402 results about "Residual neural network" patented technology

The invention provides an igniter robot production line control method and system based on deep reinforcement learning, and relates to the technical field of robot production line control, and the method comprises the steps: collecting the real-time state data of a production line station, extracting features through a multi-scale residual neural network and a spatial pyramid pooling module, and carrying out the feature extraction; channel attention and space attention modules are combined to perform feature enhancement, a cross-modal encoder is used to perform time sequence modeling, task decomposition is performed based on hierarchical reinforcement learning, soft constraint trajectory optimization and adaptive impedance control are used to generate a station control instruction, and a multi-target Pareto evaluation and priority dual experience pool is used to perform sample screening. Network parameters are optimized and updated through a near-end strategy, and a production line optimization decision scheme is output, so that the production line control precision can be improved, the system robustness can be enhanced, and the optimization of the production efficiency is realized.

The embodiment of the invention discloses an outer wall thermal insulation defect diagnosis method and system based on artificial intelligence, and the method comprises the steps: firstly obtaining an infrared thermal imaging and visible light image sequence of a target building outer wall, the former comprising continuous temperature distribution data, and the latter comprising textural feature data in time-space alignment with the latter; performing dynamic temperature gradient analysis on the infrared thermal imaging image sequence to generate a three-dimensional heat conduction abnormal map, extracting surface deformation characteristics from the visible light image sequence to generate a structure deformation distribution map, and performing multi-modal characteristic fusion on the two to obtain a joint defect characteristic matrix; performing defect type classification and region positioning on the matrix based on a pre-trained deep residual neural network model, outputting a defect type identifier and a corresponding region boundary coordinate, and finally generating a diagnosis report containing a repair priority score and a material matching suggestion according to the defect type identifier and the corresponding region boundary coordinate, and sending the diagnosis report to a user terminal for visual display. And efficient and accurate external wall thermal insulation defect diagnosis is realized.

The invention discloses an operating room intelligent monitoring method and system based on monitoring video recognition, and relates to the technical field of medical safety supervision, and the method comprises the steps: collecting a video through an operating room camera array, and constructing an operation region panoramic sequence through a residual neural network and an optical flow field; a double-branch target detection network is adopted to extract the position of a medical worker, the body position of a patient and the characteristics of surgical instruments, and a surgical scene model is constructed; performing trajectory tracking based on skeleton key point extraction and Kalman filtering, and constructing a dynamic graph of the operation process; generating an operation process state report by using the time sequence diagram convolutional network and a multi-head attention mechanism; and comparing the operation specification library through a knowledge distillation algorithm, and carrying out grading recording on abnormal events. According to the invention, efficient abnormal event tracking and recording functions are realized, technical support is provided for operation quality control and safety management, and the overall performance of operating room intelligent monitoring is improved.

The invention relates to an electromechanical fault prediction and diagnosis method and system based on big data, and the method comprises the steps: collecting the operation state data of electromechanical equipment in real time, and synchronously obtaining historical associated data; performing dynamic feature extraction on the operation state data and the historical associated data, constructing a sliding mean value feature matrix, and calculating dynamic weights of feature parameters; generating a fusion weight coefficient according to the dynamic weight and a preset fault threshold interval; extracting a distribution density curve of a historical fault occurrence probability, and calculating a dynamic threshold value; performing weighted reconstruction on the sliding mean feature matrix based on the fusion weight coefficient, and outputting a fault type and an occurrence probability through a pre-trained lightweight residual neural network model; and when the fault occurrence probability exceeds a dynamic threshold value adjusted based on a historical fault occurrence probability distribution density curve, generating an electromechanical fault diagnosis result so as to realize the purposes of real-time monitoring of the operation state of the electromechanical equipment and accurate fault prediction and diagnosis.

The invention discloses a partial discharge mode recognition method based on a residual neural network and an attention module, and relates to the technical field of partial discharge signal processing and recognition. The method comprises the following steps: acquiring partial discharge signal data to be detected; carrying out multi-scale denoising processing on the partial discharge signal by an improved ensemble empirical mode decomposition adaptive noise algorithm and wavelet packet decomposition combined method so as to remove noise interference and reserve main components of the signal; the time domain, the frequency domain and the phase information of the denoised partial discharge signals are converted into grey-scale maps through a Grubby angle field algorithm, a Grubby angle difference field algorithm and a Markov transfer field algorithm, and the grey-scale maps are fused to generate a feature RGB image. Inputting the RGB image into a residual neural network combined with a convolutional block attention module for feature extraction and classification; and finally, outputting a partial discharge mode identification result for fault detection and early warning of power equipment. According to the method, multi-scale denoising processing and multi-dimensional feature fusion are utilized, and depth feature extraction capabilities of the residual network and the attention module are combined, so that the recognition accuracy and robustness of the partial discharge mode are remarkably improved, and the method can be widely applied to fault diagnosis and early warning of power equipment.

