41 results about "Invariant feature extraction" patented technology

The invention relates to the technical field of concrete crack recognition, and discloses a concrete apparent quality defect detection method and device based on image recognition, and the method comprises the following steps: obtaining an original image of a concrete surface, and carrying out geometric correction and registration to obtain an orthoimage; performing multi-scale invariant feature extraction on the orthoimage to obtain defect feature data; segmenting the defect candidate region based on the defect feature data to obtain a defect candidate region mask; performing defect topological structure reconstruction on the defect candidate region mask and the defect feature data to obtain a defect topological network; based on the defect topology network, extracting a set and physical parameters of defects, and classifying the set and the physical parameters to obtain defect parameter data; and integrating the orthoimage, the defect topology network and the defect parameter data to generate a defect detection result report. According to the method, the potential defect area can be accurately positioned, the extraction precision of defect features can be improved, and the accuracy of defect classification is effectively improved.

The invention discloses a photovoltaic array fault diagnosis and positioning method and system based on digital twinning and deep learning. The method comprises the following steps: constructing a photovoltaic array digital twin, synchronously collecting multi-source monitoring data and converting the multi-source monitoring data into a time-frequency spectrum; constructing a twin network model, carrying out feature learning through a triple loss function, and extracting high-discrimination depth features; an adversarial transfer learning mechanism is introduced, cross-working-condition domain invariant feature extraction is realized through adversarial training of a feature generation unit and a domain discriminator, and the diagnosis robustness is improved; a multi-source domain generalization strategy is adopted, domain invariant features and domain private features are extracted through a double-branch network, difference constraints are applied, adaptive fusion is carried out, and a generalization diagnosis model oriented to unknown working conditions is constructed; and integrating the model to a digital twinborn body to realize accurate positioning and visualization of a fault component. According to the method, the problems of low fault diagnosis precision and poor generalization ability of the photovoltaic array in data scarcity, variable working conditions and unknown environments are solved.

The invention discloses a non-contact palm vein multi-mode identification system based on deep learning. The system comprises a multi-mode image acquisition and processing terminal, a mode matching and identification decision terminal, a safety protection and anti-counterfeiting terminal and an iterative optimization terminal. The multi-modal image acquisition and processing terminal is used for acquiring palm print and palm vein images, performing dynamic calibration, image quality enhancement and preprocessing, and outputting multi-modal images; the mode matching and identification decision terminal is used for carrying out feature extraction, multi-modal feature fusion, mode matching and identification decision and outputting a final matching result; the safety protection and anti-counterfeiting terminal is used for carrying out living body detection, anti-counterfeiting monitoring and data encryption; and the iterative optimization terminal is used for realizing model lightweight, knowledge distillation, end-to-end optimization and continuous learning. According to the invention, through deformation invariant feature extraction and cross-modal attention fusion, the recognition accuracy and environmental adaptability in a complex state are improved.

The invention relates to the technical field of monitoring, in particular to an intelligent camera monitoring data storage and data enhancement processing method, which effectively solves the image quality problem under a complex illumination condition through the combination of illumination invariant feature extraction and a weighted Gaussian probability model, especially the influence of dynamic shadow, uneven illumination and the like. According to the dynamic shielding synthesis mechanism, the dynamic shielding in a real scene is simulated through a Poisson fusion method based on a semantic segmentation result and a physically reasonable shielding object generation algorithm, the limitation of a conventional fixed template shielding method is avoided, the diversity and spatial rationality of shielding objects can be better reflected, and the real-time performance of the real scene is improved. The robustness of the model to shielding is improved; according to the invention, through combination of the cross-scale residual aggregation module and the gating channel-space attention mechanism, multi-scale feature reservation and deep fusion are realized, and detail information under small targets and complex illumination can be effectively captured in a complex monitoring scene.

The invention provides a diamond wire saw steel ball detection method based on improved yov8. The diamond wire saw steel ball detection method comprises the following steps: S1, acquiring an original image of a diamond wire saw bead; labImage label images are used for marking beads, and data of a training set, a verification set and a test set are formed according to the proportion; s2, carrying out the preprocessing of the image, carrying out the zooming of the image, and carrying out the preprocessing of the image through employing an improved Retinex algorithm; s3, the yov8 model is improved, and an illumination invariant feature extractor (LIF) is added into the backbone; a CA attention mechanism is integrated in a C2f module, and a small target detection head is added and a large-scale detection head is deleted based on small bead size change, so that the small target detection head is used for detecting a bead small target; and S4, optimizing a loss function of the yolov8, improving the small target detection precision by using an improved IoU loss function, and training by using an improved yolov8 model to obtain a training result best.pt file.

