79results about How to "Speed ​​up the convergence process" patented technology

The invention discloses an online reinforcement learning data increasing and expanding method based on a diffusion model. The method comprises the following steps: processing original trajectory data to generate enhanced feature data; extracting global structure representation and local detail representation; carrying out fusion by adopting a hierarchical integration method to obtain unified hierarchical representation data; generating constraint coding data based on pre-stored physical constraint parameters and task constraint parameters, and fusing to generate constraint perception representation data; generating an evaluation result based on the current strategy parameter; performing adaptive adjustment on the constraint perception representation data to obtain adjusted representation data; modal analysis is carried out, diversified trajectory data is generated, and a candidate trajectory set is obtained; and carrying out quality evaluation, carrying out trajectory screening through a multi-objective optimization method, and updating strategy network parameters to obtain updated strategy parameters. According to the invention, high-quality training data can be automatically generated, and the training efficiency and performance of a reinforcement learning system are improved.

The invention provides an additive manufacturing residual stress optimization method and system, and the method comprises the steps: searching a global optimal solution enabling the residual stress of an additive manufacturing part to be minimum from a technological parameter space through the combination of multi-physics field numerical simulation and an intelligent optimization algorithm; the multi-physics field numerical simulation comprises the steps of sampling from a process parameter space by using an optimization algorithm to obtain process parameters, inputting the sampled process parameters into a finite element model, performing thermal analysis on the process parameters based on the finite element model, and obtaining transient thermal distribution through thermal analysis. And performing structural analysis by using transient heat distribution to obtain residual stress under the current process parameters, and transmitting the obtained residual stress to an intelligent optimization algorithm for realizing process parameter optimization. The method has the advantages of high precision, low cost and the like, and high-precision collaborative optimization of multiple types of process parameters can be realized.

The invention relates to the technical field of artificial intelligence, and discloses an artificial intelligence-assisted adaptive sickbed control system and method, and the method comprises the steps: carrying out the noise reduction and normalization preprocessing of original physiological data collected by a multi-modal sensor, and obtaining standardized multi-modal data; performing time sequence fusion and dimension reduction to obtain low-dimensional fusion features; performing feature extraction through a multi-branch convolutional neural network to obtain generalization feature representation; the optimal posture demand of the patient is predicted through a long-short term memory network model with an attention mechanism, and an optimal posture demand prediction result is obtained; a layered sickbed adjustment strategy is generated through a double-time-scale reinforcement learning network comprising a priority experience playback mechanism; according to the intelligent sickbed control method and system, the multi-mode sensing data can be comprehensively utilized, the adaptive learning ability is achieved, the intelligent sickbed can be accurately controlled, and the performance and the application effect of the intelligent sickbed are improved.

The invention discloses a T-S fuzzy and TD3-based slow dynamic unknown coal-fired power generation system coordination control method, which comprises the following steps: firstly, decomposing a coal-fired power generation system into a fast subsystem and a slow subsystem by using a singular perturbation theory, and decomposing an original control task into a stabilization task of the fast subsystem and a tracking task of the slow subsystem; for the fast subsystem, a fuzzy set is selected on a definition domain of the fast subsystem by using the slow variation characteristic of steam pressure, and a T-S fuzzy model is constructed; a fast subsystem controller is obtained by solving algebraic Riccati equations corresponding to a plurality of linear systems. For a slow subsystem, a double-Q network is adopted to reduce overestimation of a Q value, a dynamic learning rate and a batch size adjustment mechanism are introduced to accelerate training convergence, and learning is carried out under a TD3 algorithm framework to obtain control input of the slow subsystem. The fast subsystem and the slow subsystem control inputs to be combined and then act on the original system to obtain state information at the next moment, and the intelligent agent interacts with the original system to complete collaborative optimization.

The invention discloses a sewage treatment effect prediction method and system based on deep learning. The method comprises the steps of data acquisition, data preprocessing, construction of a treatment effect prediction model, hyper-parameter optimization and sewage treatment effect prediction. The invention relates to the technical field of sewage treatment data prediction, in particular to a sewage treatment effect prediction method and system based on deep learning, and the method comprises the steps: obtaining sewage treatment original data through data collection; a data preprocessing method of data cleaning, data labeling, data coding, data normalization and data set segmentation is adopted; the improved space-time attention graph convolution model is adopted to predict the sewage treatment effect, so that key time sequence characteristics in time sequence data and a complex space relationship involved in the sewage treatment process can be effectively extracted; the model hyper-parameters are optimized by adopting a hunting optimization algorithm, so that the parameter space can be explored in a targeted manner when sewage treatment data with multivariable and complex spatial-temporal characteristics are processed.

