1910 results about "Signal extraction" patented technology

The invention discloses a deep learning-combined power transformer partial discharge signal extraction and diagnosis method. The method comprises the following steps of S1, setting a multi-channel synchronous acquisition system in a power transformer body area to acquire a multi-dimensional original partial discharge data set; s2, preprocessing the acquired multi-dimensional original partial discharge data set; s3, performing time alignment and amplitude matching on the processed signal, and dividing the processed signal into a sliding time window to construct a standard input tensor; s4, constructing an attention enhancement model fused by the convolutional neural network and the bidirectional gating circulation unit; s5, performing supervised training on the attention enhancement model by using the labeled sample; s6, inputting the real-time signal into the training model, and outputting a discharge type label; s7, risk grade evaluation is carried out in combination with statistical characteristics; and S8, generating a structured diagnosis report and uploading the structured diagnosis report to a monitoring platform. According to the invention, multi-source signals and a depth model are fused, and intelligent diagnosis and risk assessment of transformer partial discharge are realized.

The invention relates to an underwater robot navigation positioning method and system. The method comprises the following steps: S1, acquiring angular velocity and acceleration signals through an inertial measurement unit; s2, resolving a three-dimensional velocity observation value according to the beam radial velocity vector signal in combination with the angular velocity signal, and extracting environment feature point cloud data according to the acoustic image signal; s3, multi-source data time synchronization is carried out, and a fusion input signal with time-space alignment is generated; s4, constructing an adaptive factor graph optimization model, and dynamically adjusting an inertial navigation solution node based on a real-time weight coefficient; inputting the environment feature point cloud data into a closed-loop detection module to generate a loopback factor node, and adaptively correcting the weight of the node according to the feature matching degree; and S5, solving the adaptive factor graph optimization model through a nonlinear optimization algorithm. According to the underwater robot navigation positioning method and system, the problem that the fusion positioning precision of a multi-source heterogeneous sensor is insufficient in an underwater GPS-free environment can be solved.

The invention relates to an experimental data processing method and device, an AI analysis module and computer equipment, and belongs to the field of data processing.The method comprises the steps that multi-dimensional original data are partitioned according to types, and formats are unified; generating a similarity matrix based on time and space neighborhood information, and marking abnormal fluctuation points; effective signals are separated through a time-frequency feature matching noise library; extracting multi-layer features of basic statistics, time sequence correlation and trend change; and dynamically screening core features to update the tracking type experimental model. The matched AI analysis module integrates hardware circuits of data partitioning, similarity calculation, anomaly marking, noise matching, feature extraction and model updating, and whole-process acceleration is achieved. According to the method, through multi-dimensional data compatibility processing, accurate anomaly detection, multilayer feature fusion and model adaptive optimization, the experimental data processing efficiency and conclusion reliability are remarkably improved, and the method is suitable for real-time analysis of multiple scenes such as scientific research and industry.

The invention provides a distribution line fault location optimization method based on single-ended traveling wave location, and relates to the technical field of traveling wave detection. The method comprises the following steps: carrying out segmented modeling on a line, calculating the traveling wave propagation speed and wave impedance of each segment, and correcting the traveling wave propagation speed and wave impedance; collecting a voltage / current traveling wave signal of a detection point, and extracting a line mode component; performing wavelet transformation on the line mode component, detecting the wave head position of the initial traveling wave through a modulus maximum search algorithm, and recording the arrival time of the initial traveling wave, a corresponding first energy value and polarity; calculating a reflected wave time window based on segmented modeling parameters, screening reversed polarity waves with qualified energy attenuation, and calculating a fault distance; if no effective reflected wave is detected in the reflected wave time window, triggering a pseudo double-end mode; a result is verified through quadruple constraints; the problems of poor parameter adaptability, low signal processing precision, strong reflected wave dependence and incomplete verification in traveling wave distance measurement of a complex distribution line are solved, and the accuracy and reliability of fault distance measurement are improved.

