420 results about "Feature descriptor" patented technology

The invention provides a modified metal surface defect detection method and device and a medium, and the method comprises the steps: obtaining a multi-angle reflection image sequence of a modified metal surface under the irradiation of a multi-spectral light source, and generating a defect sensitive parameter set based on a preset modified metal material characteristic database and in combination with the spectral reflectivity distribution information of the multi-angle reflection image sequence; performing cooperative feature enhancement on the multi-angle reflection image sequence and the defect sensitive parameter set, and enhancing the feature contrast of a defect area and a normal area through weight distribution to obtain an enhanced defect feature set; joint anomaly detection of a spatial domain and a spectral domain is carried out on the enhanced defect feature set, a potential defect region of the modified metal surface is obtained through identification, and a defect region feature descriptor is generated; and performing defect morphological quantitative analysis according to the defect region feature descriptors, and determining the type, position and severity level of the modified metal surface defect. According to the invention, the comprehensiveness and reliability of a defect detection result can be improved.

The invention relates to the technical field of target detection, and discloses a pet target detection method and device and a camera, and the method comprises the steps: carrying out the motion triggering collection and image enhancement preprocessing of a front end region of a feeder, and obtaining an enhanced image frame sequence; performing feature extraction of dynamic receptive field adjustment on the enhanced image frame sequence to obtain pet feature descriptors and position information; behavior time sequence feature analysis is executed, and pet behavior sequence feature vectors are obtained; constructing a state transition diagram according to the pet behavior sequence feature vector, and performing time sequence consistency analysis to obtain a pet state judgment result; power management and decision execution are carried out on the feeder based on the pet state judgment result, feeding control under the low-power-consumption condition is achieved, behavior misjudgment caused by posture fluctuation is effectively avoided, the behavior recognition accuracy is improved, the accurate feeding control problem in a multi-pet family is solved, and the user experience is improved.

The invention discloses an operation and maintenance manipulator intelligent control method and system based on visual identification, and relates to the technical field of intelligent manipulator control, and the method comprises the steps: collecting RGB image data and depth image data of an operation and maintenance operation area, and obtaining a standardized image matrix and a mapping relation matrix; inputting the standardized image matrix into an improved ResNet residual network model, generating a comprehensive feature descriptor, and calculating a spatial position coordinate and an attitude angle of the target equipment based on the mapping relation matrix; based on the current joint angle state of the manipulator, an improved Jacobian matrix inverse kinematics algorithm is used for solving a target angle sequence of each joint, a preset operation mode library is matched based on the comprehensive feature descriptor, and a grabbing force parameter and a motion speed parameter are determined; and converting the target angle sequence into a control instruction, and sending the control instruction to each joint driver of the manipulator to drive the manipulator to complete action planning. According to the invention, full-process automation from environment perception to task execution is realized.

The invention discloses a power battery health state on-line monitoring and early warning method and system based on multi-data fusion. The method comprises the following steps: synchronously acquiring multi-dimensional heterogeneous data in a battery operation process through a multi-sensor data acquisition module; carrying out standardization processing and preprocessing on the multi-dimensional heterogeneous data, extracting a comprehensive feature vector and carrying out multi-sensor data fusion; a multi-sensor data fusion algorithm is adopted to carry out weight distribution on the fused comprehensive feature vector, a dynamic weight coefficient is calculated according to the sensitivity and reliability of each parameter to the health state of the battery, and a fused battery state feature descriptor is obtained; and performing mode recognition and state classification on the fused battery state feature descriptors by using a pre-established evaluation model to realize quantitative evaluation of the health degree of the battery. According to the invention, real-time monitoring, evaluation and early warning of the health state of the battery in the whole life cycle are realized, and a reliable basis is provided for safe operation and maintenance decision of a battery system.

