6results about How to "Efficient decision-making" patented technology

This invention discloses an active distribution network integrated optimization scheduling method and system based on SVM-L2O, belonging to the field of distribution network optimization scheduling technology. The method includes: solving a multi-timescale integrated scheduling model based on acquired historical wind power output and load data to obtain unit start-up and shutdown strategies and continuous output decision variables, and constructing a training dataset; training a support vector machine for the start-up and shutdown strategies of each unit in each time period to obtain a surrogate model predicting the unit start-up and shutdown strategies; removing start-up and shutdown related constraints from the model based on the generated start-up and shutdown strategies to obtain a simplified model; constructing an L2O neural network, using Lagrange multipliers to incorporate the constraints of the simplified model as penalty terms into the loss function, training the L2O neural network to obtain a surrogate model predicting continuous output decision variables; acquiring wind power output and load data in real time, generating optimal scheduling decisions through the two surrogate models, and realizing integrated and efficient solution of multi-timescale distribution network scheduling.

This invention relates to the field of process control technology, specifically to an intelligent control system for thin-film lithium niobate etching processes based on machine learning. The system includes: a process sensing and acquisition module that collects thin-film lithium niobate etching process parameters, etching effect detection data, process environment data, and etching equipment status data in real time; a machine learning processing center that integrates and analyzes the data, using machine learning algorithms to uncover potential patterns, correlations, and anomalies; a process visualization and interactive platform that presents a real-time heatmap of etching parameter distribution, etching defect location, and etching effect trends, automatically switching interface layouts according to different process scenarios; an intelligent process decision engine that dynamically generates etching parameter adjustment strategies and process emergency response plans; and an etching parameter adjustment unit that adjusts the process parameters of the thin-film lithium niobate etching equipment and updates the control status. This solves the problems of poor adjustment response and low etching yield in existing technologies.

The application relates to an automatic driving multitask coordination decision-making method based on hierarchical rolling optimization. The automatic driving vehicle environment state information is used as the input of a reinforcement learning decision-making framework, the driving target is planned as the connection of multiple driving tasks, the coordination among the multiple tasks is realized, each driving task is specifically realized as a control action, and only the control action of the first driving task is executed. Then, rolling forward to the next time step, based on the updated automatic driving vehicle environment state information, planning and control action execution are carried out again. The planning is repeatedly carried out, and rolling optimization decision-making is realized. The method can realize multitask coordination and is suitable for long-term decision-making of automatic driving in a complex driving scene.

The application provides an anisotropic rock mass evaluation method and system based on a directional structure index, and belongs to the technical field of geological engineering, and comprises the following steps: obtaining internal strength factor data, structure strength factor data and boundary condition factor data of a rock mass to be evaluated; calculating internal strength factor rating Ri; constructing a directional weight function W(θ); calculating structure surface comprehensive condition rating Jc, and directionally correcting the rock quality designation RQD value of a drill hole to obtain a directional structure strength index DSSI(θ) through coupling calculation; calculating boundary condition factor rating Bc; calculating a directional rock mass quality comprehensive index D-RMR(θ) and calibrating the original value of D-RMR(θ); generating a visual representation map by taking the calibrated D-RMR(θ) value corresponding to different direction angles θ; and evaluating the quality grade of the rock mass to be evaluated. The application can accurately and quantitatively reveal the directional characteristics of anisotropic rock mass, effectively avoid distortion of key parameters, and has the advantages of high accuracy, strong practicability and intuitive results.

This invention discloses a multi-UAV task allocation and fusion method based on improved reinforcement learning, comprising: determining an initial parameter set for multi-UAV task allocation; fragmenting and decomposing multi-task objectives to determine cluster centers; using an adaptive clustering strategy based on center points to screen candidate clustering strategies and determine the optimal cluster set; determining a dynamic decay gradient strategy for the improved Q-learning network based on the action value function of basic reinforcement learning; determining a spiral cross-assignment mechanism for task redistribution based on a task redistribution mechanism with weighted coefficients; and determining a multi-UAV task allocation strategy based on the optimal cluster set of task points, the dynamic decay gradient strategy of the improved Q-learning network, and the task redistribution mechanism to complete the multi-UAV task allocation. This invention can effectively avoid unnecessary redundant allocation, improve the time consumption and range of task allocation, and increase the efficiency of task allocation.

This invention proposes a hierarchical task offloading and resource allocation method for large-scale model tasks in the Industrial Internet, belonging to the technical fields of Industrial Internet and mobile edge computing. The invention includes: establishing a cloud-edge-device collaborative reasoning architecture for large-scale models in Industrial Internet scenarios, and modeling the large language model reasoning task as a phased resource consumption model including a pre-filling stage and a decoding stage; modeling the large-scale model task offloading and resource allocation problem as a hierarchical Markov decision process, constructing a composite reward function; and utilizing the proposed hierarchical multi-agent large-scale model task offloading and resource allocation algorithm based on deep reinforcement learning, adopting a two-layer collaborative architecture of distributed offloading at the bottom layer and centralized allocation at the top layer to achieve task offloading and resource allocation. This invention significantly improves memory security and service stability during the large-scale model reasoning process; greatly reduces the action space dimension, and achieves rapid convergence and efficient decision-making in large-scale scenarios.