78 results about "Offline learning" patented technology

The invention relates to a wind power plant yaw control method based on a wind process. The method comprises the following steps: 1, establishing a wind power plant simulation model; 2, acquiring operation state data of the wind power plant as an initial state of the wind power plant simulation model; 3, acquiring a wind speed fluctuation sequence and a wind direction fluctuation sequence of the wind power plant as the state of the wind power plant yaw control model; 4, performing off-line learning to obtain optimal yaw angle set values under different wind regime sequences; enabling the wind power plant yaw control model to observe the environment and guide a wind turbine generator to act, and completing online learning; the wind power plant yaw control model is established, the optimal yaw angle of each wind turbine generator in the wind power plant is obtained through the wind speed sequence and the wind direction sequence, and the total generated power of the wind power plant is greatly improved; and the timeliness requirement of solving the wind power plant yaw control model in practical engineering is met.

The invention relates to an error prediction method and system for an electronic voltage transformer, and belongs to the technical field of electric appliance measurement, and the method comprises the following steps: collecting historical operation data of the electronic voltage transformer, including temperature, humidity, load voltage, secondary voltage and a historical ratio error value; a time sequence convolutional neural network TCN is selected as a basis, an error prediction model is constructed in combination with a linear attention mechanism, and offline learning is performed by using historical data. Operating data is collected in real time, the relative entropy of the operating data and historical data is calculated, and a distribution threshold value is set; and when the relative entropy exceeds a threshold value, updating model parameters online by using real-time data. According to the method, the data distribution change is detected through the relative entropy, and the prediction precision of the model in a dynamic environment is ensured. The relative entropy serves as an index for measuring probability distribution differences, data distribution mutation can be effectively recognized, online learning can be triggered, the model can be dynamically adjusted, and errors of the electronic voltage transformer can be predicted more accurately.

The invention provides a strategy model training method and device for a robot and a storage medium, and the method comprises the steps: in an offline learning stage, firstly collecting expert demonstration data, enabling the robot to carry out the imitation learning based on the expert demonstration data, and obtaining an initial strategy model and an offline data pool; and entering an online learning stage, enabling the robot to perform reinforcement learning on the basis of expert strategies, determining training data of a current time step according to manual intervention information, adding the training data into an online data pool, performing model parameter updating according to the offline data pool and the online data pool, and after all tasks are finished, performing online learning. And taking the obtained initial strategy model as a target strategy model. In the online reinforcement learning process of the robot, autonomous exploration and manual intervention of the model are combined, the robustness of the robot strategy network is further improved, and efficient transformation of the robot strategy from demonstration to autonomy is realized.

The invention discloses an offline-to-online deep reinforcement learning method in a resource scheduling scene, and the method comprises the following steps: S1, obtaining resource scheduling data, and carrying out the data preprocessing; s2, performing offline training of the strategy model in combination with expert imitation learning and a multi-head attention mechanism; s3, using an SAC reinforcement learning algorithm to iteratively optimize the strategy model, refining the strategy model through dynamic interaction with a real-time environment, learning response resource changes, and carrying out online training of the strategy model; s4, a dynamic strategy updating module is used, optimistic and pessimistic strategy updating is combined, strategy model parameters are adjusted according to online feedback, and the trained strategy model network is returned; according to the method, the SAC reinforcement learning algorithm of online learning and the expert imitation learning technology of offline learning are fused, the priority experience playback and multi-head attention mechanism are introduced, and the efficiency and accuracy of resource scheduling can be effectively improved by dynamically updating the proxy strategy model.

The invention relates to the technical field of intelligent optimization, in particular to a network anti-fiber-breakage protection planning method based on offline learning and improved MCTS, and the method comprises the steps: solving a preset multi-target optimization model of network anti-fiber-breakage protection planning through employing a preset multi-mode multi-target optimization algorithm, obtaining at least one optimal standby path corresponding to each service; learning a topological structure and link weight information of each optimal standby path; and when a link fault exists, dynamically searching a target recovery path of the current damaged service according to the topological structure and link weight information of at least one optimal standby path corresponding to the current damaged service in all services based on a preset improved Monte Carlo tree search algorithm, and outputting the target recovery path. Therefore, the problems of poor timeliness and low service recovery rate in the existing optical network recovery technology are solved, and the performance and efficiency of network fiber breakage resistance protection planning are effectively improved by comprehensively optimizing the shortest recovery time and the maximum service recovery rate.

