Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

117results about How to "Fully capture" patented technology

Unstructured data automatic processing method and system based on deep learning

The invention provides an unstructured data automatic processing method and system based on deep learning, and relates to the technical field of data processing, and the method comprises the steps: obtaining unstructured data through an intelligent data collector, building a data feature fingerprint database, constructing a data quality evaluation model through an incremental learning algorithm, and carrying out the data standardization processing; extracting dominant features and recessive features by using a multi-layer cascade network structure and a self-attention mechanism, and constructing a feature association graph and a bidirectional reasoning channel; and performing rule matching and causal reasoning based on the domain knowledge base, and finally realizing automatic structuring of the unstructured data. According to the method, the automation degree and the accuracy of data processing are improved, the manual intervention cost is reduced, and the method has relatively high universality and expandability.
Owner:北京科杰科技有限公司

Remote sensing data processing method and system, product and readable medium

The invention discloses a remote sensing data processing method and system, a product and a readable medium, and relates to the field of remote sensing data processing, and the method comprises the steps: carrying out the registration and correction of remote sensing images in different time periods, and obtaining a remote sensing image spatial-temporal index; calculating shadow ranges generated by each building in the target area at different times based on the building height data and the remote sensing image spatio-temporal index, and superposing the shadow ranges corresponding to the buildings to obtain a shadow coverage frequency map; calculating a shielding degree score of an area of each time phase in the shadow coverage frequency diagram based on a remote sensing image spatio-temporal index, and selecting an optimal time phase with the lowest shielding degree as an optimal observation time phase according to the shielding degree scores; based on the optimal observation time phase, dividing a region in the shadow coverage frequency diagram into a plurality of target sub-regions according to a shielding degree score; and repairing each target sub-region by adopting a preset repairing strategy according to the shielding degree score. By implementing the method, the accuracy of restoring the shadow-shielded region in the remote sensing image can be improved.
Owner:MUCHENG SURVEYING & MAPPING (BEIJING) CO LTD

Knowledge distillation multi-modal recommendation method based on modal decoupling

The invention relates to the technical field of personalized recommendation, and discloses a knowledge distillation multi-modal recommendation method based on modal decoupling, for a specific user, a trained multi-modal recommendation model can recommend articles; the training process of the multi-modal recommendation model comprises the following steps: extracting text features corresponding to text information of an article, and extracting visual features corresponding to picture information of the article; enabling the text features to pass through a text teacher network and a text student network respectively; enabling the visual features to pass through a visual teacher network and a visual student network; and then training of a multi-modal recommendation model is realized through technologies such as an attention mechanism, comparative learning and knowledge distillation. The teacher network performs supervised learning by using rich semantic information, so that multi-modal data is captured more comprehensively, information in the teacher network is smoothly transmitted to the student network through knowledge distillation, and the problem of data sparseness in a recommendation system is effectively solved.
Owner:UNIV OF SCI & TECH OF CHINA

Remote sensing image ground object segmentation method based on hierarchical feature extraction and decoding

The invention discloses a remote sensing image ground object segmentation method based on hierarchical feature extraction and decoding, which relates to the technical field of remote sensing image processing, and comprises the following steps: step 1, collecting and preprocessing a remote sensing image, and constructing a training sample set; 2, constructing an image segmentation network, wherein the image segmentation network comprises a hierarchical encoder, a receptive field module unit and a network decoder which are connected in sequence; 3, training and optimizing the image segmentation network by adopting the training sample set to obtain a remote sensing image ground object segmentation model; and 4, collecting a remote sensing image to be segmented, and inputting the remote sensing image to the remote sensing image ground object segmentation model to obtain a ground object segmentation result. According to the method, the advantages of the advanced visual basic model and the U-shaped network architecture are combined, so that rapid and accurate segmentation of the ground target is realized.
Owner:耕宇牧星(北京)空间科技有限公司

Low-light image denoising method based on local-global interactive Transform

The invention discloses a low-light image denoising method based on a local-global interactive Transform, and the method is characterized in that the method comprises the following steps: 1, carrying out the denoising of a low-light image; the method comprises the following steps: step 1, constructing an overall structure of LGIT for recovering a given degraded image; 2, a Top-N Patches selection module is used for selecting N patches most related to the target patch and providing feature input for subsequent modules; step 3, the Patch selects an attention Transform module, and the Transform module is used for carrying out global feature aggregation based on the information of Top-N Patches; and step 4, mixing the double-gate feed-forward network MDGFF for further processing the features output by the PSATB and generating a final de-noised image. According to the method, the self-attention inside the patch and between the patches is effectively calculated on different scales, and accurate removal and detail recovery of low-light image noise are realized.
Owner:ZHONGBEI UNIV

