1175 results about "Noise suppression" patented technology

The present invention relates to the field of industrial intelligent predictive maintenance, and in particular to an interpretable deep feature fusion network-based industrial intelligent predictive maintenance method, comprising: acquiring gearbox vibration data comprising noise; performing preliminary extraction and noise suppression on features of the acquired data by establishing an interpretable feature extraction module having a physical information constraint; integrating multi-scale features comprising long-distance and local dependencies by means of a dual-branch feature fusion module having global and local feature fusion capabilities; performing dimensionality reduction on a high-dimensional feature and generating an output by means of a classifier to obtain a final fault identification result; and performing interpretability analysis on a diagnosis process of a model. In the present invention, by embedding the signal processing technology having a well-defined physical theory support into a deep neural network, the interpretability and reliability of model inference results are effectively improved while the fault identification accuracy of the model is improved.

The invention belongs to the technical field of artificial intelligence and intelligent sensing, particularly relates to a multi-source sensor fusion sensing system based on adaptive noise suppression, and aims to solve the problems of noise interference, modal mismatch and insufficient robustness in multi-source sensor fusion in a complex dynamic environment. The system comprises a front-end preprocessing module, an adaptive noise suppression engine, a multi-modal feature alignment unit, a credibility-driven fusion reasoning core and a closed-loop feedback optimization mechanism. Through real-time noise modeling and dynamic weight adjustment, high-precision alignment and fusion of multi-source signals are realized, and the sensing stability and real-time performance in an extreme scene are significantly improved.

The invention relates to the technical field of underwater detection, and discloses an underwater comprehensive detection system. The system collects multi-dimensional acoustic data including sound wave reflection intensity, propagation time delay and frequency dispersion characteristics of a target water area through an underwater sonar array; dividing the detection area into a plurality of layered units according to a water attenuation coefficient and a substrate reflection characteristic of the acoustic data, and extracting an environment intrinsic parameter of each layered unit; constructing an acoustic propagation path model based on the environmental intrinsic parameters, and generating adaptive filtering parameters in combination with a preset noise suppression strategy; calling sonar array hardware configuration data, matching filtering parameters with an array beam forming mode, and calculating a detection sensitivity threshold value of each layered unit; and integrating the sensitivity threshold and the acoustic data, generating a three-dimensional acoustic characteristic spectrum of the target water area, and marking the space coordinates and confidence level of the abnormal area. The system can improve the comprehensiveness and accuracy of underwater detection, and meets the requirement of high-precision detection.

The technology described herein is directed towards modular metasurfaces arranged with unit cells for narrowband, wideband and / or multiband sound absorption, in which the unit cells are based on Helmholtz resonators that are deployed in a server rack, proximate to a server, without substantially obstructing airflow from the server fan(s). Each sound absorbing unit-cells is designed and constructed based on a specific resonance frequency, and includes a neck portion and air chamber dimensioned to resonate at the desired resonance frequency and thereby inverse phase cancel corresponding narrowband frequencies of incoming sound waves. Differently-dimensioned unit cells can be built into a single metasurface module, thereby facilitating wideband and / or multiband sound absorption with that metasurface. The modular metasurfaces can be attached to the sidewalls of a server rack, or positioned in otherwise empty slots above and below a server, optionally coupled to blanking panels for covering the openings of those slots.

The invention relates to the technical field of direct-current power supply fault diagnosis, in particular to a fault self-diagnosis modular direct-current power supply system, which is characterized in that a failure mechanism dynamic modeling unit constructs a multi-stress coupling degradation mapping library, adopts a degradation mechanism decoupling algorithm to separate and superpose failure effects and generates a dynamic degradation model; the early degradation capture unit deploys a high-frequency wide-domain sampling circuit and a noise suppression signal chain, combines time-frequency domain joint feature extraction and separates degradation feature signals from background noise, and the self-adaptive life prediction unit adopts a long short-term memory network and random forest fusion algorithm to dynamically correct parameters and output residual life probability distribution. The intelligent fault judgment unit realizes progressive diagnosis through a hierarchical threshold decision mechanism, and the health management cooperative execution unit triggers a pre-maintenance strategy, executes power flexible derating, redundancy switching or directional fusing isolation, and improves the reliability of the system.

