234 results about "Algorithm convergence" patented technology

An adaptive variable step-size LMS filter based on a hyperbolic tangent function and its filtering method and computer equipment belong to the field of filter technology, and solve the problem that the LMS algorithm improved based on a nonlinear function requires too many manual adjustments of parameters and that the convergence speed and convergence accuracy of the traditional LMS algorithm cannot be satisfied simultaneously. The method of the present invention includes: determining the filter tap length and the number of iterations; initializing the filter parameters; obtaining the filter input signal vector; determining the instantaneous expected signal of the filter; obtaining the instantaneous output signal; obtaining the instantaneous error signal of the filter and the accumulated amount of the error signal based on the instantaneous output signal; obtaining the instantaneous step size using a step-size update formula based on a hyperbolic tangent function; and continuously iterating the filter tap weight coefficient vector to construct an LMS filter using the filter tap weight coefficient vector obtained after the number of iterations. The present invention is suitable for improving the performance of the LMS filter, and the filter of the present invention can be widely used in various signal processing fields.

The invention relates to a network topology dynamic optimization method and equipment for large-scale power supply and distribution equipment networking. The method comprises the following steps: step S101, real-time data acquisition and state sensing; step S102, carrying out network topology modeling and performance evaluation; step S103, dynamic risk assessment and optimization target generation; s104, carrying out topological optimization decision making based on a feasibility maintenance type genetic algorithm; step S105, carrying out optimal strategy verification and seamless switching; selecting an optimal network topology reconstruction scheme from the Pareto optimal solution set according to a preset decision strategy; and after the reconstruction scheme is verified on a control level, generating an equipment cascade and open circuit control instruction sequence, and guiding related nodes to complete undisturbed switching of the network topology in a preset time window through a distributed cooperative control mechanism. According to the method, generation of invalid solutions can be avoided, and the convergence efficiency of a large-scale network topology optimization algorithm is remarkably improved.

The invention discloses an intelligent optimization control method for a wave power generation device based on an improved MPC, and the method comprises the steps: collecting the wave height, period, flow velocity and device motion posture data in real time through a multi-source sensing module, constructing an exciting force prediction model based on a bidirectional long-short-term memory network, and achieving the precise prediction of the wave exciting force of n control periods in the future; prediction data and real-time feedback signals are input into an improved jellyfish search optimization algorithm, through a two-stage chaotic mapping perturbation mechanism, the convergence speed and the global optimization ability of the algorithm are remarkably improved, and finally optimal electric damping control parameters are output. Compared with a traditional MPC method, the method has the advantages that a feed-forward-feedback composite control framework is formed by fusing deep learning prediction and an intelligent optimization algorithm, so that the energy efficiency conversion efficiency of the power generation system is improved.

The invention provides an improved particle swarm optimization (PSO) algorithm for mechanical arm trajectory planning, and aims at solving the problems that a traditional PSO algorithm is low in convergence speed and prone to falling into a local optimal solution. Therefore, the inertia weight and the learning factor of the algorithm are dynamically adjusted, so that the inertia weight and the learning factor change along with the increase of the number of iterations, and the global search capability and the convergence speed are enhanced; meanwhile, an elite reverse learning (EL) strategy is introduced, an optimal trajectory planning scheme is selected according to a fitness function, a new search area is explored through reverse particles, and the local search capability is enhanced; and a Gaussian-Cauchy variation (GC) strategy is combined, so that the global search capability is further improved, and a local optimal solution is avoided. In the optimization process, a single-target optimization method is adopted to carry out hierarchical classification on population solutions, and the performance of the algorithm under single-target optimization and constraint conditions is improved. Finally, the trajectory of the mechanical arm is optimized based on the algorithm, and particularly, each time period in a 3-5-3 polynomial interpolation method is finely optimized, so that the time from an initial point to a target point is shortened, a trajectory planning scheme with the optimal time is obtained, and the working efficiency of the mechanical arm is improved.

The invention discloses a deep neural network model parallel reasoning method for a heterogeneous GPU cluster, and relates to the field of distributed machine learning, and the method comprises the steps: obtaining current information, remaining selectable DNN models, deployed DNN models on each GPU server, and GPU servers which do not meet the number constraint of the DNN models; the scheduler selects a DNN model and deploys the DNN model on the selected GPU server, and calculates throughput for executing parallel reasoning at the moment; the combination of the DNN model and the GPU server with the maximum throughput is found, and related information is updated; judging whether the DNN models deployed on the GPU meet the number constraint or not, and updating GPU cluster information until all GPUs meet the specific DNN model number constraint; and repeating the steps until the algorithm converges. According to the method, limited heterogeneous GPU resources are fully utilized, and the DNN model with high compatibility is selected to deploy and execute parallel reasoning, so that the throughput is maximized.