The invention provides a high-performance material visual screening system based on machine learning and an application method thereof. The system comprises a feature extraction module, a machine learning model training module, a prediction module and a feedback optimization module. The data preprocessing module is used for performing primary processing on the original data, wherein the primary processing comprises removal of invalid data and abnormal values; the feature extraction module is used for converting a time domain signal into a frequency domain signal by adopting Fourier transform, extracting a frequency domain feature, and performing data dimension reduction by adopting principal component analysis (PCA); the machine learning model training module is used for ensuring the generalization ability of the model by adopting a cross validation technology in the training process, and accelerating the convergence process of the model through a gradient descent method; the prediction module is used for predicting the material performance of the high-performance material to obtain a prediction result; and the feedback optimization module is used for automatically optimizing model parameters by adopting Bayesian optimization, analyzing a prediction result of the model and dynamically adjusting the model parameters so as to improve the prediction precision. Through the scheme of the embodiment of the invention, the law can be learned from a large amount of experimental data by a machine learning technology, and the material performance can be quickly and accurately predicted.

The invention relates to a noise feature vector classification model construction method, a speech enhancement method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: coding penalty parameters and kernel function parameters of a support vector machine; taking the penalty parameter and the kernel function parameter as optimization variables of a genetic algorithm, setting an initial population, and constructing a fitness evaluation function based on classification accuracy; performing selection operation, crossover operation and mutation operation on the initial population, and updating an iterative population according to a fitness evaluation function to obtain an optimal penalty parameter and an optimal kernel function parameter; and training a support vector machine through the optimal penalty parameter and the optimal kernel function parameter, and constructing a noise feature vector classification model. In a noisy environment, the classification effect of the noise feature vector is improved under the condition that nonlinear and non-stationary noise exists, and the noise feature classification requirement in a complex sound signal processing scene is met.

The invention discloses an IMU (inertial measurement unit) attitude estimation method based on rolling window variance detection, which comprises the following steps: acquiring acceleration data and gyroscope data from an inertial measurement unit, the acceleration data being used for providing gravity direction information, and the gyroscope data being used for providing angular velocity information of a sensor; generating a rotation matrix by using gyroscope data, and calculating an Euler angle based on the rotation matrix; attitude estimation is performed by fusing an Euler angle generated from gyroscope data and an attitude angle calculated from gravitational acceleration. According to the method, a rolling window variance detection mechanism is adopted, the vibration degree of the environment where the IMU is located can be detected in real time, the weight of acceleration data is dynamically adjusted according to the vibration strength, and when it is detected that the vibration is high, the influence of accelerometer data in attitude estimation is reduced, so that the interference of the vibration on attitude estimation is reduced; under the condition of weak vibration, the weight of the acceleration data is increased, and the accuracy and stability of attitude estimation are improved.

The invention discloses an unmanned cluster networking task planning method based on an improved ant colony algorithm, a storage medium and equipment, and the method comprises the steps: firstly determining an unmanned cluster collaborative strike task planning scene, covering task constraints, target cost and expected benefits, and guaranteeing the planning reasonability; establishing a task planning mathematical model by comprehensively considering task execution cost and benefit, task execution quality constraint and technical performance constraint factors; the ant colony algorithm is improved through local and global pheromone updating rules, the limitation of a traditional ant colony algorithm in a complex optimization problem is overcome, the algorithm is effectively prevented from falling into a local optimal solution, the volatilization coefficient is dynamically adjusted, the search efficiency and the convergence speed are improved, and the unmanned cluster collaborative strike task planning problem is efficiently solved.

