131results about How to "Few parameters" patented technology

The invention relates to the technical field of prostate MRI (Magnetic Resonance Imaging) image segmentation, in particular to a prostate MRI image segmentation method based on Mamb-Unet, which realizes effective fusion of features of different scales between an encoder and a decoder, and fuses multi-scale information on a space axis by using a space attention bridge segment to fuse fusion features of different levels from the encoder, so that the segmentation accuracy of the prostate MRI image is improved. And then global and local information is captured through 1D convolution and full connection in the channel attention bridge segment, so that a channel attention map is generated, channel information is better integrated, and multi-level different-scale feature fusion is realized.

The invention discloses a road defect detection method based on a DRR module and an SDFM. The method comprises the following steps: S1, data acquisition and processing; s2, constructing a model: replacing a DWR module with a DRB module, and replacing a BottleNeck residual module of a backbone network part C2f through the DRR module; downsampling of a backbone network and a neck is replaced by an LDConv convolution module, a neck structure of an SDFM improved model is used, and features of different scales are fused to serve as input of a detection head; s3, model training: training the improved network model by using the made training set by setting training hyper-parameters; s4, model verification: setting verification parameters to verify the trained model; and deploying the verified model to a visual interface to realize real-time detection of road defects. According to the method, the model is improved, so that the detection algorithm has higher accuracy and robustness, and can adapt to different road defects and environmental conditions.

The invention discloses a large language model parameter fine tuning method, system and device, a storage medium and a product, and relates to the field of natural language processing. The fine tuning method comprises the steps that a pre-training model and a parameter matrix of the pre-training model are acquired, a parameter fine tuning module is arranged on a self-attention layer of the pre-training model, the parameter fine tuning module comprises LoRA modules of different task types and a router, each LoRA module comprises a general feature matrix and a specific feature matrix, and the general feature matrixes of the multiple LoRA modules are shared; obtaining a fine tuning data set; loading and freezing a parameter matrix of the pre-training model, and initializing parameters of a parameter fine tuning module; and performing fine tuning on the parameters of the parameter fine tuning module based on the fine tuning data set to obtain a fine-tuned large language model. Parameters of the MoE architecture are remarkably reduced, it is ensured that the model captures differences of various tasks to the maximum extent, and the cross-task generalization of the model is ensured.

The invention discloses a power grid communication equipment fault identification method and system based on multi-source heterogeneous data characterization learning. The method comprises the following steps: firstly, collecting various complex multi-source heterogeneous data containing fault power grid communication equipment and preprocessing the complex multi-source heterogeneous data; extracting deep semantic features by using a pre-trained feature extraction network and obtaining a feature vector sequence; capturing time features of the feature vector sequence through a bidirectional long-short-term memory network, and obtaining complete sequence feature representation through a full connection layer; performing low-rank multi-modal fusion on the complete sequence feature representation in combination with cross-modal Transform to obtain three types of output splicing construction joint representation, and obtaining a fusion feature by using a self-attention mechanism; and finally, constructing a fault identification model by using the fusion features. Through innovative data preprocessing and data fusion technologies and in combination with an advanced deep learning model, fault-related characteristics can be automatically learned from multi-source heterogeneous data, and intelligent identification of the fault state of the power grid communication equipment is realized.

The invention relates to the field of short-term load prediction and power dispatching control of a power system, in particular to an energy output optimization dispatching method and system considering a random source load virtual power plant, and designs a virtual power plant double-layer optimization dispatching model. The lower-layer model constructs a user load prediction model of an improved Transform, and then a renewable energy output model is established by using a scene generation method; the upper layer model takes the power generation cost minimization of the wind-light storage and combustion virtual power plant as a target, considers constraint conditions such as gas turbine output power, ramp rate, energy storage charging and discharging power, electricity storage quantity and power balance, and proposes a single guide target function comparison algorithm considering random source load to carry out optimization solution on a virtual power plant optimization scheduling target function; and planning and deciding the output of each energy source in the next 24 hours. Experiments show that the new energy consumption level can be remarkably improved under the random source load condition, and better economic benefits are obtained while stable operation of a power distribution system is promoted.