The invention discloses a slope cutting house building deformation monitoring method based on unmanned aerial vehicle remote sensing, and the method comprises the steps: carrying out the periodic observation of an artificial slope through an unmanned aerial vehicle carrying a three-dimensional laser scanner, and obtaining slope three-dimensional point clouds in at least two different periods; performing denoising, down-sampling and coordinate normalization on the point cloud of each period to obtain a preprocessed data set; generating a global feature descriptor of each period by using a PointNet feature extraction unit; on the basis of a Lucas-Kanade iterative optimization algorithm, the descriptors of all periods are matched with the first period as the reference, and optimal rigid body transformation parameters are obtained; completing registration of the cross-period point clouds in a unified coordinate system according to the parameters; calculating displacement by adopting point-by-point difference and forming a differential deformation field; and comparing the displacement with a preset safety threshold, positioning an abnormal area and giving a risk level. According to the method, centimeter order registration and deformation identification of the cross-period point cloud under the unified stable reference are realized, and early warning and hidden danger assessment of a slope cutting and house building scene are supported.

The invention discloses a BIM-based building engineering data processing method and system, and belongs to the technical field of digital construction of building engineering. The method comprises the steps that construction scanning point cloud and BIM model data are acquired, and a feature skeleton is extracted; constructing a dynamic local coordinate system to establish a skeleton-model mapping relation; carrying out space division by adopting a locality sensitive hash index and executing ICP registration calculation; reversely deriving an error propagation path to generate a compensation instruction; adjusting a feature descriptor and reconstructing a mapping relation; and finally, model difference comparison and dynamic updating are realized. According to the method, automatic calibration of the construction point cloud and the BIM model is realized, and the problems of low efficiency and large error of traditional manual calibration are solved.

The invention discloses a traffic monitoring video rapid target extraction method for edge equipment, and relates to the technical field of intelligent traffic video processing and edge calculation target detection, and the method comprises the steps: carrying out the adaptive downsampling processing of original video frame data, and generating downsampling video frame data; extracting a foreground target candidate region, and constructing a traffic region-of-interest mask in combination with a lane line detection result; carrying out pixel AND operation on the traffic region-of-interest mask and the foreground target candidate region to generate accurate candidate target region data, and extracting a target feature vector; carrying out weighted fusion on the target feature vector through a lightweight attention mechanism, generating a fusion feature descriptor, and calculating a target confidence score; and carrying out screening and duplicate removal processing on the accurate candidate target area data, and outputting traffic target extraction result data. According to the invention, the target in the traffic video can be rapidly and accurately extracted and processed in a low-delay manner on the edge equipment with limited computing resources.

The invention discloses a gynaecology and obstetrics emergency medical data security sharing system based on a block chain, and relates to the technical field of medical information processing. The method is used for solving the security and timeliness problems of multi-mechanism data sharing in an emergency scene. The method comprises the following steps: firstly, performing grading processing and desensitization on personal identifiers and medical data of patients through a data grading and desensitization module, and outputting data which can be safely shared; then, an on-chain evidence storage module performs windowing processing on the continuous monitoring data flow, extracts key physiological features, generates feature value Hash, constructs data feature descriptors and submits the data feature descriptors to a block chain network; the emergency access token management module realizes dynamic authorization through a smart contract, and generates a temporary access token associated with the data feature descriptor; and finally, the secure decryption and data sharing module verifies the authority based on the hierarchical decryption key, decrypts the data and compares the eigenvalue hash, and shares and records an operation log with an authorization party after ensuring the data integrity, thereby realizing efficient, secure and traceable data sharing.

The invention relates to the technical field of mineral processing visual detection, and discloses a visual analysis system for detecting the grade of a phosphorite flotation froth layer. The system comprises an image acquisition and decomposition module, a parallel feature extraction module, a dynamic feature fusion module, a foam evolution analysis module and a grade decision output module. The system performs multi-scale decomposition on a foam image, extracts physical and semantic features in parallel, constructs a dynamic fusion network based on bidirectional mapping to perform iterative interaction, and generates a multi-modal feature descriptor. Therefore, self-organizing growth of a foam evolution graph is driven, an evolution track of a key foam primitive is positioned and tracked, a foam grade state vector is formed, and finally, a regulation and control decision is output in combination with external control parameters. According to the system, deep fusion of physical and semantic features and deep analysis of the foam dynamic evolution process are achieved, the accuracy and predictability of foam grade state sensing are improved, and an effective means is provided for accurate control over the flotation process.