The invention relates to the field of machining monitoring, in particular to a machine tool state monitoring and tool wear visual diagnosis system based on differential geometry, which comprises an industrial camera acquisition unit, a differential geometry vibration analysis module, a tool wear evaluation module, an intelligent decision module and a database module, according to the method, image and video data acquired by an industrial camera are creatively mapped to a Riemannian manifold representation space, and differential geometric features of vibration are extracted; through manifold representation construction, differential invariant feature extraction, multi-scale decomposition, manifold learning and dimension reduction, accurate recognition of a vibration state is realized. The vibration state of the machine tool is predicted based on a manifold evolution model, cutter wear evaluation is combined, the remaining service life is predicted, a non-contact monitoring method is adopted, a traditional physical sensor does not need to be installed, and the system complexity is reduced; the vibration analysis based on differential geometry improves the accuracy and robustness of feature extraction.

The invention relates to the technical field of medical image processing, in particular to a pulmonary nodule follow-up visit intelligent management system which comprises a pulmonary nodule intelligent matching and change analysis engine, a pulmonary nodule intelligent follow-up visit scheme generation engine, a cloud storage and collaborative service module, an early warning module and a user management and operation module. The surface of the pulmonary nodule is modeled into a differential manifold, accurate matching of the pulmonary nodule and quantitative analysis of small changes are achieved through a multi-scale differential invariant feature extraction framework and a geodesic distance-based change analysis technology, the system generates a personalized follow-up visit scheme based on a risk assessment model, and through a multi-stage early warning mechanism and multi-channel notification distribution, the risk assessment accuracy of the pulmonary nodule is improved. The system also adopts a GPU acceleration computing architecture, so that the processing efficiency is remarkably improved, multi-terminal cooperative operation is supported, the accuracy, intelligence and individuation of pulmonary nodule follow-up visit management are realized, and the follow-up visit efficiency and the early detection rate of lung cancer are improved.

The application discloses a water supply pipe network flow prediction method based on time-invariant feature extraction, relates to the technical field of water supply pipe network flow prediction, and discloses a water supply pipe network flow prediction model based on time-invariant feature extraction. A signal separation module obtains high-frequency signals and low-frequency signals based on time-domain signals, obtains time-invariant signals and time-varying signals based on the high-frequency signals and the low-frequency signals; then, a feature extraction module obtains time-invariant features and time-varying features based on the time-invariant signals and the time-varying signals; and a flow prediction module obtains predicted water supply pipe network flow based on the time-invariant features and the time-varying features. Through separate processing of the time-varying and time-invariant features, the respective characteristics of the time-varying features and the time-invariant features can be more accurately captured; fast Fourier transform and inverse transform are used to extract frequency domain signals from time domain signals, and the frequency domain signals are divided into time-varying signals and time-invariant signals, thereby improving the performance of the model and the accuracy of water supply pipe network flow prediction.

The invention discloses an underwater three-dimensional reconstruction method and system based on the combination of a bionic compound eye and a TetSphere technology. The calibration precision is controlled by using a re-projection error; correcting underwater image distortion by adopting a polynomial model; key points are obtained by using a scale invariant feature extraction algorithm, and cross-view feature matching is optimized in combination with geometric constraints; calculating pose transformation among views according to a feature matching result, and fusing multi-view images through a dynamic weight distribution strategy; generating a dense point cloud based on the fused data, constructing an initial spherical grid, and then driving the grid to deform by using a target function containing data fitting, smoothing and topology preserving items to approach the surface of an object; dynamically adjusting the grid resolution according to vertex curvature analysis, and performing fine processing on a high-curvature region; and finally, enhancing the sense of reality of the model through smooth optimization and illumination fusion. According to the method, the technical problems of low reconstruction precision and detail missing in the underwater complex environment are solved, the reconstruction error is less than 0.5 mm, and high-precision, high-quality and high-efficiency three-dimensional reconstruction of underwater objects or scenes is realized.

