16results about How to "Strong feature extraction ability" patented technology

The invention discloses a life prediction method and system of a vector thruster, and belongs to the technical field of life prediction of the vector thruster, and the method comprises the steps: collecting historical sensor data of the vector thruster, including current and voltage, vibration signals, pressure, acceleration, temperature and sound data; preprocessing the collected historical sensor data; constructing a data cube, and dividing the data cube into a training set and a test set; a life prediction model is constructed based on a three-branch fusion convolutional neural network, and the three-branch fusion convolutional neural network model combines a frequency spectrum attention branch module, a bidirectional space attention branch module and a multi-attention fusion branch module, so that features can be effectively extracted and fused from multiple angles of frequency spectrum, space and the like. And the identification capability and the generalization performance of the model are greatly improved. According to the method, more accurate vector propeller life prediction can be provided, potential faults can be found in advance, the maintenance cost is reduced, and the service life of equipment is prolonged.

The invention provides a two-stage generalized small sample target detection method and system based on self-supervision, and relates to the technical field of deep learning, and the method comprises the steps: defining a potential knowledge container to store all potential knowledge, and defining a prototype container to store prototypes of various candidate boxes; dividing the training data set into a base class set and a new class set; the self-supervised category domain carries out pre-training and fine tuning on the detection model based on the potential knowledge of the base category set and the new category set; the self-supervised detection frame field carries out pre-training and fine tuning on the detection model based on the potential knowledge of the base class set and the new class set; and inputting a to-be-detected image to the detection model, obtaining features through the feature extractor, performing potential knowledge search and segmentation on the to-be-detected image based on the potential knowledge container to obtain a relationship between the to-be-detected image and each potential knowledge, and obtaining a candidate box category. According to the method, detection model training is carried out in the category domain and the detection frame domain by using self-supervised learning based on potential knowledge, and the method has good target detection capability for both a base class and a new class.

The invention discloses a construction method of a fish detection model based on deep learning and a fish detection method and system, a residual network ResNet is used as a main network structure of the fish detection model, and the residual network ResNet has a strong feature extraction capability and can capture features such as basic forms and textures of fishes; then a mixed attention mechanism is introduced to extract more effective feature quantities, a mixed attention module is connected behind each residual block of the residual network ResNet, key features can be further extracted and emphasized, and therefore a better effect is achieved on the residual network ResNet; the mixed attention is combined with an attention mechanism of two dimensions of channel attention of GRA and space attention based on CBP, the model can more comprehensively capture feature information of fish, algorithm complexity is effectively reduced, hardware requirements of actual deployment are further reduced, the requirements for depth and different level widths of a deep learning algorithm are reduced, and the method is suitable for being popularized and applied. And the purpose of algorithm weight reduction is achieved.

The invention discloses a face super-resolution reconstruction detection method, device and equipment, and relates to the field of computer vision, and the key points of the technical scheme are as follows: detecting whether a low-resolution image has a to-be-confirmed face region or not; when it is detected that the low-resolution image has a to-be-confirmed face region, inputting the image of the to-be-confirmed face region into a face super-resolution reconstruction network for super-resolution reconstruction so as to confirm the face region in the image; wherein an enhanced generative adversarial network constructed by a generator and a discriminator serves as the face super-division reconstruction network, a DB residual dense block of the generator is replaced by a plurality of stacked Swin Transform block structures, and a reconstruction loss function of the discriminator is introduced to be used for judging whether the reconstruction loss function is a cross entropy loss function of a face region or not. The problem that the quality of the generated image is affected due to the fact that certain noise and artifacts still exist in the process of reconstructing the image resolution by an ESRGAN provided in the prior art is solved.

The application discloses a mechanical equipment fault diagnosis method, device and equipment and a readable storage medium. Known fault information multi-source frequency domain signals of same or same type mechanical equipment under a first working condition are acquired, and the known fault information multi-source frequency domain signals under the first working condition are taken as source domain data sets. Unknown fault information multi-source frequency domain signals of the mechanical equipment to be diagnosed under a second working condition are acquired, and the unknown fault information multi-source frequency domain signals under the second working condition are taken as target domain data sets. A multi-source dense adaptive adversarial network model is trained by using the source domain data sets and the target domain data sets, and a mechanical equipment fault diagnosis model is obtained. The real-time acquired multi-source frequency domain signals of the mechanical equipment to be diagnosed under the second working condition are input into the mechanical equipment fault diagnosis model, and a fault diagnosis result is output. The application can better utilize the multi-source information of the mechanical equipment in data level fusion and feature level fusion.