The invention relates to a burn treatment path planning technology, and discloses a burn treatment optimal massage path planning method based on a graph theory and an SAC algorithm. The system comprises a data acquisition and initialization module, a path modeling module, a reinforcement learning module, an optimization and generation module and a closed-loop management module. The data acquisition and initialization module is used for generating accurate point cloud data through a binocular camera in combination with an IMU (Inertial Measurement Unit), and calculating burn average degree and uniformity to provide a basis for subsequent processing; the path modeling module adopts a graph theory method to model a burn area into nodes and edges, and multi-objective optimization is carried out by integrating treatment efficiency and patient comfort; the reinforcement learning module designs a state space, an action space and a reward function based on an SAC algorithm, and realizes optimization of a path and a strength strategy; the optimization and generation module generates a final treatment path through initial exploration and local optimization, and introduces an adaptive force adjustment function to prevent secondary injury; the closed-loop management module supports off-line learning and real-time feedback, and ensures high efficiency and individuation of a therapeutic scheme through dynamic parameter adjustment and report generation. According to the method, the accuracy and efficiency of burn treatment are effectively improved, and the method has wide clinical application potential.

The invention discloses a risk prediction method and device for an energy storage system, a medium and equipment. According to the method, the adaptive sampling strategy based on model-free offline learning is implemented on the preset edge platform, the monitoring data of the energy storage equipment are dynamically acquired, and then the time service module and the time protocol algorithm are used for performing time-space alignment processing on the data. And then, the processed data are input into a lightweight LSTM-GRU hybrid neural network model, and the model is optimized through sparsification of gating weights of LSTM and GRU units and adjustment of penalty terms of weight absolute values added in a loss function in a training process, so that real-time estimation of the state of the energy storage equipment cell is realized. And finally, in combination with the first monitoring data and the cell state estimation result, according to a preset electrochemical model and a three-dimensional thermal field reconstruction algorithm, predicting the thermal runaway risk possibly occurring in the energy storage system, thereby effectively solving the problem that the risk of the energy storage system cannot be accurately and efficiently predicted in the prior art.

The invention discloses a power distribution system adaptive operation method considering differentiated demands based on joint learning. The method comprises the following steps: 1, establishing a reconfigurable soft switch model; 2, constructing a combined learning agent based on a soft actor-commentator network and a dual deep Q network; 3, performing off-line learning on the reconfigurable soft switch in the established joint learning agent to realize rapid and accurate decision of the reconfigurable soft switch in a time-varying environment; and 4, proposing an adaptive control strategy under the support of the reconfigurable soft switch, including three control modes of loss reduction control, voltage optimization and demand response, and designing an adaptive switching mechanism capable of flexibly switching among multiple modes. Differential regulation and control requirements of the power distribution system are considered, and the flexibility and adaptability of the system are improved by using the reconfigurable soft switch, so that adaptive operation of the power distribution system is realized.

A method and system for anomaly detection from time-series input data. A Gaussian Mixing Model (GMM) learns distribution parameters in an offline learning stage using sample data. The data used for offline learning and for a subsequent online anomaly detection stage are time-series data collected for multiple parameters of a machine operation, such as a robot performing a repetitive set of operations. The method includes aligning the data with a known good reference data file and taking a difference from it before providing the data to the GMM. In an online anomaly detection stage, the GMM calculates a probability that each time-series data point fits the distribution, and then a log-sum calculation is performed on each data file to determine the likelihood that the file contains anomaly data.The log likelihood of the file is compared with previous values, and an alert is issued if there are statistical deviations from the historical data.