The invention relates to the technical field of grinding machining, and particularly discloses a crankshaft connecting rod grinding force dynamic error compensation method and system.The method comprises the steps that a prediction reference signal is collected; a grinding force signal of the grinding wheel spindle is collected based on a piezoelectric sensor; extracting spectrum characteristic parameters according to the predicted reference signal; predicting grinding force fluctuation information according to the spectrum characteristic parameters; a feedforward compensation instruction is generated according to the grinding force fluctuation information; generating a feedback compensation instruction according to the difference between the grinding force signal and the target grinding force of the current task; synthesizing the feedforward compensation instruction and the feedback compensation instruction to generate a compensation control instruction; according to the method, a control strategy combining feedforward and feedback is adopted, the response speed and compensation precision of a system to dynamic changes of grinding force are remarkably improved, accordingly, elastic deformation caused by fluctuation of the grinding force is effectively restrained, and finally the grinding machining precision and surface quality of key parts of the crankshaft connecting rod are improved.

The invention discloses an intelligent self-monitoring temperature management system for a box-type substation, and relates to the technical field of intelligent power grid equipment monitoring. The problems that an existing system is large in temperature measurement deviation, low in reliability, delayed in early warning, inaccurate in hot spot positioning and extensive in heat dissipation control are solved. According to the scheme, multi-source signals are acquired in parallel through a data acquisition module, and a temperature time sequence is extracted; a boundary calibration module is adopted to fuse data to generate a three-dimensional boundary condition; the multi-physical field solving module obtains an internal temperature / stress field; the physical information prediction module is fused with a heat transfer physical constraint training graph neural network to predict a hotspot migration trend; the hierarchical scheduling module is used for solving a fan and oil pump collaborative optimization instruction in real time based on model predictive control; according to the invention, the accuracy of internal temperature monitoring of the box transformer substation, the reliability of hot spot prediction and the accuracy of heat dissipation control are remarkably improved, the insulation life of equipment is effectively prolonged, and the operation safety and reliability of the system are improved.

The invention discloses a nerve disease detection and analysis method and system, and the method comprises the steps: obtaining a bracelet collection signal, a sphygmomanometer collection signal, a movement behavior image and behavior test data, and extracting tremor intensity features, gait symmetry features and autonomic nerve rhythm features through multi-band decomposition of the bracelet collection signal; analyzing the motion behavior image and the standardized motion test to obtain a motion function score; carrying out heart rate variability analysis to identify a neural function abnormality mode; constructing a neural function state map and calculating a feature weight; predicting a disease progress trend in combination with historical monitoring data; and dynamically adjusting a prediction result through subsequent feedback correction information. Through a mode of combining short-time intensive monitoring and long-term intermittent acquisition, long-term trend prediction and dynamic correction based on initial data are realized, and the reliability and practicability of nerve disease risk assessment in a home scene are remarkably improved.

The invention discloses a multi-sensor fusion heat pump full life cycle AI maintenance early warning system, and relates to the technical field of new energy utilization, and the early warning system comprises a data collection module which obtains operation parameters in a heat pump full life cycle based on a sensor array, and constructs a data set after preprocessing the parameters; the operation parameters comprise temperature, pressure, flow and micro vibration; the data fusion module is used for extracting trend correlation characteristics and parameter coupling characteristics from temperature, pressure and flow parameters by adopting a dynamic sliding window adaptive to a working condition, and preserving core nonlinear information through KPCA dimension reduction; the micro-vibration signal extraction comprises frequency domain and time domain features. According to the method, features are extracted through a working condition adaptive dynamic sliding window, then through cross-space mapping and a life cycle-working condition double-attention mechanism, the analysis and early warning module depends on a core feature mapping library and a two-dimensional dynamic baseline, through instantaneous and accumulated deviation double judgment, abnormal accurate recognition and stage division are achieved, and early warning perspectiveness is high.

The invention provides a wind turbine generator voiceprint fault recognition method, and relates to the technical field of wind turbine generator state monitoring and fault diagnosis, and the method comprises the steps: carrying out the noise reduction of an original audio signal through variational mode decomposition, screening a target mode of which the frequency, energy and kurtosis accord with features, and reconstructing the signal; extracting a Mel frequency cepstrum coefficient and a sensing noise robust coefficient, and generating multi-dimensional voiceprint data in combination with statistical characteristics such as a frequency spectrum gravity center, a spectrum entropy, energy, kurtosis and a zero-crossing rate; constructing a support set based on the prototype network, realizing small sample fault classification by calculating the Euclidean distance between the feature vector and the prototype vector, and outputting a preliminary result; judging whether the voiceprint is abnormal according to a preset threshold value, if so, storing the voiceprint into a dynamic abnormal voiceprint knowledge base; frequently occurring abnormal samples are manually labeled and added into a support set, the prototype network is retrained to update the model, and continuous optimization of the fault recognition capability is achieved.