The present disclosure belongs to the field of geophysical exploration, and discloses a method, a system, a medium, a device and a terminal for predicting the probing depth of transient electromagnetic. Based on the existing published resistivity model database, the transient electromagnetic field in layered medium is calculated, and the probing depth is calculated based on Jacobian matrix to establish a training data set. The simulated induced electromotive force is used as the input of the neural network, and the calculated probing depth is used as the output of the network. A rapid mapping between observation data and probing depth is established by using residual neural network.

The present invention relates to the technical field of railway inspection, and relates in particular to a railway foreign-object intrusion detection method and system based on deep learning. The method comprises: S10, acquiring image data to undergo detection; and S20, inputting the image data into a trained attention semantic segmentation network to obtain a foreign-object detection result. The attention semantic segmentation network is obtained by first training a preset attention semantic segmentation network architecture using a preconfigured data set, and then re-training the attention semantic segmentation network on specified image data using an adaptive correction algorithm. A backbone network architecture is obtained by inserting a specified attention mechanism at a specified position within a pre-selected residual neural network, and using three parallel dilated convolutions as an initial convolutional layer in the residual neural network. A dual-branch decoder combines an edge recognition branch and a semantic segmentation branch. The method is applicable to various scenarios, achieves improved detection accuracy and maintains a lightweight design.

The invention provides a welding equipment state monitoring method and device based on artificial intelligence, relates to the technical field of artificial intelligence and data processing, and obtains a vibration data flow corresponding to target welding equipment by collecting vibration signals generated in the operation process of the target welding equipment in real time. And time-frequency energy distribution corresponding to the vibration data flow is determined, and energy changes of the signals in two dimensions of time and frequency are revealed, so that the signal-to-noise ratio of the signals is enhanced, non-correlation frequency band interference is reduced, early fault signals are enhanced, and the sensitivity of the model to abnormal events is improved. Rapid change features and stable structure features in the to-be-identified data are extracted by adopting a preset dynamic gating attention mechanism through a deep residual neural network, so that the rapid change features and the stable structure features can be distinguished and weighted, and the sensitivity of the model to abnormal events (such as early fault impact) is improved; therefore, accurate equipment state analysis is carried out on the welding equipment.

Disclosed is a method for fast automatic calibration of a phased array based on a residual neural network. A phase setting matrix is set and an amplitude and a phase of a array far-field complex signal are measured with a network analyzer to obtain an amplitude and phase vector of the array far-field complex signal. A real part, an imaginary part, and a magnitude of the far-field measured complex signal value are separated and normalized, and mapped to RGB three-channel image data. Datasets are automatically generated according to a preset amplitude-phase error range by a simulation software, the datasets are proportionally divided into a training set and a test set to be input into the residual neural network for training to obtain a calibration model. Measured data is input into the calibration model for automatic estimation of the amplitude-phase error of the phased array.

The invention discloses a radar lifting control method and system based on meteorological monitoring, and relates to the technical field of radar lifting control, and the method comprises the steps: completing the switching of a power supply and communication after a radar is powered on, initializing a controller, collecting the data of a meteorological station, and generating a future fusion wind speed in real time through a Kalman filtering physical model and a residual neural network; future fused wind speed is converted into wind pressure for evaluation, the risk degree is judged according to the evaluation result, early warning is given out, and the controller is preheated to enter a lifting preparation state. The input stability is improved through meteorological data sliding window smoothing and feature extraction, wind speed dynamic prediction and uncertainty quantification are achieved through XGBoost prediction and residual variance estimation, the time sequence consistency and robustness are enhanced through remote API interpolation correction and adaptive extended Kalman filtering, residual correction is conducted through a neural network, the prediction precision is improved, and the prediction accuracy is improved. And a reliable decision basis is provided for radar lifting control.