This invention discloses a method and system for intelligent fault diagnosis in power plants based on adaptive benchmark matching. The diagnostic method includes the construction of an offline benchmark model library and online adaptive benchmark acquisition. The system consists of a data acquisition and preprocessing module, an offline benchmark model library construction module, an online adaptive benchmark acquisition engine, a parallel fault analysis engine, a fusion decision and knowledge base module, and an alarm and report generation module. Both the diagnostic method and system of this invention completely abandon the traditional method of using static fixed thresholds as the diagnostic basis by combining "offline learning of personalized baselines" with "online multi-level dynamic matching." This allows the diagnostic benchmark to intelligently adjust with environmental conditions, greatly reducing false alarms caused by fluctuations in environmental factors and significantly improving diagnostic accuracy.

Disclosed is a device and method for processing tasks through model-based offline learning. The device includes: a dataset input unit configured to receive an offline dataset for offline reinforcement learning; an initialization unit configured to initialize a world model and a model generation dataset for predicting a state transition and a reward without interacting with a real environment; a model rollout unit configured to expand the offline data of the offline dataset based on the world model to generate an imagined trajectory and generate imaginary data of the model generation dataset; and a learning update unit configured to perform critic update and actor update based on the offline data and the imaginary data.

The invention provides a biologically-inspired robotic fish swimming action learning method and device, and the method comprises the steps: carrying out the extraction of fish key points based on collected biological fish swimming data, and obtaining a biologically-inspired experience database; determining a fish swimming action sequence by using a dynamic trajectory method according to the obtained positions of the joints of the robotic fish; pre-training a pre-constructed agent by using a biological heuristic experience database, and carrying out offline learning based on biological data to obtain a pre-trained agent; training a pre-trained agent based on the fish swimming action sequence, and performing online learning to obtain a robotic fish swimming action learning agent; wherein different states and action vectors are adopted in the online learning stage and the offline learning stage; and controlling the robotic fish to swim based on the robotic fish swim action learning agent. The robot fish swimming is controlled based on the robot fish swimming action learning agent, and the robot fish swimming action can be accurately controlled and optimized.

Offline teaching device (1) comprising at least one processor (2, 3, 4, 5) wherein the processor (2, 3, 4, 5): as a result of a motion program comprising several input teaching points, numerous interpolation points are generated on a motion route of a distal tool endpoint of a robot (100), the motion route being formed under the teaching points according to the motion program; Coordinates of at least one joint point of the robot are calculated when the distal tool endpoint is positioned at each of the interpolation points; and detects whether a disturbance occurs between each of the generated interpolation points and the calculated joint point and a peripheral device.

The invention relates to the technical field of education artificial intelligence, and provides a self-adaptive learning path recommendation method for artificial intelligence general recognition education, which comprises the following steps of: 1, calling a large language model to analyze unstructured course resources of AI general recognition education, mining semantic association and implicit dependency of knowledge points, and constructing a learning path; generating a space-time knowledge graph containing confidence scores, automatically capturing the latest literature and tool update of the field every 72 hours, and iteratively optimizing the topological structure of the graph; 2, deploying data acquisition points to acquire multi-source learning data of a user in real time, and calculating a dynamic cognitive state vector with knowledge points as dimensions by mastering an entropy model; the knowledge graph is automatically iterated through LLM, and the problem of update lag is solved; precise personalized recommendation is realized according to multi-dimensional data and a dynamic algorithm, and cognitive differences are adapted; visually presenting decision logic, and cracking a decision black box; the method can be migrated to multiple fields, supports multi-terminal and offline learning, exceeds an expected adaptive scene, and improves the learning efficiency and credibility.