This invention discloses a method for converting remote sensing image features based on a diffusion model, comprising the following steps: acquiring remote sensing data and preprocessing it; constructing a neural network; the neural network using a stable diffusion model as its basic network, including an image perception compression module, a latent diffusion model module, and a seasonally invariant feature learning module; training the neural network in stages to obtain the final neural network; and outputting the seasonal conversion result. The method of this invention uses a stable diffusion model as the basic generation model, leveraging the powerful generation capabilities of the diffusion model to generate remote sensing images for different seasons. This method constructs a seasonally invariant feature extraction network, fully considering the characteristics of relevant features in different seasons during the seasonal conversion process to ensure sufficient remote sensing feature information. Based on the stable diffusion model, this method uses transfer learning to add an additional domain-adaptive classifier to constrain the quality of the generated images, thereby generating higher-quality remote sensing image samples.

The invention provides a fault diagnosis method for open set domain generalization under a continuous variable working condition. The method comprises the following steps: firstly, constructing a training sample with time domain data, a working condition index and a fault category index; converting the time domain data into a time-frequency domain and extracting semantic features; a class-specific semantic reconstruction module is adopted to classify the semantic features; a cross-domain alignment module is adopted to estimate mutual information of the semantic features of the training samples and the working condition indexes, and the smaller the mutual information is, the lower the working condition dependence degree is; constructing joint loss including cross-domain alignment loss; the cross-domain alignment loss constrains the feature distribution consistency between continuous domains based on mutual information minimization; back propagation training is carried out by adopting joint loss, so that the class-specific semantic reconstruction module learns and extracts the working condition invariant feature extraction capability; and performing fault classification by using the trained feature extraction module and the class-specific semantic reconstruction module. According to the method, fault diagnosis can be realized under a cross-continuous change working condition, and meanwhile, the method has the capability of identifying unknown fault types.

This invention discloses a rotation- and scale-invariant feature extraction method and system based on dual-coordinate system collaboration, belonging to the field of image processing technology. Addressing the poor matching performance of existing image feature extraction methods under rotation and scale changes, this invention employs the following scheme: The input image undergoes a logarithmic polar coordinate transformation to generate a polar coordinate image; a dual-branch network is constructed, where the feature extraction branch extracts keypoint location information in a Cartesian coordinate system, and the feature description branch extracts a polar coordinate feature map in a logarithmic polar coordinate system; the keypoint locations in the Cartesian coordinate system are mapped to their corresponding positions in the polar coordinate feature map using a coordinate mapping function, and interpolation sampling is performed to generate feature descriptors that integrate precise location information and rotation / scale invariance information; based on the feature descriptors, matching point pairs are calculated, and the spatial transformation relationship between images is determined. This invention achieves highly robust feature extraction under rotation and scale changes while maintaining high real-time processing efficiency.

The application provides a WiFi cross-domain gesture recognition method based on domain-invariant feature extraction, and relates to the technical field of WiFi cross-domain gesture recognition.The method comprises the following steps: acquiring channel state information data collected by a WiFi card; performing data preprocessing on the channel state information data to obtain a preprocessed image; inputting the preprocessed image into a domain-invariant feature extraction network fused with a channel space mixed attention module and a ConvNeXt network to extract domain-invariant features; and outputting a gesture recognition result through a classifier from the domain-invariant features.The method can effectively suppress domain shift interference without relying on target domain samples and without complex signal processing, thereby improving the accuracy and robustness of WiFi cross-domain gesture recognition.

The application discloses a multi-feature fusion radar target recognition system and method based on ensemble learning, and belongs to the technical field of radar signal classification. The system comprises: an angle invariant feature extraction network, which is used for inputting HRRP radar data of different angles, and fusing all single features of different angles by using a multi-layer sparse autoencoder to obtain angle invariant features of different angles; the multi-layer sparse autoencoder comprises an encoder layer, a deep encoding layer, a decoder layer and an output layer, and increases a regularization constraint on the basis of a mean square error function; an HRRP radar recognition network, which is used for classifying and recognizing the angle invariant features of different angles to form a classification result corresponding to the angle invariant features of each angle; and an integrated decision network, which is used for generating an identification result label of the HRRP radar data by means of a voting decision. The method disclosed by the application can directly recognize and classify HRRP data of different targets at different angles.