This application relates to the interdisciplinary field of deep learning and protein analysis, specifically to a method, apparatus, device, and medium for analyzing multi-target proteins in obesity based on deep learning. The method includes: acquiring biological sample data and preprocessing the biological sample data to obtain preprocessed biological sample data; the preprocessed biological sample data includes protein expression data and obesity classification labels corresponding to the protein expression data; the protein expression data includes multiple protein expression features; constructing an initial deep learning model for analyzing multi-target proteins in obesity based on a multilayer feedforward neural network; training the initial deep learning model based on the preprocessed biological sample data to obtain a deep learning model for analyzing multi-target proteins in obesity; and determining multiple protein expression features related to obesity based on the deep learning model for analyzing multi-target proteins in obesity.

This invention relates to the field of deep-sea signal processing and recognition technology, and in particular to a method for recognizing weak reverberation signals in the deep sea based on a deep learning model. The method includes: collecting reverberation data containing weak signals using underwater sensors; removing sensor noise and high-frequency interference from the reverberation data using a wavelet threshold denoising algorithm; normalizing the reverberation data to map its signal amplitude to a preset range; constructing a convolutional neural network model containing convolutional layers, pooling layers, and fully connected layers; dividing the normalized reverberation data into training, validation, and test sets; inputting the weak reverberation signal to be identified into the trained convolutional neural network model after denoising and normalization; and outputting the signal and recognition result from the convolutional neural network model. This invention eliminates a large amount of tedious manual feature engineering, reduces human intervention, and improves recognition efficiency and accuracy.

The application discloses a kind of HDR image reconstruction method, system, equipment and medium, it is related to computer vision image enhancement field, the method includes: obtaining the LDR image of different exposure degree under target scene;Each LDR image is mapped to HDR domain using gamma correction, obtain the gamma correction image of corresponding exposure degree;LDR image and gamma correction image set under target scene are input into image reconstruction model, obtain the HDR image of target scene;Image reconstruction model is obtained using training data to the deep learning model training;Deep learning model includes: feature extraction module and HDR reconstruction module;Feature extraction module is used to extract the double-channel feature containing channel information and spatial information to the input image;HDR reconstruction module is used to reconstruct the input image based on three-pass residual block according to double-channel feature, obtain corresponding HDR image.The application can realize end-to-end ghost-free high-quality HDR image reconstruction.

The present disclosure relates to a power distribution network service hot migration method and device, electronic equipment, storage medium and computer program product. The method comprises: obtaining resource information of each edge node in a plurality of edge nodes contained in a power distribution network and load information of services on each edge node; inputting the resource information of each edge node and the load information of the services on each edge node into a residual network contained in a trained service migration prediction model to obtain a feature representation; inputting the feature representation into a migration strategy decision module contained in the service migration prediction model to obtain a service migration instruction, wherein the service migration instruction is used to indicate a to-be-migrated service and a migration path and a migration destination edge node corresponding to the to-be-migrated service; and issuing the service migration instruction to an edge node containing the to-be-migrated service in the plurality of edge nodes, so that the edge node containing the to-be-migrated service performs hot migration on the to-be-migrated service based on the service migration instruction.

The present invention relates to the technical field of drone control, and discloses a fully automatic low-altitude inspection and monitoring method and system based on drones. The present invention first establishes a three-dimensional grid space, completes drone performance constraints and calculates drone flight path evaluation indicators; secondly, the drone flight path evaluation indicators are used as fitness functions, and the drone inspection path is planned based on the dandelion optimization algorithm, and the dandelion seed position is continuously updated according to the fitness function value, and the drone inspection path is output; then it is determined whether the city aerial image contains fog, and the foggy city aerial image is defogged, and the YOLOv5 network is trained to realize the detection and recognition of urban aerial objects; finally, the drone feeds back abnormal information according to the abnormal coefficient of the detected and recognized object, and avoids threats. The present invention achieves the monitoring purpose by controlling the drone path planning and drone object recognition, and the method is accurate and objective.

