459 results about "Signal classification" patented technology

The invention provides an EEG (electroencephalogram) classification method based on multi-domain feature fusion. A multi-domain feature extraction network is constructed, the multi-domain feature extraction network mainly comprises a frequency domain feature extraction module and a space-time feature extraction module which are deployed in parallel, a feature fusion module and a classifier module, multiple view features such as a time domain, a frequency domain and a space domain can be separated, and electroencephalogram signal classification is achieved. According to the method, an efficient solution is provided for solving the problem of insufficient multi-domain feature utilization of the electroencephalogram signals, the cross-scene classification precision can be remarkably improved while the model efficiency is kept, and a technical foundation is laid for personalized deployment of brain-computer interfaces.

The invention discloses a radio interference identification method based on electromagnetic spectrum monitoring, and the method comprises the following steps: S1, collecting spectrum data in an electromagnetic environment through broadband spectrum monitoring equipment, and carrying out the digital sampling processing; s2, adopting a diffusion probability model to automatically remove environmental noise and non-interference signals; s3, automatically generating an expansion data set of edge and small sample interference signals by adopting an attention-enhanced data synthesis expansion technology; s4, extracting multi-dimensional time-frequency domain dynamic correlation characteristics of the spectrum interference signal based on a Transform structure; s5, adopting an attention enhancement self-supervision algorithm to generate a self-supervision soft label of an unknown interference type; s6, dynamic back diffusion iteration is carried out through the diffusion probability model, and an interference classification result is obtained; and S7, constructing a closed-loop dynamic feedback mechanism by using an interference classification result. According to the invention, accurate identification of radio interference signals is realized, and the accuracy, dynamic adaptability and automation degree of interference signal classification are improved.

The invention relates to the technical field of intelligent diagnosis of power equipment, and provides a multi-mode fusion extra-high voltage converter transformer fault diagnosis method and system, and the method comprises the steps: collecting a multi-mode signal from a sensor of an extra-high voltage converter transformer, and classifying the signal into a plurality of modes; performing intra-modal feature reinforcement learning on the multi-modal data by adopting a SimCLR framework to obtain a discriminative representation feature vector zm of each modal; inputting the zm into a Transform branch encoder of a corresponding mode, and obtaining context feature vector enhancement representation hm of each mode; mapping the hm of different modalities to the same dimension in a unified manner, and performing weighted attention fusion to obtain feature vectors zf of all modalities after fusion; and inputting a multi-layer perceptron classifier (MLP) to obtain a fault category prediction result of the extra-high voltage converter transformer. According to the method, the multi-mode signals are processed and fused in parallel, and the fault recognition capability of the model on the extra-high voltage converter transformer in the complex operation state is improved.

A method for the classification and detection of faults in a microgrid having a distance relay, includes measuring the first plurality of voltage signals and the first plurality of current signals of the microgrid, calculating a plurality of fault-loop impedance signals, comparing the plurality of fault-loop impedance signals and a plurality of reference impedance values, inputting the plurality of difference values to a convolutional neural network (CNN)-gated recurrent unit (GRU) hybrid model, generating a reference tripping signal, defining a deep reinforcement learning (DRL) agent for a deep reinforcement learning (DRL) model. The method further includes processing a second plurality of voltage signals and current signals of microgrid and classifying the one or more fault signals into one or more fault types.

In order to solve the problem of inaccurate classification caused by fixed time-frequency resolution and lack of physical rationality in sample enhancement in a traditional classification method, the invention relates to a partial discharge signal classification method based on a physical constraint generative adversarial network, and the method comprises the following steps: extracting a partial discharge signal and a historical partial discharge signal, and carrying out the double-window time-frequency coding of the partial discharge signal and the historical partial discharge signal; correspondingly obtaining a fused time-frequency graph and a historical fused time-frequency graph; determining a corresponding discharge type label based on the historical partial discharge signal, establishing a physical constraint generative adversarial network, and training the physical constraint generative adversarial network in the historical fusion time-frequency graph based on the discharge type label; and inputting the fusion time-frequency graph into the trained physical constraint generative adversarial network to obtain a fusion feature graph corresponding to the fusion time-frequency graph, performing time sequence modeling on the fusion feature graph, mapping the fusion feature graph into a time sequence feature vector, and performing classification on the corresponding partial discharge signals based on the time sequence feature vector.