The invention provides a tunnel deformation parameter inversion method and device based on distributed optical fibers, and relates to the technical field of tunnel deformation parameter inversion, and the method specifically comprises the steps: selecting a monitoring point in a tunnel, arranging an optical fiber sensor, and obtaining a Brillouin scattering signal generated by the optical fiber sensor under the stress effect of the corresponding monitoring point; extracting a Brillouin frequency shift corresponding to the monitoring point, and determining an environmental effect frequency shift correction value by using the temperature change data, the humidity change data and the service time of the optical fiber sensor; determining the structural strain of the monitoring point according to the Brillouin frequency shift and the environmental effect frequency shift correction value, generating a three-dimensional strain field cloud picture, performing spatial registration on the three-dimensional strain field cloud picture and the geometric topology of the model, and performing three-dimensional grid division; the structure strain of the monitoring point is mapped to the grid node at the corresponding position, the structure strain of other grid nodes is determined based on the space distance attenuation law, inversion of the whole tunnel deformation parameters is completed, and the tunnel deformation monitoring precision and efficiency are improved.

The invention relates to the technical field of power system fault positioning, in particular to a traveling-wave-based power distribution network fault positioning method, system and device and a medium, and the method comprises the steps: extracting a first fault traveling wave signal from a line signal when a power distribution network has a fault; taking the traveling wave sensor of the first fault traveling wave signal as a target sensor, and determining an adjacent sensor on a target power line where the target sensor is located; calculating a fault traveling wave propagation area of the fault point on the target power line according to the physical distance between the target sensor and the adjacent sensor, the timestamp difference value and the traveling wave basic propagation speed; separating a traveling wave head superposed in the first fault traveling wave signal, and extracting an original fault traveling wave head feature of each independent traveling wave head; and obtaining a power distribution network fault point positioning result according to the original fault traveling wave head characteristics and the fault traveling wave propagation area. According to the invention, rapid and accurate positioning of the fault point of the power distribution network is realized by analyzing the fault traveling wave signal, and the operation reliability of the power distribution network is improved.

The invention discloses a non-contact heart rate detection method, system and device based on visual Transform and multi-scale feature aggregation and a medium. The method comprises the steps that a face visible light video is obtained, the unified video frame rate is re-sampled through the frame rate, face key point positioning and region division are carried out on each frame of image, and a face visible light video sequence is obtained; performing time migration operation on the video sequence to obtain a difference frame sequence, performing channel fusion on the video sequence and a difference frame, and performing down-sampling on a spatial dimension to obtain a low-resolution feature tensor; constructing a non-contact heart rate extraction model, inputting the low-resolution feature tensor into the non-contact heart rate extraction model, and outputting a heart rate value of the target; the non-contact heart rate extraction model comprises a feature enhancement module, a multi-scale mask feature aggregation module, a Transform time sequence modeling module and an rPPG predictor, the system, the device and the medium are used for achieving the non-contact heart rate detection method based on visual Transform and multi-scale feature aggregation, and the precision of rPPG signal extraction is improved.

The invention provides an unmanned aerial vehicle group wide area suppression method and system based on multi-band frequency hopping interference. The method comprises the following steps: analyzing a frequency hopping rule and an encryption feature of a communication link of a target unmanned aerial vehicle group, and constructing a protocol feature library containing a multi-band frequency hopping sequence; deploying a directional focusing antenna array, and generating a directional interference energy signal covering a multi-band frequency hopping channel of the hotspot area of the unmanned aerial vehicle group; based on the encryption features and the frequency hopping sequence in the protocol feature library, performing parameter setting and subcarrier modulation adaptation on a preset interference signal, generating an adjustable interference signal, and converting the adjustable interference signal into an interference injection signal; extracting a time distribution rule of the frequency hopping sequence, dynamically and cooperatively adjusting an injection frequency band of interference energy and a signal, and generating a frequency band coordination strategy; and performing multi-band dynamic distribution on the interference energy and the signal to generate a wide-area suppression signal. According to the technical scheme provided by the invention, the blocking efficiency of unmanned aerial vehicle group cooperative control in a complex electromagnetic environment is improved.

