106results about How to "Solve the imbalance" patented technology

The invention discloses a multi-working-condition-oriented equipment fault diagnosis method based on unbalanced learning, and the method comprises the following steps: collecting the operation data of equipment under different working conditions through a plurality of sensors, carrying out the preprocessing, feature extraction and feature selection of the collected original operation data, and obtaining a feature set; processing the feature set by adopting an unbalanced learning technology and a cost-sensitive learning algorithm to obtain a balanced data set; constructing a multi-working-condition fault diagnosis model based on learning, and optimizing model parameters by adopting a method of combining cross validation and grid search according to a balanced data set in a model training process; deploying a multi-working-condition fault diagnosis model obtained through training, carrying out the online diagnosis of equipment faults, and continuously updating and optimizing the model through a continuous learning mechanism. According to the method, the unbalanced learning technology is applied to multi-working-condition fault diagnosis, the accuracy and robustness of diagnosis can be remarkably improved, and real-time monitoring and predictive maintenance of the equipment health state are achieved.

The invention provides a remote sensing image target detection method based on an improved FCOS, and relates to the technical field of target detection, and the method comprises the following steps: carrying out the convolution and pooling operation of a remote sensing target image based on a pre-trained convolutional neural network, generating a preliminary feature, and carrying out the enhancement processing of the preliminary feature through a twin multilayer perceptron; carrying out fusion processing on different levels of feature information in the multi-level feature map through a feature map splicing mode and a feature map enhancement mode; and determining the position of the remote sensing image target according to the analysis result to obtain a target detection result. According to the method, the feature pyramid network is combined with an innovative coordinate attention mechanism, fusion of high-level semantic information and low-level detail information is realized, an enhanced multi-scale feature map is generated to cope with diversity of target scales in a remote sensing image, multi-scale fusion and an anchor-frame-free design are combined, false detection is effectively reduced, and the detection accuracy is improved. Therefore, the method shows efficient, accurate and wide application potential in the field of remote sensing image target detection.

The invention relates to the field of electric digital data processing, in particular to an intelligent management and control method and system for building water. The method comprises the steps of collecting real building water consumption data, training a data expansion model based on a conditional generative adversarial network algorithm adopting a dynamic recoding strategy, training a feature extraction model, training a classifier of a deep neural decision tree algorithm based on local structure entropy, and collecting new real building water consumption data. And performing feature extraction on the new real building water consumption data, inputting the new real building water consumption data after feature extraction into the trained classifier, identifying the energy consumption level of the new real building water consumption data, and performing corresponding behaviors. An existing building water intelligent management and control system and method have the problem of poor data analysis accuracy. The building water intelligent management and control method and system provided by the invention are high in data analysis accuracy.

The invention discloses a multi-modal commodity recommendation method based on large language model semantic enhancement, and the method employs LightGCN to carry out message propagation, obtains user ID embedding and commodity ID embedding, employs a cross attention mechanism to learn the relevance between modals, solves a problem that the semantic space between the modals is not matched, achieves the alignment of modal features, and improves the recommendation efficiency. According to the method, the multi-modal information is matched with a semantic space of a large language model by using an adapter to enhance information association between modals, and the understanding of the multi-modal information is enhanced by using the large language model, so that the problem of unbalance of the modal information is solved, and user modal embedding and commodity modal embedding are obtained; and finally, fusing the user ID embedding and the user modal embedding to obtain a final user embedding, fusing the commodity ID embedding and the commodity modal embedding to obtain a final commodity embedding, performing inner product operation on the final user embedding and the final commodity embedding to obtain a preference score, and sorting the commodities according to the preference score to obtain a recommendation list.

The invention discloses a road and bridge deck disease identification method based on deep learning. The method comprises the following steps: acquiring a road and bridge deck disease image data set; constructing a road and bridge deck disease recognition model, and training the road and bridge deck disease recognition model based on the road and bridge deck disease image data set to obtain a trained road and bridge deck disease recognition model; the road and bridge floor disease identification model is constructed and obtained on the basis of a YOLOv9 network framework in combination with a CARAFE up-sampling module and a Triplet Attention mechanism; and obtaining a to-be-identified road and bridge surface image, and inputting the to-be-identified road and bridge surface image into the trained road and bridge surface disease identification model to obtain a disease identification result of the to-be-identified road and bridge surface image. According to the method provided by the invention, the problem of low recognition precision of an existing algorithm in different application scenes is effectively solved, and multiple disease types in road surface and bridge environments can be effectively and accurately recognized.