The invention discloses a power distribution network fault knowledge graph construction method and system based on multi-modal data, equipment and a medium, and belongs to the technical field of intelligent power grids, and the method comprises the steps: carrying out the change matching of spatial position signals and meteorological parameters based on regional monitoring space-time records, meteorological environment parameters and equipment operation state data, dividing time periods, and obtaining a power distribution network fault knowledge graph; and analyzing according to spatial position association, and screening data overlapping to obtain a multi-modal data association distribution table. According to the invention, through matching and screening of space-time records, meteorological parameters and equipment state data, multi-modal data integration and abnormal feature extraction are realized, and in combination with cross analysis of signal fluctuation and meteorological conditions, abnormal signal classification and path association are optimized, and a fault propagation rule is accurately analyzed. The overall optimization significantly improves the efficiency of abnormal recognition, fault location and propagation analysis of the power distribution network, enhances the operation reliability and fault processing capability, reduces data redundancy and errors, and improves the safety and stability of the power grid.

The invention discloses an electroencephalogram signal classification method based on a dynamic gating hybrid expert model, which focuses on efficient detection of electroencephalogram signals and comprises the following steps: 1, acquiring electroencephalogram signal data and preprocessing the electroencephalogram signal data to generate a standardized electroencephalogram signal sample; 2, constructing a dynamic gating hybrid expert model composed of a shared feature layer, a hybrid expert module and a dynamic gating network; 3, designing a mixed loss function containing classification loss and load balancing loss; 4, training a dynamic gating hybrid expert model based on the hybrid loss function; and 5, realizing electroencephalogram signal classification by utilizing the trained dynamic gating hybrid expert model. By means of a dynamic expert selection mechanism, expert combination is optimized in real time through a gating network, and the electroencephalogram signal classification sensitivity is effectively improved; meanwhile, a hardware sensing architecture is introduced, multiplication operation is greatly reduced, energy consumption optimization and the classification accuracy of the electroencephalogram signals are remarkably improved, and the application value of the electroencephalogram signals in the medical field is enhanced.

The invention relates to a dynamic weighted electroencephalogram signal classification method capable of resisting individual differences. The method comprises the following steps: step 1, acquiring motor imagery electroencephalogram signals of multiple subjects by using electroencephalogram acquisition equipment; 2, preprocessing the collected electroencephalogram signals, wherein the preprocessing comprises filtering, denoising and segmenting; step 3, constructing a hybrid expert model based on CNN-Transform; step 4, training the hybrid expert model; and 5, performing classification prediction on the electroencephalogram signals of the target subject. According to the method, the advantages of CNN and Transform are combined, and a hybrid expert mechanism of dynamic routing is introduced, so that the classification performance and generalization ability of the model in a cross-subject scene are remarkably improved.

Disclosed are system and techniques for classifying events such as emergencies. A system can include a computer system to perform operations including: receiving sensor signals from a group of devices at a location, determining whether one or more of the sensor signals exceed expected threshold levels, in response to determining that the one or more of the sensor signals exceed the expected threshold levels, correlating the sensor signals, classifying the correlated sensor signals into an emergency event based on applying an artificial intelligence (AI) model to the correlated sensor signals, the AI model having been trained to classify the correlated sensor signals into a type of emergency, determine a spread of the emergency event, and determine a severity level of the emergency event, generating, based on information associated with the classified emergency event as output from the AI model, emergency response information, and returning the emergency response information.

The invention belongs to the technical field of electromyographic signal classification detection, discloses an electromyographic signal classification detection method combining SNN and HDC, provides an electromyographic signal classification detection framework combining SNN and HDC, and aims to realize ultra-low power consumption operation. In the framework, the SNN executes event-driven feature extraction by using a random untrained weight, so that the calculation overhead is reduced to the greatest extent; and the HDC realizes anti-noise classification through high-dimensional representation. The integration of the two not only realizes real-time detection of energy conservation, but also is particularly suitable for being applied to resource-limited scenes such as wearable equipment and the like. The method provided by the invention realizes 95% of average accuracy (the peak accuracy is 96.44%) in three types of fatigue recognition tasks, and the training speed is 5.7 times faster than that of a one-dimensional convolutional neural network (1D-CNN) and 45 times faster than that of a five-dimensional long-short-term memory network (5D-LSTM). Even under the condition that only 20% of training data is used, the method can still keep the accuracy of 90% or above, and the high efficiency and robustness of the method in actual deployment are fully proved.

