736 results about "Time signal" patented technology

The invention relates to the technical field of radar signal processing, in particular to a radar target analytical calculation method based on multi-dimensional data fusion and a radar device. Comprising the following steps: deploying a multi-band radar sensor array comprising an X band, a C band and a Ku band in a radar monitoring area; performing pulse compression and Doppler processing on the time domain echo signal, and extracting a time domain feature; spectral analysis is carried out on the frequency domain signals, and frequency domain features are extracted; performing angle estimation on the spatial signals, and extracting spatial features; a dynamic weight distribution model is constructed, a fusion weight is calculated through an adaptive algorithm based on three-dimensional quality indexes of a real-time signal-to-noise ratio (SNR), feature stability (SI) and data integrity (CI), and a joint representation vector containing time domain, frequency domain and space multi-dimensional information is generated. According to the invention, by deploying the multi-band radar sensor array, the recognition capability of the subtle feature difference of the target is improved.

The invention discloses a relay state prediction and fault early warning method and system based on deep learning, and the method comprises the steps: S1, building a constraint condition of a generative adversarial network based on a relay physical model, and forming an enhanced fault waveform signal according with a physical rule through adversarial training; s2, receiving a real-time current and voltage signal and a mechanical vibration signal, and extracting an electric signal feature vector by using a time sequence convolutional network; s3, inputting the combined feature tensor into the lightweight assessment model, and outputting a health degree scoring signal; s4, responding to the meta-learning activation instruction, loading historical data of equipment to construct a parameter optimization set, performing online fine tuning on the early warning model based on a meta-learning framework, and generating a fault determination parameter; and S5, analyzing real-time signal characteristics according to the fine-tuned judgment parameters, and outputting graded early warning signals to a monitoring terminal. According to the method, the problems of early state prediction and accurate early warning of the relay under small sample fault data can be solved.

The invention provides a self-adaptive radar target detection method, system and device and a medium, and belongs to the technical field of self-adaptive radar target detection, and the method comprises the steps: carrying out the high-resolution decomposition and Gaussian fitting of a radar echo signal, analyzing the spectral centroid and spectral width characteristics, and determining the frequency domain interval of the radar echo signal; decomposing the radar echo signal into a plurality of intrinsic mode components, and screening out the mode components in a target frequency domain interval for reconstruction; key features in the reconstructed radar echo signals are extracted from the time domain dimension and the frequency domain dimension, and features with distinguishing force on target detection are reserved through a feature screening method; the method comprises the following steps: segmenting a long-time signal in a radar echo signal into a plurality of small windows, and respectively carrying out VMD decomposition and reconstruction; and carrying out target detection on the extracted key features by using a CA-CFAR algorithm. The method improves the precision of target detection under the background of complex sea conditions and strong sea clutters, and improves the accuracy and robustness of target detection.

The invention provides a signal shielding method based on deep reinforcement learning, and belongs to the technical field of artificial intelligence and communication crossing. The method comprises the steps that S1, a large number of historical wireless communication signals are acquired to construct a data set to train a signal interference strategy generation model; s2, deploying the signal interference strategy generation model to a signal shielding device; s3, verifying and analyzing the signal shielding instruction to obtain a shielding parameter, collecting a real-time wireless communication signal, and inputting the real-time wireless communication signal and the shielding parameter into a deployed signal interference strategy generation model to obtain a real-time signal interference strategy; and S4, the signal shielding device modulates the real-time interference signal based on the real-time signal interference strategy, and the power amplifier performs power amplification on the real-time interference signal and then transmits the real-time interference signal to the outside through the radio frequency antenna so as to perform signal shielding. The method has the advantages that the accuracy, the real-time performance and the expansibility of signal shielding are greatly improved, and the power consumption of signal shielding is reduced.