Monocular image multi-modal CAD model retrieval method based on pre-training large model

The invention discloses a monocular image multi-modal CAD (computer-aided design) model retrieval method based on a pre-trained large model, which fully extracts image, depth and text information by combining image segmentation, depth estimation, semantic generation and multi-modal feature extraction technologies and utilizing an image segmentation model, a depth estimation model and a text generation model. And through a multi-modal feature fusion module, weighted fusion of features is realized, and a final multi-modal query feature vector is generated. Afterwards, the feature alignment capability is improved through multi-modal contrast learning, matching of multi-modal query feature vectors and CAD model features in a unified feature space is ensured, in order to improve the retrieval efficiency, the invention further provides a triple index quantization graph search method, local sensitive hashing, a layered navigable small-world graph and a product quantization technology are combined, and the retrieval efficiency is improved. Efficient model retrieval is achieved in a large-scale CAD model database, and the method has the remarkable advantages in multi-modal information processing and large-scale CAD data retrieval.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Influence maximization method and system based on deep reinforcement learning and graph neural network

The invention provides an influence maximization method and system based on deep reinforcement learning and a graph neural network, and belongs to the field of influence maximization in social network analysis. The method aims to optimize selection of seed nodes through a reinforcement learning technology so as to realize maximum propagation of information in a network, and the graph neural network can accurately capture an interaction relationship between nodes in a graph structure by virtue of a message transmission mechanism of the graph neural network, which is highly matched with an information propagation process in a cascade propagation model. Therefore, in the influence maximization model based on the deep reinforcement learning and the graph neural network, the graph neural network is combined with the deep reinforcement learning, the embedded representations of the nodes are learned by using the graph neural network, and the embedded representations are used as the input of the deep Q network so as to fully capture the complex structure and node relationship in the network. In addition, a multi-head attention mechanism is introduced to aggregate information of each round, expression of key features is enhanced, and information redundancy is effectively reduced.
Owner:QIQIHAR UNIVERSITY

Deep learning-based aero-engine residual life prediction method and system

The invention provides an aero-engine residual life prediction method and system based on deep learning, and relates to the technical field of engine life prediction. According to the method, a multi-scale convolution feature extraction module (SDMCN module) based on a graph attention mechanism and a GRU module (F-GRU module) fused with the feature attention mechanism are established. Through an SDMCN module, the spatial relevance of the features is fully extracted from the two aspects of the relevance between the feature maps formed under the convolution kernels of the same size and the relevance between the feature maps formed under the convolution kernels of different sizes. And meanwhile, the F-GRU module is used for dynamically adjusting the weights of the input characteristics under different time steps, so that differential updating of the sequence data is realized. By adopting the two parallel branches, extraction of spatial relevance and time sequence dependency relationship between features is realized, so that feature degradation information is captured more comprehensively, a more accurate life degradation model is established, and the accuracy of model prediction is improved.
Owner:HEFEI UNIV OF TECH

Multi-modal information fusion AI platform and application method

The invention relates to a multi-modal information fusion AI platform and an application method, and the platform comprises a second data input module which is used for allowing a medical institution to access and input data; the second data management module is used for checking and preprocessing the data input by the second data input module; the downstream task fine tuning module is used for inheriting model parameters output by the base model pre-training module in the base model pre-training technical scheme and performing fine tuning on the model to obtain a reasoning model; and the prediction result output module is used for testing the performance of the reasoning model and displaying a prediction result. The method can cope with more complex and changeable clinical scenes, and high dependence of traditional supervised learning on data is reduced. The method has the capability of multi-modal feature fusion. The fusion is not only beneficial to capturing more comprehensive information, but also can improve the recognition ability of the model to lesions. The multi-task processing capability enables the model to cope with various clinical requirements at the same time.
Owner:SHANGHAI MEDICAL IMAGE INSIGHTS INTELLIGENT TECHNOLOGY CO LTD

Brain structure-function coupling quantitative method and device based on brain network gradient