The invention relates to the technical field of anomaly detection, and discloses an industrial equipment time sequence anomaly detection method and device. The method comprises the following steps: preprocessing collected time series data of industrial equipment to obtain preprocessed time series data; encoding and decoding the preprocessed time sequence data to obtain reconstructed time sequence data; carrying out loss value calculation according to the reconstructed time sequence data to obtain total loss; performing optimization processing on preset anomaly detection model parameters according to the total loss to obtain an anomaly detection model; and performing anomaly detection on the real-time test data according to the anomaly detection model to obtain an anomaly detection result. According to the invention, the accuracy of the time sequence anomaly detection of the industrial equipment is improved.

The invention relates to the technical field of image processing, and discloses a medical image denoising method based on a 3D chaotic mapping dung beetle algorithm, and the method comprises the following steps: 1, inputting a to-be-processed original medical image, carrying out the noise adding of the original medical image, and generating a noisy image; step 2, inputting the noisy image into a hybrid filter used for denoising the image; 3, calculating an optimal parameter combination of each filter in the hybrid filter by adopting a dung beetle optimization algorithm, and configuring the hybrid filter by adopting the optimal parameter combination; step 4, performing denoising processing on the noisy image by using the configured hybrid filter to generate a denoised image; wherein in the step 3, the distribution position of the population is initialized by adopting 3D chaotic mapping; the technical problem of poor medical image denoising effect in the prior art is solved.

The invention designs a multi-agent system consistency method under switching topology based on TOPSIS comprehensive decision. The method comprises an important agent evaluation strategy based on a TOPSIS model and a multi-agent distributed consistency protocol for important agents. According to the method, a topological structure formed by an intelligent agent at each moment is mined, useful attribute information is extracted, a comprehensive decision is made based on a TOPSIS model, and the importance of the intelligent agent is quantified; meanwhile, based on the screened important agents, a consistency protocol is redesigned, information of the important agents is effectively utilized, and convergence is promoted. The whole method can adapt to multi-agent systems of different magnitudes, solves the problem that convergence is too slow or even cannot be achieved especially under a large-scale high-density structure, and accelerates the consistency of the system.

The invention provides a small target road vehicle detection method and device and a storage medium. The method comprises the following steps: S1, constructing a CP6-YOLOv8 model; s2, constructing a data set and training a model; and S3, performing vehicle detection by using the trained model. The problems that in an existing method, precision is not high, and the number of missed detection is large are solved.

The invention discloses an attack resisting method and device for controlling training energy consumption, and relates to the field of artificial intelligence safety. The method and the device are used for solving the problem that the model training energy overhead is increased due to lack of an anti-attack principle for analyzing and understanding manipulation training energy consumption and design of a detection defense strategy. The method comprises the steps of training a data sample and a to-be-trained large model, and determining a current gradient value, a last iteration gradient value and a gradient difference of the to-be-trained large model; when the adversarial disturbance is updated according to the optimization algorithm, if the optimal adversarial disturbance meets the maximum upper-layer optimization objective function, obtaining a disturbance sample according to the training data sample and the adversarial disturbance; and if the current gradient value is equal to the gradient value of the target function of the to-be-trained large model relative to the weight parameter of the to-be-trained large model, determining the optimal weight parameter of the to-be-trained large model according to the loss function minimization optimization of the to-be-trained large model.

The invention discloses an electric power perception data completion method and device based on nonlinear Tucker decomposition coupling. The method comprises the following steps: receiving an electric power perception data completion instruction; acquiring historical power sensing data based on the completion instruction; constructing a power sensing data tensor according to the collected historical power sensing data; nonlinear Tucker decomposition coupling is carried out on historical power sensing data, and a power sensing data core tensor and a hidden feature matrix are constructed; and on the basis of the power sensing data tensor, the power sensing data core tensor and the hidden feature matrix, constructing a target loss function and performing iterative optimization, and on the basis of the target loss function after iterative optimization, performing data completion on the power sensing data to obtain a power sensing data completion value. The method is used for processing the power sensing data, and high-precision data completion can be carried out based on a statistical rule, so that the problem of missing of dynamic power sensing data containing time sequence information is solved.