The invention discloses an electronic component early fault detection method based on infrared thermal imaging, and the method comprises the following steps: collecting an infrared thermal imaging image, synchronously collecting current and voltage data, and obtaining an infrared thermal imaging sequence; distortion correction, noise suppression and radiance correction are carried out on the sequence, and metal reflection false high-temperature points are removed; executing time sequence difference to extract a continuous heating area, and generating a time sequence temperature feature vector; inputting the feature vector into an improved Times Net model, and outputting time sequence feature representation; calculating a reconstruction error, a prediction residual error and a frequency spectrum deviation, and fusing into an abnormal score; comparing the abnormal score with a dynamic threshold value, and outputting an electronic component identifier, a potential fault type and an abnormal type; and an early fault trend report is generated by combining historical data comparison. The method realizes early detection and trend prediction of electronic component faults, and is suitable for state monitoring and reliability guarantee of a complex circuit system.

The invention relates to the technical field of equipment health management and fault diagnosis, and particularly discloses a time-frequency enhanced current diagnosis method. According to the method, multi-phase current, temperature and rotating speed data are synchronously obtained, and a standardized sequence is generated through time alignment and noise suppression; self-adaptive spectrum analysis is carried out based on the working condition robust index, and a multi-scale energy diagram and frequency domain features are generated; fusion embedding is constructed through time domain feature extraction and time-frequency alignment mapping; and carrying out dynamic weight fusion and quality judgment in combination with the cross-modal consistency score, and finally generating a lightweight deployment model. According to the method, the anti-interference performance and interpretability of current diagnosis characteristics under multiple working conditions are effectively improved, accurate extraction and lightweight deployment of fault characteristics are realized, and the adaptability and reliability of a diagnosis system in a complex industrial environment are remarkably enhanced.

The invention discloses an equipment voiceprint noise reduction monitoring method fusing empirical mode decomposition and dual-channel U-Net, and relates to the technical field of power equipment state monitoring and voiceprint signal processing. The method comprises the following steps: acquiring an original voiceprint signal when equipment runs, and decomposing the signal into a plurality of intrinsic mode functions by using empirical mode decomposition to realize preliminary separation of noise and useful signals; constructing a dual-channel U-Net network, performing deep extraction on time domain features and frequency domain features of an intrinsic mode function, and introducing an ECA channel attention mechanism to strengthen fusion of effective features; designing a self-adaptive loss function, and optimizing the noise suppression capability of the network on different equipment and under different working conditions; and the noise-reduced voiceprint signal is used for equipment state evaluation to realize early recognition of an abnormal state. The method can be applied to an on-line monitoring system of power equipment, improves the signal-to-noise ratio of the voiceprint signal and the state evaluation accuracy, and has an important value for guaranteeing the stable operation of a power system.

The invention discloses a distribution line abnormity monitoring and early warning method and system, and relates to the technical field of distribution line intelligent monitoring. The method comprises the following steps: acquiring operation data acquired by multiple types of sensors, and performing time alignment, normalization and fusion processing to form a comprehensive data set; inputting the comprehensive data set into a generative denoising model based on noise and abnormal signal distribution separability learning, and outputting a clean data sequence through noise suppression and abnormal feature fidelity joint optimization; identifying an abnormal evolution trend with a nonlinear amplification characteristic by using a Lyapunov index and a Hurst index, and generating a risk assessment result; and constructing and dynamically adjusting a self-adaptive early warning threshold set according to a risk assessment result, and outputting abnormal early warning information when a risk index exceeds a threshold. The method realizes parallel noise suppression and abnormal feature fidelity, has dynamic identification and self-learning capabilities, and significantly improves the accuracy of distribution line anomaly detection and the stability of an early warning system.

The invention discloses a background noise body wave extraction method and device based on distributed optical fiber acoustic sensing, and the method comprises the steps: obtaining an original phase difference signal along an optical fiber channel through a distributed optical fiber acoustic sensing system, and converting the original phase difference signal into strain rate data according to system demodulation parameters; performing preprocessing such as noise suppression and frequency energy balance on the strain rate data; calculating an autocorrelation function for the preprocessed signal, and superposing autocorrelation results of a plurality of time segments; performing band-pass filtering on the superposition autocorrelation function in a target frequency band, and extracting a body wave reflection response in background noise; and in order to eliminate the influence of the zero-time pulse in the shallow layer or weak reflection signal, carrying out mean value removal processing on the extraction result along the space direction to obtain a zero-offset body wave reflection response. The method can effectively describe the discontinuity from a superficial sedimentary layer and a fracture to a deep mourhua surface and even a lithosphere, and makes up for the defects of a conventional seismic station method.