The invention discloses a brain structure-function coupling quantitative method and device based on brain network gradient, and the method comprises the steps: carrying out the dimension reduction of a similarity matrix through principal component analysis, obtaining a structure gradient matrix, and enabling each column to be a principal component, namely a structure connection gradient; dimensionality reduction is conducted on the similarity matrix through principal component analysis, a functional gradient matrix is obtained, and each column is a principal component, namely a functional connection gradient; performing dimension reduction on the structure connection matrix and the function connection matrix through principal component analysis to obtain a structure gradient matrix and a function gradient matrix; calculating a Pearson correlation coefficient between rows of the low-frequency structure gradient matrix and the low-frequency function gradient matrix to obtain a low-frequency gradient coupling index, and calculating a Pearson correlation coefficient between rows of the high-frequency structure gradient matrix and the high-frequency function gradient matrix to obtain a high-frequency gradient coupling index; and capturing tiny changes of the brain structure or function through the low-frequency gradient coupling index and the high-frequency gradient coupling index. The device comprises a processor and a memory.
Owner:TIANJIN UNIV

Multi-source remote sensing data classification method

The invention provides a multi-source remote sensing data classification method, which belongs to the field of hyperspectral image processing in the field of remote sensing, and comprises the following steps: acquiring remote sensing data of various target objects; extracting shallow layer features of each kind of remote sensing data; obtaining a plurality of frequency characteristics of each kind of remote sensing data; fusing the same frequency features of all remote sensing data to obtain a plurality of same frequency fusion features; splicing the plurality of same-frequency fusion features to obtain a multi-source fusion feature; enabling the multi-source fusion features to sequentially pass through a frequency modulation layer and an attention layer which are superposed to obtain fused global features and local features; and weighting the global features and the local features in the spectral dimension to obtain a prediction classification result of the target object. According to the method, directional frequency characteristic decomposition and fusion of the multi-source data are realized, the multi-source fusion characteristics are extracted based on the multi-source remote sensing data to serve as the basis of classification, more comprehensive information is provided for classification of target objects, complex ground object characteristics can be fully captured, and the classification result is more accurate.
Owner:NANJING UNIV OF INFORMATION SCI & TECH

Method and system for detecting water content of lithium battery

The invention relates to the technical field of lithium battery water content detection, in particular to a lithium battery water content detection method and system. The method comprises the following steps: acquiring a lithium battery surface thermal imaging image; carrying out temperature gradient distribution identification on the lithium battery surface thermal imaging image, and carrying out local distribution change sudden change detection to extract a temperature imbalance region and a temperature conventional region; carrying out optimal penetrating electromagnetic wave frequency calculation according to the temperature imbalance region and the temperature conventional region, carrying out a multi-band electromagnetic wave penetration test, and collecting electromagnetic reflection signals of the temperature imbalance region and the temperature conventional region; and performing multi-frequency-band reflection signal intensity calculation and region-by-region comprehensive reflection characteristic mining on the electromagnetic reflection signal to obtain a temperature imbalance region signal reflection characteristic and a temperature conventional region signal reflection characteristic. According to the invention, efficient and accurate lithium battery water content detection is realized.
Owner:SHENZHEN DAXING SHOUZHENG INTELLIGENT EQUIP CO LTD

Insect detection method and system under complex background based on deep learning feature enhancement

The invention discloses an insect detection method and system under a complex background based on deep learning feature enhancement, and relates to the field of small target detection. The problem that agricultural insect detection lacks insect images dynamically captured in a real scene is solved. The method comprises the following steps: acquiring an image, and preprocessing the image; the method comprises the following steps: constructing an S-Insert-Det network structure, wherein the S-Insert-Det network structure comprises a backbone network, a neck network and a detection head; the backbone network is an OfficientViT network based on a Transform, and the backbone network is an EficientViT network based on a Transform; the neck network is a bidirectional multi-scale fusion architecture; image feature extraction is carried out through the backbone network, and multi-scale feature fusion is carried out through the neck network; and outputting feature representation after feature fusion through the detection head, and obtaining an insect recognition result. The method is applied to the field of insect recognition.
Owner:WUXI UNIV