The invention relates to a multi-modal image matching method and system based on learning features and epipolar geometric constraints. The method comprises the following steps: carrying out edge enhancement processing on an input image through wavelet transform; extracting a multi-scale dense feature map based on the transformed convolutional neural network, and generating a feature descriptor with rotation and scale invariance in combination with principal direction normalization; adopting an FLANN algorithm and dynamic distance constraint to realize preliminary feature matching; and introducing a basic matrix construction and epipolar geometric consistency verification mechanism, and eliminating mismatching point pairs in combination with an RANSAC affine constraint model. According to the method, image enhancement, deep learning and geometric verification strategies are fused, the problems of radiation nonlinearity and geometric distortion caused by imaging mechanism differences among multi-modal images are effectively solved, the matching precision and robustness are improved, and the method is suitable for remote sensing application scenes such as optical-SAR registration, multi-source image fusion and earth surface change detection.

The embodiment of the invention discloses a building engineering crack detection method and system based on image recognition, and the method comprises the steps: obtaining a building surface image, carrying out the preprocessing of the image, obtaining a standardized image, and carrying out the multi-scale decomposition extraction and integration of various features, and forming a multi-dimensional feature descriptor set; after feature importance is evaluated, a compact feature vector is generated through dimension reduction, quantization coding and compression, and then a multi-level feature index mechanism for optimized compression is constructed. A query feature vector is extracted from a newly collected image, searching and screening are completed by means of an index mechanism and a tolerance threshold, and a crack matching result is obtained; and based on the result, positioning cracks, classifying types, measuring parameters and evaluating severity, and generating a crack state report. The crack trend is analyzed in combination with the historical data time sequence, a multi-stage early warning mechanism is designed, maintenance suggestions are provided, and a real-time monitoring and early warning system is formed. According to the embodiment of the invention, the technical problems of high storage pressure and low real-time detection efficiency in the prior art can be effectively solved.

The invention provides a method for identifying forest tree species by using laser point cloud data, and the method comprises the following steps: collecting three-dimensional laser point cloud data of a forest region, setting an elevation threshold, filtering ground points, and extracting a point cloud sample object; respectively extracting VFH, CVFH and ESF feature descriptors from the sample point cloud, and constructing three types of geometric feature vectors; performing supervised classification on the features by adopting a random forest and a support vector machine learning classifier; the output of each classifier is fused through strategies such as weighted voting, an average method or a stacking method, and a final tree species identification result is obtained; according to the method, three types of global or semi-global feature descriptors of VFH, CVFH and ESF are extracted for a point cloud sample object of a single tree, feature modeling is carried out on tree species from three dimensions of spatial attitude, local scale structure and global shape distribution, the advantage of real restoration of a target structure by using point cloud data is utilized, and the feature modeling efficiency is improved. And the problem of projection distortion of image features under multiple view angles is avoided.

The invention discloses a semantic auxiliary vision SLAM loopback detection method based on topological graph matching, and belongs to the field of computer vision. The implementation method comprises the following steps of: screening out candidate key frames without a common-view relationship by judging whether the common-view relationship exists between a current frame and each frame in a historical key frame sequence or not; and constructing a semantic topological graph, namely constructing nodes and undirected weighted edges in the topological graph and calculating node descriptors, and realizing topological expression of the key frame image by constructing the semantic topological graph and calculating a feature descriptor for each node in the topological graph. And calculating an affinity matrix, constructing the affinity matrix between the topological graphs by combining the similarity between the weights of the node descriptors and the edges in the topological graph of the current key frame and the topological graph of the candidate key frame, and calculating an incidence matrix between the nodes of the topological graphs at the same time. And calculating the topological graph similarity through the affinity matrix and the incidence matrix. And judging whether loopback detection succeeds or not by judging whether the topological graph similarity reaches a loopback detection threshold value or not.