The invention discloses a machine room group control multi-objective optimization digital twin platform and an optimization method, and relates to the technical field of machine room group control. Constructing a multi-objective optimization model, wherein the multi-objective optimization model comprises a three-dimensional objective function and constraint conditions; the three-dimensional objective functions comprise an energy consumption minimization function, a temperature and humidity control precision maximization function and an equipment life loss minimization function. Compared with a traditional static twinborn model, the method has the advantages that the deviation is greatly reduced, and a precise virtual-real mapping basis is provided for optimization decision making. According to the whale optimization algorithm, the global search capability and the NSGA-IIPareto solution screening capability are fused, the convergence speed of the algorithm is improved through fuzzy membership degree fitness calculation and crowding degree screening, when deviation exceeds a threshold value, optimization can be shortened to 15 seconds, compared with an existing algorithm, the response speed is greatly improved, and the real-time control requirement under the dynamic load of a machine room is met.

The invention provides a thermally driven micro-nano compliant mechanism topological optimization method considering a scale effect. The method comprises the following steps: defining design conditions of a thermally driven micro-nano compliant mechanism, and setting material attribute indexes; establishing a finite element analysis model of the thermally driven micro-nano compliant mechanism; obtaining a structure displacement response; establishing a topological optimization model of the thermally driven micro-nano compliant mechanism; calculating and optimizing an objective function and constrained sensitivity information; performing smoothing processing on the sensitivity information; and solving the optimization problem of the thermally driven micro-nano compliant mechanism by adopting a moving progressive optimization algorithm, judging whether the convergence condition of the moving progressive algorithm is met or not, and if so, outputting the optimal topological configuration of the thermally driven micro-nano compliant mechanism considering the scale effect. The thermally-driven micro-nano compliant mechanism obtained through topological optimization has an obvious scale effect, the topological configuration of the thermally-driven micro-nano compliant mechanism is changed along with increasing of scale parameters related to the feature length, and it is indicated that the scale effect becomes more obvious.

The invention provides a multi-objective optimization intelligent stereoscopic warehouse scheduling method and system, a medium and computer equipment. The method comprises the steps that S1, attribute data of goods in a warehouse are collected in real time; s2, based on the attribute data, weights of a plurality of optimization targets are dynamically determined through a self-adaptive weight adjustment mechanism, and the optimization targets at least comprise the space utilization rate, the access efficiency and the goods shelf gravity center; s3, carrying out multi-objective optimization on the shelf layout by adopting a particle swarm optimization algorithm, and carrying out weighted calculation on an optimization objective by the particle swarm optimization algorithm according to the dynamically adjusted weight in the step S2 to generate an optimal shelf layout scheme; s4, feeding back the optimal shelf layout scheme to a warehouse management system for execution, continuously adjusting weights and optimizing strategies according to cargo attribute data collected in real time, and dynamically balancing the space utilization rate, the access efficiency, the shelf stability and other targets through the combination of an adaptive weight adjustment mechanism and a particle swarm optimization algorithm, so as to achieve the optimal shelf layout scheme. And meanwhile, the algorithm convergence speed and the system real-time response capability are improved.

The invention proposes a robot path planning algorithm based on a particle swarm optimization algorithm and a dynamic window method, and relates to the field of control theories and electronic information, and the method comprises the steps: introducing an inertia weight updating strategy based on a state factor, setting adaptive parameters and crossover and mutation operators to improve the global search capability, increase the population diversity, and improve the robot path planning precision. On-line self-adaptive updating of inertia weight and learning factors is realized on line in combination with Q-learning, gene combination modes are enriched through crossover operators, convergence and exploratory performance of the algorithm are improved, an obstacle avoidance strategy of a traditional DWA algorithm is improved, weight parameters of a dynamic window evaluation function are dynamically adjusted according to real-time information of a target and an obstacle, and an obstacle avoidance algorithm is established. According to the method, the global planning is adopted, the path points generated through global planning are adopted as temporary targets, fusion of MOQLCOPSO and the improved DWA algorithm is achieved, local optimum is effectively avoided, the planning efficiency and path safety are improved, and the method is suitable for mobile robot navigation under the complex three-dimensional terrain.

The invention discloses a super-multi-target vehicle path planning method based on deep reinforcement learning assisted evolution, and aims to dynamically guide a search direction through deep reinforcement learning for multi-target optimization and path planning problems. The core of the method comprises the following steps: 1) constructing a super-multi-target vehicle path problem mathematical model; 2) designing a deep Q network as a decision model, and adaptively selecting a high-potential search direction in iteration; 3) designing a global search strategy, and balancing global search and local optimization; 4) generating a filial generation and evaluating the fitness, and executing environment selection to update the population; and 5) calculating a reward value according to a population evolution effect, and optimizing DQN network parameters. According to the method, through a collaborative mechanism of reinforcement learning and an evolutionary algorithm, a search strategy is dynamically adjusted, the convergence speed and stability of the algorithm are effectively improved, the adaptability to a complex path planning problem is enhanced, and the method has remarkable advantages in solving efficiency, solution set quality and dynamic environment response.