The invention belongs to the technical field of robot intelligent control, and particularly relates to a mechanical arm tracking control method based on transferable depth incremental reinforcement learning, which effectively solves the nonlinear optimal tracking control problem of a mechanical arm in a model-free mode by constructing a transferable incremental reinforcement learning framework. The method comprises the following steps: firstly, constructing a 1-degree-of-freedom depth increment model by utilizing one-step forward data offline learning, and providing universal dynamic representation for a mechanical arm which is difficult to accurately model; furthermore, an asynchronous depth value network is designed for the one-degree-of-freedom mechanical arm, stable and rapid convergence value function approximation is achieved through a separation base layer and an adaptive layer, and a cross-mechanical-arm migration mechanism is established, so that a pre-training model and a network base layer on the one-degree-of-freedom mechanical arm can be directly migrated to a high-degree-of-freedom mechanical arm subsystem; and the system difference is compensated only by updating the adaptive layer online, so that the repeated training overhead is remarkably reduced, and meanwhile, rapid, robust and adaptive tracking control on the mechanical arms with different degrees of freedom is realized.

The invention provides an intelligent vehicle man-machine sharing collision avoidance control system and method under critical working conditions, and the method comprises the steps: collecting and transmitting the current state and surrounding environment information of a vehicle through a sensing system; off-line learning and large-scale vehicle data are used for approximately solving a collision avoidance inaccessible state set, and a Hamiltonian-Jacobian accessibility value function and an action-value function are subjected to off-line iteration updating through a large amount of real vehicle collision avoidance data collected in advance; based on the accessibility value function and the action-value function, the collision avoidance capability and the collision avoidance intention of the driver are quantified, and the man-machine control weight is dynamically distributed; and generating machine operation based on a reachability heuristic reinforcement learning algorithm, generating final operation to be executed in combination with the man-machine control weight, the driver operation and the machine operation, and executing collision avoidance operation. According to the method, the collision risk of the vehicle state and the collision avoidance intention of the driver action can be evaluated theoretically, and man-machine conflicts are reduced to the greatest extent on the premise of ensuring that no collision occurs.

The invention provides a data supply acceleration system and method for single-machine to small-scale multi-GPU (Graphic Processing Unit) training scenes, and the system adopts an off-line learning and on-line inference architecture. The system comprises an offline training module, an online portrait generation module, an adaptive strategy selection module, an income inference and replacement execution module, a training cooperative scheduling module and a strategy switching control module. In the off-line stage, the system learns'retention revenue 'of data entries based on historical logs and solidifies a revenue prediction model and a strategy selector. In the online stage, the system generates a system state portrait in real time, an optimal strategy is adaptively selected according to the system state portrait, cache replacement is driven based on profit prediction, and GPU idling is reduced through a collaborative scheduling mechanism. According to the method, the model parameters are updated in an off-line manner, the operation overhead is low, the I / O waiting time and the tail time delay in the deep learning training process can be effectively reduced, and the GPU utilization rate and the overall training throughput rate are improved.

A method and system for anomaly detection from time series input data. A Gaussian mixture model (GMM) uses sample data to learn distribution parameters in an offline learning stage. The data for offline learning and for subsequent online anomaly detection phases is time series data of a plurality of parameters collected, such as machine operations of a robot performing a repeated set of operations. The method includes aligning the data with a known good reference data file and taking a difference from the reference data file prior to providing the data to the GMM. In the online anomaly detection stage, the GMM calculates the probability that each time series data point conforms to the distribution, and performs logarithmic summation calculation on each data file to determine the likelihood that the file contains abnormal data. The file logarithm likelihood is compared to previous values and an alert is issued when there is a statistical difference from historical data.

The invention discloses an unmanned aerial vehicle flight activity full-process task scheduling optimization method, and relates to the technical field of flight activity task scheduling. Historical data is utilized to construct a state vector in an offline stage, and the state vector is composed of task urgency, geographical distribution, current weather, obstacle probability and remaining power; meanwhile, a reward function is constructed according to the task completion time limit, the flight safety cost and the resource consumption cost, when the task is started, field real-time sensor data is introduced, the initial state obtained offline is corrected, a new state vector is formed, the optimal action is output through the deep Q network, and a task allocation scheme reflecting the current environment condition is generated; the method depends on off-line learning results, real-time changes can be reflected in time, and the problem that in traditional scheduling, a static model is actually disjointed from the site is solved; and an offline deep reinforcement learning model is combined with an online real-time data feedback closed loop to realize dynamic coordination of global scheduling and local path re-planning.