The invention discloses a state monitoring method for a bridge structure, and belongs to the technical field of bridge measurement and monitoring, and the method comprises the steps: obtaining an original data set of the inclination angle of a bridge main tower and the tension of an inhaul cable, analyzing a signal time feature representation factor, and carrying out the linear interpolation adjustment information judgment; and based on the original data set, analyzing an inhaul cable tension update value, then analyzing an inhaul cable tension residual error and an interpolation adjustment effect label, and carrying out signal reconstruction effect judgment. According to the method, the bridge structure can be continuously monitored, linear interpolation adjustment information is carried out by analyzing signal time characteristic characterization factors, whether adjustment is carried out or not is judged, calculation power waste is avoided, and the inhaul cable tension is aligned with a main tower inclination timestamp by analyzing inhaul cable tension update values through linear interpolation adjustment. A stay cable tension update value is analyzed to eliminate a cross-sensor clock asynchronous error, signals are classified by analyzing a frequency coherence factor, mutual interference of different frequency components in broadband signals is avoided through classification processing, and the structural health monitoring precision is remarkably improved.

The invention relates to the field of bionic hidden underwater acoustic communication, in particular to an underwater acoustic communication hidden performance evaluation method, device and equipment based on a neural network, and the method comprises the steps: carrying out the feature extraction of a to-be-evaluated underwater acoustic signal, and obtaining a feature sequence of the to-be-evaluated underwater acoustic signal; converting the feature sequence into a two-dimensional matrix with a preset size; the two-dimensional matrix is predicted according to a pre-trained underwater acoustic signal classification neural network model, a probability matrix is obtained, the probability matrix comprises a first probability and a second probability, the first probability represents the probability that the to-be-evaluated underwater acoustic signal belongs to the bionic modulation signal, and the second probability represents the probability that the to-be-evaluated underwater acoustic signal belongs to the bionic modulation signal; the second probability represents the probability that the underwater acoustic signal to be evaluated belongs to the real marine organism signal, and the underwater acoustic signal classification neural network model comprises an input layer, a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer, a global pooling layer and a full-connection output layer which are connected in sequence. The dependence on artificial feature design in a traditional recognition method is reduced, and the recognition stability in a complex underwater environment is improved.

The invention discloses an underwater acoustic signal classification method based on comparative learning and feature fusion, and the method comprises the steps: collecting an original underwater acoustic signal, and carrying out the enhancement preprocessing of the original underwater acoustic signal, and obtaining a preprocessed underwater acoustic signal; outputting the preprocessed underwater acoustic signals to a classification neural network model to obtain an underwater acoustic signal classification result; wherein the classification neural network model is obtained according to the following steps: constructing a multi-modal heterogeneous feature fusion network; performing self-supervised comparison pre-training on the constructed multi-modal heterogeneous feature fusion network to obtain a pre-trained multi-modal heterogeneous feature fusion network; a classification module is built, and the classification module takes fusion features output by the multi-mode heterogeneous feature fusion network as input and takes probability distribution of each category as output; and performing progressive supervision fine tuning on the pre-trained multi-modal heterogeneous feature fusion network and the classification module to obtain a classification neural network model.

The invention relates to an electroencephalogram signal classification method based on multi-scale causal convolution and KAN attention. The electroencephalogram signal classification method comprises the steps of 1, EEG data collection and preprocessing; 2, EEG data enhancement; and 3, motor imagery task classification based on EEG signals. According to the method, the spatial-temporal characteristics of the EEG signals under different frequencies can be effectively extracted, the multi-scale nonlinear characteristics are efficiently fused and weighted, and the problem that nonlinear fitting of the EEG signals in a motor imagery task is insufficient is solved, so that more accurate and reliable motor imagery classification is realized.

The invention provides a superconducting quench detection system and method, and the system comprises an OFDR signal collection module which is used for obtaining an optical frequency domain reflection signal and transmitting the optical frequency domain reflection signal to a data fusion and preprocessing module; the voltage signal acquisition module is used for acquiring and transmitting a voltage signal; the data fusion and preprocessing module is used for fusing and preprocessing the received optical frequency domain reflection signal and the voltage signal and outputting a processing result; and the CNN model training and recognition module is used for constructing and training a CNN model for quenching signal classification and recognition based on the processing result of the data fusion and preprocessing module, and outputting a detection result. According to the superconducting quench detection system based on optical frequency domain reflection, the convolutional neural network and voltage signal fusion, the advantage of high-precision distributed measurement of the OFDR technology, the powerful feature extraction and classification capability of the CNN and the characteristic that the voltage signal directly reflects the state change of the superconductor are comprehensively utilized, and faster and more accurate detection of superconducting quench is achieved.