The invention relates to artificial intelligence, and discloses a speech synthesis method and device with a conditional matching stream, equipment and a medium, and the method comprises the steps: receiving text information, coding the text information into a high-dimensional implicit vector, and obtaining a text information vector; label information is formed according to the alignment relation between the text information and the voice, and the relation between the acoustic features of the text information and the voice is predicted; performing matching in the voice data set according to the text information vector to obtain corresponding text-related voice, generating intermediate-state voice according to Gaussian noise, the text-related voice and the time step, performing noise prediction according to the intermediate-state voice and the time step by adopting a conditional matching flow model to obtain predicted noise, and outputting the predicted noise. Calculating the loss between the input Gaussian noise and the prediction noise, and combining the prediction noise with the intermediate state voice to extract and obtain the acoustic features of the text related voice; and generating a decoded speech waveform according to the obtained acoustic characteristics of the text-related speech by adopting an acoustic decoder. And the speech synthesis quality is improved.

The invention provides a cement decomposing furnace temperature prediction control method based on a KAN enhanced neural network, and belongs to the technical field of cement calcination. A CNN-LSTM-KAN network is established as an f-CaO and Nox prediction model, and a state parameter optimization objective function is established in connection with actual production requirements; and solving an optimal solution and an optimal solution interval of the state parameters of the decomposition furnace through a multi-target particle swarm optimization algorithm. A KAN-Enhanced-Informer network is established to predict the temperature of the decomposition furnace, a target function is established by combining a state optimization result with the more accurate prediction result, the less coal consumption and the reasonable alternative fuel quantity as targets, the optimal solutions of the coal feeding quantity and the alternative fuel quantity are obtained, and the optimal solutions are applied to a control model to ensure that the temperature of the decomposition furnace reaches the optimal set value. The problems that in the actual cement production process, energy consumption is too high, the yield is not ideal, and much sewage is discharged are solved.

The invention discloses an electric power model deployment method and device based on federated learning and knowledge distillation, and the method comprises the steps: carrying out the data division of a common data set, and obtaining a training set; constructing a teacher model, and training the teacher model through the training set; constructing a student model, and training the student model through the training set and the teacher model; and descending the student model to a power distribution network edge node based on a federated learning framework, training the student model through a local data set, deploying the student model to the power distribution network edge node for operation, and updating the student model regularly. The method and the device provided by the invention not only can effectively reduce model parameters to realize lightweight deployment of the power distribution network, but also can ensure the security of the model during data sharing.

The invention discloses a power grid abnormal situation awareness method and system. The method comprises the following steps: acquiring power grid data in real time and calculating different power grid situation evaluation indexes; weighting each power grid situation assessment index, correcting the weight of an abnormal index, and then performing linear weighting on all the power grid situation assessment indexes to obtain a situation assessment value; constructing a prediction model with a double-layer gating recurrent neural network, an attention layer and an output layer cascade, inputting historical data of a power grid situation assessment index, and outputting a future situation assessment prediction value; and inputting new historical data of the power grid situation assessment index into the trained prediction model to obtain a corresponding future situation assessment prediction value, and matching the future situation assessment prediction value with a pre-divided security level to determine whether an abnormality occurs. According to the method, a deep learning framework is utilized, the model for predicting the power grid operation situation of the double-layer gating recurrent neural network based on the attention mechanism is constructed, and a better prediction effect and higher accuracy are achieved.

The invention relates to a power transmission line fire smoke identification method based on improved YOLOv9. The method comprises the following steps: constructing a fire smoke image data set; constructing a power transmission line fire smoke detection model; inputting the training set into the power transmission line fire smoke detection model for training, and storing the optimal power transmission line fire smoke detection model obtained through training; and inputting a to-be-identified power transmission line fire smoke picture into the optimal power transmission line fire smoke detection model to obtain a power transmission line fire smoke picture detection result. According to the method, depth separable convolution is introduced, so that the calculation amount can be reduced, parameters are reduced, and the network detection speed is increased; a parallel weighted mixed domain attention module is adopted to enhance extraction of target features in the fire smoke image; the up-sampling content perception feature recombination network structure CARAFE has a larger receptive field, the perception of important content is enhanced, and the lightweight level of the model can be kept due to the fact that the operation amount is small.