The application provides an intelligent vehicle human-machine shared collision avoidance control system and method under a critical working condition, and the method comprises the following steps: collecting and transmitting the current state of the vehicle and the surrounding environment information through a sensing system; using offline learning and large-scale vehicle data to approximately solve the collision avoidance unreachable state set, and using a large amount of pre-collected real vehicle collision avoidance data to perform offline iterative updating on the Hamilton-Jacobi reachability value function and the action-value function; quantifying the collision avoidance ability and the collision avoidance intention of the driver based on the reachability value function and the action-value function, and dynamically allocating the human-machine control weight; generating the machine operation based on the reachability heuristic reinforcement learning algorithm, and combining the human-machine control weight, the driver operation and the machine operation to generate the final operation to be executed and perform the collision avoidance operation. The application can theoretically evaluate the collision risk of the vehicle state and the collision avoidance intention of the driver, and reduce the human-machine conflict to the maximum extent under the premise of ensuring that no collision occurs.

The invention discloses a distributed frequency control method and device based on security policy learning, relates to the technical field of optimized operation of a power system, and mainly aims to solve the problem that the uncertainty and load fluctuation of renewable energy power generation cannot be effectively handled by the existing frequency control of a networked micro-grid system. The method comprises the following steps: performing state design and action design on each micro-grid in the system based on historical data to obtain state characteristics and control action characteristics corresponding to each micro-grid; configuring a corresponding control agent for each micro-grid in the system, and performing centralized strategy learning processing on each control agent in an offline stage based on the corresponding state feature and the control action feature to obtain an optimal control agent meeting an offline learning requirement; and on-line distributed application is carried out based on the optimization control intelligent agent, so that each micro-grid carries out frequency autonomous adjustment processing.

The application provides an agent reinforcement learning method and device based on an iterative policy constraint, comprising: performing policy offline learning on an agent based on a state of the agent in any application scenario; taking an optimized policy obtained through offline learning as an initial policy, and constructing an iterative policy constraint term; introducing the iterative policy constraint term on the basis of online reinforcement learning for maximizing a reward, to generate an optimized target of the agent; and performing policy online reinforcement learning on the agent based on the optimized target. Through iterative updating of the policy constraint, the application can not only avoid a decrease in policy performance in an early online fine-tuning stage of offline-to-online reinforcement learning, but also weaken the policy constraint in a later training stage, to obtain an optimal policy.

The present invention relates to a space robot optimal impedance learning method based on sampled data. First, a dynamic model of a multi-degree-of-freedom space robot system is established, and a mass-spring-damper approximate interaction model is adopted; secondly, an interaction performance function is designed to convert the optimal impedance control problem into a special linear quadratic tracking (LQT) problem; then, assuming that the robot terminal position and speed are measurable, a different strategy model-free integral reinforcement learning method based on full state feedback is designed for impedance parameter solution; finally, considering the problem of missing robot terminal speed, a different strategy model-free integral reinforcement learning algorithm based on historical data feedback is designed to solve the optimal impedance parameters with the help of state reconstruction technology. The present invention uses limited sampled data to learn the optimal impedance parameters offline, which can be used for systems with missing terminal speed, unknown interaction models and instruction generator dynamics, to achieve safe and compliant interactive control of space robots and unknown target surfaces.

This invention discloses a fault mode-driven multi-mode intelligent anomaly diagnosis method and system for power automation systems. The method includes offline learning and online detection phases. In the offline phase, detection knowledge items, including purified historical statistical baselines and ramp-up discrimination models, are periodically generated and stored. In the online phase, the data is preprocessed and adapted, and corresponding dedicated detection operators are activated according to the indicator type, combined with the detection knowledge items for analysis. The dedicated detection operators include ramp-up detection operators for resource-related indicators, pulse detection operators for performance-related indicators, and trend change point detection operators for disk-related indicators. The ramp-up detection operators employ a parallel fusion structure of seasonality analysis and model discriminant analysis. Candidate events output by the detection are converted into alarm records after suppression judgment. This invention achieves accurate and interpretable intelligent fault diagnosis through a closed loop of "offline baseline purification, online mode adaptation, and diagnostic output."

