79 results about "Blind source separation algorithm" patented technology

The invention is suitable for the technical field of electrical equipment state monitoring, and provides an electrical equipment state monitoring method based on a non-contact leakage current sensor, and the method comprises the steps: collecting a leakage current signal of the surface of an insulating part of electrical equipment, and obtaining infrared thermal image data and an ultrasonic signal; variational mode decomposition is carried out on the leakage current signal to obtain a plurality of intrinsic mode functions; separating a leakage current effective component and an independent noise source based on a blind source separation algorithm; extracting a time-frequency characteristic of the effective component of the separated leakage current, extracting a local temperature gradient characteristic of the infrared thermal image data and a frequency spectrum energy characteristic of the ultrasonic signal, and generating a multi-modal characteristic vector; analyzing the space-time relevance of the multi-modal feature vector, dynamically distributing each modal weight coefficient for fusion, and generating a comprehensive fault feature; according to the method, the signal-to-noise ratio of the weak leakage current signal is improved, and the misjudgment rate is effectively reduced.

The invention relates to the technical field of unit detection, and discloses an intelligent fault self-diagnosis method for an evaporative condensation integrated screw water chilling unit, which comprises the following steps of: decoupling operation data of a compressor through a blind source separation algorithm, performing image processing on operation data of a condenser in combination with a morphological analysis method, and performing fault diagnosis on the operation data of the condenser; the operation characteristics of the compressor and the operation characteristics of the condenser can be extracted respectively, effective decoupling and clear expression of coupling signals are realized, and by constructing a dual-channel LSTM network comprising a gating fusion unit and introducing a cross-channel coupling gating mechanism, the system reliability is improved. The dynamic coupling relation between the compressor and the condenser can be modeled and regulated in the time dimension, the coupling mechanism between the compressor and the condenser is truly reflected, the time sequence parameter sequence is input into the pre-trained deep LSTM network, the fault types such as control lag and performance degradation can be accurately recognized, and the fault diagnosis accuracy is improved. Therefore, the accuracy and real-time performance of fault diagnosis are improved, and the requirement for intelligent fault management of the water chilling unit is met.

The invention relates to the technical field of vibration signal processing, in particular to a coupling vibration information source separation method based on blind source separation. The method comprises the following steps: processing an obtained multi-channel signal based on local value decomposition and adaptive singular value decomposition, and estimating the number of vibration sources in the signal to obtain the number of information sources; determining a blind source separation algorithm for multi-channel signal processing based on the number of channels and the number of information sources for signal acquisition, and if the blind source separation is underdetermined, decomposing and reconstructing the multi-channel signals, and converting the underdetermined blind source separation into positive determined blind source separation; separating the multi-channel signal or the reconstructed multi-channel signal by adopting rapid independent component analysis to obtain a vibration source estimation signal; and performing cross correlation calculation and gain compensation on the vibration source estimation signal, then performing signal processing on the vibration source estimation signal after gain compensation, setting a characteristic threshold to classify fault types, quantifying fault degrees, and calculating a fault score. According to the invention, the difficulty of underdetermined blind source separation is reduced.

The invention relates to the technical field of power equipment fault diagnosis, and particularly discloses a pole-mounted circuit breaker mechanical fault diagnosis method and system, and the method comprises the steps: firstly, synchronously collecting a dynamic force-displacement signal, a high-frequency acoustic emission signal and a broadband vibration signal in the switching-on and switching-off process of a circuit breaker operating mechanism; then, the acoustic emission and vibration signals are decoupled into an impact source component and a friction source component which are statistically independent through a blind source separation algorithm; performing envelope spectrum analysis on the impact source component to extract impact characteristics, and performing energy calculation on the friction source component to obtain friction noise energy characteristics; finally, on the basis of dynamic force-displacement curve fitting analysis, in combination with impact characteristics and friction noise energy characteristics, distinguishing and delimiting of mechanical wear and lubrication degradation faults are achieved. According to the invention, the problem that the existing diagnosis technology cannot effectively identify and distinguish the coupling fault of mechanical wear and lubrication deterioration is solved, and early warning and accurate diagnosis of the mechanical fault of the pole-mounted circuit breaker are realized.