The invention discloses a non-invasive blood pressure prediction method based on signal dimension extension and a lightweight network, which comprises the following steps: firstly collecting PPG blood pressure data and ABP data, then denoising the collected PPG blood pressure data and ABP data, and cleaning the denoised data. The processed data is used for data signal dimension expansion, a PPG blood pressure measurement model is constructed, and the PPG blood pressure measurement model comprises a basic convolution layer and a residual grouping convolution module Group ResidualBock; and then deploying the constructed PPG blood pressure measurement model into the wearable device to obtain the wearable blood pressure monitoring device. And finally, measuring the processed PPG signal by using wearable blood pressure monitoring equipment to obtain a blood pressure value. According to the method, the PPG signal dimension is expanded, the data processing link is optimized, and the model blood pressure prediction accuracy is improved; and meanwhile, a lightweight algorithm architecture is adopted, so that resource occupation is reduced, the system can be deployed in wearable embedded equipment, and the security of personal privacy data is guaranteed.

The invention discloses a high arch dam deformation state fractional order numerical analysis method and module, and relates to the technical field of hydraulic structure service state analysis and computational mechanics. The method comprises the following steps: establishing a high arch dam body and dam foundation fractional order rheological mechanical element model by constructing a fractional order characterization method of attenuation rheological, steady-state rheological and accelerated rheological in a three-dimensional stress state; calculating an internal stress increment, a viscoelastic strain increment, a viscoplastic strain increment and a deformation increment in a delta tn time period by adopting a front difference formula according to the stress, the viscoelastic strain, the viscoplastic strain and the deformation at the tn moment by virtue of an increment finite element method, so as to obtain the stress, the strain and the deformation at the tn + 1 moment; and repeatedly calculating to obtain the stress, strain and deformation of the high arch dam in the analysis time period. According to the method, the nonlinear rheological effect of the dam body and the dam foundation of the high arch dam is objectively described, scientific deformation property numerical value quantitative analysis is achieved, technical support is provided for safety monitoring and dangerous case early warning of the in-service high arch dam, and the method has wide application prospects and market prospects.

The invention discloses a gyrotron traveling wave tube low-speed scattered magnetic control injection electron gun and a design method, and belongs to the field of vacuum electronic devices. The electron gun comprises a cathode and an anode. The cathode comprises a cathode bottom table, a rear forming pole, an emission band and a front forming pole, the radius of the cathode bottom table is larger than that of the rear forming pole, the generatrix of the emission band is an arc curve, and the overall surface of the front forming pole is an arc surface; besides, in the design of the cathode, through two times of modeling and respective simulation optimization of partial parameters, the parameters in the one-time simulation optimization process are reduced, the optimization target is clearer, the design difficulty is effectively reduced, and the design time is shortened. The problem that the electric field of the gun area of the electron gun is too high due to the fact that the size of the cathode is too small is effectively solved, meanwhile, the adverse effect of the abrupt change structure of the cathode on the surface electric field of an emission band is avoided, and speed scattering of the electron gun is effectively reduced.

The invention relates to a dam disaster point identification method based on improved DeepLabV < 3 + >, and the method comprises the following steps: Step 1: data preprocessing: changing a data set composed of dam images into a size which can be trained by a network according to the demands; step2, establishing a dam disaster point identification model based on the improved DeepLabV < 3 + >, applying a lightweight network MobileNetV2 in the model, optimizing the expansion rate of a cavity space pyramid pooling module, and introducing a channel attention mechanism and a space attention mechanism, and Step3, training by using the dam disaster point identification model based on the improved DeepLabV < 3 + >, and obtaining a dam disaster point image segmentation result. According to the algorithm, the recognition precision of dam disaster points is improved by introducing an adaptive attention mechanism, a feature extraction module in the algorithm adopts specific cavity convolution configuration, the capture capability of small-scale disaster features is enhanced, and a decoder structure is improved, so that more efficient feature fusion is realized, and the accuracy of semantic segmentation is improved.