The invention provides a remote intelligent lock control method based on a cloud platform, and relates to the technical field of artificial intelligence, and the method comprises the steps that the cloud platform issues a sound wave signal emission instruction to a target intelligent lock, and triggers the intelligent lock to send multi-band sound wave signals to a preset auxiliary signal enhancement device deployment position A and a preset auxiliary signal enhancement device deployment position B; and the cloud platform receives sound wave feedback signals returned by the position A and the position B, calculates a final communication path based on signal propagation time delay, frequency band interference intensity and attenuation parameters in combination with a real-time signal quality index reported by the remote communication module, and sends a dynamic encryption instruction to the remote communication module through the final communication path. According to the method, the optimal transmission path is dynamically calculated, the traditional single channel transmission limitation is broken through, reliable transmission of the control instruction can still be guaranteed in a complex electromagnetic environment or an obstacle shielding scene, and the communication interruption rate is reduced.

A while-drilling multi-element signal sensing and early warning method for coal rock dynamic disasters comprises the steps that in the early stage of coal seam recovery, bedding gas extraction drilling is utilized, while-drilling signals generated in the drilling period of each drill rod are collected in real time through a multi-parameter sensing system integrated with a drilling machine, and while-drilling data are obtained based on the while-drilling signals; constructing a mechanical parameter inversion model, and calculating the compressive strength of the coal rock mass; a gas parameter inversion model is constructed, and gas pressure and coal rock mass permeability are obtained through decoupling; according to the method, coal rock mass compressive strength, gas pressure and coal rock mass permeability are used as core indexes, a spatial interpolation method is adopted to realize continuous representation of disaster risk distribution of a whole area, and a comprehensive risk index is established accordingly; and according to the value range of the comprehensive risk index, further quantifying the risk level of the coal and rock mass dynamic disaster based on the comprehensive risk index. According to the method, real-time sensing, accurate inversion and active prevention and control of coal rock dynamic disasters can be realized, and the problems of low detection accuracy, poor real-time performance, insufficient overall performance and the like in the traditional technology can be effectively solved.

The invention discloses a multi-mode fusion time service method and system based on dynamic calibration of DCP equipment. The method comprises the following steps: completing initial time reference data acquisition based on a multi-mode satellite signal; meanwhile, time data of a ground time service network are collected, and motion parameters of DCP equipment are monitored in real time through an inertial navigation unit; establishing a correlation model of the motion parameter and the time service error; quantitative analysis of error sources is completed based on the correlation model; fusing the multi-source time data; dynamically adjusting the fusion weight of each data source according to the real-time motion state of the DCP equipment; redundant time slots are automatically distributed to high-error equipment; outputting the calibrated time signal to DCP equipment through an interface to complete clock synchronization; and continuously monitoring the time deviation of the DCP equipment, and dynamically updating the calibration parameters to form closed-loop optimization. And the environmental adaptability and the precision stability of the timing system are improved.

The invention relates to the technical field of electric power facility anomaly monitoring, in particular to a computer monitoring system anomaly monitoring method for large-scale electric power construction engineering, which comprises the following steps of: acquiring an insulator leakage current signal, a temperature signal and an ultrasonic signal, and calculating a corresponding energy gradient; calibrating the correlation coefficient of the sensor based on the physical characteristics of an insulator material, and calculating the dynamic weight according to the energy gradient, thereby achieving the dynamic weighting of a fault sensitive signal; generating a fusion reference signal through weighted summation; constructing a dynamic threshold by combining the thermal physical parameters of the equipment, the real-time signal characteristics and the environmental parameters; calculating a signal difference quantity between the original signal and the fusion signal, and if the signal difference quantity exceeds a dynamic threshold value, triggering abnormal early warning; noise influence on a single sensor is suppressed, the signal-to-noise ratio of a fusion signal is effectively improved, the problems of abnormal missing report and false report easily caused by a fixed threshold value are avoided, and the insulator abnormal detection precision is improved.