The invention provides an electric vehicle helmet detection method and system based on an improved YOLOv8 algorithm, the electric vehicle helmet detection system comprises a detection data acquisition module, a training data construction module, a data preprocessing module and a detection module, the training data construction module is used for constructing a data set of an electric vehicle helmet detection model, the data preprocessing module is used for preprocessing a data set, the detection data acquisition module is used for acquiring a real-time detection picture, and the detection module has the following functions: 1) training an electric vehicle helmet detection model based on the data set from the data preprocessing module; and 2) inputting a real-time detection picture into the electric vehicle helmet detection model to obtain a detection result. According to the electric vehicle helmet detection system, the electric vehicle helmet detection model based on the improved YOLOv8 algorithm is adopted for helmet detection, and the prediction precision of the model is improved.

The present application relates to a kind of 5G / 5G-A network slice resource allocation methods supporting high reliability low latency service and enhanced mobile bandwidth service coexistence, belong to mobile communication field.It includes: obtaining URLLC and eMBB service coexistence 5G / 5G-A network parameter information;Optimization target and constraint condition of minimum physical resource block usage are constructed;According to system model and optimization target, establish the hierarchical PPO model assisted by transfer learning, and design state space, action space, reward function and action space truncation mechanism;Pre-training and the parameters of the pre-trained resource allocation model are migrated to hierarchical PPO model;Hierarchical PPO model is trained, and network parameters are updated according to loss function until model converges, obtain the physical resource block allocation method for URLLC and eMBB service coexistence.The present application minimizes physical resource block usage while guaranteeing slice service quality, improves resource utilization.

The invention discloses an infrared small target segmentation method based on weak supervision. Only the infrared small target image and the infrared small target bounding box data are input, and the final output result is the segmentation mask of the small target in the infrared small target image. The method comprises the steps of model pre-training, model loading, teacher model pseudo mask generation, student model training and double-model EMA, wherein teacher model pseudo mask generation, student model training and double-model EMA need to be repeated for multiple times of iterative training. On the basis of using weak supervision loss PS-Loss, an adaptive learning rate adjustment mechanism is introduced, and the learning rate is dynamically adjusted according to the expression of the model on a verification set. In an infrared small target weak supervision training process, an EMA-based strategy, namely index moving average, is adopted. Two models are maintained, one model is used for training, the other model is used for obtaining weak changes of the infrared small target image, and instability and fluctuation of the models in training are successfully reduced.

The invention discloses an encrypted traffic classification method based on feature fusion and a packet dilated convolutional network, which identifies network traffic with high precision and ensures privacy and computational efficiency at the same time, and comprises the following steps: data preprocessing: only retaining 26 bytes to protect privacy through segmentation, filtering and truncation; feature extraction: adopting a double-sliding window mechanism and a designed hash function, generating concrete and abstract features in cooperation with an embedded layer, and realizing joint feature representation; in the model design, firstly, lightweight convolutional network design is carried out, a receptive field is expanded through a lightweight grouping dilated convolutional structure, and channel mixing and point-by-point convolution are added to increase interchannel communication; and in a classification output stage, a cosine annealing mechanism is used to dynamically adjust a learning rate so as to improve a training effect and a convergence speed. The method is superior to an existing lightweight method in the aspects of accuracy, stability, processing speed and resource occupation, is suitable for efficient traffic classification application of resource-constrained equipment, and has practical and promotional values.

The invention discloses a terrain simulated annealing inversion solving method, device and equipment and a medium, through innovative combination of multi-dimensional initial search and a genetic algorithm optimization mechanism, dual improvement of prediction precision and efficiency is realized, and the terrain simulated annealing inversion solving method has remarkable technical advancement and wide application prospects. The method has the beneficial effects that the prediction performance is remarkably improved, the multi-dimensional initial search and a genetic algorithm optimization mechanism are fused, so that the scheme shows excellent performance in complex and variable prediction tasks, and the prediction precision and stability are greatly improved. And calculation efficiency optimization: a dynamic mutation probability adjustment mechanism effectively reduces unnecessary calculation overhead and accelerates a convergence process, so that the scheme has relatively high calculation efficiency while maintaining high-precision prediction. The embodiment of the invention can efficiently and accurately carry out simulated annealing inversion solution of the terrain, and can be widely applied to the technical field of data processing.