The invention discloses a transformer substation equipment identification method and system for image identification unmanned aerial vehicle route planning, and the method comprises the following operation steps: obtaining a layout plan of a transformer substation, and constructing a three-dimensional plan of transformer substation equipment for the layout plan of the transformer substation; generating an unmanned aerial vehicle flight route according to the three-dimensional plane graph; generating an unmanned aerial vehicle flight plan for the unmanned aerial vehicle flight route; when an unmanned aerial vehicle control system of the unmanned aerial vehicle flies according to the unmanned aerial vehicle flight plan, a transformer substation equipment image is collected according to the position of the transformer substation equipment in the three-dimensional planar graph; identifying the substation equipment from the substation equipment image and identifying a to-be-identified target object of the substation equipment at the target orientation; the to-be-identified target object is an electrical element on the substation equipment. According to the invention, the equipment image of the substation equipment is acquired through the unmanned aerial vehicle flight plan of the unmanned aerial vehicle, and the type of the substation equipment and the fault type when the fault occurs are further identified according to the equipment image.

The invention discloses a bearing fault diagnosis method integrated with a support vector dynamic neural network, and the method comprises the following steps: obtaining vibration data of a key position of a bearing of a rotating machine, carrying out the data preprocessing of the vibration data, and obtaining a preprocessed vibration signal data set; constructing a support vector machine model with a quadratic programming problem form based on the vibration signal data set, and designing a corresponding penalty function and a Lagrange function to simplify the support vector machine model; designing a variable parameter dynamics solving equation, and establishing a final integrated support vector dynamic neural network bearing fault diagnosis model to solve the support vector machine model; and simultaneously training a plurality of support vector dynamic neural network bearing fault diagnosis models based on a bagging classifier method, carrying out bearing state diagnosis on the vibration signal data set, and outputting a diagnosis result. According to the invention, the accuracy of the machine learning method, the convergence proof of the neural network solver and the interpretability of the intelligent fault diagnosis model are improved.

The invention provides an igneous rock fluid identification method based on a CXDF algorithm, and the method specifically comprises the following modules: S1, data preprocessing: obtaining core and logging data of a research area, and sorting the data into a table file in an xlsx format; performing logarithm processing on the specified logging data; performing normalization processing on the logging data; 78% of the preprocessed data is a training data set, and 22% of the preprocessed data is a verification data set; dividing a training data set label into two parts, namely multi-hydrocarbon and low-hydrocarbon; s2, model establishment: constructing a fluid identification model based on a CXDF algorithm and other artificial intelligence algorithms; constructing a simulation well based on the verification data set; identifying the simulated well according to the fluid identification model; s3, model optimization: performing model evaluation and model comparison based on a table, a radar map and a histogram; and determining an optimal fluid identification model. According to the method, rebalance processing is carried out on the data set based on an adaptive multi-target group cross optimization algorithm, and recognition of the complex lithologic igneous rock reservoir fluid is realized in combination with an integrated learning model.

The invention provides a data tamper-proofing method and system in a data sharing scene, which solves the problem of data imbalance of a training data set by using an oversampling algorithm and an undersampling algorithm, optimizes a depth anomaly detection model, shares trained model parameters among nodes participating in sharing, and improves the data tamper-proofing efficiency. According to the method and the system, the nodes can use the model with the same detection effect, and the deep anomaly detection model is used for identifying attacks such as counterfeit synthesis or tampering, so that data communication security and efficient matching are ensured, and the problem that privacy leakage and security threats are easily caused by a disclosed channel in the prior art is solved.

The invention provides a method and a system for detecting network hidden attacks, which solve the problem of data imbalance of a training data set by using an oversampling algorithm and an undersampling algorithm, and highlight confused key features by capturing the long-distance dependency relationship of features and calculating the importance degree of each attribute feature, so that the network hidden attacks can be detected. A depth anomaly detection model is optimized, a node uploads trained model parameters, a control node optimizes and aggregates, and then issues the model parameters to each node, and the hidden attack is quickly identified by using the depth anomaly detection model, so that the problems that obfuscated codes cannot be effectively resisted and hidden attack means cannot be quickly and accurately identified in the prior art are solved.

