1104results about "Material analysis using acoustic emission techniques" patented technology

The invention discloses an acoustic emission intelligent detection method and system for hydrogen-induced damage of a high-pressure hydrogen system, and the method comprises the steps: collecting a system operation signal through an acoustic emission sensor, carrying out the combined preprocessing of variational mode decomposition and adaptive wavelet threshold noise reduction, restraining noise, constructing a lightweight MobileNet-TCN network, carrying out the deep feature extraction, and carrying out the detection of the hydrogen-induced damage of the high-pressure hydrogen system. GRU and a three-dimensional point cloud technology are fused to realize submillimeter-level positioning of an acoustic emission source, a big data damage case library is associated based on an acoustic emission parameter accumulation model, dynamic assessment and early warning of damage risks are realized, multi-physics field monitoring data are combined, damage classification is optimized through a GCNs (Graph Convolutional Networks), and the above processes are systematically integrated. And full-chain intelligent processing from signal acquisition to risk early warning is completed. The scheme has the advantages of strong anti-interference capability, submillimeter positioning precision, high edge end reasoning efficiency, high damage classification accuracy and dynamic early warning capability, and is suitable for safety monitoring of hydrogen energy storage and transportation equipment.

The invention relates to the technical field of construction surrounding rock stability evaluation, discloses a tunnel surrounding rock stability evaluation method and system based on multi-physics field parameter inversion, and aims to solve the problems that an existing method is insufficient in data collaboration, high in parameter inversion multiplicity and poor in surrounding rock stability evaluation accuracy and timeliness. According to the scheme, the method mainly comprises the steps that an acousto-optic electromagnetic vibration drill multi-mode sensing array is arranged, and time-space synchronization is implemented; establishing a mutual interference entropy spectral density model to realize multi-physics field collaborative excitation and acquisition; a unified feature vector is obtained through data correction, feature extraction and weighted fusion; a joint inversion objective function embedded with rock physical constraints is constructed, a three-dimensional physical property parameter field is obtained through inversion, and a dynamic permeability field is calculated in combination with acoustic emission energy; and finally, dynamically updating the model by utilizing ensemble Kalman filtering, and obtaining a final risk probability based on updated parameters and seepage-uncertainty coupling correction. According to the method, the accuracy, the real-time performance and the reliability of the stability evaluation of the surrounding rock of the deep-buried tunnel are improved.

The present invention provides a dual-level thermal runaway warning method of a lithium battery based on a sound signal, comprising: obtaining a battery sound signal sequence; performing outlier identification on the battery sound signal sequence, and providing a level-1 thermal runaway warning when an abnormal data point exists; extracting a time-frequency domain feature of the abnormal data point, and identifying a presence of a thermal runaway expansion sound through a sparrow search algorithm-optimized eXtreme Gradient Boosting (SSA-XGBoost) algorithm, to providing a level-2 thermal runaway warning. In the SSA-XGBoost algorithm, optimal parameter adjustment is performed on a number of iterations, a learning rate, and a decision tree depth of the XGBoost algorithm through the SSA. A dual-level thermal runaway warning strategy is adopted to perform grading identification on general anomalies or deep anomalies, thereby effectively improving identification accuracy of a weak abnormal sound signal in an early stage.

The invention belongs to the technical field of grouting compactness detection, and particularly discloses and provides an intelligent detection system and method for the grouting compactness of a bridge prestressed pipeline, and the system comprises a signal acquisition and analysis module, a defect boundary calibration module, a defect recognition and analysis module and a compactness judgment and processing module. The method specifically comprises the steps that acoustic emission and fluctuation response signals are collected in real time through a sensor array arranged on the outer wall of a pipeline, and three-dimensional slurry density distribution is recognized; constructing an inner wall three-dimensional model in combination with a pipeline design drawing, dynamically setting a slurry density threshold value according to a grouting material formula and an environment temperature, and further calibrating a slurry defect boundary; extracting multi-dimensional features such as spatial positions, effective volumes, geometric regularity and types of the defects on the basis of boundaries, and calculating grouting compactness; and finally, according to whether the compactness reaches the standard or not, a grout supplementing early warning instruction or a detection report is automatically generated. According to the method, the reliability of defect identification and compactness calculation under complex working conditions is remarkably improved.