The invention provides an intrusive electroencephalogram signal classification system based on SHAP interpretable feature selection and Transform, and relates to the technical field of brain-computer interfaces and intelligent neural information processing. The system comprises a candidate feature extraction module, an SHAP feature optimization module, a space-time Transform classification model and an interpretability and visualization module. The candidate feature extraction module is used for extracting time domain, frequency domain and nonlinear candidate features from the preprocessed interventional electroencephalogram signals; the SHAP feature optimization module performs importance scoring and recursive screening on the candidate features based on a random forest and a Shapley value method to generate an optimal feature subset; according to the space-time Transform classification model, a space-time feature matrix is constructed through feature embedding and a time position coding mechanism, and high-precision classification is achieved through a multi-head self-attention structure; and the interpretability and visualization module is combined with the SHAP heat map and the attention weight map to provide physiological interpretation of a model discrimination basis. The system is suitable for various interventional brain-computer interface scenes such as neural rehabilitation and motion intention recognition.

The invention belongs to the field of electroencephalogram signal classification detection, and particularly relates to a neuropsychiatric disease electroencephalogram diagnosis method based on iteration polar coordinate attention, which comprises the following steps: acquiring a multi-channel EEG (electroencephalogram) signal and preprocessing the multi-channel EEG signal; inputting the EEG preprocessing signal into a pre-trained improved LaBraM model to obtain a plurality of node features; calculating a Pearson's correlation coefficient matrix and a cosine similarity matrix according to the EEG preprocessing signal, and then constructing a brain function fusion connection matrix as an adjacent matrix through an iteration polar coordinate attention mechanism; according to the method, the large-scale pre-trained EEG model and polar coordinate attention are used for brain graph structure construction for the first time, and collaborative optimization of time feature generalization and space structure modeling capacity is achieved.

The invention relates to the technical field of electromagnetic compatibility and signal processing, and discloses a multi-dimensional feature fusion-based electromagnetic leakage signal classification and identification method, which comprises the following steps of: preprocessing an original electromagnetic signal to obtain standardized data, extracting time domain, frequency domain and space domain features to construct a nine-dimensional feature vector, and extracting a three-dimensional feature vector; constructing an initial feature library and completing the initial feature library through a self-supervision verification mechanism, training the initial feature library through a CNN-LSTM fusion model with an attention mechanism to obtain a classification model, classifying signals to be identified, starting a self-supervision reinforcement learning mechanism optimization model according to an F1 score, and dynamically optimizing the feature library each month; the method solves the defects of the traditional technology, improves the recognition accuracy and the system adaptability, and can be used for cable information safety leakage protection.

The invention discloses a bearing steel open-set classification system based on differential pulsed eddy current and a double-branch network, and the system comprises a differential collection module which is used for obtaining steel induction eddy current signal data and providing required original data; the data preprocessing module is used for carrying out signal preprocessing on the collected original data and improving the signal-to-noise ratio of signals; the model structure optimization module is used for fusing manually selected statistical features and machine learning features to form a double-branch network model structure, so that the signal classification precision and the discrimination capability of unknown bearing steel samples are improved; by calculating the confidence coefficient of a to-be-tested sample and the distance between the class center of the to-be-tested sample and each class center recorded by the model, which class is in known classes can be judged, and by setting a class center distance threshold, an unknown class can be effectively identified.

The embodiment of the invention discloses a modulation signal classification system based on a lightweight network. The modulation signal classification system comprises a signal acquisition module for acquiring an IQ modulation signal; the model detection module performs judgment based on a trained modulation signal identification model by taking an IQ modulation signal as input, and the feature extraction unit obtains a feature matrix of the IQ modulation signal through depth separable convolution; the feature optimization unit performs multi-level wavelet decomposition and pooling processing on the feature matrix to obtain a feature vector, and obtains an attention weight corresponding to each feature in the feature vector through a self-attention algorithm; the classification unit obtains a prediction probability corresponding to each modulation category label based on the feature vector and an attention weight corresponding to each feature in the feature vector; and the result output module outputs the prediction category. Through cooperative use of depth separable convolution and multi-level wavelet decomposition, the time-frequency feature characterization capability of the model is remarkably improved while the calculation amount is reduced, so that light weight and edge deployment of the recognition model are realized.