The invention belongs to the related technical field of neural rehabilitation engineering, and particularly relates to a cerebral apoplexy rehabilitation method based on fusion of a motor imagery brain-computer interface and transcranial direct current stimulation, which comprises the following steps: acquiring a corresponding artifact template based on transcranial direct current stimulation parameters; carrying out source separation on the collected electroencephalogram test times by adopting a joint blind source separation algorithm to obtain clean electroencephalogram signal components; wherein the construction mode of the artifact template library comprises the following steps: extracting electroencephalogram trial artifact samples of multiple stimulation periods, and generating a transcranial direct current stimulation artifact template through an average analysis or principal component analysis mode to obtain the artifact template library; performing motion intention decoding on the clean electroencephalogram signal component to obtain a motion intention of the patient; inputting the motion intention, pre-collected patient body state evaluation information and patient feedback comfort into a fuzzy system algorithm to obtain stimulation parameters of to-be-applied transcranial direct current stimulation, and realizing active rehabilitation through the transcranial direct current stimulation. According to the invention, algorithm-driven closed-loop rehabilitation regulation and control can be realized.

The invention relates to an array microphone noise reduction recording method based on cascade noise reduction and blind source separation, which belongs to the technical field of voice signal processing and recording, and comprises the following steps: configuring a multi-channel array microphone, ensuring that the amplitude and phase of a channel signal are consistent, and collecting an original multi-channel voice signal; a weighted kernel function blind source separation algorithm is adopted, signal-to-noise ratio distribution characteristics of signals are extracted, kernel function weights are given, and target voice and interference signal components are obtained through decoupling of an independent component analysis model; executing target-oriented adaptive cascade noise reduction, locking the voice of a keynote speaker through directional pickup, reducing noise, filtering out reverberation, and enhancing the voice of a far-field target by combining a voice mask neural network with a far-field pickup algorithm in sequence; and processing the target voice through voice feature perception lossless coding and storing the target voice. According to the invention, stable acquisition of multi-channel signals, accurate separation of mixed signals and layered suppression of noise reverberation are realized, the signal-to-noise ratio and definition of far-field voice are significantly improved, and the method is suitable for single-person speaking or multi-person dialogue scenes.

The invention discloses a rapid high-precision frequency measurement method for super-synchronous inter-harmonics, and relates to the field of signal processing, and the method comprises the steps: S1, presetting a reference fundamental wave signal, and generating a modulation fundamental wave signal on a discrete time sequence through a super-synchronous source; s2, setting the reference fundamental wave signal and the modulation fundamental wave signal in a discrete time sequence, and intercepting an abnormal frequency interval; s3, extracting all abnormal fundamental wave data and all reference fundamental wave data; s4, abnormal components, higher than the corresponding reference fundamental wave data, of the abnormal fundamental wave data are screened out, and accurate frequency harmonic correction is carried out. The blind source separation algorithm is adopted to accurately extract the abnormal frequency interval, and the abnormal fundamental wave data and the reference fundamental wave data are compared, so that the frequency correction can be carried out in time, the data processing and analysis can be carried out in real time, the processing delay is reduced, and the reliability of the frequency measurement is improved.

The invention discloses a gesture recognition method, system and terminal based on an attention residual pulse neural network, and the method comprises the steps: collecting high-density surface electromyogram signal data of a gesture action executed by a target individual, carrying out the preprocessing of the high-density surface electromyogram signal data, and obtaining a plurality of activity section signals; decomposing the plurality of active section signals through a convolution blind source separation algorithm to obtain a motion unit pulse sequence corresponding to each active section signal; building an attention residual pulse neural network, and training and testing the attention residual pulse neural network to obtain an electromyographic gesture recognition model; inputting all the motion unit pulse sequences into an electromyographic gesture recognition model for recognition, and outputting an electromyographic gesture of the target individual; according to the invention, the accuracy of gesture recognition based on the attention residual pulse neural network is improved, the energy consumption is reduced, and the actual application of the gesture recognition technology in the fields of neural interfaces and human-computer interaction can be promoted.