The invention discloses a three-level T-type inverter grid-connected control method based on a sliding-mode observer, and relates to the technical field of grid-connected control. According to the three-level T-type inverter grid-connected control method based on the sliding-mode observer, a preset time sliding-mode control scheme based on the sliding-mode observer is provided, a continuous Sigmoid function is introduced to replace a nonlinear sign function to construct a sliding-mode observation reaching law, signals can be effectively and smoothly controlled, and the control precision of the three-level T-type inverter grid-connected control method based on the sliding-mode observer is improved. The inherent high-frequency buffeting phenomenon of traditional sliding mode control due to a sign function is remarkably suppressed, and meanwhile, the convergence speed and tracking precision of the system are improved. On the basis of observing power grid voltage serving as external disturbance through a sliding-mode observer, feedforward compensation is performed on the external disturbance, and the feedforward compensation is applied to a sliding-mode control reaching law of preset time so as to suppress buffeting and accelerate the convergence process of output current. And the timeliness and the stability of grid-connected control of the three-level T-type inverter based on the sliding-mode observer are improved.

This invention provides a multi-UAV sensor data acquisition trajectory planning method based on deep reinforcement learning, comprising the following steps: S1, establishing the basic framework of a UAV-assisted sensor data acquisition model in a land scenario; S2, constructing a persistent trajectory planning strategy based on an improved deep reinforcement learning algorithm according to the basic framework, and generating a UAV flight trajectory map that satisfies energy balance constraints and maximizes data acquisition value based on velocity vectors. This invention introduces a feature extraction unit module containing self-attention weight calculation to extract spatiotemporal differential features of sensor observations based on traditional multi-agent deep reinforcement learning algorithms, and combines a packet retransmission mechanism and an energy balance coefficient to optimize UAV flight energy consumption while improving the value and reliability of data acquisition. This system improves the processing efficiency of UAVs for dynamic monitoring tasks.

The present application relates to the technical field of robots, and in particular to a motion generation method, system, device and storage medium for a humanoid robot, comprising: physical simulation rendering generates a visual video containing visual representation of joint motion state of the robot; analyzing the visual video to obtain frame images, natural language instructions and motion sequences, decoding output trajectory data; and outputting control instructions through a hierarchical architecture of high-level motion planning and bottom-level dynamics tracking to drive the robot to perform actions. The present application implicitly encodes the joint state of the humanoid robot in the visual features, improves the inference efficiency and generalization ability of the model, and the hierarchical decoupling architecture of the large model high-level trajectory planning and the reinforcement learning bottom-level dynamics tracking controller pays a small performance cost, which can compress the inference time delay to within 50ms and the parameter quantity to below 2 billion, and balances the high generalization of the stateless VLA and the small model, few-step inference, edge low latency, and low power requirement.

The invention discloses an emergency evacuation planning method based on improved ant colony algorithm and genetic fusion, and belongs to the technical field of emergency management and public safety. The method comprises the following steps: constructing a multi-objective optimization model taking minimization of total evacuation time T, total road section risk R and total personnel panic index P as objectives, and solving the multi-objective optimization model based on fusion of an improved ant colony algorithm and a genetic algorithm to obtain an optimal evacuation path scheme. The evacuation efficiency, safety and personnel psychological factors are comprehensively considered, the state transition probability and the pheromone updating strategy of the ant colony algorithm are improved, the global search mechanism of the genetic algorithm is introduced for deep fusion, and finally, the evacuation efficiency can be improved in a complex evacuation scene. And a global optimal evacuation path giving consideration to timeliness, safety and personnel psychological factors is quickly planned, and the evacuation efficiency is effectively improved.

The application discloses a sea surface small target detection method based on multi-domain multi-dimensional feature combination, and adaptively extracts deep features of sea clutter and target echo signals by using a stack sparse auto-encoder, so that the feature dimension is improved to ensure the feature feasibility. Since the feature extraction is a complete adaptive process, the complexity of the model is reduced. Meanwhile, aiming at the problem that the feature distinction degree of the sea clutter and target echo data in a single domain is low, a time-frequency domain feature combination method is provided to improve the feature difference and ensure the stable and efficient detection performance of the detector. Through an adaptive genetic algorithm, the convergence process of the super parameter group optimization is accelerated, and the local optimization of the super parameter is prevented to a certain extent, so that the final detection probability is effectively improved. The experimental results show that the detector provided by the application has better detection effect on high sea state data, the detection probability is improved by 27.6%, and the sea surface small target detection under high sea state can be coped with.