The invention discloses a method for analyzing and predicting drug-target interaction by using deep learning, which comprises the following steps: encoding a drug and a target protein, and extracting the characteristics of the drug and the target protein for interaction; inputting the interaction characteristics of the drug and the target protein into a multi-head cross attention mechanism, and extracting the interaction characteristics of the drug and the target protein; obtaining independent characteristics of the drug and the target protein; fusing and re-classifying the independent characteristics of the drug, the independent characteristics of the target protein and the interaction characteristics of the drug and the target protein, and predicting drug-target interaction; the invention provides a network based on feature extraction between global molecules and local feature molecules of a drug-target, and the DTIs of the drug-target is predicted; according to the method, the interaction features of the drug target are extracted by adopting a cross attention mechanism, and the independent features of the drug target are extracted by using GAT and CNN, so that rich drug-target information is obtained, and the prediction performance is improved.

The invention belongs to the technical field of image processing, and particularly relates to a non-uniform low-illumination image enhancement method and system. The method comprises the following steps: step 1, constructing a network model: constructing a non-uniform low-illumination image enhancement network model, wherein the model comprises a Retinex network, an illumination image enhancement network, a reflection image enhancement network and a multi-scale enhancement network; step 2, preparing a data set: dividing a training set and a test set by using an LOL-v1 data set, and preprocessing the training set and the test set; and performing fine adjustment on the model by the LOL-v2 data set. According to the invention, based on deep learning, an efficient two-way feature enhancement network is designed and is used for improving the performance of image features. On the basis of Retinex network decomposition, an input image is decomposed into an illumination image component and a reflection image component, and the characteristics and channel dimensions of the illumination image component and the reflection image component are modulated respectively, so that the characteristics of a low-illumination image are effectively enhanced. According to the method, the quality and definition of the image can be remarkably improved, and illumination and reflection details are brighter.

The invention relates to an electroencephalogram signal automatic sleep staging method based on a residual network and multi-level attention, and belongs to the technical field of sleep monitoring, and the method comprises the following steps: S1, constructing a sleep data set, and carrying out data preprocessing; s2, building a single-channel electroencephalogram automatic sleep staging network model based on deep learning; s3, training the model by using a gradient descent method; s4, sleep staging of the single-channel electroencephalogram signals is achieved through the sleep staging model with the optimal parameters. According to the method, multi-scale feature extraction is realized by using convolution kernels of different sizes, signal features are extracted more comprehensively by combining a style pooling-based recalibration module with a space attention module, and time sequence information is captured and important sequences are highlighted by using a gated loop network fused with a self-attention mechanism. And finally, the sleep staging accuracy is improved.

The invention discloses a force measurement wind tunnel test device with a jet flow control airfoil profile, which belongs to a flow control technology and at least comprises but is not limited to a test section, an end plate, an airfoil profile main wing and an airfoil profile flap, accommodating cavities for accommodating the end plates are formed in the side walls of the two sides of the test section, the end plates are movably arranged in the accommodating cavities, the airfoil flap is connected with the airfoil main wing, the airfoil main wing is arranged between the end plates on the two sides, and the end face, far away from the airfoil main wing, of the end plate on one side is connected with the balance through a connecting piece; beveling parts are arranged between the wing-shaped flaps and the end plates; according to the scheme, angular separation and wingtip vortex between the airfoil profile and the end plate can be effectively inhibited, so that the force measurement result is closer to the value of a two-dimensional airfoil profile.

The invention discloses a convolutional neural network structure search method based on a genetic algorithm, and belongs to the technical field of image classification. According to the method, an optimizable convolutional structure FlexCell unit is introduced, the structure uses a depth separable convolution technology and a multi-scale design, and various convolutional structures can be generated through corresponding weight parameters to fully extract features of input data, so that the performance of a convolutional neural network is improved; according to the invention, a three-dimensional coding space is designed and FlexCell is combined to generate various candidate convolutional neural network structures, and an improved two-stage genetic algorithm and a cross-compilation operator are used to search for an optimal convolutional neural network structure. Experimental data prove that the optimal structure of the neural network is obtained through the search method, and compared with an existing search method, higher image classification precision can be achieved with fewer parameters and lower time cost.

The invention discloses an Android malicious application detection method based on a multi-view deep neural network, and relates to the technical field of information. The invention provides an Android malicious application detection method based on a multi-view deep neural network in view of the technical problems of numerous attack means, complex and changeable semantics, difficulty in ensuring the coverage rate of attack behaviors by executing detection only from a single view and the like of the current Android malicious application. According to the method, multi-view static feature information is organically fused, the synergistic effect of static features under all views is fully exerted, a target object is comprehensively described, limitation and fuzziness caused by application analysis from a single view are avoided, and finally accurate detection of malicious applications is achieved.