The invention discloses a local feature detection description method based on multi-scale semantic feature fusion, and the method comprises the steps: firstly, generating a preliminary feature descriptor through homography transformation and pyramid feature extraction normal forms in combination with dynamic weight fusion; performing multi-dimensional feature fusion on the image by using parallel convolution and self-attention, and extracting richer local descriptor information from coarse to fine and from local to global; and then the robustness and discrimination capability of the features are optimized by introducing a semantically weighted triple loss function, and the global representation capability of the features is further improved. And finally, category-known global mask information is generated by using a semantic segmentation network to guide feature point screening, so that global features are more effectively captured, and interference of dynamic objects is reduced. According to the method, the feature detection description effect in a complex scene is remarkably improved, high calculation efficiency and accuracy are achieved, and the method has important practical significance on technical application of robot navigation, unmanned driving and the like.

The embodiment of the invention provides a three-dimensional space change detection method and device, equipment and a storage medium, and relates to the field of digital image processing. The method comprises the following steps: acquiring image sequences of the same area shot by the unmanned aerial vehicle in two periods; for each image sequence, performing point cloud reconstruction on the region based on the image sequence to obtain the group of point cloud data; point cloud registration is carried out according to the similarity between the feature descriptors of all the points in the two sets of point cloud data, a matching point pair set comprising a plurality of matching point pairs is obtained, and two points in each matching point pair belong to two pieces of point cloud data and are closest to each other; and for each matching point pair, geometric information of two points in the matching point pair in respective point cloud data is acquired, and if it is determined that the difference between the two pieces of geometric information meets a preset difference condition, it is determined that the corresponding position of the matching point pair in the region is changed. According to the embodiment of the invention, the problem of insufficient spatial change detection precision in a complex scene is solved.

The invention relates to the technical field of unmanned aerial vehicle image processing, and discloses a high-definition image processing and transmission method based on an unmanned aerial vehicle. The method comprises the following steps: acquiring a multi-frame high-definition image sequence obtained in the flight process of an unmanned aerial vehicle; analyzing the image sequence frame by frame, extracting key feature points and generating feature descriptors; establishing a feature matching relationship between adjacent frames, and calculating an inter-frame motion vector; constructing a global motion model according to the motion vector and performing motion compensation; performing region segmentation on the compensated image sequence to divide the image sequence into a dynamic region and a static region; performing multi-scale noise reduction on the dynamic region, and performing texture enhancement on the static region; carrying out fusion reconstruction on the processed dynamic and static regions to generate an optimized image sequence; performing layered coding on the optimized sequence according to a transmission bandwidth condition, and generating base layer and enhancement layer data; dynamically adjusting the priority of two layers of data transmission according to the network state; and sending the data to a ground receiving end through a multi-path transmission protocol.

The invention discloses a mobile robot pose estimation method based on mixed point and twin line feature re-projection joint optimization, which comprises the following steps: acquiring an RGB-D image, and extracting point and line features from two continuous frames; calculating point and line feature descriptors based on a point and line feature description algorithm, and constructing point and line feature data association; obtaining point and line feature matching pairs; performing verification in combination with depth information, dividing the point feature matching pairs into 3D-2D matching pairs and 3D-3D matching pairs, and constructing a mixed point feature re-projection error function; a virtual right eye line is constructed for the line feature matching pair, RGB and depth clues are considered at the same time, and a twin line feature re-projection error function is constructed; and constructing a joint unified error optimization model, correcting point and line reprojection errors, and estimating the optimal pose of the robot. According to the method, the optimal pose estimation with complementary advantages of point-line feature fusion is realized, and the trajectory estimation accuracy and self-positioning robustness of the robot in a complex environment are ensured.