The invention discloses a cross-domain steganographic text recognition and analysis method and system based on multi-adversarial domain adaptation, and belongs to the technical field of network security. The method comprises the following steps: constructing a feature extractor of double heterogeneous branches, and performing fine-grained semantic feature extraction on a real text and a text in a public data set; constructing a steganography text analyzer based on the combination of a multi-adversarial domain self-adaptive domain invariant feature extractor and a discriminator based on a full connection layer, allocating a unique domain discriminator for each class, realizing cross-domain feature alignment, and updating parameters of the feature extractor and the discriminator; for the trained steganography text analyzer, a mutual learning mechanism and a feature alignment means are further used to optimize the model; and deploying a steganography text analyzer and carrying out real-time detection. Compared with a traditional single-branch method or a method without a mutual learning mechanism, the method has the advantages that the cross-domain knowledge migration efficiency is improved, and stable recognition performance can still be maintained even in a scene with remarkable inter-domain distribution difference.

The application discloses a kind of non-contact palm vein multi-modal identification system based on deep learning, including multi-modal image acquisition and processing terminal, mode matching and identification decision terminal, security protection and anti-fake terminal, iterative optimization terminal;Multi-modal image acquisition and processing terminal are used to collect palm print and palm vein image, carry out dynamic calibration, image quality enhancement and pre-processing, output multi-modal image;Mode matching and identification decision terminal are used to carry out feature extraction, multi-modal feature fusion, mode matching and identification decision, and output final matching result;Security protection and anti-fake terminal are used to carry out living body detection, anti-fake monitoring, data encryption;Iterative optimization terminal is used to realize model light weight, knowledge distillation, end-to-end optimization and continuous learning.The application improves the recognition accuracy and environmental adaptability under complex state by deformation invariant feature extraction and cross-modal attention fusion.

The application discloses a hyperspectral image anti-attack method based on invariant features, which comprises the following steps: step one, constructing a sample set; step two, pre-training a deep convolutional neural network classification model; step three, building an anti-attack model; step four, constructing a loss function of the anti-attack model; step five, iteratively training the anti-attack model; and step six, testing the trained anti-attack model. The anti-attack method can enhance the robustness of a convolutional neural network and improve the classification accuracy of a hyperspectral classification model against an anti-attack.

This application relates to the field of industrial inspection technology and discloses a method for detecting surface defects in industrial products based on an AI large-scale model. The method includes the following steps: S1, preprocessing the surface image of the industrial product to generate illumination-invariant features and multi-scale features; S2, using the AI ​​large-scale model to extract deep features from the preprocessed image and generating a multi-level defect feature map through multi-scale feature fusion; S3, optimizing the AI ​​large-scale model using knowledge distillation technology to generate a lightweight model; S4, deploying the lightweight model to an edge device for surface defect detection; and S5, optimizing the confidence level determination during the detection process by dynamically adjusting the detection threshold. By combining illumination-invariant feature extraction and multi-scale feature decomposition, the method achieves the effect of extracting detailed surface features under complex lighting conditions, solves the problem of detection instability caused by changes in lighting, and improves the robustness of the detection.

This disclosure provides a method, device, electronic equipment, and storage medium for HVAC fault diagnosis, relating to the field of fault diagnosis technology. It acquires multi-source time-series operational data of an HVAC system and performs standardized preprocessing. A multi-scale feature extraction network is constructed, containing convolutional branches with different receptive fields set in parallel and achieving adaptive fusion of features from each branch based on an attention mechanism. This network is then optimized using domain adversarial training to align feature distributions on the source and target domain datasets, thereby obtaining a domain-invariant feature extractor. Finally, this domain-invariant feature extractor is combined with a few-sample learning paradigm of metric learning to calculate feature prototypes for each category in the dataset. The fault category is determined based on the distance metric between the fault query data and the feature prototypes. Therefore, this method can solve the problems of poor model generalization and difficulty in accurately diagnosing faults in small-sample scenarios in existing technologies.

The invention discloses a multi-feature fusion radar target recognition system and method based on ensemble learning, and belongs to the technical field of radar signal classification, and the system comprises an angle invariant feature extraction network which is used for inputting HRRP radar data of different angles and fusing all single features of different angles through a multi-layer sparse auto-encoder, obtaining angle invariant features of different angles; the multi-layer sparse auto-encoder comprises an encoder layer, a deep encoding layer, a decoder layer and an output layer, and regularization constraint is added on the basis of a mean square error function; the HRRP radar identification network is used for classifying and identifying the angle invariant features of different angles to form a classification result corresponding to the angle invariant feature of each angle; and the integrated decision network is used for generating an identification result label of the HRRP radar data in a voting decision mode. According to the method provided by the invention, the HRRP data of different targets and different angles can be directly identified, classified and identified.