The invention provides a many-to-many saturation interception target allocation optimization method and system based on threat sorting. In order to solve the problem of target distribution in multi-target multi-interception saturation interception, threat attribute values such as attack object value, residual distance, flight speed and type value of an air attack target are introduced, and a comprehensive threat quantitative evaluation sorting method is provided through normalization and weight coefficient processing. Meanwhile, an interception success probability rapid calculation model based on the zero-control miss distance and the relative position and a first-time and second-time target distribution optimization algorithm based on threat sorting and a success rate matrix are constructed. The method has the advantages of being few in parameter, easy to obtain, small in calculation amount, capable of achieving real-time dynamic processing, wide in application range and the like, and the comprehensive efficiency of large-scale saturated multi-target multi-interceptor collaborative interception combat is remarkably improved.

The present invention discloses an edge computing task scheduling method based on ARPSO, characterized in that it includes: initializing a task scheduling cluster, forming a scheduling cluster through an initial random scheduling strategy for the subtasks of task scheduling and the virtual machines that execute the subtasks; initializing a particle swarm; optimizing the particle swarm using an ARPSO algorithm formula, taking the shortest time required for all tasks as the fitness value; updating and iterating the particle swarm using the fitness value formula, and obtaining the optimal scheduling cluster according to the global optimal position. The method for scheduling edge computing tasks based on the ARPSO algorithm of the present invention can overcome the disadvantage of falling into local optimality on the basis of the ARPSO algorithm, an optimization algorithm based on PSO, and ensure the diversity of the population. It can more easily optimize a reasonable task scheduling scheme, effectively reduce the scheduling time of edge computing tasks, and improve the computing and processing efficiency of edge computing.

The invention belongs to the field of distributed optical fiber signal vibration event classification, and discloses a perimeter security area abnormal event identification method based on optical fiber signals. An optical fiber vibration event data set is collected through a phase-sensitive optical time domain reflectometer and preprocessed, and a training set is formed; the 1DCNN model is improved; inputting the training sample into the improved 1DCNN deep learning model for training, and obtaining a trained improved 1DCNN model; and abnormal event identification is carried out. The method improves the recognition accuracy of the abnormal events in the perimeter security area, and solves the problems that a traditional feature extraction method for optical fiber signals needs to manually manufacture features, seriously depends on expert knowledge and is weak in generalization ability, and the calculation amount is large in the process that an existing model carries out recognition through the optical fiber signals.

The invention discloses a demand side flexible resource participation multi-objective optimization modeling method and a related device. The method comprises the following steps: determining initial data including wind power generation, thermal power generating units, electric vehicle disordered charging, distributed electric heating and user side energy storage; an objective function of the multi-objective optimization model is determined, boundary conditions of the multi-objective optimization model are designed according to the objective function and the basic data, and the multi-objective optimization model is constructed; designing a conventional thermal power adjustment scene and a typical demand side flexible resource adjustment scene based on the auxiliary service market; based on a conventional thermal power adjustment scene and a typical demand side flexible resource adjustment scene, the obtained initial data are utilized, an improved particle swarm optimization algorithm is adopted to solve a multi-target optimization model, and an optimization solving result is output. According to the method, the regulation capability of the power grid is optimized, the wind curtailment rate and the wind curtailment cost are effectively reduced, the absorption capability of new energy is improved, the problem of power curtailment caused by blockage of a delivery section is reduced, and the method has important significance in promoting sustainable development of the new energy.

The invention provides an Iwan model modeling method and device of a bolted connection structure and electronic equipment, and the method comprises the steps: constructing a dynamic pressure distribution function of the bolted connection structure based on a contact boundary of a contact surface in the bolted connection structure by applying a linear pressure distribution function; solving a density function based on the dynamic pressure distribution function and a friction theory to obtain a density function of yield displacement; and introducing the density function of the yield displacement into a general Iwan model to construct an Iwan model. According to the method provided by the invention, the dynamic pressure distribution function of the bolt connection structure is constructed by selecting the linear pressure distribution function and combining the contact boundary of the contact surface. And density function solving is carried out based on the dynamic pressure distribution function and the friction theory, and a density function of yield displacement is obtained. The density function of the yield displacement is introduced into the universal Iwan model, the Iwan model of the bolt connection structure is obtained, Iwan model construction with few parameters and good representation effect is achieved, and the calculation complexity of the Iwan model is reduced.