The invention provides a train axle box bearing early-stage fault diagnosis method comprising the following steps: obtaining train axle box bearing operation data, and obtaining an original signal data set of a train axle box bearing early-stage state; balancing an early-stage original signal data set, obtaining initial time-frequency distribution, and obtaining an initial optimization time-frequency graph through reconstruction and denoising; gaussian distribution is used for fitting a main energy region of the normalized preliminarily optimized time-frequency graph, and an enhanced time-frequency graph is obtained; obtaining a modal interval based on the denoised and enhanced data; according to the coded two-dimensional time-frequency image, carrying out preset proportion division according to the state type to obtain a divided sample; and identifying a modal interval based on the trained MIA-Mamba2 model. According to the method, the problem of data imbalance can be solved, weak signals can be reserved, noise can be removed, and the problems that feature extraction is incomplete and complexity is too high in the early fault diagnosis process of the train axle box bearing are effectively solved.

The invention relates to the technical field of network security detection systems, in particular to a multi-modal fusion network abnormal behavior detection system and method. The multi-modal feature extraction module is connected with the multi-modal data collection module; the multi-modal fusion module is connected with the multi-modal feature extraction module and used for fusing the feature vectors Vi; the behavior recognition module is connected with the multi-modal fusion module and is used for analyzing the fusion vector F, judging whether the host to be tested has an abnormal behavior or not, and judging the category and confidence of the abnormal behavior; the active learning annotation screening module is used for screening and annotating unannotated data so as to optimize the model performance; multi-modal data collection provides rich original information for feature extraction, deep feature extraction provides high-quality feature representation for multi-modal fusion, a fusion method of an attention mechanism makes full use of the features, and an active learning module continuously optimizes the performance of the whole system.

The invention discloses a domain adaptive crowd counting method based on multi-aspect fine-grained alignment. The method comprises the following steps: 1, weighted sampling of a source domain image and a target domain image; 2, image coding and density map generation of a source domain and a target domain; 3, crowd density alignment based on conditional domain adversarial training; 4, image style alignment based on comparative learning; 5, optimizing model parameters on the crowd counting data set; and 6, performing crowd density map prediction by using the optimized model. According to the method, crowd specific information related to the target domain can be extracted, interference of irrelevant source domain features is filtered, crowd distribution of the source domain and the target domain is aligned in a fine-grained mode from multiple aspects, and the crowd distribution of the target domain is accurately aligned through weighted sampling and two loss functions related to distribution alignment. The consistency of the number of training samples, crowd density and image styles of the source domain and the target domain is constrained respectively, so that crowd distribution between the source domain and the target domain is correctly aligned, and generalization and robustness of a cross-domain crowd counting model can be improved.

The invention discloses a cross-regional load prediction method, system and device based on a shared encoder, and a storage medium. The method comprises the following steps: constructing a common covariable pre-training data set and a specific region data set; constructing a time sequence prediction backbone network, wherein the time sequence prediction backbone network comprises an input coding layer and a shared encoder based on a self-attention mechanism; designing a multi-task learning framework which comprises a multi-task learning network architecture and a dynamic weighting loss function; pre-training the encoder by using the common covariable pre-training data set; performing fine adjustment on the encoder in a specific region by utilizing the specific region data set of each region and combining with a multi-task learning framework; performing time sequence prediction on large-scale and cross-regional load data by using an encoder; and evaluating the performance of the encoder according to the time sequence prediction result. According to the method, the problems of data sparsity, regional difference, long-term dependency relationship capture, data imbalance and the like in cross-regional load prediction are effectively solved, and the prediction precision and the model generalization ability are remarkably improved.