The invention discloses a phi-OTDR (Optical Time Domain Reflectometer) vibration signal classification method based on multi-scale residual convolution and a bidirectional long-short-term memory network, relates to the technical field of phase-sensitive optical time domain reflectometer vibration sensing, and solves the problems of insufficient feature extraction, single model fusion mechanism, poor system real-time performance and the like of an existing phi-OTDR vibration signal classification method. The method is realized through the steps of a multi-scale deep convolutional network, a bidirectional long-short term memory network, a cross attention fusion module, a learnable gating mechanism and the like. A cross attention fusion module is adopted, association between spatial features and time sequence features is dynamically established in a double-path network, feature interaction and information coupling are deepened, and the sensing ability of the model to key information is remarkably improved. Meanwhile, the fusion proportion of the multi-path features is adaptively adjusted according to the actual distribution of the input features, background noise interference is effectively suppressed, and the robustness and discrimination performance of the model are enhanced. Accurate identification and classification of external vibration signals are realized.

The invention discloses a Conformer-based multi-task wireless communication signal classification method, and belongs to the technical field of crossing of signal processing and artificial intelligence. In order to solve the problems of task modeling isolation, insufficient feature sharing mechanism and weak model generalization ability in existing wireless communication signal classification, the method comprises the following steps: acquiring an IQ signal, performing dimension raising through a front-end convolution module, inputting the IQ signal into a Conformer network fusing local convolution and a global attention mechanism, and performing depth time sequence feature extraction; and synchronously realizing discrimination of a signal-to-noise ratio grade, a channel type, a modulation mode and a communication system by using a parallel multi-task classification head. The method can improve the classification accuracy and the model generalization ability, reduces the consumption of computing resources, and is suitable for signal recognition in wireless communication, radar and Internet of Things systems.

The invention discloses an electroencephalogram data enhancement and classification method and related equipment, relates to the cross technical field of artificial intelligence and neural signal processing, and aims to overcome the defects that high-frequency information is lost when electroencephalogram signals are generated by a traditional diffusion model, and potential space mismatch is caused by isolation and optimization of a generation-classification task. Proposing an end-to-end joint training framework of a conditional auto-encoding diffusion model, modeling a degeneration and reconstruction process of an electroencephalogram signal through a de-noising diffusion model, and dynamically compensating information loss in a diffusion process by using a jump connection mechanism of a conditional auto-encoder; according to the method, the robustness and generalization ability of electroencephalogram signal classification are remarkably improved through end-to-end joint optimization of generation and classification tasks, and the robustness and generalization ability of electroencephalogram signal classification are improved; and an efficient solution is provided for the fields of target classification, signal enhancement, physiological signal analysis and the like.

This invention relates to the field of robot interaction technology and discloses an embodied humanoid robot interaction system. The system includes: interaction perception, intent parsing, action generation, and feedback calibration modules. The interaction perception module collects a first interaction signal within a first preset time period and converts it into perceptual features after preprocessing. The intent parsing module identifies the behavioral entity of the object to be interacted with, uses its semantic set as a reference label, and trains a parsing network model by combining reference samples and perceptual features. The action generation module collects a second interaction signal within a second preset time period, extracts the encoder and decoder of the parsing network model, generates instructions based on the encoder, constructs a rule mapping execution unit, and optimizes the mapping relationship through the decoder. The feedback calibration module collects a third interaction signal within a third preset time period, classifies it into regular signals and irregular signals, and processes them through calibration by the mapping execution unit or generation by the encoder, respectively.

The invention provides an MEMS heart sound and electrocardio detection system, method and equipment, and relates to the technical field of medical instruments, the MEMS heart sound and electrocardio detection system comprises a bionic cilium heart sound sensor, an electrocardio acquisition circuit and a signal fusion model; the bionic cilia heart sound sensor comprises hollow bullet type bionic cilia and a cantilever beam microstructure; the hollow bullet type bionic cilia and the cantilever beam microstructure are mechanically coupled, and the cantilever beam microstructure comprises a Wheatstone bridge formed by arranging a plurality of piezoresistors and is used for collecting heart sound signals; the electrocardio acquisition circuit and the bionic cilium heart sound sensor are packaged in an acoustic impedance matching mode, and the electrocardio acquisition circuit comprises an electrocardio acquisition electrode plate, a power supply voltage stabilization module, an instrument amplification module, a band-pass filtering module and a notch filter and is used for acquiring and conditioning electrocardio signals; the signal fusion model comprises a Resnet18 feature extractor, an encoder and a mutual cross attention mechanism, and is used for performing feature extraction, linear transformation and feature deep fusion on the collected electrocardiosignals and electrocardiosignals and outputting a signal classification result.