The invention discloses a single air conditioner load regulation potential evaluation method based on transfer learning and multi-task learning, and relates to the technical field of air conditioner management.The method comprises the steps that a regional association model is built based on air conditioner operation data in a general scene, and the regional association model is analyzed to obtain a cooperative regulation relation between air conditioner equipment; constructing an air conditioner load regulation potential evaluation model by using a deep residual neural network; a multi-task learning framework is formulated according to the cooperative adjustment relation between the air conditioning equipment, and the air conditioning load adjustment potential evaluation model in the general scene is optimized by using the multi-task learning framework; and adjusting the weight of the optimized air conditioner load regulation potential evaluation model in combination with a transfer learning technology to obtain an air conditioner load regulation potential evaluation model in a specific scene. According to the method, the adaptability and generalization ability of the air conditioner load regulation potential evaluation model are remarkably improved by constructing the regional correlation model and introducing self-supervised learning and adversarial training.

The invention belongs to the technical field of ocean remote sensing, and relates to a spaceborne microwave radiometer tropical cyclone wind speed inversion method based on physical constraint deep learning, comprising the following steps: acquiring tropical cyclone parameter information; extracting multi-band brightness temperature data of the satellite-borne microwave radiometer in a corresponding space-time range, and constructing a sample data set; a deep learning inversion algorithm model with physical constraints is loaded and trained; the physical constraint deep learning inversion algorithm model comprises an input layer, a network layer, a physical layer and an output layer; the network layer is composed of a residual neural network, the physical layer is composed of a D matrix remote sensing statistical formula and provides physical constraints for the whole model, and the D matrix is a nonlinear D matrix; and outputting the tropical cyclone wind speed in the current space-time range. According to the method, the brightness temperature information of the satellite-borne microwave radiometer is obtained by utilizing the tropical cyclone trajectory information, and the network model with physical information is constructed by utilizing the combination of the D matrix equation and the neural network, so that more accurate and high-precision tropical cyclone wind speed information is obtained.

The invention discloses a circulating fluidized bed temperature intelligent prediction method based on a physical information neural network, and mainly relates to the technical field of industrial process intelligent control and energy power engineering crossing. Comprising the following steps: S1, acquiring operation data of the circulating fluidized bed, and preprocessing the operation data to obtain a data set; s2, constructing a physical information residual neural network; s3, constructing a loss function of adaptive weight adjustment; s4, training the physical information residual neural network by using the data set, and performing iterative optimization in combination with the constructed physical information residual neural network and the loss function to obtain a bed temperature prediction model; s5, inputting operation data of the circulating fluidized bed into the bed temperature prediction model to obtain a bed temperature prediction value; the method can solve the problem of complexity and nonlinearity of dynamic prediction of the bed temperature of the circulating fluidized bed, can optimize the operation efficiency of the boiler, improves the combustion stability, and reduces the emission of pollutants.

The invention discloses a super-resolution image reconstruction method based on a multi-scale large-kernel convolution double-residual neural network, which is suitable for the field of image processing, and comprises the following steps: cutting a data set, inputting a cut original low-resolution image into a preprocessing module, carrying out image normalization and data enhancement operation, and carrying out image reconstruction; generating a preprocessed low-resolution image; the preprocessed low-resolution images form a distorted image block data set, and a training set, a verification set and a test set are formed; according to an existing distorted image block data set, a super-resolution image reconstruction method based on a multi-scale large-kernel convolution double-residual neural network is constructed; and inputting the data set into the constructed multi-scale large-kernel convolution double-residual neural network to extract semantic features, and amplifying a feature map by using an up-sampling module of the model to generate a super-resolution image. According to the method, a multi-scale large-kernel convolution and double-residual structure is introduced, a visual attention mechanism is used in the neural network, the extracted features better conform to human visual perception features, and super-resolution image reconstruction is more accurate.

The invention discloses an electroencephalogram auditory attention classification method and system based on a time-frequency attention mechanism, and belongs to the field of pattern recognition and biomedical signal processing. Specifically, firstly, multi-band filtering, re-reference, multi-band electroencephalogram splicing and windowing slicing preprocessing are carried out on original electroencephalogram signals. Then different weights are distributed to different frequency bands in the multi-band electroencephalogram signals, the multi-band electroencephalogram signals are fused into two-dimensional electroencephalogram signals, frequency domain features of the electroencephalogram signals are extracted, and time sequence features of the electroencephalogram signals are extracted; and finally, extracting deep auditory attention features in the electroencephalogram signals from which the frequency domain features and the time domain features are extracted by using a lightweight residual neural network, and carrying out auditory attention classification. Experimental results show that the method can extract more discriminative features from the original electroencephalogram signals, in the execution of auditory attention classification, the average classification accuracy of 96.5% and 76.3% is obtained in a subject and a cross-subject experiment under a one-second decision window, and compared with other methods, the classification effect is obviously improved.