The application discloses a single-source domain target recognition generalization method, product, medium and equipment, relates to the field of domain adaptive target recognition, and comprises the following steps: generating a stylized image corresponding to an original image through a style feature space; encoding original image and stylized image features; jointly decoupling the original image and the stylized image features into domain-invariant features and domain-unique features; training a region candidate network using the domain-invariant features, and optimizing the network using orthogonal loss and target recognition loss functions; and inputting a complex unknown weather sea target image into the optimized network to obtain the category and position of the sea target in the complex unknown weather sea target image. The application can overcome the problems of difficulty in extracting domain-invariant features in complex weather data sets, single style generation and data generated being biased towards source domain distribution, and difficulty in method model generalization, improve the generalization ability of the model, and effectively improve the recognition ability of sea targets under different complex unknown weather conditions.

This invention provides a cross-device domain adaptation method based on domain decoupling and class confusion minimization feature alignment. The main steps include: collecting vibration signals from different devices to construct labeled source domain and unlabeled target domain datasets, and dividing them into training and testing sets; constructing a domain decoupling module based on a feature extractor with convolutional channel separation and a decoder reconstructing the input data, and constructing a classifier and domain discriminator on this basis; constraining the model's learning behavior through sample reconstruction loss, conditional adversarial domain adaptation loss, classification loss, and class confusion minimization loss, the model decouples features into domain-specific features and domain-invariant features to enhance the extraction effect of domain-invariant features, aligns domain-invariant features, and simultaneously minimizes inter-class confusion in the target domain; completing model training on the training set, and finally establishing a high-precision fault diagnosis model to achieve fault diagnosis of the target device. This invention enhances the representation performance of domain-invariant features through the decoupling module, improves feature alignment by combining conditional domain adaptation loss and class confusion minimization loss, and optimizes the classifier's classification behavior in the target domain, effectively addressing the problem of completely missing labels in the target device dataset.

The present invention discloses a learning-based Tchebichef moment invariant feature extraction method, which relates to technical fields such as image processing, computer vision, and machine learning. The specific steps are: 1) rotating the dataset image to the principal axis and moving the image coordinate origin to the image centroid to obtain a normalized image; 2) constructing a scale space for the normalized image, calculating and fusing the Tchebichef rectangles of the multi-scale images into moment features that are invariant to geometric transformations; 3) utilizing a two-stage feature learning strategy to effectively reduce the dimensionality of the moment features to obtain the final Tchebichef moment invariants; 4) feeding the moment invariants as features into an SVM classifier for subsequent tasks such as image classification or invariance recognition. The Tchebichef moment invariant recognition proposed by this method has good performance and low computational complexity, and can be applied to real-time scenarios such as face recognition and object recognition, thus having practical significance.

The invention discloses a low-duration calibration electroencephalogram decoding method and system based on invariant feature extraction, and relates to the technical field of electroencephalogram signal decoding, and the method comprises the steps: obtaining electroencephalogram data with labels, and carrying out Fourier transform to obtain amplitude information and phase information; inputting the phase information and the tag into a teacher network for training to obtain feature output of the teacher network; performing random pairing and reconstruction on the labeled electroencephalogram data to obtain reconstructed electroencephalogram data, inputting the reconstructed electroencephalogram data into a student network, and learning phase information extracted from a teacher network through the student network to obtain feature output of the student network; and acquiring real-time data, and inputting the real-time data into a student network to obtain an electroencephalogram decoding recognition result. Similarity features among different individuals are extracted through an invariant feature extraction method, when electroencephalogram signals of a new user are analyzed, the similarity features can be directly used for electroencephalogram analysis of a new subject, and the use efficiency of a non-intrusive brain-computer interface and the electroencephalogram recognition accuracy are remarkably improved.

The application belongs to the field of artificial intelligence and relates to an identity verification method, which comprises the following steps: obtaining a user voice and a face image of a user through smart glasses; performing speech enhancement processing on the user voice to obtain an enhanced voice, and performing identity verification on the user according to the enhanced voice to obtain a first verification result; inputting the face image into an illumination-invariant feature extraction model to obtain an illumination-invariant feature of the face image, and performing identity verification on the user according to the illumination-invariant feature to obtain a second verification result; extracting a facial feature of the face image, and performing identity verification on the user according to the facial feature to obtain a third verification result; and generating an identity verification result of the user according to the first verification result, the second verification result and the third verification result. The application also provides an identity verification device, a computer device and a storage medium. The application improves the accuracy of identity verification based on smart glasses.