The invention provides a login method and system based on a 5G message voiceprint verification code, and the method comprises the steps: generating a 5G message, receiving a message receiving confirmation feedback of a user, obtaining a composite audio stream through combining with environment sound collected based on a local voiceprint collection device, carrying out the processing through a blind source separation algorithm, obtaining a preliminary composite voiceprint sample, and carrying out the verification of the voiceprint verification code. A target composite voiceprint sample is obtained after optimization; performing encryption processing based on a preset encryption protocol, obtaining a decrypted target composite voiceprint sample in combination with a quantum key distribution mechanism and a cloud authentication platform, and calculating a preliminarily adjusted comprehensive score by using a convolutional neural network, a recurrent neural network and a generative adversarial network combination model; performing processing by utilizing a behavior analysis algorithm to obtain a final adjusted comprehensive score, and performing access permission confirmation to obtain an access confirmation result; according to the invention, the security and accuracy of user identity verification are enhanced, efficient user experience is provided, and the security and reliability of the user login process are ensured.

The invention provides a monitoring method and system for a cutting penetration state in a water-jet guided laser processing process based on sound signal blind source separation, and the monitoring method comprises the steps: S1, in the water-jet guided laser processing process, collecting a plurality of observation sound signals in real time, the observation sound signals being mixed sound signals composed of a plurality of independent sound source signals; s2, estimating and solving a plurality of independent sound source signals by using a blind source separation algorithm according to the plurality of collected observation sound signals; s3, the frequency spectrums of the multiple independent sound source signals are compared with sound signals generated during material laser processing, so that sound signals generated during water-guided laser processing due to material removal are determined from the frequency spectrums; and S4, the water-jet guided laser machining process is judged according to the relation that sound signals generated due to material removal change along with time. Compared with a traditional coaxial visual monitoring scheme, the method is not affected by factors such as water flow and light intensity, and can be applied to monitoring of the water-guided laser machining process.

The invention provides a multi-modal fusion unmanned aerial vehicle identification method and system, and the method comprises the steps: obtaining a radio signal, an image signal and a sound signal of an unmanned aerial vehicle; performing feature extraction on the radio signal based on a blind source separation algorithm and adaptive filtering to obtain radio features; performing feature extraction on the image signal based on image super-resolution reconstruction and a double-flow feature extraction network to obtain image features; performing feature extraction on the sound signal based on spectral analysis and harmonic feature extraction to obtain an audio feature; fusing the radio feature, the image feature and the audio feature to form a multi-modal fusion feature; and performing identification based on the multi-modal fusion features to obtain an unmanned aerial vehicle category identification result. By adopting the scheme, the accuracy, reliability and environmental adaptability of unmanned aerial vehicle identification can be remarkably improved.

The invention provides an aero-engine main bearing micro-defect nonlinear phased array ultrasonic nondestructive testing method and device, and relates to the technical field of ultrasonic nondestructive testing, the method comprises the following steps: according to the sound beam focal spot diameter of the emission aperture of a phased array excitation probe, carrying out grid division on a target detection area; according to a focusing rule of a phased array emission aperture, focusing scanning of each grid is completed in sequence, and ultrasonic signals of each grid are collected through a phased array receiving probe in the scanning process; carrying out noise reduction processing on the ultrasonic signal by utilizing a self-adaptive bilateral filtering algorithm; a signal blind source separation algorithm is adopted to decouple the processing signals, nonlinear harmonic signals generated by the microdefects are separated, and positioning and quantitative analysis are conducted on the microdefects; and the two phased array probes scan along the contour of the cross section of the bearing ring to complete the full-coverage detection of each cross section of the bearing ring. According to the invention, the microdefect of the aircraft engine bearing can be subjected to nondestructive detection.