The invention relates to the technical field of mining mechanical equipment, and particularly discloses a mining mechanical equipment anomaly detection system and method. Current signals, voltage signals and vibration signals in the operation process of mining mechanical equipment are obtained; the method comprises the following steps: extracting an equipment operation current-voltage correlation feature vector and a mining mechanical equipment time frequency correlation feature vector, fusing to obtain a mining mechanical equipment anomaly classification feature vector, and obtaining a classification result through a classifier to indicate whether the mining mechanical equipment is abnormal or not, thereby realizing anomaly detection of the mining mechanical equipment.

The present application pertains to the technical field of neural stimulation. Disclosed are a temporal interference-based closed-loop multimodal neural stimulation system and method. The system comprises a temporal interference stimulation system, an electroencephalography-functional near-infrared spectroscopy sampling system, and an upper-level control system. The temporal interference stimulation system utilizes a beat-frequency electric field generated by two sets of electrodes to precisely stimulate a specified brain region. The electroencephalography-functional near-infrared spectroscopy sampling system is a bimodal collector coupling electroencephalography and functional near-infrared spectroscopy, including two parts: signal extraction and correlation analysis, and analyzes stimulation effects and adjusts stimulation schemes by integrating unified brain signal data that combines the temporal precision of EEG and the spatial precision of fNIRS. The upper-level control system includes bimodal fusion model computation, graph convolutional neural network prediction, and stimulation scheme formulation. The present application addresses the problems that traditional stimulation methods lack a closed-loop regulation system, have no means for calibration and optimization, and require a long adaptation period between the stimulation scheme and the user, thus being disadvantageous for applications.

The invention relates to the technical field of biomedical signal processing and intelligent health monitoring, and particularly discloses an intelligent heart rate monitoring method and system based on heart sound and electrocardiosignals, heart sound signals and electrocardiosignals of a user are collected in real time, quality evaluation is conducted on the collected signals through signal quality indexes, and accurate signals are extracted; extracting time domain and frequency domain features of the first heart sound and the second heart sound of the heart sound signal, fusing multiple features by adopting wavelet transform and a main frequency analysis algorithm, and calculating a heart sound abnormal coefficient to evaluate the abnormal degree of the heart sound signal; the vibration amplitude and frequency characteristics of P waves in the electrocardiosignals are extracted, and an electrocardiograph abnormal coefficient is calculated through a vibration amplitude abnormal coefficient and a vibration frequency fluctuation coefficient and used for evaluating the stability of the electrocardiosignals; based on the heart sound abnormal coefficient and the electrocardiogram abnormal coefficient, a decision tree model is constructed, a heart rate abnormal index is dynamically calculated, dynamic monitoring of the heart rate is achieved, a dynamic early warning mechanism is conducted, and heart rate abnormal information is output.

The invention relates to the technical field of narrow-band filters, and discloses an ultra-low power consumption narrow-band filter implementation method based on a digital phased array system, and the method comprises the following steps: S1, collecting input signal data, carrying out the adaptive preprocessing, and generating preprocessed signal data; s2, performing digital beam forming processing based on the preprocessed signal data to generate digital beam forming data; s3, performing narrowband filtering parameter matching processing according to the digital beam forming data to generate narrowband filtering parameter data; in the narrowband filtering processing process, disturbance of environmental electromagnetic interference to a target signal is identified and eliminated in real time through adaptive noise suppression and a multi-dimensional signal preprocessing mechanism, so that the system can guarantee the pointing precision of digital beam forming, the pointing offset problem in the space signal capturing process is avoided, the accuracy of narrowband signal extraction is improved, and the accuracy of narrowband signal extraction is improved. And the reliability of filtering output and the signal fidelity are enhanced.

