44 results about "Defect reconstruction" patented technology

The invention belongs to the field of computer vision and industrial defect detection, and discloses a steel coil end face defect detection method and system based on CBAM-BiFPN and multi-loss optimization, and the method comprises the steps: image preprocessing and region extraction: extracting a steel coil end face region through OpenCV and other image processing methods; dividing the high-resolution image into a plurality of small blocks and performing data enhancement; the method comprises the following steps: constructing a YOLOv11 network based on CBAM-BiFPN, introducing a CBAM attention mechanism and BiFPN feature fusion structure, and constructing an improved YOLOv11 detection network; multi-loss function joint optimization training is carried out, and model training is carried out in combination with loss functions such as Focal Loss and WIoU; and fusion of detection results and defect reconstruction output: reconstructing original image defects of all tile image detection results in a space coordinate mapping and redundant region fusion mode, and realizing high-precision overall detection output. Compared with a traditional method, the method still has the high recognition capability in a complex background and low-contrast scene, the detection precision and stability are obviously improved, and higher industrial adaptability and practical value are achieved.

The invention provides a cranio-maxillofacial hard tissue deletion repair method based on a general repair model, and relates to the technical field of jaw defect reconstruction, the method comprises the following steps: constructing a cranio-maxillofacial hard tissue general repair model by using a plug-and-play conditional attention mechanism and a query generator based on curvature perception; inputting the cranio-maxillofacial hard tissue point cloud data into a cranio-maxillofacial hard tissue general repair model, and training by using a weighted loss function to obtain a trained cranio-maxillofacial hard tissue general repair model; performing de-noising processing on the missing repair point cloud features to obtain de-noised missing repair point cloud features; and carrying out point cloud gridding modeling processing by using the denoised deletion repair point cloud features to obtain a cranio-maxillofacial hard tissue deletion repair result, and completing the deletion repair of the cranio-maxillofacial hard tissue. The problem that repair and reconstruction of hard tissues at the head part are difficult to solve uniformly is solved.

The invention relates to a defect detection method and system based on multi-modal feature fusion. The method comprises the following steps: acquiring multi-modal data of a transformer; predicting based on the multi-modal data through the fusion prediction model, and outputting an elastic modulus distribution diagram of the insulating material in the transformer; carrying out super-resolution enhancement on the elastic modulus distribution diagram based on a physical constraint diffusion model; and positioning the defects of the transformer through a time reversal algorithm on the basis of the internal Young modulus distribution and the super-resolution elastic modulus distribution diagram of the transformer. According to the invention, the problems of feature loss, large single modal error, fuzzy fractal defect reconstruction, insufficient defect positioning precision and the like caused by signal attenuation in traditional detection are solved. According to the method, the signal-to-noise ratio and modulus distribution prediction precision of the signal is remarkably improved, micron-order super-resolution reconstruction is achieved, winding deformation and insulation layering are accurately distinguished, harm is quantified, traditional imaging limitation is overcome, and a high-precision and physically consistent basis is provided for transformer state evaluation and maintenance.

The invention relates to the technical field of semiconductor manufacturing and detection, and discloses a wafer defect detection data processing method and system.The wafer defect detection data processing method comprises the steps that a structured random measurement matrix is constructed based on wafer surface characteristics, and compression measurement data is collected; identifying local manifold structures corresponding to different defect types by using a spectral clustering algorithm; constructing a multi-scale image Laplacian operator, and extracting defect geometric characteristics; performing differential reconstruction processing according to the defect type, and solving an optimization target containing a nuclear norm and a graph Laplacian regularization item; dynamically adjusting a sampling strategy based on reconstruction quality evaluation; according to the method, high-precision defect reconstruction under a low sampling rate is realized, the data processing efficiency is improved, the complex defect reconstruction quality is improved, the method adapts to diversified defect processing, the storage and transmission burden is reduced, and the computing resource allocation is optimized.

The invention provides a wafer defect detection method and device, and belongs to the technical field of semiconductor manufacturing. The wafer defect detection method comprises the steps that defect data of discontinuous defects on the surface of each wafer are acquired, and the defect data comprise the positions, sizes and types of the discontinuous defects; processing the defect data by using an image reconstruction algorithm, and reconstructing the discontinuous defect into a defect in a complete form; analyzing the spatial distribution characteristics of the defects in the complete form by utilizing a spatial clustering algorithm, and judging whether a preset defect distribution mode exists or not; if the preset defect distribution mode exists, calculating a risk score of the wafer according to the defect distribution density, the defect size and the defect distribution rule by utilizing a defect identification model; and comparing the risk score of the wafer with a preset risk threshold, and if the risk score is greater than the preset risk threshold, determining the wafer as an abnormal wafer. According to the invention, the discontinuous defect of the wafer can be detected.