The invention discloses a semi-supervised LPI radar signal modulation identification system and method based on entropy perception pseudo labels, and relates to the technical field of radar signal processing and mode identification. The system comprises a preprocessing module, a multi-scale reconstruction enhancer, a classification backbone network and a semi-supervised training module. The multi-scale reconstruction intensifier is used for reconstructing dual-channel separation through high-frequency detail enhancement and a low-frequency structure and enhancing discriminative characteristics in a noise environment; the classification backbone network introduces an adaptive contraction unit to realize channel-level noise suppression; and the semi-supervised training module dynamically evaluates the uncertainty of the unlabeled samples by adopting an entropy sensing mechanism, and generates weighted pseudo labels to carry out consistency regularization training. The method realizes signal modulation identification based on the system. According to the method, the problem of feature shielding under the condition of low signal-to-noise ratio is solved, the dependence of the model on labeled data is reduced through a reliable pseudo label generation mechanism, and stable and efficient modulation identification can still be realized in a severe channel environment with scarce labeled data.

The invention relates to the technical field of power quality monitoring, in particular to a method and system for constructing a power quality disturbance recognition model based on multidimensional data, and the method comprises the steps: obtaining voltage and current waveform data and environmental parameter data of a key node of a power transmission line, carrying out the hardware defect self-inspection and phase compensation of the voltage and current waveform data, and obtaining a power quality disturbance recognition model; clean transmission electric energy data is obtained; and performing multi-scale noise suppression and time sequence correlation analysis on the clean transmission electric energy data, and constructing a high-fidelity disturbance sequence. According to the method, through the hardware defect self-inspection and phase compensation steps, denoising preprocessing is carried out by utilizing wavelet packet transformation, the frequency response deviation of equipment is identified through Fourier transformation, a frequency domain interpolation method is adopted to reconstruct a frequency-closed defect mark segment, the phase deviation error can be accurately compensated, and the detection accuracy is improved. And self-systematic errors of hardware are eliminated from a data acquisition source, high fidelity of clean transmission electric energy data used for subsequent analysis is ensured, and a foundation is laid for high-precision identification.

The invention relates to the technical field of radar echo denoising, in particular to a radar echo signal filtering noise self-adaptive suppression method and a radar echo signal filtering noise self-adaptive suppression system. Acquiring radar station position and beam pointing data, and synchronously acquiring forest vegetation data and environment interference data of a beam pointing target area to form radar environment data; the radar environment data are identified through the multi-band decision model, and multi-modal waveform parameters are obtained; based on the multi-modal waveform parameters, radar equipment is controlled to perform periodic detection on the target area, and radar echo data are obtained; the method comprises the steps of identifying radar echo data and radar environment data, extracting dynamic spectrum characteristics in the radar echo data, performing clutter suppression processing on the dynamic spectrum characteristics by using the radar environment data, calculating the confidence probability that an early fire exists in a target area, and executing space-time consistency joint verification; according to the invention, fire early warning is carried out through the confidence probability of the fire.

The invention belongs to the technical field of image processing, and particularly relates to an intelligent agricultural product pesticide residue detection method and system based on a spectrum technology, and the method comprises the steps: obtaining the hyperspectral reflectivity according to the original hyperspectrum, dark current and whiteboard image data; calculating an illumination confidence factor by using the average spectral intensity; performing linear scaling on the obtained standard biological matrix background spectrum according to the illumination confidence factor to obtain a local background estimated value and obtain a net residual spectrum; generating a pesticide residue distribution thermodynamic diagram by combining the cosine similarity of the net residual spectrum and the target pesticide standard fingerprint spectrum and the noise suppression weight based on the illumination confidence factor; and pesticide residue detection is carried out according to the statistical characteristics of the connected region of the suspected defect mask. Through adaptive background deduction and noise suppression, the problems of uneven curved surface illumination and strong background interference are solved, and the detection accuracy is improved.

The invention discloses an automatic monitoring device and method for an open pit coal mine slope, particularly relates to the technical field of mine safety monitoring, and is used for solving the problem that existing equipment and methods are insufficient in monitoring precision and real-time performance. Slope displacement, vibration, stress and visual image data are collected in real time through a multi-source sensor array; performing cross-modal feature extraction and noise suppression on the multi-modal data to generate a structured time sequence feature vector and spatial gridding image feature data; fusing the time sequence and the visual data based on a space-time alignment algorithm and an edge calculation framework to generate high-precision space-time synchronization data; performing deep correlation analysis through a multi-head attention mechanism by using an AI large model, and outputting slope deformation characteristic data and a stability risk assessment value; and when the risk value exceeds the preset threshold value, real-time early warning is triggered, and an interactive monitoring report is output through a three-dimensional visual interface, so that the problem that the existing equipment and method are insufficient in monitoring precision and real-time performance is effectively solved.