The invention discloses a tunnel monitoring method and system based on a vibrating wire sensor, and relates to the technical field of tunnel engineering construction safety monitoring, and the method comprises the steps: collecting the vibration frequency data and spatial position coordinates of the vibrating wire sensor in a monitoring region; the method comprises the following steps: calculating a time difference and an energy attenuation ratio between adjacent sensors by extracting spectrum energy density distribution, and constructing a stress wave propagation field; dividing grids in the propagation field to calculate node stress values, generating a stress field distribution cloud picture and extracting a stress concentration area; calculating a gravity center position coordinate change rate and a stress time sequence curve of the stress concentration area, and determining fracture extension parameters; and calculating a surrounding rock bearing capacity attenuation curve based on the parameters, and outputting an early warning signal when the slope exceeds a threshold value. According to the invention, real-time monitoring and early warning of the tunnel surrounding rock instability risk are realized.

The invention discloses a rock damage assessment method fusing wave velocity and microscopic fracture, and belongs to the technical field of rock damage assessment, and the rock damage assessment method comprises the following steps: arranging a wave velocity testing device on a rock sample, and respectively making an unloaded rock sample and a damaged snapshot rock sample under different stress loading; microcosmic fracture information of the damaged snapshot rock sample is identified, a three-dimensional wave velocity model of the damaged rock sample under different stress loads based on a wave velocity test is constructed, and then a macro-micro scale fusion multi-dimensional data set is constructed; based on the macro-micro scale fusion multi-dimensional data set, constructing and training a rock damage identification model; and inputting the characteristic parameters of the rock sample to be evaluated into the rock damage identification model, identifying the damage distribution characteristics of the rock sample on the spatial scale, and evaluating the rock damage degree. According to the method, accurate prediction and evolution process evaluation of the rock damage degree and spatial distribution can be realized, and a reliable technical means is provided for disaster early warning, stability evaluation and risk prevention and control in complex rock mass projects such as deep mines and tunnels.

The invention discloses a deep well rock mass instability failure time accurate forecasting and early warning system, and relates to the technical field of deep well rock mass failure early warning, and the deep well rock mass instability failure time accurate forecasting and early warning system comprises the following steps: collecting a plurality of deep well rock samples to carry out a uniaxial compression experiment, and collecting acoustic emission signals in real time based on an acoustic emission sensor to obtain original acoustic emission signal data; carrying out self-adaptive preprocessing, and carrying out data classification and integration to obtain rock sample acoustic emission parameter data; constructing an original damage forecasting model, and performing model training and verification optimization based on the rock sample acoustic emission parameter data to obtain a rock damage forecasting model; collecting an acoustic emission signal of the deep well rock mass, and predicting the instability failure time of the deep well rock mass in real time based on the rock failure forecasting model; the method is used for solving the problems that when an existing deep well rock mass damage early warning technology carries out early warning on rock mass instability damage through acoustic emission monitoring, single or few characteristic parameters are manually processed and analyzed, and the early warning reliability and timeliness are not high.

The invention relates to the technical field of rock mechanical tests and safety monitoring, and discloses a rock fracture prediction method based on acoustic emission and surface strain cooperative monitoring, and the method comprises the steps: building a monitoring system comprising acoustic emission and an industrial camera array, and building a unified timestamp of each subsystem through a GPS time service module; through load triggering logic, a synchronous trigger is utilized to synchronously acquire an acoustic emission signal and a sample surface image sequence, and evolution characteristics of three-dimensional coordinates of an acoustic emission source and surface full-field strain data are solved. And on the basis, calculating a main strain field variation coefficient, and performing cross-correlation analysis on the resampled energy rate and strain rate. And finally, according to multi-parameter coupling criteria of acoustic emission time sequence parameters, positioning events and surface strain, identifying rock fracture precursor types, and predicting fracture moments and areas by combining a Voight model inverse velocity method and a seismic source projection technology.