The invention discloses an urban canyon positioning method and system fusing GNSS, vision and low orbit satellites, GNSS signals and images near a visual sign are collected in an urban canyon to serve as mapping points, and sign angular point coordinates are recorded; and analyzing to obtain a GNSS latitude and longitude list corresponding to each mark, and extracting LoFTR feature descriptors and storing the LoFTR feature descriptors in a map database. During positioning, firstly performing rough matching with the current position through the KNN, and then realizing fine positioning in the candidate area through LoFTR feature matching and homography matrix calculation; and if the matching fails, calculating a joint confidence coefficient based on the satellite PDOP / number, and estimating the current position through dynamic weighting by fusing Kalman filtering with a visual odometer. According to the method, a two-stage positioning strategy is adopted, GNSS and visual information are preferentially used for high-precision matching positioning, a fusion positioning mechanism based on low-orbit satellite joint confidence is started after failure, and the matching success rate and the positioning precision under the complex visual condition are improved.

The invention relates to the technical field of data processing, in particular to an automatic driving vehicle data processing system based on identity recognition, comprising: a data acquisition module outputting an original data stream carrying a digital signature; the preprocessing module filters illegal data streams according to the digital signature, and outputs time-aligned laser radar data and visual data; the feature fusion module outputs a six-degree-of-freedom pose estimation result; the safety processing module generates safety feature descriptors according to the cosine similarity, the timestamp difference constraint range and the encryption seeds; the verification storage module stores the Merkel tree, the encrypted point cloud and the encrypted image to a candidate node group; and the calibration module calculates a correlation coefficient between the timestamp of the visual data and the timestamp of the laser radar data, and reconfigures a hardware trigger time sequence of the data acquisition module. According to the method, the problem of cross-modal data fusion credibility caused by sensor clock skew is solved, and the identity recognition accuracy is improved.

The invention provides a multi-camera-based AI glasses FOV extension method and system, and the method comprises the steps: transmitting a synchronization signal to a plurality of cameras, enabling the plurality of cameras to carry out the exposure at the same time, and obtaining a plurality of frames of original images at the same time; pre-processing the multiple frames of original images to obtain pre-processed images; key feature points of the preprocessed image are extracted through a feature point detection algorithm, and feature descriptors are generated; through a feature matching algorithm, feature point matching is carried out on the adjacent preprocessed images by utilizing the feature descriptors, and a local transformation matrix between the adjacent preprocessed images is calculated; based on the local transformation matrix, fusing the adjacent preprocessed images to obtain a fused image of the adjacent preprocessed images; and all the fused images are spliced to obtain a large-view-field-angle image covering the target view angle, so that the method has the advantages of effectively expanding the shooting view angle, eliminating image distortion and improving the image splicing naturalness.

The application provides a large space real-time positioning method and system based on SLAM and visual graphics, relates to the technical field of space positioning and intelligent navigation, and the method comprises the following steps: acquiring a space scene image and an environment point cloud and performing pretreatment; detecting the scene image based on a deep learning target detection model, identifying a dynamic target and a corresponding category and a boundary box; reserving static space feature points of the environment point cloud and constructing an initial space point cloud map; performing ORB feature extraction on the static space feature points to obtain feature descriptors and constructing a space visual feature map; jointly optimizing the initial space point cloud map and the space visual feature map to generate a multi-modal global space map; combining space inertial measurement information to estimate the pose of the dynamic target to obtain an initial pose, and obtaining a final pose after optimization, so that the positioning accuracy and robustness in a large space dynamic environment can be improved, the consistency of the multi-modal map is optimized, and the positioning stability in a dynamic environment is enhanced.