The invention provides a variational auto-encoder anomaly detection algorithm NK-DSAVE based on a dynamic sparse attention mechanism, and the algorithm optimizes the calculation efficiency of the model while keeping high precision. Firstly, an enhanced few-sample data preprocessing method based on kernel density guidance is put forward to solve the problem of normal data category imbalance; secondly, providing a lightweight network DSCAVE, and balancing the precision and speed of the model by using an auto-encoder of a dynamic sparse attention mechanism and an auto-encoder of a dynamic skipping mechanism; and finally, providing a kernel density estimation-based dynamic selection threshold and sparse attention mechanism weighted scoring algorithm, and solving the problem of increased misjudgment rate caused by data fluctuation of small and medium-sized factory production data, thereby improving the accuracy and reliability of anomaly detection.

The invention provides a network intrusion detection method based on a de-noising diffusion probability model and a double-attention residual network, and belongs to the field of network intrusion detection. The method comprises the following steps: step 1, selecting and extracting features of original network traffic through three different types of claddings, cleaning the extracted features, and representing the cleaned features in an RGB image form; step 2, based on the network traffic RGB image generated in the step 1, learning local / overall features and fine-grained features of the network traffic by using a denoising diffusion probability model, and generating a network traffic sample of an attack type with a small scale to balance distribution of different types of network traffic; and step 3, dividing the expanded network traffic RGB image into a training set, a verification set and a test set by using a uniform random division mode, putting the training set into the network intrusion detection model based on the double-attention residual network for training, and performing verification by using the verification set to obtain an optimal network parameter. And finally obtaining a pre-trained network intrusion detection model.

The invention relates to the technical field of unmanned aerial vehicles, and discloses an unmanned aerial vehicle rotor device which comprises an arm assembly, a motor assembly, a damping assembly, a folding paddle assembly and a folding paddle limiting assembly, when an unmanned aerial vehicle needs to work, folding paddles in the folding paddle assembly are unfolded in parallel, and the folding paddle limiting assembly is fixed to paddle pressing pieces through a quick release mechanism in a matched mode; the folding blades are clamped between the limiting blocks, and the parallel unfolding state of the folding blades is fixedly kept. At the moment, when the motor assembly is started to output power torque, the folding blades cannot deviate due to uneven stress, and large vibration cannot be generated and transmitted to the unmanned aerial vehicle body and application equipment. And meanwhile, the damping assembly is in a working state, the damping rubber sleeve obstructs and filters vibration generated by rotation of the motor assembly and the folding paddle assembly, and the vibration is effectively prevented from being transmitted to an unmanned aerial vehicle body and application equipment. The invention further provides the unmanned aerial vehicle comprising the rotor wing device.

The invention relates to the technical field of power system operation control, and discloses a method and a system for inhibiting three-phase current imbalance of a power transmission line through series reactance, which comprises the following steps: establishing a power transmission line mathematical model, and calculating the positive sequence impedance of each phase line in the power transmission line based on the power transmission line mathematical model, the power transmission line comprises a single-circuit line and / or a multi-circuit line; determining a phase line needing to be compensated in the same circuit and a final compensation reactance value of the phase line; and connecting the final compensation reactance value to the corresponding phase line in series to form a series reactance compensation balanced power transmission line. According to the method, the problem of three-phase current imbalance can be thoroughly solved from the source, the method is not influenced by the operation mode and the network topology change, and the method is more feasible than the whole-line complete rolling transposition.

The invention relates to a remote sensing data change detection system, and the system comprises a single-flow-based lightweight change detection network model Lite-CDNet which comprises a depth feature fusion module DFFM, a multi-scale feature extractor, and a multi-scale axial attention module MAA; after feature fusion is carried out on an input dual-time-phase image through a depth feature fusion module DFFM, multi-scale feature extraction is carried out by using a lightweight network model ShuffleNetv2, and a multi-scale axial attention module MAA is used to help the model to identify changed regional features and improve feature details; a progressive change balance sampling strategy PCBS is used in the training process to promote model convergence. The method can guarantee the detection precision, and solves a problem of data sample imbalance.