The present invention discloses a method and application for probabilistic prediction of household power load, belonging to the technical field of household load prediction. Considering the time correlation of household load data, a neural network model is used to model the time series. Aiming at the strong uncertainty of household load, a sparse Gaussian process regression model is used for uncertainty characterization. In addition, during the model training process, an offline-online dual-mode learning method is constructed. The initial performance of the neural network model is ensured through offline learning, and the posterior distribution in the sparse Gaussian process regression model and the parameters in the neural network model are updated in real time through online learning, enhancing the accuracy and adaptability of the neural network model and the sparse Gaussian process regression model, and learning the uncertainty of residents' electricity consumption behavior from real-time data. The present invention fully considers the time correlation and strong uncertainty of household load, can dynamically capture the change trend of household power load, and can accurately predict household load.

The present invention discloses an intelligent detection method and system for arrester faults. The method includes: arranging a sensor network around the target arrester device to comprehensively monitor the working environment and operating parameters of the device; using the data collected by the sensor network to perform a series of preprocessing operations; adopting an improved one-dimensional signal denoising processing algorithm of OMLSA to denoise the multi-sensor data so as to remove the noise in the signal; sending the denoised data into a residual network based on channel convolution for model training, and using a genetic algorithm to search for the optimal parameters of the model; combining online learning and offline learning algorithms to realize real-time update and optimization of the model; and performing error determination after optimizing the model through a particle swarm annealing fusion algorithm. This application has significant beneficial effects in improving efficiency, accuracy, accurately grasping the health status, and enhancing adaptability compared with the traditional threshold determination method.

The invention relates to the technical field of laser welding, and discloses a laser welding seam tracking and quality real-time detection system and method based on OCT image guidance. According to the method, through system calibration and offline learning, a coordinate mapping and feature database is established; during welding, the coaxial OCT is used for synchronously scanning a front groove and a rear molten pool area; tracking and correcting a welding path in real time based on the front three-dimensional point cloud; meanwhile, a dynamic feature sequence of the molten pool is extracted and analyzed; inputting the features into a pre-training machine learning model, and judging quality and predicting defects in real time; according to the judgment result, parameters such as laser power and welding speed are adjusted in a self-adaptive mode, and closed-loop control is formed; and full-process data is fed back to optimize the model. According to the invention, synchronous closed-loop control of groove tracking and internal quality detection is realized, and the welding precision and the quality reliability are improved.

The application discloses a general enhancement method for target character recognition in a motion scene and a related device, uses a network structure construction strategy of a double branch, carries out data fusion and parameter exchange through an implicit text statistical branch and an explicit text recognition branch, can control the model size without increasing the model complexity, and reduces unnecessary parameters of the network. Meanwhile, a basic backbone network is provided for subsequent downstream tasks, and a solution can be provided for text analysis in more complex scenes. The offline learning method used in the application can reduce the cost when iterating and strengthening the model. With the increase of data diversity, the model can dynamically adjust the parameters each time, so that the iteration process can adaptively extract and update the parameters of the data, can improve the convergence speed of the iteration process while ensuring the performance of the model without increasing the network complexity.

The application discloses a kind of water turbine blade topological optimization methods combining double-line learning neural network and conformal mapping.First, the water turbine blade model is mapped to two-dimensional plane by conformal mapping algorithm, generates data sample library and corresponding conformal factor.The fluid-structure interaction analysis is used to obtain the external force field and displacement field of the model nodes under specific flow field conditions.The method of the application introduces a global attention U-NET neural network, and uses the conformal factor, structure topology, external force field and displacement field as the input and output of the network, and trains the neural network.The optimization process reduces the dependence on traditional finite element analysis, improves the optimization efficiency, and realizes efficient topological optimization of the water turbine blade through the combination of offline learning and online learning, thereby improving the performance and reliability of the water turbine.