacturing and coating resource scheduling problem in three stages; meanwhile, in order to enhance the interpretability of a scheduling strategy and ensure the convergence of the algorithm, KAN (Kolmogorov-Arnold Networks) is adopted as a neural network structure of an intelligent agent. The method is widely applied to finished vehicle manufacturing and coating production enterprises, the provided model and method can obtain a scheduling scheme meeting the requirements of energy consumption and completion time, and dynamic events such as resource maintenance and vehicle body return can be efficiently and autonomously processed.

The invention relates to the field of computer systems based on specific calculation models, and discloses a knowledge graph automatic construction system assisted by a large language model, which comprises a semantic extraction module used for extracting text attention weight distribution based on a neural network structure and generating an initial semantic vector; the logic calibration module is used for converting the ontology rule into a constraint subspace manifold and extracting a local tangential vector field of the initial semantic vector at a constraint subspace boundary; the projection mapping unit is used for calculating a displacement vector and a deviation angle generated by projection of the initial semantic vector to the constraint subspace, and obtaining a knowledge representation vector through momentum compensation when the deviation angle is greater than a threshold value; and the triple generation module is used for feeding back the knowledge representation vector to the residual connection layer to correct the distribution bias and decode the distribution bias, and real-time alignment of calculation model probability distribution and knowledge topology certainty requirements is realized through submerged space geometric constraint and momentum compensation.

The invention discloses a distributed photovoltaic decomposition method and system based on intelligent electric meter data, and relates to the technical field of non-intrusive power load monitoring, and the method comprises the steps: constructing a data set, and carrying out the normalization processing of the data set, and obtaining the input data of model training, verification and testing; constructing a teacher neural network structure and a student neural network structure, and performing supervised training and verification; setting hyper-parameters of a knowledge distillation algorithm, calculating difference loss, and retraining to obtain a student photovoltaic power decomposition model; and inputting the total power signal data of the target load equipment into the student photovoltaic power decomposition model to obtain photovoltaic power generation equipment power data, and performing evaluation. According to the invention, high-precision analysis of the photovoltaic power generation power decomposed from the total power signal is realized. The teacher model can learn a complex nonlinear mapping relationship, and the student model learns the decomposition capability of the teacher model through a knowledge distillation process, so that the model complexity is greatly reduced while the higher precision is maintained.

The invention discloses an infrared small target detection method and system, a detection device, an electronic device and a medium, and belongs to the field of image processing. A complete infrared image is input into a coarse and fine detection infrared small target detection framework, and the coarse and fine detection infrared small target detection framework screens a target area of the complete infrared image and then performs accurate target detection; obtaining an infrared small target detection result; the method comprises the following steps: inputting a complete infrared image into a region dichotomy network, carrying out dichotomy of an image block level, judging whether each image block contains a target or not, generating a multi-scale region feature map based on a judgment result, and in a lightweight target detection module, utilizing a convolutional neural network structure and combining a context-guided knowledge distillation module to detect the target. Carrying out different-level feature extraction and fusion on the multi-scale region feature map, and generating an infrared small target region detection result based on the combination of multi-level features; and carrying out region mapping on the infrared small target region detection result and the complete infrared image to obtain an infrared small target detection result.

The invention relates to the technical field of artificial intelligence, in particular to a knowledge distillation acceleration method and system for a multi-modal large model, and the method comprises the steps: obtaining multi-modal input data; feature mapping of topology maintenance is executed, topological representation of a multi-modal feature space is constructed, and a feature mapping module is designed based on a residual module; a topological hierarchical attention mechanism is applied, and multi-head topological attention fusion is realized through sensing of a local topological attention unit and a global topological structure; topology-driven multi-task knowledge distillation is executed, five cross-modal distillation tasks are designed, and distillation loss is calculated based on topological similarity measurement; a topology-aware model acceleration technology is adopted, adaptive quantization is performed based on feature topology importance, neural network structure search for topology maintenance is executed, a knowledge distillation process is guided through a topology principle, a topological structure relationship of a feature space is maintained, and multi-modal knowledge is effectively transmitted. Experiments show that compared with an original large model, the method has the advantage that the size of the model is reduced by 80-90%.

The invention provides an electric power operation and maintenance big data monitoring method, and relates to the technical field of data monitoring management, and the method comprises the steps: carrying out the joint expression of electric power data through a multi-dimensional data fusion scheme; embedding the physical topological relation and the power flow information of the power system into the graph neural network structure, and identifying spatial correlation and load imbalance characteristics between devices; embedding a neighborhood load change guide item and a periodic stability constraint based on a gated loop network, and carrying out precise modeling on an equipment state change rule on different time scales; the prediction probability and the state offset score are fused, a hierarchical early warning mechanism oriented to regional risks is established, a scheduling priority function is constructed in combination with the importance weight and the operation load of the equipment, and intelligent scheduling for different equipment is realized; through dynamic load fluctuation analysis and scheduling optimization of the computing nodes, high-risk equipment preferentially obtains computing resource support, and it is ensured that the system has efficient response and computing capacity in a high-concurrency and high-load power grid environment.