The invention relates to the technical field of data visualization, in particular to a multi-modal fusion anorectal data visualization analysis method and system, and the method comprises the following steps: synchronously collecting an anorectal image and a pressure signal, aligning a timestamp, carrying out the preprocessing, outputting a standardized image and a coded physiological signal, and extracting edge and texture features. After LSTM coding, splicing with image features, and fusing into a joint feature map; generating a multi-scale heat map by the feature pyramid network, and coarsely positioning a lesion; after boundary optimization, U-Net recovers details, and a pixel-level lesion probability graph is output; superposing the Jet color gradation to the original image in a semitransparent manner, and marking a pressure abnormal time period; and performing weighted scoring to generate a fourth-level clinical suggestion. According to the anorectal disease diagnosis method, through multi-modal space-time alignment, multi-scale feature fusion, boundary optimization and a quantitative scoring system, the problems of data splitting, insufficient precision and low efficiency of a traditional method are solved, a high-precision and high-robustness intelligent diagnosis tool is provided for anorectal diseases, and the scientificity and efficiency of clinical decision making are remarkably improved.

The invention relates to the technical field of automatic control, in particular to a multi-parameter cooperative control method and device for a clamping system of a precision boring and milling machine. According to the method, an industrial camera is used for collecting and processing a workpiece image and extracting visual features, and the visual features are fused with process parameters of a workpiece and geometric distribution parameters of a workpiece key area obtained from a process database; generating a comprehensive state vector; based on the vector, outputting a target clamping force adjustment coefficient by a pre-trained MLP decision model, and calculating a final target clamping force in combination with a safe clamping force range; in the main clamping stage, vibration, temperature and pressure signals are synchronously collected, multi-modal disturbance characteristics are extracted, observation vectors are constructed, the observation vectors are input into a preset fuzzy rule base for reasoning, and compensation activation factors are obtained; and finally, a current correction instruction is dynamically generated according to the clamping force deviation and the compensation factor, and an electro-hydraulic proportional valve is driven to achieve accurate compensation. According to the invention, the stability and the machining reliability of the clamping system are obviously improved.

The invention discloses a wearable exoskeleton man-machine cooperation real-time control method based on artificial intelligence, and relates to the technical field of exoskeleton robots, and the method comprises the steps: recognizing an exoskeleton scene in power grid maintenance, analyzing the demand degree, and constructing a maintenance demand sequence; determining a collaborative analysis scene based on the maintenance demand sequence; performing quantitative analysis on the man-machine confrontation event in the collaborative analysis scene to obtain a collaborative deviation value and generate a collaborative analysis signal; constructing a data set according to signal extraction features, and predicting man-machine cooperative control behaviors by using a genetic algorithm; finally, the exoskeleton is controlled in real time according to prediction, the man-machine cooperation degree is judged, and the control mode is switched when necessary. The exoskeleton man-machine cooperation performance is improved, the cooperation problem can be found in time, the control strategy is optimized, and it is guaranteed that electric power overhaul work is conducted efficiently and safely.

The invention discloses a main power grid short-time load prediction method using a hybrid active filter, and particularly relates to the technical field of load prediction. The method comprises the following steps: acquiring active control parameters and passive branch parameters of a hybrid active filter, combining a real-time load fluctuation signal of a main power grid, extracting harmonic suppression characteristics and phase distortion characteristics, and analyzing and generating a time scale compensation factor through a dynamic coupling effect; and constructing a phase correction model based on the transient harmonic residual component and the time scale compensation factor, and performing frequency domain and time domain combined reconstruction on the real-time load fluctuation signal to obtain a corrected load fluctuation characteristic sequence. A short-time load prediction model is calibrated through a collaborative mapping relation, a load power prediction value of a main power grid in a future preset time window is output, a secondary high-frequency interference signal generated by real load fluctuation and filter self-resonance is effectively distinguished, and the problem of coupling interference of harmonic residual components on the load prediction model in a power grid impedance sudden change scene is solved.