A disaster relief system using AI-powered intelligent antennas in drone swarms, consisting of: a plurality of drones configured to collect environmental data in real time, with the drones being deployed in a disaster area environment; a smart antenna system mounted on each drone, each smart antenna system configured to perform adaptive beamforming to maintain communication links between drones; an artificial intelligence (AI) processing unit configured to receive real-time signal data, including obstacle information, drone positions, and interference patterns from the disaster environment, analyze the received signal data using reinforcement learning algorithms, generate optimized beamforming parameters based on the analysis, and transmit the optimized beamforming parameters to the intelligent antenna systems; a swarm communication protocol module configured to establish communication links between the plurality of drones using the optimized beamforming parameters, coordinate task assignments within the drone swarm, and maintain network integrity during operation; and a central control system configured to monitor all swarm operations, process environmental data, and adapt swarm behavior based on disaster relief requirements.

The invention discloses a wireless network coverage optimization method based on spatial positioning and transmitting power regulation and control. The method comprises the following steps: S1, collecting real-time signal quality and link state data of a base station and user equipment; s2, dynamically adjusting the transmitting power of the base station according to the collected signal quality and link state data; s3, constructing an interference sensing matrix, further calculating a conflict weight according to the interference sensing matrix, and optimizing frequency and time slot resources based on the conflict weight; s4, adjusting a frequency subset, a time slot subset and a power upper limit according to an optimization result; s5, dynamically adjusting the transmitting power and the interference coordination strategy by receiving interference information from other base stations in real time and the feedback of the user; and S6, adjusting power distribution, spectrum resources and channel selection of the network according to the real-time feedback of the network environment. According to the method, an efficient and scientific optimization scheme can be provided in wireless network coverage optimization, and remarkable technical values and economic benefits are brought to practical application.

The invention belongs to the technical field of bearing fault diagnosis, and particularly discloses a press machine bearing fault diagnosis method and system, a terminal and a medium, and the method comprises the steps: collecting multi-source signal data of a press machine bearing in an operation process; performing denoising and standardization processing on the signal, and extracting time domain and frequency domain features; different sensor features are fused, and multi-dimensional feature representation is constructed; inputting the features into a deep learning model combining a convolutional neural network and a long-short-term memory network for training and reasoning, and introducing a multi-kernel maximum mean value difference strategy to realize feature distribution alignment; and performing fault identification on the real-time signal based on a multi-label classification mode, and triggering an alarm when the prediction probability meets a preset condition. According to the method, fusion modeling of multi-source data and accurate recognition of composite faults are achieved, and the method has high cross-working-condition adaptive capacity and real-time diagnosis capacity and is suitable for intelligent operation and maintenance scenes of press equipment.

The embodiment of the invention provides an emergency data quality control analysis method and device based on big data. Wherein a microcirculation dynamic mapping model with time-space correlation is constructed and integrated through a nanofiber sensing array of the flexible electronic skin device. And performing time reference synchronous compensation and space coordinate transformation mapping on the model and spatio-temporal data of emergency treatment monitoring equipment to form a fusion data field, thereby realizing joint feature distribution of microcirculation parameters and emergency treatment parameters. The fused data field is subjected to mode coupling verification with a microcirculation compensation track map in a shock compensation mode feature library through a dynamic quality control engine, and when it is detected that mode mismatching exists between a parameter evolution path and a historical track, space-time signal fragments are reconstructed based on phase features and space distortion features; and generating a quality control report associated with the abnormal skin perfusion gradient node. According to the technical scheme provided by the embodiment of the invention, the quality control effect of the emergency data of the shock patient is improved.