Network suitable for medical image segmentation and implementation method

The invention discloses a network suitable for medical image segmentation, which is characterized in that an encoder firstly passes a given medical image through four feature extraction stages, a single Enhanced CBAM module is used for guiding a continuous Residual CNN layer to extract local features with global information in each stage, and then the local features are encoded into features with long-distance dependence through an EnNon-local module; and the decoder takes the final output feature of the encoder as initial input after passing through a convolution block, and splices the high-resolution feature from the encoder and the high-dimensional feature of the decoder through jump connection, so that the target resolution is recovered step by step by the cascaded upsampler. The invention also discloses an implementation method suitable for medical image segmentation by using the network. According to the method, the defect that an existing model lacks global information in a CNN part is overcome, long-distance information is coded by using a self-attention mechanism, and the calculation burden is reduced.
Owner:ANHUI UNIV OF SCI & TECH

Engine support assembly assembling quality appearance detection method based on machine vision

An engine support assembly assembling quality appearance detection method based on machine vision is characterized by comprising the following steps that 1, an adaptive sampling algorithm is combined with actual features, and a sampling scheme is formulated; 2, after an engine support assembly image is collected and marked, a GAN model is trained to generate a composite image, and a data set is made; 3, an attention mechanism and lightweight convolution are introduced into the YOLOv9 algorithm, and then the model is trained; 4, using a camera light source adaptive algorithm to automatically adjust camera and light source parameters, and then carrying out image acquisition; 5, comparing and analyzing a detection result with a qualified standard after target detection, and judging the assembly state of the part; 6, associating a detection result with the product to establish a quality tracing mechanism; and 7, regularly triggering a continuous learning automation process, and iteratively optimizing the model. According to the invention, the detection accuracy and efficiency of the assembly state of the parts of the engine support assembly are improved, the labor cost is reduced, and appearance detection of the assembly quality of the engine support assembly, quality problem tracing and continuous learning are realized.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Multi-head context attention gait phase classification method based on TCN network

The invention relates to the technical field of gait analysis, in particular to a multi-head context attention gait phase classification method based on a TCN network, and the method specifically comprises the following steps: constructing a model based on the TCN network and a multi-head context attention module, inputting the data collected by a sensor into the TCN network of the model for feature extraction, and obtaining a feature # imgabs0 #; a # imgabs1 # multi-head context attention module is constructed, the feature # imgabs2 # is input to a # imgabs3 # module, and a fusion feature # imgabs4 # is obtained; inputting the fusion feature # imgabs5 # into a # imgabs6 # channel attention module to obtain a comprehensive feature # imgabs7 #; calculating the total loss of the model; and inputting the comprehensive feature # imgabs8 # into a linear layer classifier to obtain a final phase classification prediction score # imgabs9 #, and taking the category corresponding to the phase classification prediction score with the highest score as the final category of prediction. According to the method, the time context features of the sensor data can be extracted more accurately, and the accuracy of gait phase classification is improved.
Owner:深圳市翼健人工智能科技有限公司

Flue gas dust removal equipment for preventing and treating atmospheric pollution

The utility model discloses flue gas dust removal equipment for preventing and treating atmospheric pollution, and relates to the technical field of flue gas dust removal. The device comprises a rectangular bottom plate, wherein a spraying mechanism and a mixing mechanism are arranged on the rectangular bottom plate; the spraying mechanism comprises a plurality of spraying assemblies and a conveying assembly, each spraying assembly comprises a dust removal box fixedly installed at the top of the rectangular bottom plate, a catalyst pipe is fixedly installed on the inner wall of each dust removal box, a plurality of catalyst nozzles are fixedly installed on the outer wall of each catalyst pipe, and a water inlet is formed in the front face of each dust removal box; and the water inlet is matched with the top end of the catalyst tube. By arranging the spraying mechanism, the problems that only larger particulate matters in smoke dust can be removed, gaseous pollutants cannot be directly removed, short circuit between the discharge electrode and the collector can be caused by collected dust, regular cleaning is needed, and the maintenance cost is increased are solved.
Owner:BEIJING PANSHI ENVIRONMENTAL PROTECTION ENGINEERING CO LTD