The embodiment of the invention provides a coal rock stability monitoring method and system based on acoustic signal dynamic characteristics, and relates to the technical field of coal rock stability monitoring. The method comprises the following steps: after acquiring an acoustic signal, segmenting the acoustic signal into a plurality of data segments by adopting a sliding time window; nonlinear features are extracted from the data segments to obtain a comprehensive feature vector, and then a monitoring early warning state is triggered according to the comprehensive feature vector. Wherein the comprehensive feature vector can be constructed by fusing a plurality of non-linear features, and the non-linear features are system evolution features extracted from the acoustic signal based on a non-linear dynamics principle. According to the method, the similarity between the current system state and the historical instability state is quantified by introducing the dynamic time warping distance, sudden change detection is executed in combination with the real-time feature sequence corresponding to the comprehensive feature, hybrid early warning monitoring combining mechanism and data driving is formed, and the timeliness and accuracy of coal rock stability monitoring and early warning are improved.

The invention discloses a blade bolt state monitoring system and method based on an acoustic emission technology in the technical field of state monitoring of wind power generation equipment. The method comprises the following steps: acquiring acoustic emission signal data of a blade bolt connection area acquired by an acoustic emission sensor array; sequentially carrying out preprocessing and feature extraction processing on the basis of the acoustic emission signal data, and then calculating a wavelet packet energy entropy value; judging whether a triggering condition of multi-sensor data fusion weighting judgment is met or not based on the wavelet packet energy entropy value; when any triggering condition is met, it is judged that the state of the bolt is abnormal, and after comprehensive state recognition is conducted through multi-sensor data fusion weighted judgment and modal acoustic emission wave velocity correction positioning, early warning information including the damage type, the severity degree and position information is output; when the triggering condition is not met, it is judged that the bolt state is normal, and circulating monitoring continues. According to the invention, accurate evaluation and early warning of the blade bolt state are realized through signal acquisition, processing, analysis and early warning.

The invention provides a method for evaluating the crack resistance of tunnel body concrete, and belongs to the technical field of wind tunnels, and the method comprises the steps: uniformly arranging multiple types of sensors on the surface of a tunnel body concrete structure to form a high-density monitoring network, employing a concrete circular ring constraint test piece to establish an anti-crack reference database, and constructing a multi-working-condition temperature stress database; acquiring multi-dimensional data such as strain, temperature and acoustic emission in real time, inputting the monitoring data into a liquid adaptive neural network model to predict crack initiation probability and expansion risk, establishing a crack risk assessment function, formulating a corresponding processing strategy according to a risk coefficient range, and starting an intelligent spray maintenance system; a closed-loop control system from monitoring perception to risk early warning to active protection is formed, and the technical problem that crack initiation and expansion risks of a hole body concrete structure cannot be accurately predicted under complex working conditions is solved.

The invention discloses an acoustic emission signal noise reduction and feature extraction method and system suitable for a deep roadway, and relates to the technical field of safety monitoring of deep mineral resource mining, and the method comprises the specific steps: arranging an acoustic emission sensor array along the deep roadway, collecting multi-source data, converting the multi-source data into digital signals, and storing the digital signals; identifying an interference type through a wavelet packet decomposition and environment correction algorithm; self-adaptive noise reduction is carried out by using a complexity sensitive penalty algorithm; time domain and frequency domain features are extracted, coupling parameters are calculated, and time domain and frequency domain features are obtained through Hilbert-Huang transform; and finally, through principal component analysis dimensionality reduction and mutual information entropy screening, constructing a feature vector and transmitting the feature vector to a safety early warning system. According to the invention, the processing precision and reliability of the acoustic emission signal are improved through the multi-source signal acquisition module, the interference identification module and the adaptive noise reduction module; signal characteristics are comprehensively described through algorithm optimization, key characteristics are output through characteristic optimization, real-time monitoring and early warning are achieved through a dynamic damage vector algorithm, and deep roadway construction safety is guaranteed.