The invention belongs to the technical field of bridge rotation weighing construction, and discloses a bridge horizontal rotation construction weighing auxiliary structure, which comprises at least 2n groups of weighing brackets symmetrically arranged on an upper bearing platform, n is a natural number of 2-6, and each group of weighing bracket comprises a weighing tripod, an upper anchoring assembly and a weighing jack, the weighing tripod is detachably installed on the upper bearing platform through an upper anchoring assembly, a weighing jack is arranged between the weighing tripod and the lower bearing platform, the weighing tripod is composed of a cross arm, an inclined strut and a stand column, and the upper anchoring assembly is composed of an anchoring connecting rod, a nut and a base plate. According to the weighing auxiliary structure, the problem that the height difference between the upper bearing platform and the lower bearing platform is large during weighing can be solved, the weighing jack is arranged on the outer side of the upper bearing platform, and the convenience, safety and reliability of construction can be improved. The invention further provides a weighing adjustment method for bridge horizontal rotation construction, the weighing operation construction process can be simplified, the construction efficiency is improved, the construction risk is reduced, and smooth proceeding of engineering is ensured.

The invention provides a management method and system for automatically generating standardized OT data based on a large model. The method comprises the steps that S1, an OT metadata ontology library is constructed into an OT term vector space according to standard regularized metadata meeting preset requirements; s2, mapping a natural language instruction to an OT term vector space through a large model to obtain standard structured OT data; and S3, carrying out quality verification and enhancement processing on the standard structured OT data. According to the method, the data consistency can be improved, the naming conflict in the integration process is solved through the unified cloud standard specification, and the data interoperability is remarkably enhanced; the efficiency revolution can be implemented, the data cleaning workload is effectively reduced, the qualitative change from a project system to productization is realized from traditional manpower integration, and the basic support of high-quality training data is provided for large-scale industrial deployment.

The embodiment of the invention discloses a stator winding and a motor. The stator winding comprises a plurality of winding branches, wherein each winding branch comprises a wire inlet end and a wire outlet end; wherein the number of winding layers of the winding branches is multiple, the winding branches conduct winding in the stator grooves, the winding mode of the winding branches is a continuous wave winding mode, and the stator grooves at the wire inlet end and the wire outlet end of each winding branch are different stator grooves. According to the stator winding and the motor provided by the embodiment of the invention, the problem of imbalance of inter-phase current can be solved, and the output efficiency is improved.

The invention discloses a micro-expression recognition method and device based on AU guidance, and the method comprises the steps: carrying out the preprocessing of a micro-expression sample video, and obtaining a micro-expression sequence; generating a facial muscle movement text description for each micro-expression sample through an AU coding label of the public data set and a facial movement coding system; sending the processed micro-expression sequence into a visual encoder to obtain encoded visual motion features; sending the motion text description into a text encoder to obtain text motion features; by generating AU-guided fine-grained micro-expression facial muscle motion text description and utilizing CLIP comparison loss to perform cross-modal semantic alignment, perception and capture of a model on weak local micro-expression motion can be improved, remarkable space-time micro-expression motion features are learned, the motion features are effectively converted into emotional features, and the motion features are effectively converted into emotional features. And the Focal Loss classification loss is used to solve the problem of micro-expression data class imbalance, so that the recognition performance of the model is greatly improved.

The invention discloses an igneous rock reservoir fluid identification method based on a cascade forest, and relates to the field of rocks, the igneous rock reservoir fluid identification method based on the cascade forest comprises the following steps: step 1, establishing an igneous rock reservoir fluid identification pre-training model data set, and preprocessing data; compared with the prior art, the method has the advantages that the result-oriented parameter optimization process is avoided, the data set is balanced under the condition that the data scale is kept, and the classification accuracy of the unbalanced logging data set is improved; the method has the advantages that the applicability is higher; according to the method, reservoir fluid identification work can be efficiently and accurately completed in igneous rock stratums with complex fluid properties; according to the invention, the prediction rate and the back-judgment rate of fluid identification are improved; the problem of data imbalance in the field of igneous rock fluid identification is effectively solved, and the effect and applicability of the model are improved.

The present invention discloses a method and system for cleaning and classifying abnormal power consumption data of power users. The method includes the following steps: collecting historical power consumption data of power users; preprocessing the historical power consumption data; expanding the preprocessed historical power consumption data to obtain a data set; constructing a power theft discriminator; using the trained power theft discriminator to classify the power consumption data of monitored power users in the distribution network in real time, and judging them as non-power theft users or power theft users according to the classification results. The present invention adopts a scheme for expanding the historical power consumption data set, adds synthetic samples of the minority class and deletes redundant majority class samples, realizes a balanced distribution of the data set, effectively solves the problem of unbalanced data sets, thereby improving the detection accuracy of the power theft discriminator for minority class samples, and enables the power theft discriminator to detect power theft more accurately.