The invention provides an EMD (empirical mode decomposition) and correlation analysis-based double-probe vortex shedding flowmeter anti-interference method, which relates to the technical field of signal processing, and is characterized in that a vortex shedding sensor signal sequence containing periodic vibration interference is decomposed into multi-scale IMF components through self-adaptive characteristics of an EMD method, and spectrum components of a flow signal and vibration noise are accurately separated. According to the method, aiming at the non-stable and multi-band coupling characteristics of double-probe signals, the vibration noise interference under the complex vibration interference of an industrial field is effectively solved, and the environmental adaptability of noise suppression is remarkably improved. According to the method, on the basis that the advantages of self-adaptive decomposition are reserved, the IMF component series is dynamically controlled, that is, only the IMF components of the first four stages are taken, redundant calculation caused by over-decomposition is avoided, and the real-time performance of the system is guaranteed. An upper probe signal is introduced to serve as a reference channel, interference components are removed through a correlation analysis method, the complexity of a blind source separation algorithm is reduced, and meanwhile the method has higher detection precision and stability.

The invention discloses a DDGS feed detection method and system based on wireless transmission, relates to the technical field of intelligent Internet of Things monitoring devices, and aims to solve the problems of incomplete data acquisition, unstable communication link, large sensor data error and inaccurate abnormality positioning in existing DDGS storage yard monitoring. According to the method, channel attenuation is predicted through RSSI and bit error rate data, and signal transmission is optimized in combination with self-adaptive frequency hopping and an MIMO antenna; a blind source separation algorithm is used for inhibiting a multipath effect, and the data accuracy is improved; inertial navigation and UWB distance measurement are fused to realize high-precision positioning, and a thermodynamic diagram is generated to mark an abnormal region; meanwhile, the edge gateway adopts a BP neural network to correct sensor errors, so that the measurement reliability is improved; according to the invention, the monitoring precision, the stability and the real-time performance are obviously improved, and the safety management level of the DDGS storage yard is improved.

The invention relates to the technical field of power equipment fault monitoring, in particular to a distribution box fault monitoring method, and aims to solve the problem that a traditional monitoring method in the prior art depends on a single filtering or fixed threshold strategy and is difficult to effectively separate fault features. According to the method, mechanical vibration and electromagnetic interference signals can be effectively separated through an adaptive blind source separation algorithm, the problem of early fault signal identification in a mixed interference environment is solved by combining multi-scale feature fusion and a dynamic environment compensation mechanism, and the method has the advantages of improving monitoring accuracy and realizing accurate quantification of fault energy.

The invention discloses a de-noising system based on adaptive beam forming and ICA (independent component analysis). The de-noising system comprises a multi-channel sensor array, an adaptive beam forming unit, an independent component analysis unit and a cooperative control module, the multi-channel sensor array is used for collecting a mixed signal containing a target signal and noise; the adaptive beam forming unit suppresses noise in an interference direction through spatial filtering and outputs a preliminary enhanced signal; the independent component analysis unit is used for receiving the preliminary enhanced signal and separating residual independent noise components through a blind source separation algorithm; the cooperative control module dynamically adjusts a beam forming weight and an ICA separation parameter, and balances voice distortion and noise suppression effects; through cooperation of beam direction nulling and blind source separation, reverberation, multipath scattering and Gaussian / non-Gaussian mixed noise are effectively processed, the system is suitable for scene coverage speech enhancement, medical signal processing and radar anti-interference, and the denoising effect of the system is more excellent comprehensively.