The invention relates to the technical field of data processing, in particular to a three-dimensional live-action model construction system for building structure demolition and reconstruction. The system extracts event combinations with obvious transfer correlation features for localization and analysis of dangerous sound sources. Through simulation of transmission of test waves in an initial acoustic slowness field, a most probable dangerous sound source position for generating a current event combination under each test wave is obtained by using an objective function optimization solution method. And further performing statistics on simulation information of all test waves, establishing a residual curve, screening out a brittleness event position based on feature extraction, and adjusting a slowness value in a current voxel through various parameters corresponding to the brittleness event position in an initial acoustic slowness field. Through the dynamic correction method, the obtained corrected acoustic slowness field can more effectively represent the specific change of the building structure in the dismantling process, so that the internal damage can be more clearly quantified.

The invention relates to the technical field of sodium battery energy storage safety, and discloses a thermal runaway early warning method and device for a sodium battery energy storage system. Multi-modal data such as acoustic emission, gas dielectric characteristics and electrical parameters are collected in real time through multiple sensors, pre-processing and feature extraction are performed through an edge calculation unit, and the data are transmitted to a central decision-making unit for multi-source information fusion and risk assessment; the thermal runaway risk probability is dynamically calculated by adopting a deep learning algorithm based on an attention mechanism, a grading early warning instruction is generated according to the risk grade, and accurate response is realized through multi-system linkage execution. According to the invention, early-stage monitoring of internal microscopic damage and gas environment abnormity of the sodium battery is realized, timeliness and accuracy of thermal runaway early warning are improved, and safe and stable operation of a sodium battery energy storage system is guaranteed.

The invention belongs to the technical field of testing, and particularly discloses a comprehensive evaluation method for rock damage and fracture acoustic emission events. The method comprises the following steps: collecting an acoustic emission full-waveform signal released by a rock sample in a damage and fracture process, and separating an independent acoustic emission event from a full waveform by utilizing peak identification time, impact identification time and impact locking time; respectively extracting a time domain characteristic parameter and a frequency domain spectrum parameter for each independent event; entropy weight quantitative analysis is carried out on various extracted parameters based on an information entropy theory, and a comprehensive evaluation index of the acoustic emission event is constructed on the basis. According to the method, synchronous extraction and fusion of multiple time domain and frequency domain parameters of the acoustic emission event are realized, objective weight distribution is performed in combination with an information entropy theory, and a rock damage and fracture comprehensive evaluation index capable of comprehensively representing global features of the acoustic emission event is established. The limitation that a traditional method only depends on single time domain or frequency domain parameter analysis is effectively solved.

The invention provides a sensor fusion-based pig feed crushing particle size monitoring method, which comprises the following steps of: synchronously acquiring vibration, acoustic emission and optical signals, carrying out band-pass filtering, normalization, feature extraction and wavelet packet decomposition, and dynamically adjusting the confidence coefficient of each channel in combination with working condition perception and a sensor performance knowledge base so as to monitor the crushing particle size of the pig feed. Weighted fusion and conflict evidence modulation of multi-source signals are achieved, the improved Dempster-Shafer evidence theory is introduced to improve the abnormal granularity recognition accuracy, key parameters of crushing equipment are controlled in a linkage mode through a closed-loop feedback mechanism, high-robustness detection and self-adaptive adjustment of the granularity state are achieved, and the method has the advantages of being high in robustness and high in robustness. And the stability and the automation level of the feed crushing process are improved.

The invention relates to the technical field of bag type dust collector filter bag abrasion detection, in particular to a filter bag damage non-contact detection method and system based on acoustic array positioning. The method comprises the following steps: arranging an acoustic sensor array in an air purification chamber of the dust remover, and collecting acoustic signals in real time; after band-pass filtering is carried out on the signals, feature vectors of the signals are extracted and matched with a pre-established acoustic fingerprint database, so that a filter bag damage event is recognized; after identification, based on the time difference of arrival of the signal to at least three sensors in the array, combining the coordinates of the sensors and the sound velocity, and utilizing a TDOA positioning algorithm to calculate the space coordinates of the damaged sound source; and finally, matching the coordinates with a pre-stored filter bag coordinate mapping table, determining the number of a specific damaged filter bag, and performing visual highlight marking on a pattern board plane layout of an application layer terminal. The online, real-time, automatic and accurate positioning of the damaged filter bag is realized, the problem that the prior art can only give an alarm but cannot position is solved, and the operation and maintenance efficiency and safety are improved.