The invention relates to the technical field of transformer substation defect identification, in particular to a transformer substation defect identification method and system based on lightweight model improvement, and the method comprises the steps: constructing a transformer substation defect data set; the YOLOv5 neural network model is improved based on a lightweight model, and a transformer substation defect identification model is constructed; training super parameters and network parameters are set, a training set in the transformer substation defect data set is input into a network, the transformer substation defect recognition model is trained, and a trained weight file is stored; outputting predicted bounding box information and category probability; and the detection frame is filtered by using a softened non-maximum value, the detection picture is visualized, and a final target detection frame and an identification result are generated. According to the invention, various defects in the transformer substation can be quickly and accurately identified, the detection result is presented in a visual mode, and powerful support is provided for safe operation and efficient maintenance of the transformer substation.

The invention belongs to the technical field of fish feeds, discloses a low-fish-meal mandarin fish compound feed as well as a preparation method and application thereof, and particularly discloses the low-fish-meal mandarin fish compound feed. Comprising the following components: fish meal, chicken meal, pig spray-dried animal blood cells, shrimp meal, dephenolized cottonseed protein powder, starch, soybean oil, monocalcium phosphate, microcrystalline cellulose, premix, rice hull powder and amino acid. In the components of the low-fish-meal mandarin fish compound feed provided by the invention, a proper amount of chicken meal and dephenolized cottonseed protein powder are used for replacing fish meal, so that the growth performance of mandarin fish can be improved. Therefore, a proper amount of chicken meal and dephenolized cottonseed protein powder are used for replacing fish meal in the mandarin fish feed, so that the breeding cost can be obviously reduced without reducing the production efficiency, and the healthy and sustainable development of the industry is promoted while the economic benefit is improved. Lysine, methionine and threonine are supplemented, and the problem of amino acid imbalance caused by replacement of fish meal with chicken meal in the feed is solved.

The invention discloses a training data balance processing method and device, equipment, a medium and a product. The invention relates to the technical field of data processing. The method comprises the following steps: when a user in a user set is associated with an object in an object set, generating associated data according to the associated user and object, and adding the associated data into an associated data set; acquiring other users of the same category as the target user corresponding to the to-be-supplemented data of the associated data set; obtaining a target object associated with the target user in the associated data set; according to each target object, determining candidate objects of the target user in other objects associated with the other users in the associated data set; and generating associated data according to the target user and each candidate object, and adding the associated data into the associated data set. The embodiment of the invention can balance the training data of the model.

The invention discloses a method for processing bearing fault sample data imbalance by using an MRS-GNN model and a fault classifier. The method comprises the following steps: firstly, constructing a label set for all one-dimensional vibration signals of a bearing; and constructing all vibration signal samples into graph data by using a GNN graph neural network and calculating a new embedded representation of each node, and finally, expanding the number of all minority class samples by using an MRS algorithm, so that the number is equal to the number of the samples with the maximum label number. According to the method, the problem of unbalanced bearing fault sample data in bearing fault intelligent diagnosis is effectively solved, the classification accuracy of a fault classifier on all classes can be improved, and particularly the prediction capability on minority classes of faults is improved; the detection capability of a few kinds of faults is improved, high-cost faults can be prevented, accidental shutdown time and maintenance cost are reduced, and production efficiency and equipment health are guaranteed.

The utility model discloses a tire mold heating structure, which belongs to the field of tire molds and comprises a heating plate body, and a plurality of annular grooves are arranged on the end face of the heating plate body. At least one group of electric heating elements is arranged in each annular groove, the number of each group of electric heating elements is three, and the lengths of the three electric heating elements in each group are equal; the three electric heating elements in each group are connected end to end, and the three end-to-end connection parts are respectively connected with three phase lines of three-phase power, or one ends of the three electric heating elements in each group are connected together, and the other ends of the three electric heating elements are respectively connected with the three phase lines of the three-phase power. According to the structure, an electric heating mode is adopted, the energy utilization rate is high, and impact on a workshop power grid is avoided.