The invention discloses a method and a system for detecting fan blade defects based on computer vision. In computer image visual inspection of the fan blade, the shooting visual angle of a camera and the fan blade are of a three-dimensional structure with curvature, so that the shot image of the fan blade is distorted and deformed, and the defect identification precision is influenced. Therefore, by adopting a Mosaic data enhancement technology, the shot image of the fan blade is corrected according to the curvature of the fan blade, so that the analysis precision of subsequent blade defects is improved. In addition, an attention module CBAM is introduced, so that the detection efficiency of the visual image of the blade is improved; by improving the three-dimensional defect reconstruction method, the three-dimensional defect reconstruction precision of the fan blade is further improved; by subsequently introducing laser detection equipment and ultrasonic detection equipment, the accuracy of blade defect detection is further improved by adopting a fusion judgment method.

The invention discloses an industrial detection metal part internal tiny defect quality evaluation method, and relates to the technical field of metal part quality detection, and the method comprises the steps: employing a Peephole-LSTM model to carry out the dynamic weight distribution of the credibility coefficient of multi-modal data, carrying out the fusion, generating a defect feature pattern of a metal part, and carrying out the calculation of the defect feature pattern of the metal part; carrying out local CT scanning based on the defect feature map of the metal part to obtain metal part defect reconstruction data, calculating the equivalent diameter, the maximum sectional area and the volume of the metal part defect based on the metal part defect reconstruction data, obtaining defect quantization parameters, and calculating the defect quality score of the metal part according to the defect quantization parameters. And dividing quality grade intervals for comparison based on the defect quality score of the metal part, and obtaining a quality evaluation result of the metal part. According to the metal part quality evaluation method, the safety and reliability of the high-precision advanced equipment metal part in actual service are effectively guaranteed.

The invention provides an additive repair blade high-cycle fatigue limit prediction method based on random defect probability distribution, and relates to the field of aero-engine fan and compressor blade maintenance, and the method comprises the steps: obtaining the defect distribution of a real blade; establishing a prediction model based on a critical distance theory; according to the prediction model, critical distances of the multiple real blades are determined, and a first critical distance is generated; performing defect reconstruction based on the defect distribution of the real blade to generate a virtual blade; obtaining the first high-cycle fatigue strength of the virtual blade according to the defect distribution of the virtual blade, the first critical distance and the prediction model; respectively determining a plurality of defect parameters and a Pearson coefficient of the first high-cycle fatigue strength, and screening a first parameter significantly related to the first high-cycle fatigue strength; constructing a fatigue strength evaluation model; and inputting the first parameter into the trained fatigue strength evaluation model, and outputting the predicted high-cycle fatigue strength. According to the scheme, the high-cycle fatigue limit of the blade can be quickly predicted, and the prediction accuracy is improved.

The invention discloses a multi-data fusion boiler pipeline outer wall defect detection method and system, and belongs to the technical field of boiler pipeline defect detection.The method comprises the steps that three types of original data of the outer wall of a boiler pipeline are obtained; if the data are point cloud data, converting the data into a depth map; performing feature extraction on the three types of original data through three independent encoders of a multi-branch feature extraction layer, and performing channel standardization and scale alignment operation through a standardization layer after extraction to obtain corresponding visible light features, infrared features and depth features; adaptive fusion is carried out through a cross-modal attention mechanism of a cross-modal feature fusion layer, and fusion features are obtained; performing feature processing through the multi-scale residual fusion layer, and outputting a defect region mask; and performing three-dimensional defect reconstruction based on the depth map and the defect area mask to obtain a detection result of the boiler pipeline outer wall defect. According to the invention, high-precision and high-robustness defect detection under complex working conditions can be realized.