The invention provides a construction project quality detecting and monitoring method and system, and relates to the technical field of data processing.The method comprises the steps that spatial positioning sensors are deployed at steel structure beam column welding joints, a concrete core shear wall root pouring area and a curtain wall top cantilever connecting end; welding acoustic emission frequency domain signals of beam-column joints, concrete vibration energy distribution waveforms of the root of the shear wall and dynamic load stress spectrums of the cantilever connecting ends are collected respectively, and a spatial heterogeneous original data set is generated; acquiring three-dimensional coordinates of positioning sensors on a steel structure beam column welding node, a concrete core shear wall root pouring area and a curtain wall top cantilever connecting end so as to construct a dynamic space reference frame, and calculating a deformation feature vector of the dynamic space reference frame; the deformation feature vector comprises a reference frame area change gradient value, a frame side vector fluctuation coefficient and a space included angle offset entropy value. According to the invention, the real-time performance of construction project quality monitoring is improved.

The invention discloses a novel induction-type magneto-thermo-acoustic detection method for the conductivity of a supercapacitor, and relates to the technical field of nondestructive material detection.The method comprises the steps that a steady-state static magnetic field and a pulse alternating magnetic field are introduced to form a composite excitation field, and a magneto-acoustic effect and a thermo-acoustic effect are simultaneously and cooperatively excited in a solid-state electrode material; the magnetoacoustic-thermoacoustic coupling effect is formed, eddy current induced by a pulse alternating magnetic field in the material not only generates joule heat, but also generates a direct carrier of Lorentz force under the action of a steady-state static magnetic field, the two physical effects are derived from the same electromagnetic excitation process, but the mechanisms for generating acoustic signals are complementary to each other, so that the effect of the magnetoacoustic-thermoacoustic coupling is achieved. The two effects are coupled as a unified sound source item, a sound pressure wave equation is established, the equation describes a sound field excitation process under the combined action of a force source and a heat source, the coupling mechanism remarkably enhances the strength and information abundance of ultrasonic signals, and the inherent defect that a single thermoacoustic detection method is insensitive to a high-conductivity material is overcome.

The invention provides an acoustic emission ore pulp granularity online detection system and method based on a Hertz collision mode, and belongs to the technical field of ore dressing process monitoring and control. The system comprises an ore pulp bypass circulation module, a particle size calculation module and a particle size measurement control module. A built-in acoustic emission sensor is used for collecting acoustic emission signals generated by Hertz elastic collision between signal ore pulp particles and a probe; multi-band energy features and time domain features are extracted in combination with wavelet packet decomposition, and a fusion feature vector is constructed by fusing ore pulp flow velocity and density information; the fusion feature vector is input into a BP neural network model after dimension reduction processing, and the proportion of particles with the particle size smaller than a set threshold value in the ore pulp is predicted online. Full-process management of sampling, preparing, measuring and liquid discharging is achieved through automatic control, and the system has the advantages of being high in measuring precision and automation degree, low in cost, high in anti-interference capacity and the like, is suitable for continuous online monitoring of the ore pulp granularity on the ore dressing site and provides data support for flotation process optimization.

The invention relates to the technical field of borehole fracture analysis, discloses a borehole fracture evaluation method and system based on a neural radiation field and acoustic emission, and aims to solve the problem of poor accuracy in the prior art. The scheme mainly comprises the following steps: constructing a high-fidelity hole wall three-dimensional model through a neural radiation field technology; meanwhile, time-space coordinates and energy parameters of an acoustic emission event are obtained through an acoustic emission sensor array; uniformly converting acoustic emission coordinates into a model coordinate system, and identifying and quantifying geometric features of the fissure surface; and finally, constructing a space-time diagram structure taking the fracture surface as a static node and the acoustic emission event as a dynamic node, learning a space-time evolution mode through a graph neural network, outputting a fracture surface activity index, and realizing activity grade evaluation and extension trend prediction. The method improves the accuracy of borehole fracture analysis, and is particularly suitable for safety monitoring of geotechnical engineering.