The invention provides an intelligent shelter equipment operation state monitoring method and system based on machine learning, and the method comprises the steps: firstly obtaining a synchronous operation real-time signal set which comprises the real-time parameters of all operation parts, the interaction between equipment and the comprehensive influence of a shelter environment, and carrying out the mutual feedback correlation processing of the synchronous operation real-time signal set to extract a mutual feedback correlation feature set; inputting the set into an operation state deduction model to generate a short-term operation state evolution sequence, identifying a potential abnormal evolution trend and determining an abnormal association influence range based on the short-term operation state evolution sequence, and generating collaborative regulation and control demand information; then, inputting the collaborative regulation demand information and the mutual feedback correlation feature set into a collaborative regulation model to generate a multi-device collaborative operation regulation instruction, after the multi-device collaborative operation regulation instruction is sent, collecting an execution feedback signal, updating a feature extraction rule, and adjusting model parameters; the comprehensive, dynamic and accurate monitoring and regulation of the operation state of the square cabin equipment are realized, and the stability and the reliability of the equipment operation are improved.

The invention discloses a high-precision high-speed pipeline time-to-digital converter. The converter comprises a pulse selection circuit, a parallel delay line TDC, a margin extraction module, a time register type TDC, a vernier type TDC and a digital encoder. The pulse selection circuit converts an input bipolar time signal into a unipolar time signal and generates a polarity bit, the three TDCs are sequentially in transmission connection to form a three-stage running water working mode, and the first-stage parallel delay line TDC is used for roughly quantizing and determining a value of a high binary bit; meanwhile, the output end is connected with the margin extraction module to generate time margin and transmit the time margin to the second stage for fine quantization, thereby compensating the quantization error of the first stage and improving the accuracy. And after the second-stage time register type TDC is quantized, the time margin can be directly generated and transmitted to the third-stage vernier type TDC for fine quantization, so that the use of a digital time converter is reduced, and the conversion efficiency is improved. And the digital encoder encodes and outputs the TDC quantized data.

The invention discloses a fetal state dynamic monitoring method and system based on multi-modal deep learning, and the method comprises the steps: segmenting a fetal heart rate signal and a uterine contraction signal into a plurality of segmented time signals through a sliding window, and carrying out the denoising preprocessing of each segmented signal; performing wavelet transformation on the signal to obtain a time-frequency spectrogram, and inputting the time-frequency spectrogram into a 3D convolutional neural network to extract features; a cross attention module is introduced to fuse the two modal features, a transform encoder is put into use to complete time sequence feature extraction, and finally fetal state monitoring is achieved through a full connection layer. According to the method, the multimodal fusion and deep learning technology is utilized, and the fetal state can be accurately and dynamically monitored. Manual monitoring errors can be effectively reduced, the monitoring efficiency and accuracy are improved, powerful support is provided for medical staff to know the fetus condition in real time, the abnormal state of the fetus can be found in time, and the safety of the fetus is guaranteed.

The invention relates to a detection-interference integrated unmanned aerial vehicle electromagnetic interference device, which belongs to the technical field of electronic countermeasure, and comprises an integrated design of an antenna module, a radio frequency front end module, a digital signal processing module and a main control module, the radio frequency front-end module comprises a detection receiving channel and an interference transmitting channel to process signal conversion, the digital signal processing module executes signal detection and analysis, intelligent interference decision and anti-self-interference signal processing based on a self-adaptive filtering algorithm, and the main control module is responsible for overall control and power supply. According to the invention, the technical problems of large response delay, complex system cooperation and incapability of continuous reconnaissance in the interference process of traditional anti-unmanned aerial vehicle equipment are solved. Real-time signal cancellation is achieved through the normalized least mean square algorithm, the reconnaissance capability is kept while interference is applied, the method has the advantages of being rapid in response, accurate in interference, low in power consumption and the like, and the countering efficiency is remarkably improved.

The invention discloses a power distribution network fault early warning method and system based on online monitoring, and relates to the field of fault early warning, and the method comprises the steps: continuously collecting real-time electrical signals; signal waveform prediction of the real-time electrical signal is completed according to the real-time signal prediction result, and whether an early fault signal exists in the target power distribution network is judged; if the target power distribution network has the early fault signal, obtaining power distribution network information, environment prediction data and geographic position data; constructing a topological structure of the power distribution network, and extracting early fault information of the target power distribution network; constructing an icing evolution model of the target power distribution network; completing fault risk coupling between the icing evolution model and the early fault information; and carrying out risk accumulation analysis on the topological structure of the power distribution network, and outputting fault early warning information of the target power distribution network according to a risk accumulation analysis result. According to the invention, the power distribution network fault early warning precision and efficiency can be effectively improved.