The present invention provides a method for repairing craniofacial hard tissue loss based on a universal repair model, which relates to the technical field of mandibular defect reconstruction. The method utilizes a plug-and-play conditional attention mechanism and a curvature-aware query generator to construct a universal craniofacial hard tissue repair model. Point cloud data of craniofacial hard tissue is input into the universal craniofacial hard tissue repair model and trained using a weighted loss function to obtain a trained universal craniofacial hard tissue repair model. Denoising is performed on the missing repair point cloud features to obtain denoised missing repair point cloud features. Point cloud meshing is performed using the denoised missing repair point cloud features to obtain a craniofacial hard tissue loss repair result, thereby completing the repair of craniofacial hard tissue loss. The present invention solves the problem of the difficulty in uniformly addressing hard tissue repair and reconstruction in the skull.

This invention discloses an electromagnetic eddy current defect imaging method and system based on parameter level sets. The method includes optimizing the parameters of an array of eddy current sensors; acquiring data from the metal component under test to obtain eddy current response signals under different excitation-reception conditions; reconstructing the three-dimensional defects based on a parameter level set reconstruction algorithm; setting the location of discrete point sources, the conductivity values ​​of the metal and defects, and the initial coefficient parameters of the basis functions; inputting the eddy current response signals into the level set reconstruction algorithm model to obtain the defect reconstruction objective function based on the parameter level set; calculating the Jacobian matrix and iteratively solving the objective function using the Gauss-Newton method, performing iterative updates, and determining whether the defect reconstruction has converged based on whether the deviation between the reconstruction results before and after the iteration is less than a threshold; and obtaining the final defect imaging result. This invention is easy to implement and does not require a mechanical scanning device; it can acquire information on internal surface defects of metal components through computational imaging.

The invention relates to the technical field of data processing, in particular to a 3D printing material defect detection method and system based on multi-sensor fusion. The method comprises the steps of capturing thermal radiation flux and a pose change track, extracting thermodynamic divergence and a transient motion vector, constructing a spatial delay compensation coefficient by combining a heat exchange dissipation coefficient, generating a priori estimation set by a feedforward correction state prediction matrix, constructing a divergence suppression factor according to a transient temperature change rate, and multiplying the divergence suppression factor into a covariance prediction link. Filtering to generate a posterior estimation set, extracting a reflectivity optical gradient for cross-domain verification, mapping an optical reference and calculating a residual matrix, superposing a high-frequency residual to the posterior estimation set, generating a defect reconstruction set, and analyzing the set to output defect space coordinates and morphology distortion information. According to the invention, the printing material defect detection precision is obviously improved.

The application discloses a kind of based on CT scanning image's additive repair blade fatigue failure analysis method.Combining the way of CT technology and optical microscope is used to carry out defect test analysis and crack imaging to additive repair titanium alloy blade, establish the correlation law between the defect characteristics of titanium alloy blade additive repair area and fatigue performance.First, utilize high-resolution CT technology to carry out nondestructive testing to blade, carry out global defect reconstruction to the leading edge of additive repair titanium alloy blade, obtain the distribution characteristics of defect parameters by statistical analysis;Analysis of defect-related fatigue source and crack propagation behavior, combined with defect-dependent additive repair blade high-cycle fatigue life (limit) model, establish a kind of fatigue failure analysis method based on CT scanning image.Through the method, key defects can be accurately identified and its influence on blade service life is predicted, so as to provide scientific basis and theoretical guidance for repair and reuse of aero-engine blade.

The invention discloses an iliac defect reconstruction device and a preparation method thereof, the iliac defect reconstruction device comprises an implant, the implant comprises a biological implant, the shape of the biological implant is matched with the shape of a bone defect part; the memory metal bracket is embedded in the biological implant; the memory metal stent is formed by mutually connecting a plurality of tubular structures; wherein the memory metal stent can be molded into a first form at a first temperature, and is embedded and mounted in the biological implant in the first form; the memory metal stent deforms into a second form at a second temperature so as to generate stress stimulation on the biological implant; the first temperature is lower than the second temperature; and an embedding groove matched with the first form is formed in the biological implant. The ilium defect reconstruction device provided by the invention has multiple functions of personally adapting to a bone defect part, stimulating new bone growth and mechanically stabilizing.

The application discloses a kind of based on computer vision fan blade defect detection method and system.In the computer image vision detection of fan blade, due to the shooting angle of camera and fan blade itself is the solid structure with curvature, will cause the image of fan blade shooting to produce distortion, to affect the precision of defect identification.Therefore, the application corrects the shooting image of fan blade according to the curvature of fan blade by adopting Mosaic data enhancement technology, to improve the analysis precision of subsequent blade defect.In addition, the application also improves the detection efficiency of blade visual image by introducing attention module CBAM;By improving the three-dimensional reconstruction method of defect, the three-dimensional defect reconstruction precision of fan blade is further improved;By subsequent introduction of laser detection equipment and ultrasonic detection equipment, the accuracy of blade defect detection is further improved by using fusion judgment method.