The invention relates to a magnetotelluric noise suppression method based on ResAtt-CAE, and the method comprises the steps: generating a noise-free signal, adding a noise type into the noise-free signal to construct a noisy signal, and enabling the noisy signal to be matched with the corresponding noise-free signal to form a training set and a test set; designing a ResAtt-CAE model architecture, and realizing cross-level feature fusion by adopting a symmetric structure and jump connection; the ResAtt-CAE model architecture is trained and optimized through the training set and the test set, and the magnetotelluric noise is suppressed through the optimized ResAtt-CAE model architecture. The method is high in noise suppression capability: ResAtt-CAE captures cross-time scale signal features through multi-scale residual learning, enhances effective signal weights in combination with a time domain attention mechanism, and has a remarkable suppression effect on common magnetotelluric noise (square waves, harmonic waves, pulses, triangular waves and the like).

The invention discloses a ship key equipment impact type fault interpretable detection method based on wavelet scattering and time-frequency feature enhancement, and belongs to the field of ship equipment fault detection. According to the method, a vibration signal of ship key equipment is acquired through a sensor, and the vibration signal is converted into a time-frequency image with cross-domain consistency by adopting improved wavelet scattering transform; adaptive enhancement processing based on statistical features is carried out on the time-frequency image to realize noise suppression and fault feature enhancement; and inputting the processed time-frequency image into a pre-training model embedded with class activation mapping to complete fault identification and decision process visualization. Aiming at the impact type fault detection requirement of the ship key equipment, the method solves the problems that a traditional method is weak in generalization ability and cannot explain the diagnosis result, has the advantages of being high in detection precision, high in adaptability and traceable in diagnosis result, and can be widely applied to bearing fault detection of key equipment such as a ship main lubricating oil pump, an oil separator and a turbine.

The invention relates to the technical field of digital-analog hybrid integrated circuit design, and particularly provides a FlexRay bus receiver with low noise and wide common-mode input range, which is characterized in that a common-mode voltage division module receives a differential signal output by a bus and carries out voltage division, and then a pre-amplification module carries out amplitude limiting amplification on the signal after voltage division; the hysteresis comparator module generates threshold hysteresis and generates a logic level signal based on the signal after amplitude limiting amplification, and the digital logic receiving module receives and processes the logic level signal, generates a receiving data signal and transmits the receiving data signal to an external controller. According to the invention, the differential signal pair received on the FlexRay bus is subjected to voltage division and amplitude limiting amplification, so that a wider common-mode input range is provided, the problem of large ground potential difference is solved, and the capability of suppressing common-mode noise and the communication stability are improved. Meanwhile, the hysteresis comparator module suppresses noise false triggering by generating threshold hysteresis, and the anti-noise capability of the receiver is remarkably improved.

The invention discloses an active pen and touch screen interaction system resistant to common-mode interference and a signal demodulation method. The system comprises a signal receiving terminal and a signal transmitting terminal. The signal transmitting terminal modulates data to be transmitted by adopting a differential binary phase shift keying modulation method, and transmits a generated modulation signal to the signal receiving terminal; the analog front-end receiving module is coupled with the signal transmitting terminal, receives the modulation signal and outputs a digital square wave signal after fidelity extraction processing; and the digital demodulation processing module performs differential coherent digital demodulation on the digital square wave signal based on the prior characteristics of the modulation signal, inhibits residual noise and recovers data to be sent. The analog front end focuses strong common-mode noise suppression and analog filtering, the digital demodulation algorithm performs secondary digital purification by using signal time sequence characteristics, and the two constructs an efficient anti-interference pipeline. Meanwhile, the regular square wave signals can be directly processed through differential coherent demodulation, and the requirements for performance and power consumption of a rear-end processor are lowered.

The invention relates to the technical field of sensing data processing, and discloses a sensing data chip method based on multi-source information fusion and dynamic parameter adjustment. The method comprises the following steps: collecting original data streams of a plurality of heterogeneous sensors, and generating synchronized sensing data through timestamp alignment and format standardization processing; extracting an environment noise component, and dynamically suppressing noise by using an adaptive filtering algorithm to obtain de-noised sensing data; performing multi-dimensional feature decomposition on the de-noised data, calculating time domain, frequency domain and space domain feature vectors, and generating a multi-dimensional feature set; dynamically adjusting a feature weight distribution strategy in combination with a current system load state and a multi-dimensional feature set historical distribution rule, and generating an optimized fusion weight matrix; and carrying out weighted aggregation on the multi-dimensional feature set and the optimized fusion weight matrix, and outputting a multi-source fusion feature vector. According to the method, the problems of data synchronization, noise suppression and feature fusion suitability in multi-source heterogeneous sensing data processing can be solved, and the processing requirements of different scenes are met.