The invention discloses a dual-mode TDC implementation method and system based on an FPGA, and relates to the technical field of electronic circuits, and the technical key points are as follows: after a dual-mode signal generation circuit receives each STOP pulse, a logic sequence opposite to the last time is immediately output as an effective delay signal, the reset of the last time signal in a time delay chain (TDL) is not required, and the time delay time is shortened; when the logic signal propagated last time does not completely fade, the new reverse logic signal can be independently propagated in the TDL, and the new reverse logic signal and the new reverse logic signal do not interfere with each other; meanwhile, the rising edge of the system clock only updates the state of the main trigger to serve as the logic reference of the next trigger, and an additional reset process is not needed, so that the dead zone time of single measurement is strictly controlled to be a single period corresponding to the system clock, and compared with a double-period dead zone in an existing scheme, the dead zone time is remarkably shortened, and the measurement rate is synchronously doubled; in a high-frequency pulse measurement scene, pulse loss caused by an overlong dead zone can be effectively avoided, and the measurement efficiency is remarkably improved.

The invention discloses a low-altitude economic flight data management method based on a block chain technology, and relates to the technical field of low-altitude traffic management, and the method comprises the steps: verifying an encrypted positioning proof, generating a verification state set, decrypting flight coordinates according to the verification state set, and generating a credible coordinate data stream; performing sensitive airspace intrusion detection according to the credible coordinate data stream and the high-security protection node, performing collision risk analysis by the traffic management node to obtain an encrypted aggregated threat vector, and identifying a threat level according to the encrypted aggregated threat vector; and dynamically adjusting the working parameters of the airborne equipment according to the threat level, generating an airborne equipment regulation and control instruction set, scanning the signal-to-noise ratio and the threat intensity in real time, dynamically allocating a communication frequency band, and generating a new positioning strategy parameter. According to the method, the real-time signal-to-noise ratio and the threat intensity scanning result are combined, communication frequency band dynamic allocation and encryption strategy dynamic optimization are driven, the airspace situation awareness capacity is formed, the resource utilization rate is increased, and the anti-interference capacity is enhanced.

The invention relates to the technical field of positioners, and discloses an anti-lost real-time position positioning method and system based on a positioner, and the method comprises the steps: collecting the current position information of a person under guardianship in real time, and obtaining original multi-source data; denoising the original multi-source data based on a real-time signal-to-noise ratio in combination with a Kalman filter to obtain processed multi-source data; and constructing an electronic fence verification model, inputting the processed multi-source data into the electronic fence verification model, verifying whether the current position of the person under guardianship is within a safety range in real time, if the current position exceeds the safety range, determining that the person under guardianship may have a risk of getting lost, and immediately triggering an alarm mechanism by the locator. After the guardian receives the alarm information, the positioner establishes real-time communication connection with the terminal equipment of the guardian, and the guardian obtains the moving track and the current position of the person under guardianship in real time through the terminal equipment; according to the invention, the risk caused by a lost event is reduced.

The invention discloses a signal reconstruction and noise suppression method and system for a distributed Raman temperature measurement sensing system, and the method comprises the steps: obtaining original anti-Stokes light and Stokes light time domain signals of the distributed Raman temperature measurement sensing system, and constructing a space-time signal matrix; performing preprocessing and data enhancement on the space-time signal matrix; constructing a dual-path feature fusion network for Raman signal reconstruction and noise suppression, and initializing the network; defining a loss function fusing temperature physical constraints, and training the dual-path feature fusion network; and inputting an original Raman signal to be processed into the trained network, outputting the reconstructed anti-Stokes and Stokes signals with the high signal-to-noise ratio, and carrying out temperature demodulation according to the anti-Stokes and Stokes signals with the high signal-to-noise ratio. While the spatial resolution is maintained or improved, the noise of the Raman temperature measurement system is effectively suppressed, especially the real signal of a temperature abrupt change point can be recovered, the temperature demodulation precision, stability and reliability are improved, and reliable data are provided for infrastructure safety monitoring.