The invention relates to the technical field of nondestructive testing, and particularly discloses a bent plate defect reconstruction method based on an SH and Lamb guided wave inverse scattering method, and the method comprises the following steps: S1, solving a semi-analytical Green function in a bent plate; S2, constructing an equation between the Green function and a scattering coefficient; s3, reconstructing the defects in the bent plate: introducing Born approximation by utilizing an integral equation between the deduced semi-analytic Green function and scattering displacement, replacing a total field with a background field, introducing a defect index function as an unknown number into the integral equation, solving the unknown number by utilizing a moment method, and calculating the defects in the bent plate; and reconstructing the position and the shape of the internal hole or the surface thinning defect of the bent plate. According to the method, only a small number of ultrasonic excitation probes and receiving probes need to be arranged at the port, the position and shape of the defect can be accurately positioned through the change of the excitation frequency range and related mathematical analysis, and the method has very high utility value in engineering.

The invention discloses an electromagnetic eddy current defect imaging method based on tight-supported radial basis function sparse representation, which comprises the following steps: acquiring eddy current response signals of different excitation combinations, and realizing three-dimensional reconstruction of defects by adopting a tight-supported radial basis function sparse representation algorithm; setting the position of a sparse representation primary function, and carrying out sparse representation on the conductivity distribution through a tightly-supported radial primary function; inputting the eddy current response signal into a tightly-supported radial basis function sparse representation algorithm to obtain a defect reconstruction objective function of tightly-supported radial basis function sparse representation; the fitting coefficient vector is iteratively solved according to the measured value through the SART algorithm, the objective function is solved, and whether defect reconstruction is converged or not is judged according to whether the deviation of two reconstruction results before and after the iteration process is smaller than a threshold value or not; a final defect reconstruction result is output by conducting multiple times of iteration updating on the coefficient of the tightly-supported radial basis function, and defect information is obtained. According to the method, the distribution information of the near-surface defects of the metal component can be obtained only in a computational imaging mode without the help of a mechanical scanning device.

The invention belongs to the technical field of defect detection, and particularly relates to a defect reconstruction method applied to phased array ultrasonic detection of a spinning shell. Aiming at the problems of difficulty in feature extraction and multi-direction detection and reconstruction of spinning textures in phased array ultrasonic detection of spinning shell defects, noise interference caused by the spinning textures is effectively inhibited by adopting a multi-channel blind separation processing method provided by the invention, and the feature echo extraction effect is improved; and in combination with data in four directions, a position reconstruction algorithm based on a geometrical relationship is established, and reconstruction of a workpiece structure and defects is realized.

A computer-implemented method for automated orthopedic prosthesis design includes the steps of receiving at least one medical image of a patient's bone, generating a three-dimensional (3D) model of the bone from the at least one medical image, determining a defective region in the bone, generating a defect reconstruction model, generating a 3D prosthesis model corresponding to the defect reconstruction model, and generating a 3D prosthesis model corresponding to the 3D prosthesis model. Wherein the 3D prosthesis model is patient-specific.

The present invention provides a detection method and system for the inside of a switch cabinet based on defect reconstruction technology, which relates to the field of defect detection technology, including obtaining a cross-sectional boundary temperature curve at the position of the highest temperature point, and using the cross-sectional boundary temperature curve as the temperature input for defect reconstruction and positioning; using a multi-layer equivalent analysis module for processing, and using a multi-layer rectangular parallelepiped structure model as a model input for defect reconstruction and positioning; simulating defects occurring during material manufacturing to obtain prior information on material defects; obtaining preliminary positioning information on potential defects inside the switch cabinet; using known quantities to correct the result value of the piecewise polynomial singular value truncation decomposition method to obtain a corrected result; determining the reconstruction and positioning result of the defect inside the switch cabinet, and clarifying the location and type of the defect based on the reconstruction and positioning result. The beneficial effects of the present invention are to improve the intelligent level of defect detection and realize comprehensive monitoring and management of complex engineering structures.