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 provides a steel shell concrete interface void detection system and method, and relates to the technical field of civil engineering structure health detection, and the system comprises a mobile scanning unit, an excitation unit, an infrared imaging unit, a signal processing and acquisition unit and a comprehensive analysis terminal. The method comprises the following steps: controlling a mobile scanning unit to carry out step-by-step impact excitation and signal acquisition so as to obtain a frequency diagram, and synchronously sampling by using an infrared thermal imager so as to obtain a thermal analysis diagram; and then binarizing the two images respectively, fusing the two images by adopting a noise suppression algorithm to generate a comprehensive image, and judging that the interface is void according to the fused image. According to the method, the high sensitivity of the impact echo method to the layering defect and the accurate description capability of the infrared thermal imaging method to the defect shape are fused, so that nondestructive, efficient and high-precision detection of the steel shell concrete interface void is realized, and the misjudgment and leak detection risks of a single method are effectively reduced.

The invention discloses a belt conveyor intelligent transportation method and system based on an intelligent sensor and electronic equipment, and the method comprises the steps: collecting key parameters from a belt conveyor through a multi-source heterogeneous intelligent sensor, including a state parameter of the belt conveyor, a state parameter of a belt and an environment change parameter; performing synchronous calibration, noise suppression and feature extraction on the multi-source heterogeneous data, and performing multi-source heterogeneous data fusion; constructing a belt conveyor operation multi-dimensional state vector based on the fused data; and inputting the state vector into a prediction model to obtain a future operation state prediction result. According to the method, the problems of'inaccurate prediction, insufficient advance and high missing report rate 'caused by'strong data isomerism, key feature weight deficiency, rare fault samples, insufficient model stability' and the like are solved.

The invention relates to the technical field of alarms, and discloses an infrastructure catastrophe sound-light alarm system with a fault self-checking capability, and the system comprises a data collection module which is configured to synchronously collect a sound signal, an optical signal, an electrical parameter and an environmental parameter of an alarm; the data preprocessing module is configured to perform noise suppression, normalization and abnormal value elimination on the acquired data; the feature extraction module is configured to extract a sound time-frequency domain feature, an optical signal fluctuation feature, a circuit stability feature and an environment correlation feature; the fault diagnosis module is configured to perform fault type judgment by adopting a multi-modal fusion model and a predefined rule base; and the grading processing module is configured to execute emergency response, maintain early warning or self-adaptive adjustment strategies according to the fault grades. According to the audible and visual alarm fault self-checking system, multi-modal data fusion, self-calibration, mobile detection and graded response are integrated, and the reliability of industrial safety early warning is improved through multi-dimensional data collaborative analysis and dynamic adjustment.

The invention discloses an SAR ship image detection method based on an improved YOLOv11 model, an improved C2PSA module C2DyMoETAttn is introduced, the core innovation point is that a PSABlock module is replaced by a DyMoETAttnBlock module, the DyMoETAttnBlock module fuses a Dynamic Tanh activation function, a Mona module, a TSSA attention mechanism and a frequency domain enhancement feedforward network (EDFFN), multi-dimensional modeling and robust enhancement of features are realized, and the detection accuracy is improved. The feature expression capability and the noise suppression performance under the background of small targets and complex sea clutters are effectively improved; in the deep feature fusion stage, a C3k2 module of YOLOv11 is optimized, an ScConv structure is introduced, adaptive fusion of space and channel features is realized through a joint reweighting mechanism of SRU and CRU, and the multi-scale target discrimination capability and feature selectivity are enhanced; on the bounding box regression layer, a Focaler-MPDIOU loss function is provided, and a Focaler-IoU sample difficulty adaptive mechanism is combined with MPDIOU positioning matching constraint, so that the learning ability of the model for small targets and shielded targets is enhanced, and the bounding box positioning precision and convergence stability are improved.