Face feature extraction method based on image data

The invention discloses a face feature extraction method based on image data, relates to the technical field of face feature extraction, and better adapts to face image data in complex scenes such as different illumination, expressions, postures and shielding by adopting a mode of multi-task optimization and dynamic adjustment of feature selection weights. According to the method, the robustness and generalization ability of a model are improved, tensor principal component analysis TPCA and an improved block PCA algorithm are introduced to more effectively extract and express high-level semantic information in a face image, the discrimination and expression ability of features are improved, and the face recognition problem in a complex scene is effectively solved by introducing a regularization item and an area projection model. According to the method, the tolerance to factors such as shielding and illumination is improved, so that the model is more excellent in performance in a complex scene, finally, the selection and weight of features are dynamically adjusted according to different scenes and data through a preprocessing technology of multi-task optimization and block recombination, and thus the adaptability and generalization ability of the model are improved.
Owner:BEIJING ZAIXIN HUITONG TECHNOLOGY CO LTD

Vehicle-mounted multi-target classification and detection method based on multi-teacher distillation and dynamic reasoning

The invention discloses a vehicle-mounted multi-target classification and detection method based on multi-teacher distillation and dynamic reasoning, and the method comprises the steps: collecting an image through a vehicle-mounted image collection device, taking the image as the input through a dynamic neural network, and outputting the classification and bounding box regression of multiple targets. The dynamic neural network is composed of a multi-teacher network and a student network. The multi-teacher network is composed of a plurality of teacher models; a dynamic weight distribution system based on an attention mechanism is introduced into the multi-teacher network, and different weights are distributed to each teacher model according to the characteristics of the current input scene; a confidence coefficient threshold value is set in a multi-teacher network, and regional knowledge possibly containing a target is only taught to a student network. The student network is composed of a strategy network and a detection network, and the detection network is a two-stage target detection network obtained by integrating a feature extraction network and a target positioning network; the strategy network adaptively extracts task features according to knowledge provided by the multi-teacher network; and the detection network dynamically selects a route according to the policy network decision vector.
Owner:NANJING TECH UNIV

Hyperspectral image classification method of graph self-attention network based on greedy strategy guidance

The invention relates to a hyperspectral image classification method, in particular to a hyperspectral image classification method based on a greedy strategy guided graph self-attention network. The invention provides a hyperspectral image classification method of a graph self-attention network based on greedy strategy guidance in order to solve the problems that in existing HSI classification, samples are limited, GAT tends to only consider directly-connected nodes, indirectly-related relations are insufficiently considered, and the classification effect is affected. The method comprises the following steps: step 1, constructing a graph self-attention network based on greedy strategy guidance; the greedy strategy guidance-based graph self-attention network comprises a data preprocessing stage, a super-pixel-based graph self-attention branch stage, a pixel-based multi-attention fusion branch stage, a classification stage and a greedy training strategy stage. And step 2, classifying the hyperspectral image to be measured based on the trained greedy strategy guided graph self-attention network to obtain a classification result. The method is applied to the field of hyperspectral image classification.
Owner:HUZHOU UNIVERSITY

Aquaculture filtering equipment

The invention relates to the technical field of aquaculture, in particular to aquaculture filtering equipment which mainly comprises a filtering tank and a stirring mechanism, a water drainage opening is formed in the bottom face of the filtering tank in a penetrating mode, a water inlet and a medicine adding opening are formed in the top face of the filtering tank in a penetrating mode, and the stirring mechanism is arranged in the filtering tank and comprises a baffle located in the filtering tank. And the vibrating mechanism is arranged below the barrier plate. A motor drives a rotating shaft, a limiting strip and a rotating plate to rotate, when the rotating plate drives a connecting shaft and a stirring blade to rotate, a roller on the connecting shaft rolls on the inner wall of a fixed frame, and under the action of the roller, the fixed frame, a groove body and a fixed rod, the connecting shaft and the stirring blade revolve, rotate and move up and down in a reciprocating manner at the same time; therefore, contact and reaction between the flocculating agent and the water body are more uniform, the flocculating agent can fully play a role, impurity particles are fully captured or coagulated, and the impurity separation and precipitation effect and the water body filtering quality in the water treatment process are improved.
Owner:ZHUHAI HAICHUAN AGRI CO LTD