The invention provides a micro-seismic P-wave first arrival pickup method based on deep learning and an adaptive time window, and the method comprises the steps: (1) collecting and preprocessing a micro-seismic signal, making a data set, and dividing the data set into a training set and a test set; (2) building an MSC-NET deep learning neural network, taking a data set as input for training, and adjusting model parameters to achieve an optimal model effect; (3) performing a micro-seismic signal classification task by applying the trained deep learning model, and dividing a large number of micro-seismic signals into an effective available class and an ineffective unavailable class; and (4) finally, carrying out P-wave first arrival time pickup on the effective micro-seismic signals based on an energy ratio algorithm of an adaptive time window to obtain a relatively reliable pickup result. According to the method, the deep learning technology and the improved traditional signal processing technology are combined, the reliability and accuracy of the automatic pickup result of the micro-seismic signal P wave first arrival time are greatly improved, and meanwhile the method has the advantages of being high in robustness and applicability and the like.

A radio frequency (RF) signal classification device may include an RF receiver configured to receive RF signals, a quantum computing circuit configured to perform quantum subset summing, and a processor. The processor may be configured to generate a game theory reward matrix for a plurality of different deep learning models, cooperate with the quantum computing circuit to perform quantum subset summing of the game theory reward matrix, select a deep learning model from the plurality thereof based upon the quantum subset summing of the game theory reward matrix, and process the RF signals using the selected deep learning model for RF signal classification.

The invention provides a hard and brittle material subsurface damage mechanism signal classification method based on an acoustic emission technology. The method comprises the following steps: firstly, acquiring an acoustic emission original signal and surface appearance of the hard and brittle material through grinding tests at various grinding speeds; then, carrying out preprocessing and time-frequency domain feature extraction on the acoustic emission signals by using a wavelet packet signal processing algorithm and short-time Fourier transform; finally, distinguishing a micro-crack signal, a radial crack signal and a transverse crack signal from the characteristic space by combining the damage characteristics and acoustic emission characteristic parameters of the hard and brittle material, and obtaining a characteristic frequency band range corresponding to each crack damage mode; a hard and brittle material subsurface damage mechanism signal classification model is constructed, and a theoretical basis is provided for monitoring of grinding subsurface damage of hard and brittle materials under complex working conditions. According to the method, the damage mechanism of the hard and brittle material can be quickly identified, the subsequent online evaluation of the subsurface damage of the hard and brittle material is realized, and the technical problem of non-destructive accurate monitoring in the grinding process is solved.

The invention provides an AI-driven multi-wireless-signal candid photographing detection device which comprises a mounting shell, a hardware acquisition layer, an edge computing layer, a cloud federation layer and a man-machine interaction layer, and all the layers achieve signal interaction through PCIe4.0 and SPI hardware interface communication protocols. The broadband patch antenna, the ceramic antenna and the helical antenna are adopted to cover a full target frequency band, the millimeter wave radar chip is matched, the 16 * 16 metamaterial RIS panel is additionally configured, and the weak signal receiving power is improved by synchronously controlling a reflection phase focusing signal, so that the problem of missing detection is solved; the multi-signal tensor decomposition unit and the CNN-LSTM signal classification unit construct frequency, intensity, time and phase four-order tensors, and overlapped signals are separated through Khatri-Rao space-time coding; a three-layer CNN and a two-layer LSTM are combined, precise classification of candid photographing signals is realized, the misjudgment rate is reduced, millimeter wave assisted precise distance measurement is combined with millimeter wave flight time data and an RSSI attenuation model, a distance measurement error is controlled through a dynamic weighting algorithm, and the problem of positioning misalignment is solved.

The invention discloses a secondary equipment alarm signal classification and grading method and system fused with artificial intelligence, and the method comprises the steps: collecting standard alarm signals and actual alarm signals of secondary equipment, dividing grades and types according to the types of the secondary equipment, and respectively constructing a standard table and an actual table of the alarm signals of the secondary equipment; constructing a text matching database, a text matching standard library, a text matching standard vector library and a text matching data set based on the standard table and the actual table; constructing a cascade text semantic matching model, and training the cascade text semantic matching model in combination with the text matching data set; and obtaining a to-be-processed secondary equipment alarm signal, and processing the to-be-processed secondary equipment alarm signal based on the text matching database, the trained cascade text semantic matching model and the text matching standard library to obtain a classification result of the to-be-processed secondary equipment alarm signal. According to the method, the intensity of manual intervention can be reduced, the warning signal grading and classifying efficiency is improved, and the misjudgment rate and the missed judgment rate are reduced.