The invention discloses a cable force calculation method and system. The cable force calculation method comprises the steps that a first image of a to-be-detected cable is acquired; inputting the first image into a trained image segmentation model to obtain a second image; according to the second image, through Hilbert transform and a blind source separation algorithm, calculating a power spectral density map of the cable to be detected; according to the method, the accuracy of initial data is improved through the image segmentation model, and the accuracy of frequency measurement is improved through Hilbert transform and a blind source separation algorithm, so that the accuracy of cable force calculation is improved.

The invention discloses an underwater structure low-frequency radiation sound power forecasting method based on blind source separation, and the method comprises the following steps: (1), setting a housing sound source in a shallow sea environment, and obtaining discrete sound pressure; (2) obtaining an estimation signal of the source signal through a blind source separation algorithm; (3) windowing the estimated signal space data of the source signal in the z direction to obtain the sound pressure propagating outwards after windowing; (4) the sound pressure propagating outwards is converted into a wave number domain through discrete space Fourier transform, and a holographic surface sound pressure cylindrical wave spectrum is obtained; (5) filtering evanescent waves in a wavenumber domain by using a wavenumber domain filter to obtain propagation waves on a holographic surface; (6) transmitting the filtered sound pressure to a far field in a spherical shape through a near-field acoustical holography technology by means of stable-phase estimation; (7) deducing the sound intensity by using the far-field sound pressure so as to obtain the radiation sound power; according to the invention, the measurement workload is reduced; measurement is carried out on a holographic surface close to a sound source, the influence of boundary reflection is small, and a calculation result is accurate.

Disclosed is an online estimation method for wrist torque based on neural features and LSTM, including following steps: (1) an experimenter keeps his / her arms stationary and applies torque to a torque sensor through his / her wrist; (2) acquiring data from the torque sensor and high-density surface EMG ((HD-sEMG) synchronously; (3) decomposing the HD-sEMG using a blind source separation algorithm to obtain a motor unit spike train (MUST); (4) constructing input and output vectors on the basis of the original HD-sEMG and the decomposed MUST, performing training of the LSTM, and performing polynomial regression of a discharge rate and torque of a neural feature; and (5) calculating a real-time discharge rate (DR) of the CST using a sliding window approach for real-time estimation of the torque.

The invention relates to a harmonic source positioning method and device, equipment and a storage medium. The method comprises the following steps: acquiring measurement data at each node in a power system, wherein the measurement data comprises harmonic voltage measurement data and branch harmonic current measurement data; determining an estimation matrix of node harmonic injection current according to the measurement data and a preset blind source separation algorithm; determining a target conversion matrix according to the estimation matrix, wherein the target conversion matrix is used for representing a corresponding relation between the estimation matrix and an actual matrix of the node harmonic injection current; and carrying out harmonic source positioning according to the target conversion matrix, and carrying out estimation processing on the injection current of the positioned harmonic source. By adopting the method, the harmonic source positioning accuracy can be improved.

A method for extracting effective information of a communication signal in a low signal-to-noise ratio complex environment relates to the field of communication signal processing, and comprises the following steps: firstly, obtaining a plurality of intrinsic mode functions mixed with effective signals with different frequencies and complex noise interference by using an adaptive noise complete empirical mode decomposition method, and carrying out wavelet denoising and reconstruction on the intrinsic mode functions to obtain a plurality of intrinsic mode functions; the method comprises the following steps of: obtaining a de-noised signal with a high signal-to-noise ratio, pre-processing the de-noised signal, calculating a separation matrix of an observation signal matrix after pre-processing according to a blind source separation algorithm, and extracting an effective communication signal from the original observation signal by utilizing the separation matrix so as to complete the effective information extraction of the communication signal. According to the method, noise and invalid signal interference in the signal transmission process can be suppressed under the conditions of strong environmental noise and low signal-to-noise ratio, signals containing effective information can be accurately extracted, and the target detection efficiency can be improved under the condition of high signal-to-noise ratio.