The invention discloses a plastic production quality defect detection method based on image detection, and relates to the technical field of image detection, and the method comprises the following steps: executing refractive index estimation and light path inversion calculation on light offset characteristics, and generating a light path correction image; performing illumination normalization, local contrast enhancement and texture gradient extraction on the light path correction image to form a candidate area image containing a defect candidate area; and inputting the candidate region image into a self-supervised reversible reconstruction network for secondary reconstruction to generate a corresponding candidate region reconstruction image, and calculating a defect reconstruction difficulty score based on a pixel residual between the candidate region image and the candidate region reconstruction image. According to the method, the candidate region image is input into the self-supervised reversible reconstruction network, and the defect reconstruction difficulty score is constructed based on the reconstruction error, so that the refined quantitative expression of the authenticity performance of the candidate region in the image detection process is realized.

The invention relates to the technical field of nondestructive testing and intelligent signal processing, in particular to a reinforcing steel bar signal suppression and reinforced concrete structure defect reconstruction method and system. Feature modeling is carried out through a Transform architecture, a dynamic attention mask mechanism is introduced, explicit modeling and suppression are carried out on steel bar echoes, meanwhile, defect related features are enhanced, and the problem that defect information is prone to being lost due to the fact that a traditional method depends on artificial experience parameters or simple filtering is solved. Meanwhile, weak reflection defect signals such as cracks and cavities in the concrete are enhanced and spatially reconstructed on the basis of inhibiting the interference of the reinforcing steel bars, so that a reconstruction result has higher definition and interpretability, and the imaging quality and defect identification reliability of the ground penetrating radar in a complex reinforcing steel bar environment are improved. Besides, an end-to-end trainable network structure is adopted, so that the method has good generalization ability and anti-noise performance, can adapt to detection scenes in different structural forms and different construction environments, and has high engineering application value.

The invention provides a mandible defect reconstruction method and device. The method comprises the following steps: acquiring to-be-processed CT (Computed Tomography) data; the to-be-processed CT data comprises CT data of a defective mandible; inputting the to-be-processed CT data into a pre-trained jaw segmentation model, and extracting three-dimensional structures of a mandible, an upper jaw and teeth from the to-be-processed CT data to obtain target three-dimensional data; inputting the target three-dimensional data into a pre-trained jaw reconstruction model, and performing defect completion on the target three-dimensional data to obtain completed target three-dimensional data; wherein the jaw segmentation model is obtained by training marked CT data samples based on a neural network; the jaw reconstruction model is obtained by training a mandible three-dimensional data sample segmented by a computer based on a neural network. According to the method, the jaw segmentation model is used for segmenting the CT data, the jaw reconstruction model is used for reconstructing and complementing the segmented data, the universality is good, and the precision is high.

The invention discloses a 3D printing Ti metal bone trabecular acetabulum reconstruction pile and an operation method thereof, the 3D printing Ti metal bone trabecular acetabulum reconstruction pile comprises a plurality of reconstruction piles corresponding to the ilium, the pubis and the ischium, and adaptive acetabular cup prostheses are arranged between the reconstruction piles; the reconstruction pile comprises a pile body, one end of the pile body is a conical head end, the other end of the pile body is a tail end, a hollow hole channel allowing a guide pin to penetrate through is formed in the pile body in the axial direction, holes are distributed in the side wall of the pile body, and the stable foundation of the acetabulum is expanded to normal sclerotin of the ilium, the ischium and the pubis. The reconstruction pile is arranged in the medullary cavity of the part to form stable support, the bone cement is connected with the acetabular cup prosthesis, the shape and degree of acetabular bone defects do not need to be considered, the method is suitable for reconstruction of all types of acetabular bone defects, and the problem that a traditional method is limited in adaptation range is solved.

The present application relates to the technical field of image data processing and three-dimensional image reconstruction, and discloses a complex curved surface pipe defect reconstruction method, system and medium, comprising: collecting annular multi-view projection fringe images of a complex curved surface pipe, generating fringe images and initial three-dimensional point clouds, and converting the point clouds to a unified three-dimensional coordinate system under a clamp reference; extracting fringe centers, recording fringe image quality data and collecting optical path data; reconstructing a defect-free reference pipe curved surface based on a point cloud with measurement data and determining reference curved surface data; calculating point cloud measurement reliability and pipe curved surface defect residual determination values according to fringe image quality data, collecting optical path data, reference curved surface data and signed normal residual, generating a defect starting point set, a defect connected region and a defect boundary; performing secondary curved surface reconstruction in the defect connected region to obtain defect area reconstruction point clouds, and generating a complex curved surface pipe defect three-dimensional model and a single-channel defect depth map.