SOFC-oriented multistage solid hydrogen storage system and method

The invention discloses an SOFC-oriented multistage solid hydrogen storage system and method. The SOFC-oriented multistage solid hydrogen storage system comprises a gaseous hydrogen storage device and an air conveying device, the gaseous hydrogen storage device is connected with the SOFC and the combustion device through the hydrogen heat supplementing device; the air conveying device is connected with an air supply device, the end part of the air supply device is connected with an air heat compensation device through an air heat recovery device, and the air heat compensation device is connected with the SOFC; the hydrogen storage reactors are installed between the gaseous hydrogen storage device and the hydrogen heat supplementing device, the hydrogen storage reactors comprise a TiFe reactor, an Mg2Ni reactor and a TiH2 reactor, and the TiFe reactor, the Mg2Ni reactor and the TiH2 reactor are sequentially communicated. The system provides a safe, high-density and low-cost hydrogen storage function for the SOFC through integration of the SOFC and multi-stage solid hydrogen storage, high-temperature waste heat generated in the SOFC power generation process just provides a driving heat source for solid hydrogen storage and hydrogen desorption, and the defects in the prior art are overcome.
Owner:XIAN THERMAL POWER RES INST CO LTD

Remote fetal heart rate monitoring automatic analysis system and method based on smart watch

The present application provides a remote fetal heart monitoring automatic analysis system and method based on a smart watch, which relates to the field of intelligent signal analysis. It collects mixed signals through a smart watch and transmits the mixed signals to a remote server for fetal heart monitoring. In the remote server for fetal heart monitoring, artificial intelligence-based signal processing and analysis technology is used to decompose the mixed signals and extract and enhance the semantic features of the IMF component waveforms. Then, the fetal heart rate value is intelligently obtained based on the semantic features of the fetal signal waveform obtained after clustering and mean calculation of the semantic features of the waveforms of each IMF component, and sent to the smart watch. In this way, artificial intelligence technology can be used to decompose and extract the mixed signals of the heart rate of pregnant women and fetuses, which can more fully capture the key information in the signal, and then obtain more accurate fetal heart rate data, realizing more intelligent remote fetal heart monitoring.
Owner:JILIN UNIVERSITY

Precise recording system and method for aircraft defects

The invention relates to the technical field of aircraft maintenance project management, and discloses an aircraft defect accurate recording system and method, and the system comprises a data collection module, an image processing module, a feature processing module, a defect recognition module and a result output module. The data acquisition module comprises an image acquisition unit and an auxiliary information acquisition unit; the image processing module is used for preprocessing the surface image; the feature processing module is used for extracting target features; the target features are converted into feature vectors; an identification model is arranged in the defect identification module; the recognition model takes the feature vector as input, and takes the defect rate and the defect category as output; and the result output module is used for positioning a defect position and visually displaying and storing a defect analysis result according to the output result of the defect identification module and the corresponding feature vector. According to the method, defect feature analysis dimensions are diversified, defect information can be fully captured, the identification precision is high, and systematic intelligent management of aircraft defects can be realized.
Owner:CHONGQING CHUNZHIYI INFORMATION TECH CO LTD

Method for enhancing super-resolution of single image through double-domain learning network, electronic equipment and storage medium

The invention discloses a method for enhancing the super-resolution of a single image through a double-domain learning network, electronic equipment and a storage medium, solves the problem of insufficient reconstruction details and textures in the prior art, and can integrate frequency domain and spatial domain information to improve the reconstruction quality from a low-resolution image to a high-resolution image. The method comprises the following steps: 1, inputting a low-resolution image into a double-domain learning network comprising a plurality of double-domain learning blocks, and generating two super-resolution image outputs through processing of the plurality of double-domain learning blocks: one is frequency domain output, and the other is spatial domain output; step 2, introducing a complex convolution discriminator and cross-modal distillation loss to enhance the performance of the double-domain learning network, specifically, the complex convolution discriminator is used for processing data for converting an image from an HSV color space into a complex form; the cross-modal distillation loss serves as a loss function, and effective fusion of frequency domain and space domain output is guided in the model training process.
Owner:XIAMEN UNIV

Mother-child wind generating set

The utility model relates to a mother-child wind generating set which comprises a base, a tower is arranged on the base, a cabin is arranged on the tower, one end of the cabin is connected with a first wind wheel mechanism, the outer wall of the cabin is connected with at least two supporting cylinders in the circumferential direction, and the other ends of the supporting cylinders are connected with second wind wheel mechanisms. The first wind wheel mechanism and the second wind wheel mechanism are both connected with a power generation mechanism capable of converting mechanical energy into electric energy. The wind power generation system has the advantages that the first wind wheel mechanism serving as the mother wind wheel and the second wind wheel mechanisms serving as the son wind wheels are integrated on the tower, so that the wind power generation system can capture wind energy more comprehensively in a complex and changeable wind field environment, and wind field resources can be utilized more effectively compared with a single-wind-wheel system; through wider wind speed adaptability and wind energy capturing strategies, the utilization rate of wind field resources is increased by more than 22%.
Owner:CNOOC POWER INVESTMENT CO LTD