The invention belongs to the technical field of boiler heating surface high-temperature corrosion monitoring, and relates to a boiler heating surface high-temperature corrosion online monitoring method and system based on data fusion. The method comprises the following steps: acquiring an electrochemical signal, infrared thermal image data and acoustic emission characteristics of a key corrosion sensitive area of a boiler heating surface; based on data collected by a sensor network, a corrosion rate dynamic prediction model composed of a physical driving sub-model and a data driving sub-model is adopted to obtain a final corrosion rate prediction value; fusing the infrared thermal image data and the acoustic emission features, calculating a regional corrosion risk confidence coefficient according to the fused infrared thermal image data and acoustic emission features, and outputting a confidence coefficient level according to the regional corrosion risk confidence coefficient; and outputting an early warning signal according to the final corrosion rate predicted value and the confidence level, and dynamically adjusting combustion parameters. Accurate prediction of high-temperature corrosion of the boiler heating surface is realized, and corrosion development of the boiler heating surface is actively inhibited.

The invention discloses a crack detection method and system for multi-modal fusion attention, and relates to the technical field of aviation structure health monitoring, and the method comprises the steps: pairing an acoustic emission sample and an image sample, and forming a visual acoustic emission detection data set; carrying out alignment processing on the acoustic emission signal and the image data; and acoustic self-attention features, image self-attention features, acoustic cross-attention features and image cross-attention features are extracted from the aligned acoustic features and image features, the features are fused and then input into a decoding detection head, and cracks are identified and positioned. According to the application, deep semantic association of vision and acoustic emission signals is realized through the feature alignment module, hidden cracks which are easy to leak in a traditional method are effectively detected, meanwhile, interaction of self-attention and cross attention is realized, redundant information interference is inhibited, and the perception capability of weak crack signals is remarkably enhanced.

The invention relates to the technical field of creep age forming, in particular to an online monitoring and repairing method for creep age forming, which realizes closed-loop intelligent control of a creep age forming process by integrating acoustic emission real-time monitoring and electric pulse online repairing. According to the invention, real-time acoustic emission characteristic parameters are collected and extracted in real time, and damage initiation activities in the material can be captured immediately; the real-time acoustic emission characteristic parameters are compared with the creep aging damage information base in real time, and the current damage can be subjected to early recognition and accurate quantitative diagnosis according to historical damage evolution data, so that the damage type and the damage degree are accurately judged; and an optimal electric pulse parameter combination predetermined for the damage type and the damage degree of the target damage is called as a repair parameter, and electric pulse repair is immediately applied, so that damage self-adaptive accurate intervention is realized. And after repairing is completed, the process automatically circulates and returns to the monitoring step, and whole-process closed-loop control of damage monitoring, damage diagnosis and damage repairing is formed.

The invention relates to the technical field of anti-seismic performance detection, in particular to an anti-seismic performance detection method and system for an assembled steel-wood composite structure, and the method comprises the steps: arranging a multidirectional acoustic emission sensor in a steel-wood structure node area, applying simulated seismic vibration, and synchronously collecting acoustic emission signals; the method comprises the following steps: preprocessing collected acoustic emission signals, dividing the acoustic emission signals into signals corresponding to microcracks and contact slippage, respectively calculating an energy attenuation rate and a phase offset, and constructing a matrix; micro-impact is applied to the steel-wood node through an electromagnetic excitation device, a response signal is collected, resonant frequency is extracted, the drift distance between the resonant frequency and a reference value is calculated, and the severity of interface damage is determined according to the value of the drift distance; the damage correlation index calculation takes the characteristic value of the interface wave propagation characteristic matrix and the resonance frequency drift distance as input, the damage correlation index is calculated through the correlation coefficient, and the damage grade is divided according to the correlation coefficient. And differential characterization of different damage types is realized through the interface wave propagation characteristic matrix.