The invention discloses a noise blind source separation method and system for a hydroelectric generating set, belongs to the technical field of acoustic signal processing, and aims to solve the problem that the noise reduction effect of acoustic signals is affected due to the fact that all kinds of noise are difficult to effectively separate by an existing acoustic signal separation method. The method comprises the following steps: firstly, preprocessing actually measured sound signals of a bulb tubular hydroelectric generating set operation site through time domain, frequency domain and time frequency analysis, then carrying out feature analysis by adopting a YOLOv3 network, finally carrying out noise separation by adopting a blind source separation algorithm, and obtaining human voice signals of the operation site based on sound contribution. Therefore, human voice separation and noise reduction processing of actually measured sound signals in a working site are realized.

The invention discloses a machine vision-assisted method for monitoring the size accuracy of an automobile injection molded part, and relates to the technical field of machine vision, and the method comprises the steps: irradiating the injection molded part through the combination of a visible light source and a near-infrared light source, synchronously collecting a three-view image, segmenting an injection molded part region, selecting a key-sized ROI region, and carrying out the fusion to generate a multi-view fusion image; identifying the minimum key feature size from the ROI region, decomposing and fusing the image through multi-scale morphological iteration processing, extracting a real contour signal by adopting an ICA blind source separation algorithm, and generating a complete contour model through multi-view edge point fusion reconstruction; marking feature points based on a CAD standard model, positioning the feature points by adopting particle swarm optimization and a Bayesian iterative algorithm, and calculating critical dimension parameters; environment and injection molding part surface error factors are collected, a dynamic error calibration model is constructed to compensate dimensional deviation, a final size value after calibration is output, and the accuracy and reliability of automobile injection molding part size detection are remarkably improved.

The application discloses a machine vision assisted automobile injection molding part size precision monitoring method and relates to the technical field of machine vision, which comprises the following steps: combining visible light and near-infrared light to irradiate an injection molding part, synchronously collecting three-view images, segmenting the injection molding part region and framing the ROI region of a key size, and fusing to generate a multi-view fusion image; identifying the smallest key feature size from the ROI region, decomposing the fusion image through multi-scale morphological iteration processing, extracting a real contour signal by using an ICA blind source separation algorithm, and generating a complete contour model through multi-view edge point fusion reconstruction; marking feature points based on a CAD standard model, positioning the feature points by using a particle swarm optimization and a Bayesian iteration algorithm, and calculating key size parameters; collecting environmental and injection molding part surface error factors, constructing a dynamic error calibration model to compensate for size deviation, and outputting the final size value after calibration, so that the accuracy and reliability of automobile injection molding part size detection are significantly improved.

The invention discloses a device and a method for detecting the crushing degree of dry grain particles based on an acoustic emission sensor. The device is composed of an acoustic emission sensor probe, a waveguide rod, a signal conditioning module, a data acquisition module, a signal analysis module, a display module and a single-particle friction collision experiment table. Wherein the front end of the waveguide rod is in contact with particles, and the acoustic emission sensor is mounted on the section of the rear end of the waveguide rod and used for detecting acoustic signals transmitted from the waveguide rod; the signal conditioning module amplifies a signal output by the acoustic emission sensor through a pre-amplifier, and then the acoustic emission signal is acquired through a data acquisition module formed by an acoustic emission signal analyzer; the signal analysis module processes the collected signals by adopting a blind source separation algorithm and a deep learning method to obtain the damage degree of the particles and transmits the damage degree to the display module for display; influence factors and types of particle crushing are explored on a single-particle friction collision experiment table by adjusting particle sizes, particle materials, flat plate inclination angles, flat plate friction coefficients, collision speeds, collision positions and the like. The invention provides a novel grain nondestructive testing technology based on an acoustic emission sensor and a deep learning method.