The invention discloses an image invariant feature extraction method based on feature decoupling and a network thereof, which are used for detecting a copy image, and the method mainly comprises two parts of neural network construction and network training. The method comprises the following steps: firstly, constructing a decoupling neural network based on five network modules including an invariant feature encoder, a distortion feature encoder, a decoder, a mutual information estimation network and a feature compression module; when the network is trained, a mutual information loss function and a reconstruction loss function are used to decouple the invariant features of the image, a feature loss function is used to constrain the invariant features of the copy image to be close to the invariant features of the original image, and the invariant features of the irrelevant images are far away from each other. Further separating the features of the copy image and the irrelevant image by using a nearest neighbor sample separation loss function; according to the method, the robust low-dimensional invariant features can be extracted only by retaining the invariant feature encoder and the feature compression module in the reasoning stage.

This invention relates to the field of medical equipment management technology and discloses an intelligent surgical instrument identification and real-time inventory image analysis system. The system includes an image acquisition module, an image preprocessing module, a topological feature extraction module, an instrument identification module, a spatiotemporal trajectory analysis module, a state prediction module, and a decision support module. This system achieves high-precision identification of surgical instruments through topological invariant feature extraction technology; accurately identifies instrument usage anomalies using spatiotemporal topological manifold trajectory analysis; and achieves forward-looking prediction of instrument states based on topological manifold learning prediction technology. This overcomes the bottleneck of low accuracy in complex environments inherent in traditional image recognition methods, providing a new technical guarantee for surgical safety.

This invention relates to the fields of computer graphics and image processing technology, specifically to a 3D reconstruction system and method for a 3D unfolded image. The system includes a topological feature extraction module, a folding axis positioning module, a coordinate mapping module, a mesh generation module, an error warning module, and a 3D rendering module. First, it acquires images of the folded paper image and the target unfolded image, extracts topologically invariant feature points, and determines the position parameters of the folding axis in 3D space based on the feature point matching results. It then establishes a mapping relationship from 2D coordinates to 3D coordinates, constructs a triangular mesh, and detects fold lines. The mesh is classified, and the relationship between the normal vector and the center point is analyzed to identify erroneous folding regions. Finally, it generates a 3D model visualization result. Topologically invariant feature extraction and manifold mapping techniques are used to improve the accuracy of feature matching. Lie group transformation theory is introduced to construct an accurate coordinate mapping relationship, and an error warning mechanism based on nonlinear dynamic system theory is developed, effectively improving reconstruction accuracy and efficiency.

This invention discloses an adversarial domain-adaptive human behavior recognition method and system applicable to IMU data. The method includes: acquiring a training dataset; filtering user-dimensional and device-dimensional source domain data based on the target user's specific device; extracting features based on sensor characteristics; using an adversarial training module to simultaneously perform multi-dimensional domain-invariant feature extraction training and task classification training while ensuring dimensional differences, and validating and testing the model's performance; and performing human feature recognition and classification on the target domain data. This invention utilizes the correlation between source domain devices and target domain devices in the user and device dimensions to perform domain adaptation for newly added specific devices, thereby meeting the user's needs for human behavior recognition in the context of new devices.

The application discloses a photovoltaic array fault diagnosis and positioning method and system based on digital twinning and deep learning. The method comprises the following steps: constructing a photovoltaic array digital twinning body, synchronously collecting multi-source monitoring data and converting the multi-source monitoring data into time-frequency spectrum; constructing a twinning network model, performing feature learning through a triple loss function, and extracting high-discriminative deep features; introducing an adversarial transfer learning mechanism, performing adversarial training through a feature generation unit and a domain discriminator, realizing cross-condition-domain invariant feature extraction, and improving the diagnosis robustness; adopting a multi-source domain generalization strategy, extracting domain-invariant features and domain-private features through a double-branch network, applying difference constraints and adaptively fusing, and constructing a generalization diagnosis model for unknown conditions; and integrating the model into the digital twinning body to realize accurate positioning and visualization of fault components. The application solves the problems of low fault diagnosis precision and poor generalization ability of photovoltaic arrays in the conditions of data scarcity, variable working conditions and unknown environments.