The invention relates to the technical field of artificial intelligence and data processing, and discloses an energy storage equipment operation state monitoring method based on Internet of Things acquisition, which comprises the following steps: constructing a vibration data sample; performing state labeling on the vibration data sample to form a labeling database; performing sliding mean filtering and linear interpolation processing on the vibration data sample; carrying out adaptive spectrum noise suppression by adopting a dual-threshold wavelet packet noise reduction function; carrying out frequency band division by adopting a weighted multi-scale spectral entropy feature enhancement method; constructing a deep neural network model for classifying the running state of the energy storage equipment, and training the deep neural network model by using a labeling database; and inputting preprocessed vibration data acquired in real time into the trained deep neural network model, and performing state identification and fault alarm according to a category probability prediction vector output by the model. The running state of the energy storage equipment can be accurately monitored in real time, potential faults can be found in time, and measures can be taken.

The invention relates to the technical field of intelligent monitoring of fire-fighting equipment, in particular to a fire-fighting pipe fitting connector leakage real-time alarm system based on a gas sensor, which comprises the following steps of: acquiring concentration data of various gases by arranging a sensor array, comparing the concentration data with an environmental background feature library by utilizing a background noise suppression algorithm, and determining the leakage of the various gases; and after interference is filtered, an effective leakage characteristic signal is generated. The signal is analyzed through a multi-dimensional leakage evaluation model, and leakage confidence, intensity and preliminary positioning are obtained. And in combination with a fire-fighting pipeline topological structure, the system deduces a leakage influence range and estimates pressure loss, and finally triggers a grading alarm mechanism to generate a composite alarm instruction including grades, positions, influence areas and disposal suggestions. According to the system, false alarms caused by environmental interference can be reduced, the influence range of a leakage event is pre-judged in advance, and the alarm accuracy and the emergency disposal pertinence are improved.

The invention relates to the field of mining laser gas detection, in particular to a modulation and demodulation method and system for carrier noise suppression, and the modulation and demodulation method comprises the following steps: S1, generating a driving current sequence through a laser gas sensor; s2, collecting a light intensity sequence to carry out data reconstruction; s3, extracting a harmonic signal, sending the reconstructed sequence into a lock-in amplifier, and respectively extracting a second harmonic signal and a first harmonic signal; and S4, detecting the gas concentration through the ratio by using the mapping relation between the gas concentration and the ratio of the second harmonic signal to the first harmonic signal. According to the method, a continuous data discrete reconstruction technology is introduced into a modulation and demodulation process, and a reference time sequence is generated by utilizing the characteristics of a laser output signal, so that self-matching and dynamic adjustment of modulation frequency are realized, external signal interference is effectively avoided, and the harmonic extraction stability is improved; meanwhile, the hardware structure is simplified, and the adaptability of the system to different gas absorption spectral lines is enhanced.

The invention discloses a rock slope sliding interface identification and degradation monitoring method based on distributed sound wave sensing. The monitoring method comprises the steps that a plurality of vibration sensing optical cables are vertically arranged in a rock slope along a drill hole, multi-channel vibration time sequence data are obtained through a distributed sound wave sensing demodulator, and the multi-channel vibration time sequence data are obtained through detrending and noise suppression of a data preprocessing unit, space-time consistency filtering of apparent velocity constraint and phase weighted stacking. STA / LTA triggering and DBSCAN clustering are utilized to realize single-cable event merging, and unique pairing and three-dimensional positioning of cross-cable events are completed in combination with geometric matching degree and waveform form correlation degree; the sliding interface inversion unit adopts a deep learning model to classify abnormal events, constructs an event density field and an energy intensity field for sliding related events, forms a sliding interface evidence field, and optimizes an inversion sliding interface in a limited solution domain; the degradation state monitoring unit identifies a hot spot area on a sliding interface, tracks intensity and scale evolution, constructs a degradation index, and can realize early warning in combination with multi-source information such as earth surface displacement.

The invention discloses an underwater side-scan sonar target detection system and method based on an attention mechanism, and the system comprises a data collection module which collects an underwater side-scan sonar image, and obtains a side-scan sonar image data set; the network construction module is used for constructing a target detection network based on the YOLOv8n architecture, and the target detection network comprises an inattention Transformer module, a double-branch weighted multi-scale attention module and a fusion bridging attention module; the model training module is used for training the target detection neural network by using the side-scan sonar image data set to obtain a trained target detection model; and the target detection module inputs the underwater side-scan sonar image to be detected into the trained target detection model and outputs the position information of the target in the image. The problems of poor adaptability to underwater complex acoustic images, insufficient target feature extraction capability and limited background noise suppression effect are solved, and high-precision underwater side-scan sonar target detection is realized.