The invention discloses a point cloud identification method based on dynamic feature fusion and full-process dynamic parameter adjustment. The method comprises the following steps: step 1, collecting an original point cloud of an industrial part and removing invalid points, constructing a training set in combination with a CAD model point cloud, calculating an average point spacing based on a k-d tree, dynamically adjusting the leaf size of a voxel grid, and generating a standardized point cloud; 2, calculating a point cloud normal vector, extracting a CVFH feature descriptor and an SHOT feature descriptor, dynamically fusing the two types of features based on the average point spacing and the spatial range of the point cloud, and carrying out smoothing processing; step 3, using the fusion features to train a KNN classification model, establishing a mapping relation between the features and target categories, and storing model parameters; 4, after the test point cloud is processed in the step 1 and the step 2, model parameters are input, and a prediction result with the highest confidence coefficient is output and output in a log. According to the method, the problem of low recognition precision caused by insufficient global and local feature capture of a complex industrial part by a single feature descriptor in the prior art is solved.

The invention relates to the technical field of composite material digital detection, in particular to a composite material skin grinding amount calculation method based on clustering analysis and a symbolic distance field, which specifically comprises the following steps: acquiring three-dimensional measurement data of the surface of a composite material skin, and designing a three-dimensional measurement point feature descriptor; based on the feature descriptors, a clustering analysis algorithm is designed, and a grinding area three-dimensional measuring point class and a non-grinding area three-dimensional measuring point class are divided; aiming at the three-dimensional measuring points of the non-grinding area, carrying out implicit curved surface reconstruction based on a radial basis function; aiming at the three-dimensional measuring point of the grinding area, a grinding area symbol distance field is constructed, and the symbol distance is the grinding amount of the measuring point; according to the method, the problem that in the prior art, profile tolerance estimation cannot be obtained during aircraft CAD mathematical model is solved, the grinding allowance of the aircraft skin repairing area can be accurately analyzed, and aircraft maintenance personnel are guided to conduct grinding. Compared with a traditional method for judging the profile tolerance based on manual touch, the method has the advantages that interference of human subjective factors is eliminated, the grinding allowance is quantified, and the precision is higher.

In various examples, epipolar constraint-based cross-camera calibration validation is disclosed. For a pair of cameras that have partially overlapping fields of view, a shared region of their overlapping fields of view may be extracted and used as the basis to perform an epipolar constraint-guided feature descriptor matching process. A camera calibration metric may be computed based on the degree to which a feature descriptor appearing at a pixel of the first image aligns as expected in the second image with an epipolar line associated with the pixel of the first image, where the epipolar line is computed using extrinsic camera calibration parameters associated with the pair of cameras. Epipolar matching may be performed for a plurality of feature points and an aggregate validation score computed based on measuring the computed deviations for each feature. A sensitivity analysis may be applied to better assess the usefulness of the validation score.

The invention relates to the technical field of goods identification of a laneway stacker, in particular to a goods identification method and system of the laneway stacker, and the method comprises the following steps: collecting a goods image; performing quality evaluation on the cargo image, and judging the degradation type of the cargo image; based on the degradation type, performing adaptive image enhancement processing on the cargo image to obtain an enhanced image; generating a feature descriptor having resistance to the degradation influence of the cargo image; inputting the enhanced image and the feature descriptor into a deep learning model for cargo identification to obtain an identification result and confidence; and performing identification process control according to the confidence coefficient. According to the method, the recognition accuracy and stability of the deep learning model can be improved, so that the problems of recognition failure and efficiency reduction caused by image quality reduction are effectively solved.

The invention discloses a high-precision satellite attitude correction method, system and equipment for a maximum initial positioning error, and belongs to the technical field of machine vision image matching. A proper reference region is selected to prepare a first reference image and a second reference image, and feature descriptors of the reference images are extracted offline; performing down-sampling on a remote sensing image acquired by a satellite remote sensing camera, and performing image matching on a real-time image after down-sampling and the first reference image; calculating the optimal window position of the ground calibration point of the reference area in the real-time image according to the matching result; cutting the real-time image according to the window position to obtain a high-resolution calibration point real-time image; performing image matching on the high-resolution calibration point real-time image and the second reference image; and calculating latitude and longitude coordinates of the center of the real-time image according to a matching result for satellite attitude correction. The position error of the target area is gradually reduced in a two-stage remote sensing image matching mode, the longitude and latitude coordinates of the center of the real-time image are accurately positioned, and high-precision satellite attitude correction is realized.