The invention discloses a deep tight reservoir crustal stress field boundary condition inversion method integrated with machine learning, and belongs to the field of petroleum and natural gas engineering. The method comprises the following steps: firstly, constructing a fine three-dimensional heterogeneous modeling model through high-precision scanning and image processing; then, multi-source data such as hydraulic fracturing, acoustic emission and logging are fused, and the real ground stress of a target point is determined; an integrated machine learning model trained by an optimization algorithm is utilized to intelligently invert and generate a high-precision boundary load required by the crustal stress site; and finally realizing reliable prediction of the global crustal stress field. The method is used for providing key and reliable geomechanical basis and boundary condition input for well location trajectory optimization, hydraulic fracturing scheme design and development scheme adjustment of a deep tight reservoir, and effectively supporting safe and efficient drilling and effective utilization of reserves.

The invention discloses a federal width learning optimization method for data isomerism. The method comprises the following steps: acquiring a parameter updating matrix of each client; carrying out dimension reduction processing on the parameter updating matrix of each client; after the dimension reduction processing is completed, calculating the cosine similarity between the parameter matrixes of the clients; determining the number of clusters according to the cosine similarity between the parameter matrixes of the clients, and clustering the clients to obtain a plurality of groups of client sets; training a corresponding intra-group local width model for each group of client sets to obtain a corresponding intra-group local width model parameter matrix; and updating the global width model parameters through the intra-group local width model parameter matrix corresponding to each group. According to the method, the problem of data isomerism existing in federal width learning is solved, and the overall performance and training efficiency of the model are improved.

The present invention provides a counterfactual explanation generation method and system based on a multi-objective genetic algorithm, which obtains the original instance of the learner from the knowledge tracking data set; obtains the number and length of the questions to be added and randomly generates multiple length codes; obtains the questions to be added from the knowledge tracking data set and obtains the corresponding answer values ​​through the deep knowledge tracking model to be explained, forming the interaction pairs of the questions to be added; obtains the counterfactual instances based on the length codes, the interaction pairs of the questions to be added and the original instances; repeatedly obtains different interaction pairs of the questions to be added to obtain different counterfactual instances, generates a population of counterfactual instances and screens them to obtain the optimal counterfactual instance; and implements the interpretation of the deep knowledge tracking model based on the optimal counterfactual instance. The present invention provides a post-hoc interpretation strategy based on the causal inference theory for the deep knowledge tracking model, and proposes a counseling counterfactual interpretation idea and corresponding method suitable for the knowledge tracking problem context.

This invention discloses a SAR image classification method and system based on scattering cues and optimal transmission, belonging to the field of synthetic aperture radar image classification technology. The main steps include: thresholding and connected component analysis of the SAR image to extract the coordinates of the image scattering center; generating scattering cues text and cues vector sequences based on the normalized coordinates of the scattering center, obtaining scattering perception text feature vectors and image feature vectors to achieve cross-modal alignment; introducing uniform edge probability to supplement global category constraints, dynamically separating clean and noisy samples; and optimizing model parameters through joint training to achieve robust SAR image classification. This invention, by introducing prior knowledge of the scattering structure unique to SAR images and combining it with the cross-modal capability of a visual-language model, effectively improves the classification accuracy and robustness under noisy label conditions, making it suitable for complex remote sensing scenarios such as disaster monitoring, military reconnaissance, and marine surveillance.

The present invention discloses a method and system for predicting the effect of sewage treatment based on deep learning, and the method includes data collection, data preprocessing, construction of a treatment effect prediction model, hyperparameter optimization and sewage treatment effect prediction. The present invention relates to the technical field of sewage treatment data prediction, and specifically refers to a method and system for predicting the effect of sewage treatment based on deep learning. The present invention obtains the original data of sewage treatment through data collection; adopts a data preprocessing method of data cleaning, data labeling, data encoding, data normalization and data set segmentation; adopts an improved spatiotemporal attention graph convolution model to predict the effect of sewage treatment, which can effectively extract key time series features in time series data and complex spatial relationships involved in the sewage treatment process; adopts a hunting optimization algorithm to optimize the model hyperparameters, which can conduct targeted exploration of the parameter space when processing sewage treatment data with multiple variables and complex spatiotemporal characteristics.