The invention discloses a transformer sound signal adaptive wavelet optimization and feature extraction method and system, and the method comprises the steps: calling a Pywt wavelet analysis library, decomposing an original signal according to a decomposition layer number J, and obtaining a multi-layer detail signal; for each layer of detail signals, the following steps are executed: introducing an M estimator to improve a noise variance calculation model, and calculating a standard deviation and a unified monitoring threshold value; constructing a dynamic threshold value based on a denoising signal approximation error minimization criterion; designing a correction factor; correcting the wavelet coefficient of each layer of detail signal; reconstructing a pure signal by using an inverse decomposition method; dividing the pure signal into a plurality of short-time signals; extracting an MFCC feature vector of each short-time signal; weighting and screening MFCC feature vectors by adopting a support vector machine recursive feature elimination method; and compressing the dimension of the feature vector in combination with a principal component analysis algorithm to generate a final feature matrix. According to the method, the problems of contradiction between noise suppression and signal fidelity and low recognition rate caused by high-dimensional feature redundancy in a traditional method are solved.

The invention discloses a sleep monitoring method and system based on a non-contact video data sequence. The method comprises the steps that S1, video data streams of human body sleep are collected through a camera system; utilizing a YOLOv11 network to obtain face video data and thoracoabdominal video data; s2, the RPPG signal extraction model extracts and obtains an RPPG signal by using the face video data; s3, the breathing signal extraction model extracts thoracic and abdominal micro-motion change characteristics in the thoracic and abdominal video data by using an optical flow method, and noise filtering processing is carried out to obtain thoracic and abdominal motion signals as breathing signals; s4, the oxyhemoglobin saturation extraction model detects and outputs an oxyhemoglobin saturation signal by using the RPPG signal; and S5, performing multi-modal fusion analysis on the multi-physiological index fusion recognition model according to time slice T1 division to obtain a long-time-sequence sleep stage staging result. According to the invention, the physiological index signals are extracted and recognized by adopting the non-contact video data sequence, and the sleep stage staging result with a long time sequence is obtained, so that high-precision sleep monitoring and sleep stage recognition are realized.

The invention provides an air-ground cooperative unmanned aerial vehicle countering signal adaptive generation method and system, and relates to the technical field of unmanned aerial vehicle countering, and the method comprises the steps: obtaining a target unmanned aerial vehicle communication signal, and extracting a feature analysis protocol; a secondary coding structure is adopted, and parameters are optimized by using a genetic algorithm with a composite fitness function; selecting and adjusting an interference waveform template based on the protocol type; executing air-ground collaborative resource optimization allocation, and dynamically allocating power and computing resources by adopting a reinforcement learning algorithm; and controlling the air-ground countering equipment to generate an interference signal. According to the method, the interference effect can be improved, the energy consumption is reduced, the detection resistance is enhanced, and intelligent dynamic allocation of countering resources is realized.

The invention belongs to the technical field of ocean remote sensing, and discloses an ICESat-2 shallow sea sounding signal extraction method and system, and the method comprises the steps: carrying out the data preprocessing based on the obtained ICESat-2 sounding data; constructing an elliptical neighborhood direction adaptive model based on submarine topographic features, and determining the orientation of an elliptical neighborhood; constructing an elliptical neighborhood size adaptive model considering the depth change, and determining the size of an elliptical neighborhood; refraction correction and tide correction are carried out, and water depth correction of the seabed photon points is completed. Through the density clustering algorithm, accurate detection of the underwater topography of the shallow sea water area is realized, and a new analysis thought is provided for shallow sea water depth detection. The submarine photon point extraction problem caused by non-uniform point cloud density and weak connectivity of the photon counting laser radar ICESat-2 is solved, the sounding precision is remarkably improved, and the long-term requirements of the marine surveying and mapping field on the high-precision and low-cost sounding technology are met.

The invention relates to the technical field of biomedical engineering and computer vision, in particular to a non-contact physiological signal extraction method and system based on frequency self-adaption and illumination noise perception.The method comprises the following steps of multi-mode video stream collection and spatio-temporal data preprocessing, illumination-noise perception mask generation and feature filtering, multi-mode video stream collection and spatio-temporal data preprocessing, illumination-noise perception mask generation and feature filtering, and non-contact physiological signal extraction. Frequency adaptive gating and frequency domain feature enhancement, depth time attention feature re-calibration, physiological signal regression and closed loop optimization; the method has the beneficial effects that a lightweight end-to-end deep learning network architecture is constructed by systematically fusing three core modules of illumination-noise perception mask, frequency adaptive gating and depth time attention, and the defects that a traditional physical model depends on artificial prior and is poor in anti-interference performance and high in reliability are overcome. And the one-sidedness caused by high calculation complexity and difficulty in distinguishing the signal and noise of the existing deep learning model is avoided, and the weak physiological signal can be recovered from the face video more accurately and robustly.