The invention provides a microtopography recognition method and device fusing multi-source data and an image processing technology, and relates to the technical field of computer data processing, and the method comprises the steps: collecting the multi-source data of a target region; the multi-source data comprises remote sensing images, vector data and topographic factors; the multi-source data of the target area is used as an input sample through a micro-topography recognition model, and micro-topography information of the target area is determined through recognition; the microtopography recognition model is obtained through training by the following steps: establishing a microtopography training sample library, and expanding training samples by selecting topography factors, performing sample enhancement processing and performing image processing; constructing initial models of a plurality of different neural network structures, training the plurality of initial models through training samples of a microtopography training sample library, adjusting and optimizing model parameters through multiple rounds of dynamic optimization training strategies, and determining a performance index corresponding to each model; and selecting a model of which the performance index meets a preset condition as a microtopography recognition model.

The invention discloses a transformer substation equipment defect image recognition method based on a yo11 structure improved neural network. The method comprises the following steps: step 1, constructing and preprocessing a transformer substation defect image data set; 2, improving the structural design of the YOLO11 neural network; 3, model training based on an ATSS dynamic label distribution strategy; 4, model reasoning and defect identification; 5, performing model performance verification and iterative optimization; according to the method, the ARConv captures multi-direction defect features, the GAM focuses on small sample defects, the AFPN optimizes feature fusion, after improvement, the overall mAP50 is improved, and the recall rate of key defects such as meter damage and insulator damage is improved; the calculation amount is reduced by simsppf, the parameter amount is saved by AFPN, although the reasoning speed is slightly reduced, the model parameters are increased, and the edge calculation capability of the unmanned aerial vehicle / inspection robot is adapted; aTSS dynamic label distribution adapts to similar defect form differences, data enhancement covers multiple illumination / view angles, and the generalization ability of the transformer substation in a complex environment is improved.

The invention discloses a power equipment operation abnormal behavior prediction system based on big data analysis, and the system comprises a data collection module which is used for collecting multivariable operation monitoring data; the data preprocessing module is used for preprocessing the multivariable operation monitoring data; the sliding window construction module is used for generating an input window and a prediction target; the improved prediction modeling module is used for constructing a neural network structure formed by stacking task decomposition type structured basic blocks in sequence and outputting a prediction component and a reconstruction component respectively; the comparative learning modeling module is used for extracting hidden state representation; the multi-target prediction module is used for outputting a main task and an auxiliary task based on the prediction output vector; the frequency domain residual detection module is used for generating a reconstructed time domain residual sequence; and the abnormal score fusion module is used for outputting an abnormal judgment result and corresponding early warning information. The method is suitable for stability monitoring and intelligent early warning scenes of new energy equipment under complex working conditions.

The invention provides a head and neck cancer image area multi-target classification method and system and a medium, and belongs to the technical field of medical image processing, and the method comprises the steps: obtaining a data set of a complete head and neck cancer CT image; randomly generating a plurality of neural network structure models, performing training and evaluation according to the data set, performing optimization by taking sensitivity and specificity as multiple optimization targets, and generating a Pareto optimal candidate model set; obtaining a weighting coefficient of each candidate model according to the sensitivity, the specificity and the AUC evaluation result of the candidate model; extracting the reliability and uncertainty of the to-be-classified sample, and adjusting the output probability of each candidate model according to the reliability and uncertainty; and taking the weighting coefficient of each candidate model, the adjusted output probability and the prediction reliability as input, and obtaining a classification result, a prediction probability and uncertainty through ER-rule reasoning fusion. According to the method, the robustness of the classification performance of the multi-fusion model is effectively improved.

The invention discloses an autonomous berthing method for a double-water-jet-propeller water surface unmanned ship, and the method comprises the steps: defining a state space, an action space, a reward function and a neural network structure element, employing a reinforcement learning method, and according to the current radar observation information of the unmanned ship, the target berth position information, and the current speed information of the unmanned ship; according to the method, the unmanned ship control output information is obtained, the problems that a traditional manual design berthing collision avoidance rule, a physical motion model, a machine learning method, an environment model and the like are greatly influenced by the environment, and intermediate steps are multiple and complex are solved, the calculation efficiency and the one-time planning berthing success rate are effectively improved, and therefore the berthing efficiency is overall improved.

The invention provides a mobile terminal skin parameter inversion method based on spectral information, and the method comprises the following steps: constructing an optical model according to the characteristics of a skin layered structure and a spectral response mechanism of three skin parameters: melanin content, hemoglobin concentration and dermis thickness, and building a skin parameter and reflection spectrum database based on the model; based on the database, establishing a skin multi-parameter inversion MLP neural network structure adaptive to the collection characteristics of a mobile phone end sensor, and screening an optimal four-waveband channel through multi-waveband combination traversal; the mobile phone spectrum sensor is subjected to wave band optimization, data acquisition and skin parameter inversion. According to the method, through efficient decoupling of a nonlinear coupling relation among multiple skin parameters by waveband optimization and an MLP model, and targeted design of four optimal visible light narrow-band channels, synchronous quantitative detection of melanin, hemoglobin and dermis thickness is realized, core physiological parameters from epidermis to dermis superficial layer are covered, information coverage is comprehensive, and specificity is high.