This invention relates to the field of surrounding rock quality prediction technology, and discloses a method for predicting the quality of surrounding rock from massive datasets based on U-Time residual connectivity and attention mechanisms. It aims to address the difficulty in effectively capturing the spatiotemporal feature dependencies in long sequences when processing massive high-dimensional time-series data. Existing technologies suffer from gradient vanishing or low computational efficiency issues when processing long sequences, and insufficient mining of spatial relationships of high-dimensional features. This invention includes the following steps: S1: Data preprocessing and loading; S2: Model building; S3: Model training and optimization; S4: Model prediction; S5: Online model warning. This invention effectively manages memory through lazy loading and intelligent caching mechanisms, supporting the training of thousands of large data files, and solving the problem that traditional methods cannot load all data at once.

The present invention discloses a method for detecting anomalies in bridge structure health monitoring data based on deep learning. The method abandons the traditional method of over-reliance on data analysis in the time domain. Instead, the method visualizes the data in the time domain, frequency domain and Gram angle field (GAF) and then superimposes the data into a three-channel composite image through an image processing algorithm. The composite image of the three channels is input into a VGG16 neural network model that incorporates a channel attention mechanism for processing. The VGG16 neural network model that incorporates a channel attention mechanism can dynamically adjust the weight of each channel according to image features and perform dimensionality reduction processing, thereby improving the accuracy of abnormal data recognition and reducing the complexity of the model. In addition, the neural network model that incorporates a channel attention mechanism in the present application is not affected by trend, seasonality, periodicity and random disturbances in traditional time series, and has a strong feature extraction capability and good robustness.

The invention provides a plateau railway icing early warning method and system based on sequence learning, and is applied to the technical field of meteorological disaster prediction, and the method comprises the steps: obtaining attention points and original meteorological observation data along a railway for several years, extracting the original meteorological observation data corresponding to the attention points, and obtaining meteorological data; preprocessing the meteorological data, generating an icing label corresponding to each concerned point location according to a preset icing standard, performing interval grouping based on longitude and latitude, and performing gridding processing on the meteorological data with the icing labels to obtain aggregated data; dividing the aggregated data into training data and test data according to a preset rule, and inputting the training data and the test data into a constructed space-time fusion deep learning model for rolling training to obtain a model parameter corresponding to each prediction year; and obtaining model parameters corresponding to the year to be predicted, substituting the model parameters into the model, inputting the meteorological data to be predicted into the model to obtain a corresponding icing risk prediction result, and performing early warning.

The invention provides a medical image map construction method and system, a storage medium and electronic equipment. The method comprises the following steps: acquiring medical images of a plurality of individuals; extracting high-dimensional features of the medical image based on an encoder; performing feature fusion on the high-dimensional features, and calculating a feature center of the high-dimensional features after feature fusion; and converting the feature center into a medical image map based on a decoder. According to the medical image atlas construction method and system, the storage medium and the electronic equipment, the efficiency of medical image atlas construction is effectively improved based on the deep learning algorithm, and the accuracy and applicability of the medical image atlas are enhanced.

The present application discloses a method for acquiring a feature model, an image processing method, an apparatus, a computer device, and a storage medium, and belongs to the field of computer technology. The present application obtains a discriminative parameter for characterizing the degree of difference of the first image feature of sample images under different categories, so that the discriminative parameter can control the trained target feature model to have a better feature extraction capability, and obtains a compatibility parameter for characterizing the degree of similarity between the first image feature and the second image feature of the same sample image, so that the compatibility parameter can control the target feature model to have a better compatibility capability with the original first feature model. Therefore, under the joint constraints of the discriminative parameter and the compatibility parameter, the target feature model obtained by training the initial feature model not only has a better feature extraction capability, but also has a strong compatibility capability.

The invention discloses a fault distance calculation method and system for a power system power distribution network. The method comprises the steps that a power engineer monitoring end sends a fault distance safety self-checking signal to a power distribution network real-time operation edge calculation gateway monitoring platform; after the power distribution network real-time operation edge computing gateway monitoring platform receives a fault distance safety self-checking signal, the fault distance safety self-checking signal is detected. The multi-modal information integration end under different user groups collects electrical parameters and load data of the power distribution network of the power system in each fault area under different user groups and equipment state parameters of the fault distance of the power distribution network of the power system in each fault area, stores the collected data and sends the collected data to the power engineer monitoring end; and the signal is sent to the power system power distribution network fault distance calculation model module through the signal collection processing server. According to the invention, more accurate fault positioning information can be provided for power engineers, the troubleshooting time is shortened, and safe and stable operation of the power distribution network is guaranteed.