The invention discloses a screening method of insulating gas decomposition product sensing materials based on machine learning, and relates to the technical field of functional material design and gas sensing. The method provided by the invention comprises the following steps: selecting a first candidate sensing material according to an insulating gas and a decomposition product; doping elements or embedding atoms into a central cavity of the first candidate sensing material to obtain a second candidate sensing material, and constructing a candidate sensing material library; obtaining the most stable adsorption configuration and adsorption energy of gas molecules, constructing feature descriptors, forming an initial data set, and dividing a training set and a test set; constructing and training a model, and evaluating and screening out an optimal model by using a test set; predicting and screening the second candidate sensing material by using the optimal model to obtain a third candidate sensing material; and performing DFT calculation verification and performance index evaluation on the third candidate sensing material, and outputting a final candidate sensing material. The method provided by the invention is high in prediction accuracy and reliability, and a novel sensitive material can be found.

The invention discloses a method, a device, a medium and equipment for improving the positioning precision of a visual inertial odometer, and the method comprises the steps: carrying out the unified representation of point features, line features, plane features and obtained camera attitudes through a unified representation model, determining a six-dimensional attitude according to the conversion relation between the positions and directions of geometric features, and carrying out the positioning of the visual inertial odometer. Screening effective information in the six-dimensional attitude vector by using a self-binding matrix; performing feature association based on the uniformly expressed features, generating feature descriptors, and matching feature correspondence between continuous image frames; the method comprises the following steps: acquiring motion data of an unmanned aerial vehicle through an IMU (Inertial Measurement Unit), dynamically selecting an integration method and adjusting a time step length according to a current motion state and an environmental condition, and pre-integrating the data acquired by the IMU to obtain an integration result so as to estimate displacement, speed and rotation increment; by introducing the visual inertial odometer and optimizing the data processing method thereof, the positioning precision of the unmanned aerial vehicle can be improved, and the high efficiency and reliability of the unmanned aerial vehicle during task execution are ensured.

The invention relates to the technical field of power electronics, and discloses a surge voltage suppression system and a control method thereof. The system comprises a surge feature extraction unit, a suppression map generation unit, a strategy deduction and check unit and an instruction synthesis and distribution unit which are connected in sequence. According to the method, surge feature descriptors are extracted and fused with a historical case library and a real-time power grid topology, and a suppression atlas containing multi-path parameter combination is dynamically generated; and performing time sequence deduction and interaction influence calculation on each path in the map, iteratively correcting parameters to output a checked strategy sequence, and finally converting the strategy sequence into an instruction to control the action of the physical suppression equipment. According to the method, the whole process of the suppression strategy from historical experience learning, dynamic generation to global collaborative rehearsal optimization is realized, and the adaptability, the collaboration and the reliability of responding to surges in a complex power grid environment are improved.

The invention discloses a semiconductor heterojunction interface thermal resistance prediction method based on machine learning, and the method comprises the steps: collecting semiconductor material data, obtaining semiconductor intrinsic attribute data through a semiconductor public database, and carrying out the preprocessing of the data; calculating statistics of element attributes through a Magpie algorithm to obtain feature descriptors, eliminating redundant features by adopting a variance filtering method and recursive feature elimination, and normalizing the redundant features; model building and training are carried out by designing CNN and XGBoost algorithms; performing parameter optimization on the trained model through forward propagation, back propagation and a DBO algorithm; and predicting the thermal resistance of the semiconductor heterojunction interface based on the optimized model. The method solves the problems that in an existing semiconductor heterojunction interface thermal resistance prediction method, the experimental measurement period is long, the cost is high, environmental parameters are difficult to control accurately, the theoretical calculation complexity is high, and the deviation between a prediction result and an actual working condition is large due to the dependence on ideal interface conditions.