The present application relates to a kind of bridge underwater pile pier structure defect reconstruction methods based on laser scanning device, including laser scanner and with laser scanner connection and drive its with annular first guide rail sliding drive unit, first guide rail vertical sliding connection in a detection frame, second guide rail is fixed on the inner wall of detection frame and is extended vertically to be used for the sliding of first guide rail, the second guide rail is vertically provided with screw rod and first guide rail is driven to slide by it, the depth data of pile pier apparent defect site is obtained by the above device, data is processed in combination with coordinate conversion, reconstructs the damage location, shape and depth of pile pier, reconstructs the apparent defect of bridge underwater pile pier structure, and then can establish numerical model to calculate and analyze.It is compared with prior art reconstruction method, the numerical model corresponding to the pile pier structure with defect can be established by the present application, to provide reliable technical support for the safety evaluation and maintenance of bridge structure.

The embodiment of the invention discloses a generation method of a grid defect transformation scheme. The method comprises the following steps: acquiring information and equipment data of a distribution network line of a target area; establishing a topology network model of the distribution network line according to the information and the equipment data of the distribution network line; determining a non-contact line and an unreasonable line in the distribution network line based on the topological network model; determining a candidate contact point set according to the non-contact line and the unreasonable line, and determining a target candidate contact point pair according to the candidate contact point set; and determining a target path of the target candidate contact point pair based on the target candidate contact point pair so as to generate a network frame contact defect transformation scheme of the distribution network. According to the generation method of the grid structure defect transformation scheme provided by the embodiment of the invention, the generation efficiency and reliability of the grid structure defect transformation scheme can be improved.

The invention discloses a circuit board defect generation and repair model construction method and system and a medium, and the method comprises the following steps: generating a diversified welding spot defect point cloud sample with a real structure through employing the adversarial learning capability of a deep convolution generative adversarial network and a three-dimensional point cloud cutting method; a diffusion model is introduced to carry out step-by-step modeling and reconstruction on a defect area, geometric details and spatial continuity of point cloud are fully recovered, and welding spot defects are repaired. The intelligent level and the industrial practical value of DI P circuit board welding spot three-dimensional point cloud defect repair are improved, the defect reconstruction capability and the image quality evaluation effect in a real industrial environment are improved, and the quality control requirement in the manufacturing process of high-precision and high-reliability electronic products can be met.

The invention provides a method for predicting fatigue strength of a metal sample based on internal defect characteristics, which comprises the following steps of: establishing a scaling model containing random ellipsoid defects, and obtaining a stress concentration coefficient through finite element simulation; extracting defect geometric features to construct a data set, and training to R2 > = 0.85 by using a machine learning model; performing micro-CT scanning on an actual sample, fitting defect point cloud into an ellipsoid by adopting an MEE algorithm, and inputting the ellipsoid into a model to predict stress concentration; and combining a small amount of fatigue test correction material parameters, and integrating a defect-free S-N curve to construct a prediction model. According to the method, three-dimensional defect reconstruction, machine learning and parameter correction mechanisms are fused, and accurate fatigue strength prediction under different service life working conditions is realized with the minimum experimental quantity by quantifying relevance between defect characteristics and stress concentration. Compared with a traditional means, the method has the advantages of being low in cost, high in precision and high in generalization, and a reliable solution is provided for engineering component service life evaluation.

The invention relates to an additive manufacturing 3D porosity detection method based on an X-ray DR image, and the method comprises the steps: carrying out the DR detection of a to-be-detected object before and after the movement through an X-ray DR detection system, carrying out the translation alignment operation of the obtained DR image, then carrying out the image erosion, binarization and translation alignment, and obtaining a binary image after translation alignment, all pore defect pairs belonging to the same isolated pore defect in the new binary image are screened out, defect distribution reconstruction is carried out on the isolated pores in a three-dimensional space, and the three-dimensional space after defect reconstruction and position information of the isolated pores in the three-dimensional space after defect reconstruction are obtained; and calculating the ratio of the pore volume per unit volume to the unit volume, and taking the ratio as the 3D porosity of the object to be detected. Therefore, the defect three-dimensional space distribution reconstruction is realized by utilizing the image of the internal volume defect of the to-be-detected object detected by the X rays, and the 3D porosity detection efficiency is improved.