The invention discloses an end slope mining side slope real-time stability testing system and method, and relates to the technical field of open pit coal mine end slope mining safety monitoring and early warning, and the method comprises the steps that a distributed optical fiber sensing network arranged on a side slope surface and a mining chamber top plate collects acoustic emission and strain time sequences; a solid-state laser radar array arranged on the stope platform collects slope surface point cloud data of the stope platform; during data acquisition, the solid-state laser radar array and the distributed optical fiber sensing network are in time alignment; carrying out slope displacement increment extraction on the slope point cloud data of the monitored area by the edge GPU node; the data analysis cloud platform is used for performing microfracture identification according to the acoustic emission and strain time sequence; and inputting the slope displacement increment, the micro-fracture event count and the strain time sequence into the trained stability evaluation model to obtain a stability evaluation result, and capturing the internal micro-fracture, surface micro-displacement and shear-expansion coupling characteristics in real time, and providing high-reliability instability prediction.

The invention provides a high-stress rock mass disturbance catastrophe real-time early warning method based on a fracture comprehensive signal, which belongs to the technical field of geotechnical engineering, and constructs a comprehensive acoustic parameter ASCP by fusing various parameters such as amplitude, dominant frequency, energy distribution, crack fractal characteristics, rock mass fracture event density and the like in an acoustic emission signal. The calculation process is combined with contribution weights of different parameters to the destruction stage, and weight values are jointly calibrated through data analysis. On the basis of a large amount of engineering field monitoring and indoor true triaxial test data, the evolution law of the ASCP in the rock mass damage process is analyzed, multiple early warning thresholds of an ASCP evolution curve starting early warning threshold and an ASCP catastrophe early warning threshold are provided, and the early warning accuracy and timeliness are improved. According to the early warning method, various parameters of sound signals are integrated, a multi-threshold early warning method is established, the contribution degrees of various main sensitive parameters of high-stress rock mass disturbance damage sound emission are integrated, and the early warning accuracy, timeliness, high efficiency and economical efficiency are improved.

An intelligent monitoring and early warning method for damage failure of a filling body beside a gob-side entry retaining roadway comprises the steps that a high-water-content material standard sample is prepared, uniaxial compression testing and acoustic emission monitoring are carried out, and mechanical property data and acoustic emission waveform signals are synchronously obtained; carrying out failure stage division based on the maximum stress value and a sliding linear fitting method, and carrying out automatic classification and labeling operation; solving variational mode decomposition key parameters through an intelligent optimization algorithm to obtain decomposed intrinsic mode components; constructing a sample data set through a data enhancement process; training to obtain a waveform-based destruction stage classification model; elastic wave signals are collected in real time, variational mode decomposition and noise reduction processing are carried out, intrinsic mode components highly related to the damage degree are obtained and serve as input data, and a classification result is output through a waveform-based damage stage classification model; and performing graded early warning. According to the method, the real-time dynamic monitoring of the damage failure of the roadside filling body can be realized, and the early warning of the damage failure of the high-water material roadside filling body can be realized.

The invention relates to the technical field of acoustic emission damage detection, in particular to an acoustic emission source positioning method based on lightweight convolution and an attention mechanism, according to the method, a four-channel continuous wavelet image (CWT) is used as input, a DSConv module carries out integral solution on a standard convolution into channel-by-channel convolution and point-by-point convolution, and the network parameter quantity and the calculation overhead are effectively reduced; the attention module adaptively adjusts feature weights through channel and space attention combination, highlights key time frequency features and inhibits redundant information; the four-branch features integrate multi-channel complementary information through adaptive weighted fusion, so that the signal characterization capability is improved; gradient propagation is improved through residual connection, the deep feature learning efficiency is enhanced, and therefore light-weight and high-precision sound emission source positioning is achieved.

The invention provides a multi-source monitoring and evaluating system for a deep underground space energy storage project, and the system comprises a data monitoring module which is used for monitoring the multi-source rock mass mechanical parameters of the surrounding rock of the deep underground space energy storage project, and obtaining the multi-source monitoring data; the data transmission module is used for transmitting multi-source monitoring data; and the data early warning module is used for receiving the multi-source monitoring data, analyzing the multi-source monitoring data based on multi-source data space-time alignment fusion and an AI algorithm, and obtaining an evaluation and early warning result of the deep underground space energy storage project. According to the technical scheme, through rock mechanics multi-source monitoring and intelligent analysis, the surrounding rock stability evaluation capability of the deep underground space energy storage project can be remarkably improved.