The invention discloses a programmable hyperspectral laser radar device and a real-time registration method thereof.The programmable hyperspectral laser radar device comprises an optical module and a real-time signal processing module, the real-time signal processing module carries out real-time processing on received laser echo signals, and selects a windowing position and a spectral wavelength width based on converted non-laser echo signals; acquiring a plurality of arbitrary programmable spectrum channels, and reconstructing the acquired image information of the plurality of spectrum channels through a spectrum separation method to obtain different spectrum images corresponding to the target scanning area; and the data integration module is used for real-time registration of the laser point cloud and the hyperspectral image and assigning the three-dimensional coordinate information and the spectral information needing to be reserved to the laser point cloud. According to the technical scheme, a user is supported to define the windowing position and the spectral wavelength width, only the specific wave band is extracted, full-wave band data redundancy is avoided, the processing efficiency can be improved, meanwhile, key spectral features are reserved, and the method is suitable for specific scenes.

The invention belongs to the technical field of credible time, and particularly discloses a credible time source device and an implementation method and application thereof, and the credible time source device comprises a network management system and time source equipment which integrates a satellite signal identification module, an optical fiber signal identification module, an equipment identity identification module, a fault monitoring service stopping module, a time information encryption module and a time heaven and earth mutual backup module. Through multi-module cooperation and full-process management and control of a network management system, time signal authenticity identification, equipment identity authentication, encrypted transmission, fault monitoring and space-ground mutual backup switching are realized. The trusted time source implementation method comprises the steps of time signal identification, identity authentication solidification and the like. The credible time source device provided by the invention is applied to the fields of data right confirmation, finance, electric power, block chains and the like, solves the five defects that the authenticity of a traditional time source signal is not identified, and equipment is easy to counterfeit, improves the credibility and stability of time service, and has important technical value and wide application prospect.

The invention discloses a GIL equipment fault detection method, system and equipment based on a voiceprint dynamic coupling model and a storage medium, and relates to the technical field of power system equipment monitoring and operation and maintaining.The method comprises the steps that sound signals in GIL equipment are collected in real time, feature parameters are extracted, and feature vectors are obtained; establishing a Gaussian mixture model by using the normal working condition data, and training the Gaussian mixture model based on the feature vector to obtain an anomaly detection model; carrying out feature parameter extraction on a real-time signal to be detected, and calculating an estimated value and a residual error of an extracted feature on the anomaly detection model; and based on the calculated estimated value and the residual error, calculating an abnormal score and outputting corresponding early warning information and a fault positioning result. According to the method, the whole process from data acquisition to fault diagnosis is optimized, the accuracy, timeliness and intelligent level of GIL equipment voiceprint monitoring are effectively improved, and a powerful guarantee is provided for safe and stable operation of equipment.

The invention provides a fan fault diagnosis method for recognizing a vibration map based on a convolutional neural network, and relates to the technical field of neural networks, and the method comprises the steps: obtaining a multi-dimensional vibration signal in the operation process of a fan, and generating a two-dimensional vibration map through time-frequency transformation; and a convolutional neural network is utilized to automatically extract multi-layer time-frequency features and realize fault category discrimination. In the training stage, parameter optimization is carried out based on known fault samples, in the reasoning stage, real-time signals are input into a trained model to obtain fault type probability distribution, the fault type is determined according to the maximum probability, a fault evolution result is generated in combination with the historical operation trend, and therefore automatic, intelligent and rapid diagnosis of fan faults is achieved.