This application provides a signal processing method, chip, electronic device, and storage medium. The method includes: acquiring an input signal, wherein the input signal is a speech signal received by multiple microphones; estimating the covariance matrix of the Nth frame of the input signal to obtain a target covariance matrix of the Nth frame; updating the demixing matrix based on the target covariance matrix of the Nth frame to obtain target elements in the demixing matrix of the Nth frame; performing amplitude demixing based on the target elements in the demixing matrix of the Nth frame to obtain a target demixing matrix of the Nth frame; and performing signal separation based on the target demixing matrix of the Nth frame and the input signal of the Nth frame to obtain an output signal of the Nth frame. The method provided in this application helps to balance the performance and robustness of blind source separation algorithms and improve the signal-to-noise ratio of speech signals.

The invention discloses an inter-beam coupling signal decoupling judgment, decoupling and velocity measurement method in acoustic Doppler velocity measurement, and belongs to the technical field of coupling interference suppression in an underwater acoustic navigation technology. In order to solve the problem of signal cross coupling interference of phased array acoustic Doppler velocity measurement equipment, the method comprises the following steps: aiming at received velocity measurement beam echo signals, performing decoupling judgment on the beam echo signals by utilizing correlation between signals on a channel; and when it is judged that the speed measurement beam echo signal can be decoupled, performing preprocessing including whitening on the signal to obtain a signal, and processing a real part of the received signal by using a blind source separation algorithm to obtain a decoupled echo signal real part. And Hilbert transform is carried out on the obtained signal to obtain a complex signal for speed measurement.

The application relates to the field of radar technology and provides a method and device for resisting towed interference of an airborne radar. The method comprises the following steps: constructing sum channel data, azimuth difference channel data and elevation difference azimuth data of echo signals; constructing sum-difference three-channel data of each pulse according to the sum channel data, the azimuth difference channel data and the elevation difference azimuth data; processing the sum-difference three-channel data by using a blind source separation algorithm to obtain target echo channel data and a separation matrix; pulse compressing the target echo channel data to obtain a target distance estimation value; determining an azimuth angle and an elevation angle of a target according to the target echo channel data and the separation matrix; and constructing a target echo matrix by using target echo channel data of each pulse, and performing Doppler processing on the target echo matrix to obtain a target speed estimation value. The application can resist towed interference, determine the distance, the azimuth angle, the elevation angle and the speed of the target, and realize effective detection of the target.

This invention proposes a method for suppressing short-duration diurnal magnetic field interference based on dual-aircraft collaboration. Addressing the challenges of establishing fixed diurnal variation monitoring stations and lacking effective diurnal variation reference information in offshore dual-aircraft collaborative airborne magnetic surveys, this method utilizes airborne magnetic survey data collected during near-shore airborne magnetic surveys and synchronous observation data from diurnal variation monitoring stations. It proposes a dual-aircraft collaborative diurnal magnetic interference suppression method based on a neural network-guided blind source separation algorithm. This method first uses a deep neural network to learn and extract prior features of diurnal variation interference from the dual-aircraft observation signals. These features are then used as guiding information in the blind source separation process to separate the independent source components corresponding to the diurnal magnetic interference, ultimately achieving high-precision identification and suppression of diurnal variation interference components in the original signal. This method can efficiently separate and suppress short-duration diurnal magnetic interference, significantly improve the signal-to-noise ratio of magnetic survey data, and effectively preserve the target magnetic anomaly characteristics, providing reliable technical support for high-precision airborne magnetic surveys.

The application discloses a time-frequency domain underdetermined blind source separation method and system based on double sensors, which comprises two stages: in the first stage, a single source point with high clustering characteristics is detected by using a clustering and matching tracking algorithm, and a mixing matrix is estimated, so that high-precision mixing matrix estimation is realized; in the second stage, a time-frequency domain signal recovery problem is converted into a sparse recovery model with a relaxed sparse condition, the constraint of the number of sources on the self-source point in the traditional blind source separation algorithm is broken, and good separation effect is realized. The application is suitable for the double-sensor underdetermined blind source separation scene with more source numbers, low mixing signal-to-noise ratio and serious aliasing, and has strong applicability and practicability.