The invention provides an intelligent abnormal value detection and processing method based on deep learning product quality data. The method comprises the following steps: collecting multi-dimensional product quality data from a production line; an encoder module is constructed, and an encoder adopts a multi-layer neural network structure and is used for compressing and mapping input high-dimensional quality data into low-dimensional hidden layer feature representation; constructing a decoder module, receiving low-dimensional representation features output by an encoder, and reconstructing original data through a reverse neural network structure; training the automatic encoder by adopting an unsupervised learning mode, and learning a distribution mode and feature representation of normal data; and based on the trained automatic encoder, performing reconstruction error calculation on the quality data input in real time, judging an abnormal value through a preset threshold value, and triggering an alarm. Through the steps, the problem that high-precision detection of product quality data in production cannot be achieved in the prior art is solved, the alarm function is achieved, and therefore the quality problem of products in the future is avoided.

The invention discloses a material granularity identification method and system based on appearance analysis, and the system generates a standardized image matrix through image collection and preprocessing, employs a two-channel neural network structure to extract spatial positioning features and morphological structure features, carries out the fusion of the features to form a guide mask pattern, and carries out the recognition of the granularity of a material based on an improved active contour evolution model. Position constraint and form constraint are introduced into an energy function at the same time, dynamic evolution of the contour is achieved, the system monitors boundary consistency in the evolution process, and local topology reinitialization is triggered when the boundary consistency is lower than a threshold value so as to guarantee segmentation stability. After evolution is completed, a final contour area is extracted, particle size distribution data are calculated in combination with image scale parameters, and a particle size recognition result is output, automatic recognition and statistical analysis of the material particle size are achieved, and the method is suitable for particle material detection and distribution evaluation scenes.

A hardware accelerator and acceleration method based on a VisionTransformer neural network, the accelerator is to deploy the VisionTransformer neural network on a ZYNQ development platform; the acceleration method is: an ARM processor stores a feature picture into a DDR memory, the read data is dispersed to an input cache and a weight cache, the processed feature picture is input to an on-chip cache unit, the processed data is sent to a PL end, the hardware IP of the PL end is configured, and read-write operation is performed at the same time, the final calculation result is obtained, written into the DDR memory, the data in the DDR memory is taken out and probability operation is completed, the probability operation result is transmitted to a PC, a PetaLinux operating system is transplanted to the hardware accelerator system of the VisionTransformer neural network, and a prediction result of inference is obtained from the PC; the neural network structure is optimized through the parallel method of multiple input and multiple output channels, the calculation speed is fast, the hardware resource occupation is low, the recognition accuracy is high, and the image classification task can be efficiently completed.

The application belongs to the technical field of zinc powder purification, and provides a condensation and sedimentation system for zinc powder purification, which comprises the following steps: collecting a time sequence of original radiation intensity of a condensation chamber, performing frequency spectrum analysis through fast Fourier transform, calculating energy values of high and low frequency band frequency domain signals, solving a signal coherence factor and calculating a transmittance attenuation coefficient, constructing a metal thin film radiation compensation model based on a long short-term memory network, inputting the attenuation coefficient and the time sequence of original radiation intensity to output a corrected real temperature of the condensation chamber, expanding an inference layer of a full connection neural network structure, outputting a calibrated attenuation coefficient through the inference layer, selecting an effective attenuation coefficient input model by comparing a deviation threshold value, dynamically responding to temperature measurement nonlinear attenuation caused by zinc film deposition, guaranteeing production continuity and product quality of zinc powder purification, adapting to industrial multi-working condition operation requirements, being convenient to operate and controllable in cost.

The application discloses an electromagnetic interference identification method and device, equipment and a readable storage medium, and relates to the technical field of signal processing. The in-phase and quadrature data of a to-be-identified radar signal in multiple distance banks is acquired, and the maximum power variation coefficient, the skewness coefficient, the kurtosis coefficient and the maximum sharpness of the to-be-identified radar signal are calculated according to the in-phase and quadrature data. The above characteristic parameters are input into a pre-trained electromagnetic interference identification model, the electromagnetic interference identification model adopts a full connection neural network structure, the identification results of the to-be-identified radar signal in the multiple distance banks are obtained through an output layer, and the identification results are used for distinguishing meteorological echo useful signals from electromagnetic interference signals. The pollution area of the to-be-identified radar signal is determined according to the identification results of the to-be-identified radar signal in the multiple distance banks, the pollution area is recorded, and an alarm prompt is sent to technical personnel, so that the missed judgment of electromagnetic interference and the misjudgment of useful signals can be avoided, and the identification accuracy of various electromagnetic interferences is improved.