Image recognition method for electric power inspection scene

The invention relates to an image recognition method for an electric power inspection scene, and the method comprises the steps: obtaining electric power inspection image data, carrying out the data enhancement processing, achieving the data amplification through a generative adversarial network, constructing an electric power inspection image data set through marking, and carrying out the sample balance processing; for a convolutional neural network model trained on a large-scale data set in advance, performing fine tuning by using an electric power inspection image data set; the method comprises the following steps: acquiring a to-be-identified electric power inspection scene image, inputting the image into a convolutional neural network model, extracting multi-scale features of the image in a residual connection mode, obtaining high-dimensional fusion features through cascade fusion or weighted fusion, improving the attention on a region of interest through an attention mechanism, and performing identification by using multiple models. And fusing the recognition results of the plurality of models to obtain a final image recognition result. Compared with the prior art, the method has the advantages of being good in performance, low in false detection rate and omission ratio and the like on power inspection image data with small volume.
Owner:STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER CO

Method and device for predicting remaining service life of cutter

The invention provides a method and a device for predicting the remaining service life of a cutter. The method comprises the following steps of: making a plurality of labels for wear values in a cutter wear experiment data set; vibration signal data and cutting force signal data of the tool are collected and preprocessed; randomly dividing the plurality of labels and the preprocessed vibration signal data and cutting force signal data into a training set, a verification set and a test set; extracting multi-domain features of the training set, the verification set and the test set; inputting the multi-domain features into a first training model for training, and outputting nonlinear features; inputting the multi-domain features into a second training model for training, and outputting linear features; fusing the nonlinear feature and the linear feature to obtain a fused feature; and inputting the fusion feature into a third training model, and outputting a predicted value of the remaining service life of the cutter. The method improves the prediction precision of the residual service life of the cutter.
Owner:QILU INST OF TECH

Multi-source generalization method based on Markov classifier

The invention discloses a multi-source generalization method based on a Markov classifier. The method comprises the following steps: acquiring image data of a plurality of source domains; according to the image data of the plurality of source domains, a training data set is obtained, one image in the image data of each source domain serves as a sample image, and the training data comprises the sample image and a category label corresponding to the sample image; an image detection model is constructed, the model comprises a feature extractor and a generation classifier which are connected in sequence, the feature extractor adopts a convolutional neural network, and the generation classifier adopts a Mahalanobis classifier based on Mahalanobis distance; constructing a target detection loss function; training an image detection model by using the training data set based on the target detection loss function; and obtaining a to-be-classified image, inputting the to-be-classified image into the trained image detection model, and obtaining and outputting a category corresponding to the to-be-classified image. According to the method, cross-domain class change can be fully captured, image data of a transition fitting source domain is avoided, and the classification precision of the model on different source domain images is remarkably improved.
Owner:NAT INNOVATION INST OF DEFENSE TECH PLA ACAD OF MILITARY SCI

Online brain grain recognition method for cross-session scene

The invention belongs to the technical field of brain grain recognition in a brain-computer interface, and discloses an online brain grain recognition method for a cross-session scene, which comprises the following steps: acquiring electroencephalogram data of K users under a session, performing non-overlapping segmentation on each test time according to the length T into brain electron segments, and storing the brain electron segments in a database; performing sliding window processing on the brain electron fragment under S different dynamic window scales to correspondingly generate S groups of data sets with different dynamic window scales; performing offline training on M different random seed models by adopting each group of dynamic window scale data sets to obtain M brain grain recognition models; and in the second session, performing gliding window processing on data which is received online and has the length of T in a corresponding scale, inputting the processed data into the corresponding brain grain recognition model for user identity prediction, averagely integrating prediction results, and performing weighted integration to obtain a user identity prediction result, thereby realizing cross-session online brain grain recognition. According to the method, the accuracy, robustness and recognition rate of cross-session electroencephalogram signal identity recognition can be improved.
Owner:HUAZHONG UNIV OF SCI & TECH