The invention relates to the technical field of fault diagnosis, and discloses a scroll compressor thrust bearing fault diagnosis method and system based on artificial intelligence. The method comprises the following steps: acquiring an original vibration signal of the thrust bearing of the scroll compressor through a piezoelectric acceleration sensor array, and performing angle domain synchronization and modal decomposition on the original vibration signal to obtain a demodulated vibration signal; according to the demodulation vibration signal, extracting fault characteristic frequency spectrums of inner ring damage, outer ring crack, rolling body peeling and retainer deformation in the scroll compressor thrust bearing; extracting fault features from a time domain, a frequency domain and a time-frequency domain based on the fault feature frequency spectrum, and constructing a fault feature vector; and inputting the fault feature vector into an integrated learning model to carry out fault identification analysis to obtain a fault type and severity. According to the invention, the accuracy of fault diagnosis of the thrust bearing of the scroll compressor is improved.

The invention belongs to the technical field of permanent magnet synchronous generator demagnetization fault detection, and particularly discloses a permanent magnet motor fault early warning system based on big data, which comprises a high-frequency injection and grid-connected control module, a fault early warning module and a fault early warning module, actively injecting a high-frequency disturbance signal of which the frequency is higher than the fundamental frequency into a control loop of the permanent magnet synchronous generator; the multi-source synchronous acquisition module is used for synchronously acquiring multi-dimensional operation parameters of the permanent magnet synchronous generator and performing time domain alignment and frequency domain separation on the multi-dimensional operation parameters to obtain synchronous acquisition signals; the composite feature extraction module is used for extracting a multi-dimensional demagnetization criterion of the permanent magnet synchronous generator based on the synchronous acquisition signal; the self-adaptive threshold regression prediction module is used for performing fusion evaluation on the multi-dimensional demagnetization criteria by using the demagnetization health index model to generate a demagnetization judgment result of the demagnetization degree of the permanent magnet synchronous generator; the method has the advantages that the demagnetization recognition accuracy is improved, and early warning is achieved.

The invention relates to the technical field of data processing, and discloses a propeller fault diagnosis and predictive maintenance method and system. The method comprises the following steps: collecting current, temperature, vibration and pressure signals of a propeller, extracting characteristic parameters to construct a time sequence data set, mapping the characteristic parameters into nodes, establishing a multi-physical field coupling hyperedge to construct a time sequence incidence matrix, inputting an encoder, extracting a degradation state characteristic vector, and mapping the degradation state characteristic vector into a health index; and calculating a degradation rate function in combination with the working condition parameters, and integrating the degradation rate function to predict the remaining service life. According to the method, the high-order coupling relation and the time sequence evolution characteristics among multiple parameters of the propeller are captured through the multi-physics field coupling hypergraph time sequence encoder, the influence of different operation conditions on degradation is quantified in combination with the degradation rate model sensitive to the working condition, and the problem that the fault evolution trajectory and the remaining service life cannot be predicted is solved; and an accurate time window reference is provided for predictive maintenance.

The invention relates to the technical field of power systems, in particular to a UPQC harmonic compensation method and system based on repetitive control, and the method comprises the steps: obtaining a load current signal and a voltage signal of a power distribution network, and extracting a harmonic instruction current based on the load current signal; and inputting the harmonic instruction current into a feed-forward channel constructed based on an adaptive filter, and generating a feed-forward control quantity. The phase and frequency of the voltage signal of the power distribution network are tracked in real time through a digital phase-locked loop, the fundamental frequency of the power grid is accurately solved, and the power distribution network can be accurately controlled. The internal model period and the phase lead compensation amount of the frequency adaptive repetitive controller are dynamically calculated, and the internal model structure of the repetitive controller is always matched with the current power grid frequency by updating the two core parameters in real time, so that the compensation precision decline caused by frequency deviation is avoided; and high-precision suppression of the periodic harmonic waves can be realized in a normal fluctuation range of the fundamental wave frequency of the power grid.