The invention discloses a neural patient rehabilitation training method based on task training and brain-computer interaction, and belongs to the technical field of rehabilitation training. The method comprises the following steps: acquiring data signals of a patient in current rehabilitation training in real time, performing segmentation processing to obtain a plurality of independent data blocks, performing frequency domain conversion on the independent data blocks, extracting time-frequency features, and calculating KL divergence between adjacent data blocks; if the KL divergence of any adjacent independent data block is larger than or equal to a preset threshold value, historical data signals are obtained, the motion decoding model is corrected, motion decoding is carried out on the patient according to the corrected motion decoding model, rehabilitation training is carried out on the patient according to the motion decoding model, and rehabilitation training is carried out on the patient. According to the method, the corresponding model is selected according to the current rehabilitation training task, dynamic adjustment is performed in combination with real-time signal features, high matching of the decoding result and the training target is ensured, and the rehabilitation training effect of the patient is improved.

A method and system for cloud-based V2X for providing real-time broadcast of signal phase and timing (SPaT) data. An example method includes receiving SPaT data from one or more traffic signal controllers, processing the SPaT data by converting the SPaT data from an original format into one or more different formats, where the processing includes distributing a processing load over a plurality of docker containers using a grouping or clustering algorithm that takes into account a raw data arrival sequence from the traffic signal controllers, determining one or more nearest intersections based on geolocation of a client device, and transmitting processed SPaT data related to at least one of the one or more nearest intersections to the client device.

According to an aspect, there is provided an all-digital phase-locked loop, ADPLL, for a radio receiver, transmitter or transceiver. The ADPLL comprises a time-to-digital converter for generating a digital time signal based on an external reference clock signal and a feedback signal, a switched capacitor digitally controlled oscillator, SC-DCO, for generating a radio frequency signal used as the feed-back signal, a phase-locked loop for controlling the SC-DCO based on the digital time signal for achieving a phase and frequency lock and digital processing means. The digital processing means are configured to maintain, in at least one memory, a lookup table defining a plurality of switching configurations of the SC-DCO corresponding to a plurality of frequencies of the radio frequency signal and to cause the phase-locked loop controller to adjust the switching configuration of the SC-DCO according to the lookup table.

The invention discloses an electrocardiosignal feature extraction and classification method and a sensor system, and particularly relates to the technical field of electrocardiosignal processing and mode recognition. The core of the method is that an original electrocardiosignal is obtained through a sensor, after preprocessing, a self-adaptive strategy based on real-time signal quality evaluation is adopted to dynamically select and fuse time domain, frequency domain and nonlinear features, and then a machine learning model integrated with an incremental learning function is utilized to classify the features; the corresponding system comprises a sensor module, a preprocessing module, a feature extraction module, a classification module and a system control module which are connected with one another. According to the core structure, the dynamic optimization of the feature extraction strategy along with the signal quality is realized, and the classification model can be continuously self-updated according to new data, so that the adaptability of electrocardio analysis and the accuracy of long-term monitoring are improved.

The invention discloses a soft soil foundation structure visual monitoring network and navigation system synchronous settlement early warning method, and relates to the technical field of geological monitoring and investigation. The soft soil foundation structure visual monitoring network and navigation system synchronous settlement early warning method comprises the steps that S1, image data, time signal data and environment data in the soft soil foundation monitoring process are collected and preprocessed, and a standardized soft soil foundation state data set is constructed; s2, evaluating the spatial offset characteristic of the reference point, and dynamically adjusting the stability identifier and the subsequent replacement trigger condition of the reference point; s3, analyzing the image semantic consistency of the candidate reference points, and screening stable replacement points; s4, the coordinate consistency of the replacement reference points is evaluated, and the spatial positions of the reference points are dynamically corrected; and S5, performing difference comparison on the multi-base-station monitoring data after rollback correction, and repairing curve abrupt change. The problems that the visual reference is prone to drifting and an automatic repairing mechanism is lacked under the condition that the reference point in the soft soil foundation is unstable are solved.