The invention discloses a road thrown object classification detection method integrated with environmental information perception. The method comprises the following steps: acquiring road thrown object image data; the method comprises the following steps: marking pixel point information belonging to different types by using a semantic segmentation model according to various real object information, such as roads, vehicles, thrown objects and the like, in an environment in front of a vehicle in running, and extracting refined information of each pixel point in thrown object image data; and using the trained target detection model to perform feature extraction on the refined information of the road spilled objects obtained by semantic segmentation, and outputting the detected road spilled objects and categories thereof. The method can detect the thrown objects which are static in the area in front of the running of the vehicle, is suitable for various complex scenes in the running process of the vehicle, is excellent in detection performance of various thrown objects, and has high practical value.

The invention discloses a cake surface flaw detection method and system based on YOLOv8 improvement, and the method comprises the steps: S1, obtaining a cake image through an image collection device, and constructing a data set of cake surface flaws with labels; s2, a C2f module of the YOLOV8s backbone network is replaced by a C2f-OD module; s3, adding a small target detection layer in the neck network of the YOLOv8s; s4, the CIoU of the YOLOv8s is replaced by the Inner-MPDIOU, so that an improved YOLOv8s model is constructed and obtained; and S5, training the improved YOLOv8s model to obtain a final pancake surface defect detection model, and finally detecting the pancake surface defect image to be detected by using the pancake surface defect detection model. According to the method, accurate positioning can still be realized under the condition that various noises exist in the flour cake surface defect image.

A robust control method for an aero-engine starting control plan comprises the steps that in the engine starting process of an aero-engine, according to a control program of a first redundancy fuel control plan, an acceleration fuel flow target # imgabs0 # is obtained at the current moment j, and an acceleration fuel flow fusion target # imgabs1 # at the previous moment j-1 is obtained; a fusion coefficient # imgabs2 # at the current moment is obtained through weighted calculation, and then a weight # imgabs5 # is obtained through calculation according to the fuel oil deviation # imgabs3 # of the fuel oil control plan and the acceleration deviation # imgabs4 # of the second conversion acceleration control plan; inputting # imgabs6 # into Proportional-integra control to output accelerated fuel flow at the current moment j, fusing the accelerated fuel flow with # imgabs7 #, obtaining a steady-state fuel flow target # imgabs8 # at the current moment j according to a control program of a third steady-state fuel control plan, and taking a minimum value of the accelerated fuel flow target # imgabs8 # and the steady-state fuel flow target # imgabs9 # to obtain a final fuel flow target # imgabs9 # of the starting control plan.

A K-CNN-BiGRU-based ship outfield coating atmospheric pollution concentration prediction method comprises the following steps: firstly, deploying an environment monitoring terminal to collect data such as weather and pollutant concentration, performing grid division on a research area, performing spatial interpolation by adopting IDW, performing calculation and arrangement to obtain a grid data set of atmospheric pollutant concentration, and calculating the atmospheric pollutant concentration according to the grid data set of the atmospheric pollutant concentration; the method comprises the following steps: firstly, calculating spatial correlation by using a KNN tree algorithm, screening to obtain a spatial correlation matrix, arranging and splicing the spatial correlation matrix into a space-time class diagram according to a time sequence, secondly, inputting the space-time class diagram into a CNN model to extract local space-time characteristics, and finally, sending the extracted space-time characteristics into BiGRU to carry out global prediction. According to the invention, the atmospheric pollution concentration of the ship outfield coating plant in the future period can be predicted, and employees are guided to scientifically carry out coating construction and safe and environment-friendly management.

The application relates to the technical field of artificial intelligence optical character recognition, in particular to an end-to-end communication big data journey card recognition method, and the steps of the method comprise the following steps: adjusting and correcting a text box according to size information of the text box, so that the size of the text box meets the required angle and proportion of adjustment; performing separated feature extraction on the corrected text box through a preset neural network to obtain feature data of a font; and obtaining text data corresponding to the feature data through a Bi-GRU recurrent neural network combined with an activation function.