The invention provides a blast furnace carbon emission anomaly prediction method based on digital twinning, relates to the technical field of blast furnace carbon emission, and provides a blast furnace top abnormal carbon emission detection method based on deep learning and mechanism fusion. Firstly, key features of carbon traces in the blast furnace production process are collected, and gas components at the top end of a blast furnace and peripheral production data are collected through a sensor. Feature data which cannot be acquired by some sensors in real time are iteratively solved through a Navier-Stokes NS equation. Then, cross-correlation analysis is carried out to find the hysteresis relation of carbon traces in production, and a carbon emission hysteresis relation model is established; abnormal operating conditions are detected by a residual neural network. And finally, testing and evaluating the performance of the model by using actual production data. The result shows that the provided method can accurately detect the abnormal carbon emission at the top end of the blast furnace, early warning can be given out in time, and environmental pollution and energy waste caused by the abnormal carbon emission are effectively reduced.

The invention discloses a power grid construction subpackage management and control method based on big data, and the method comprises the following steps: collecting the data of a power grid construction site in real time, carrying out the preprocessing, and carrying out the storage through a distributed storage system; generating a comprehensive evaluation report by using the residual neural network and the graph convolutional network; adopting a particle swarm optimization algorithm to carry out subpackage provider selection and task allocation; predicting the construction progress through a long short-term memory network; performing image analysis on the video stream of the construction site by using a residual neural network and a single-time multi-frame detection algorithm; a Bayesian network and a multi-layer perceptron are used to predict construction risks, an isolated forest algorithm is used to carry out abnormal value detection on data, and a risk early warning report is generated and notified to related personnel. According to the invention, big data, deep learning and reinforcement learning technologies are fully combined, the power grid construction subpackage management and control method based on big data is described in detail, and the method has the advantages of high construction efficiency, accurate risk prediction and resource optimization.

A video processing method is provided. The video processing method obtaining a clip representation based on a frame index and a global representation of an input video, obtaining a residual frame representation based on the frame index and a residual representation of the input video using a residual neural network and outputting a final frame representation generated based on the clip representation and the residual frame representation.

The invention provides an insulator defect detection method based on mixed attention and multi-scale features. By constructing a multi-scale feature extraction module and combining a bottom-up residual neural network and a top-down reverse residual neural network, the ability of the model to extract different scale features is improved. An introduced multi-head mixed attention mechanism enhances the attention of the model to details and overall information through the combination of local attention and global attention. An improved Transform framework is combined with a multi-head mixed attention and Hungary bisection matching algorithm, so that the target distribution and detection precision is optimized, and the small defect recognition capability of the model under a complex background is improved. According to the method, high-precision detection is realized at low calculation cost, and particularly, the method has a remarkable detection effect and practical application value when being used for coping with multiple targets, complex backgrounds and small defects.

The invention discloses an Alzheimer's disease deep joint learning diagnosis method based on multi-modal feature fusion, and provides a new method for constructing a 3D fusion image through multi-modal feature fusion of an MRI-p value under the condition that a 3D image structure is not damaged. End-to-end deep joint learning diagnosis based on a residual neural network and an attention mechanism is planned to be constructed, and feature information and position information related to AD are automatically learned to obtain a classification basis of diagnosis. Experiments include classification of three levels, respectively, disease diagnosis based on AD and HC, AD and MCI, and MCI and HC. By introducing gene data, feature information of disease diagnosis can be expanded, and more comprehensive feature representation is formed, so that a diagnosis model is promoted to better capture complex features of diseases. And inputting the single-mode MRI into the deep joint learning diagnosis model to carry out an experiment so as to verify the effectiveness of the multi-mode fusion image information.

The invention belongs to the field of tunnel engineering construction, and provides an anomaly detection method and system before shutdown of a shield tunneling machine, and the method comprises the steps: collecting and preprocessing multi-system sensor data of the shield tunneling machine; performing grouping, feature extraction and dimension reduction processing on the data by adopting a hierarchical hybrid dimension reduction strategy; a multi-scale space-time attention residual error neural network model is constructed and trained; and real-time monitoring and shutdown early warning are carried out on the operation state of the shield tunneling machine. Experiments prove that the accuracy rates of the method on four test sets all exceed 95%, the F1 score is 0.90 or above, and the abnormal state of the shield tunneling machine before shutdown can be accurately predicted. According to the method, engineers can take measures in advance, construction period delay and economic loss caused by sudden shutdown are avoided, the safety and efficiency of shield construction are improved, and the method has important significance in promoting shield tunneling machine construction intelligentization.

The invention provides a rock image classification method based on attention guidance and multi-feature fusion, and the method comprises the following steps: (1) constructing a rock data set, carrying out the data enhancement of the data set, and dividing the data set into a training set and a test set; (2) constructing a residual neural network ResNet-50, inputting a prepared training set into a network structure for training, and extracting third-stage features, (3) inputting the third-stage features into a space-channel attention module, and outputting spatial features # imgabs0 # and channel features # imgabs1 #, (4) inputting # imgabs2 # and # imgabs3 # into a multi-feature fusion prediction module for classification, and outputting identified rock type names; (5) verifying by using the test set to obtain a trained rock image classification model; and (6) identifying and classifying the rock image by using the rock image classification model to obtain the name of the rock type. The classification method is high in precision, the precision rate is 97.03%, the recall rate is 96.42%, and the F1 score is 96.72%.

The invention discloses an RIS-assisted indoor fingerprint positioning method based on a residual neural network, which is suitable for an RIS-assisted downlink multipath transmission SISO millimeter wave positioning system, and the system comprises a base station, an RIS and a user. The method is realized through the following steps: defining a received signal matrix of a user, including three-dimensional positions of a base station, an RIS, the user and a scatterer; normalizing the received signal matrix of the user to obtain a real value matrix as a sample; adjusting a three-dimensional position of a user in an indoor environment, recording a real three-dimensional position as a label, constructing a data set, and dividing the data set into a training set and a verification set; performing off-line training on the residual neural network by using the training set, optimizing network parameters and storing an optimal weight; in an actual positioning scene, processing a real-time received signal matrix, inputting the processed real-time received signal matrix into the trained model, and outputting a predicted three-dimensional position of a user; according to the invention, the RIS and the residual neural network are combined, the precision and robustness of indoor positioning are improved, and rapid positioning is realized.

The present disclosure belongs to the technical field of health status assessment of secondary circuits in power systems, and specifically relates to an image recognition method for a secondary circuit terminal based on contrastive learning and an improved CRNN. The method includes: step 1: pre-training sample data of a secondary circuit terminal block of a power system through the contrastive learning; step 2: improving a feature extraction layer of a CRNN by using a residual neural network; and step 3: introducing an ECA-Net on the basis of the step 2 to construct a recognition model for the secondary circuit terminal based on the contrastive learning and the improved CRNN. In the method of the present disclosure, an image of the secondary circuit terminal block can be accurately recognized, and the accuracy of image recognition, detection accuracy and detection efficiency can be greatly improved.

The invention provides an electricity meter running state online calibration method, which relates to the technical field of electric power metering, and comprises the following steps: acquiring voltage signals and current signals of an electricity meter to be calibrated under different load conditions, and extracting instantaneous phase characteristics and instantaneous amplitude characteristics of the voltage signals and the current signals; a voltage feature sequence and a current feature sequence are obtained, and a deep residual neural network model is constructed based on a load feature vector to output a dynamic compensation parameter matrix, so that online calibration is performed on a measured value of the electric meter. Therefore, the accuracy and the real-time performance of ammeter calibration under the complex load condition can be remarkably improved, the influence of environment change and nonlinear load characteristics on the calibration result is effectively avoided, and the long-term metering reliability of the ammeter and the operation efficiency of a smart power grid can be improved.

The invention discloses a sonar image classification method based on high and low frequency combined features, and the method comprises the steps: obtaining a to-be-recognized sonar image, inputting the to-be-recognized sonar image into a trained image classification network, and outputting a target classification result in the sonar image; the image classification network comprises a wavelet transformation module, a residual neural network, a bidirectional cross attention mechanism module, an adaptive fusion module and an output module, wherein the wavelet transformation module is used for transforming an input sonar image into a high-frequency sonar image and a low-frequency sonar image; the residual neural network has a high-frequency branch and a low-frequency branch which are parallel and is used for extracting high-frequency features and low-frequency features; the bidirectional cross attention mechanism module is used for performing interaction and complementation on the high-frequency features and the low-frequency features; the self-adaptive fusion module is used for performing deep fusion on high-frequency feature maps and low-frequency feature maps output by the high-frequency branch and the low-frequency branch; and the output module is used for classifying the fused image features and outputting a classification result of the target.

The invention provides a mineralogical substance composition testing method and system based on multispectral data fusion. The method comprises the following steps: separating out a first characteristic interference signal caused by the oxidation state of an iron element and a second characteristic interference signal caused by the oxidation state of a manganese element by adopting wavelet transform in a superposition region of a Raman spectrum signal and a visible light absorption spectrum; performing spatial weighting on the intensity of the first feature interference signal and the intensity of the second feature interference signal to construct a multi-dimensional feature vector, inputting the multi-dimensional feature vector to a pre-trained residual neural network, and combining a radioactivity attenuation parameter measured by a gamma spectrometer to determine the radioactivity attenuation of the first feature interference signal and the second feature interference signal. And generating a mineralogical substance composition test result containing a mineral phase, an isomorphic substitution ratio, color cause analysis data and a radiation safety level. According to the method, the collaborative interpretation of the multispectral data and the radiation parameters can be realized, the mineral component analysis precision is improved, the color formation mechanism is synchronously analyzed, and the radioactive risk level is quantitatively evaluated.

The invention relates to the technical field of remote maintenance of a power distribution cabinet, in particular to a remote maintenance system of an intelligent power distribution cabinet, which constructs a component operation parameter matrix by collecting current, voltage, component temperature, starting time and internal and external environment data of the power distribution cabinet in real time, and combines environment parameters of the power distribution cabinet to maintain the power distribution cabinet. And carrying out deep learning training by using a residual neural network algorithm. The method not only can detect common fault modes, but also can identify abnormal conditions caused by component aging, so that the problems of false alarm and missing alarm in a traditional fault detection method are solved. Through the residual neural network, the system can automatically learn normal and abnormal operation modes from historical data, and the accuracy of fault detection is improved. And the exception type is further pushed to the operation and maintenance personnel and is visually displayed, so that the judgment time and the round-trip times of the operation and maintenance personnel on the maintenance component are saved, and the maintenance efficiency is improved.

The invention discloses a bridge damage identification method under a moving load. The method comprises the following steps: 1, substituting bridge damage displacement data obtained through finite element simulation into a residual neural network to obtain a predicted damage reduction coefficient; 2, based on a Newmark-beta method, embedding available physical knowledge of a bridge structure into a feature learning process, and substituting a damage reduction coefficient obtained by network prediction into a physical equation to obtain predicted damage displacement data; 3, substituting the solved damage reduction coefficient and displacement damage data into a loss function to obtain a loss value, and updating network parameters; and 4, predicting bridge damage by using the trained physical guidance residual neural network. The method has high damage identification precision under the condition of considering the uncertainty of the vehicle weight and the uncertainty of the bridge structure parameters, and can improve the accuracy of damage identification of the network when the actually measured data is less.

The invention discloses a visual detection test method for damage cracks of a solidified soil test piece, and particularly relates to the technical field of geotechnical engineering material detection. The method comprises the following steps: doping fluorescence labeling particles in a solidified soil test piece, and applying periodic load to induce crack formation after curing and forming; synchronously exciting fluorescent particles through an ultraviolet excitation light source, and collecting a short-wave fluorescence response image sequence; inputting the image sequence into a deep residual neural network model, identifying a nonlinear enhancement region of a fluorescence signal, and deducing a crack initiation position and a propagation path; constructing a three-dimensional dynamic model of crack evolution in combination with an image space reconstruction algorithm and time sequence comparison, extracting indexes such as a crack propagation rate, a bending angle and crack density, performing comparative analysis on the indexes and initial parameters of a material, evaluating a microstructure damage development mechanism, and outputting a visual damage evolution result; the method provided by the invention can realize high-precision, non-destructive and dynamic detection of the fine cracks in the solidified soil, and has the advantages of high identification sensitivity, strong modeling precision and good engineering adaptability.