The invention discloses a power distribution network harmonic suppression method and system, and the method comprises the steps: building an objective function with the minimum total harmonic distortion rate of nodes of a whole network, building a power flow constraint, a harmonic distortion rate constraint and an active filter device related constraint, and obtaining a power distribution network harmonic suppression model according to the objective function and constraint conditions. A distributed partially observable Markov decision process is established based on the MADDPG algorithm, and harmonic suppression is performed on the power distribution network based on the distributed partially observable Markov decision process by using the PRE-combined MADDPG algorithm, so that the problem of low sample efficiency of a reinforcement learning algorithm is effectively solved, the stability of a training process and the convergence speed of the algorithm are promoted, and the robustness of the power distribution network is improved. According to the method, the effectiveness of the finally obtained harmonic suppression strategy is ensured, based on a centralized training-distributed execution architecture, it can be ensured that a plurality of active filter devices can make a cooperative control strategy giving consideration to the harmonic problem of the whole power distribution network in real time only by means of distributed observation, and therefore efficient whole network harmonic cooperative governance is achieved.

The invention discloses an energy storage frequency modulation control method and system for a super capacitor coupled lithium battery, and belongs to the technical field of energy storage and frequency modulation control, and the method comprises the steps: collecting data from an original frequency modulation instruction sequence, generating a substitution sequence through a search method, and generating a regular optimal substitution sequence through positive, negative and comprehensive optimization; training a GRU model by using the optimal substitution sequence, and optimizing hyper-parameters of a GRU neural network through an improved whale optimization algorithm; and inputting the optimal substitution sequence into the optimized GRU model to generate a preliminary prediction result, and correcting the prediction result in combination with the deviation between the prediction residual error and the original data to obtain a final prediction result. According to the method, prediction errors are remarkably reduced, the prediction precision of the frequency modulation control system is improved, the local optimum problem is effectively avoided, the globality of the optimization process is improved, and it is ensured that the generated optimal sequence has higher quality; the whale optimization algorithm is improved, the algorithm convergence efficiency is remarkably improved, and falling into a local optimal solution is avoided.

The invention provides an improved salmons swarm optimization algorithm, and aims to solve the problems that the global exploration capability of the algorithm is weak, and the algorithm is easy to fall into local optimum in the later stage, and the method comprises the following steps: firstly, solving a population with more uniform distribution as an initial population through adding Cubic chaotic mapping, increasing the diversity of salmons population, and improving the convergence speed of the algorithm; secondly, a spiral search strategy is added in the prey search stage, so that the salmons have multiple search paths to better adjust the positions of the salmons, and the global search performance of the algorithm is improved; and finally, a sparrow early warning mechanism is introduced, so that the rate of convergence of the Karat swarm algorithm is increased more quickly. According to the method, 12 basic test functions of a CEC2017 test set are used for testing the improved algorithm, and compared with path planning experiments of PSO, GWO, AWOA, GA and SCSO algorithms under a complex map, the optimal values of the shortest paths of the improved algorithm are reduced by 9.46%, 14.83%, 14.32%, 5.76% and 1.06% respectively. It is verified that the search efficiency of the algorithm is improved, the capability of avoiding falling into local optimum is high, and the convergence speed, the convergence precision and the optimization time are all superior.

In some implementations, a transmitter may determine that a difference between a total age of incorrect information (AoII) obtained in a current iteration of an iterative algorithm and a total AoII in a previous iteration of the iterative algorithm satisfies a tolerance factor for algorithm convergence. The transmitter may use the iterative algorithm to solve a convex optimization problem based on a plurality of iterations that continue until an objective function associated with AoII converges to within the tolerance factor for algorithm convergence. The transmitter may determine a precoder matrix and a vector of scheduling indicators from a solving of the convex optimization problem. The transmitter may transmit, using a downlink multi-user communication framework based on rate-splitting multiple access (RSMA) in a semantic-aware network, one or more updates to one or more receivers based on the precoder matrix and the vector of scheduling indicators.

The invention discloses a robot control optimization method based on deep reinforcement learning, and the method comprises the steps: firstly initializing a control system, constructing an experience playback buffer pool, and setting an Actor network strategy function, a Critic network weight, a hyper-parameter, and a target network parameter; then, the robot generates an action according to the Actor network, collects environment feedback after executing the action, and stores the state transition tuple into a buffer pool; next, a small batch of data is sampled, a time difference error is calculated, and a network parameter is updated accordingly to minimize a value estimation deviation, synchronously optimize the network parameter, maximize an expected value of a state-action value function, and improve control performance. According to the method, a multi-thread architecture and a deep reinforcement learning technology are fused, the real-time performance, stability and generalization ability of robot control are improved, the problem of algorithm convergence in a non-stationary environment is effectively solved, the cost of adjustment and calculation is reduced, and the robustness of long-term stable operation and deployment feasibility in a complex scene are enhanced.

The invention relates to a differential privacy distributed gradient tracking optimization method and system based on a state decomposition technology, and belongs to the technical field of information communication. According to the method, the state, related to privacy, of each node is decomposed into two sub-states, only one sub-state is exchanged with a neighbor, the other sub-state is not shared, and therefore potential attackers are prevented from inferring sensitive information. In addition, Laplacian noise is introduced into the exchanged sub-states and decision variables to achieve differential privacy. Through a state decomposition mechanism, the method can reduce the influence of Laplacian noise on algorithm convergence precision, and shows higher precision under the same privacy protection level. The algorithm is specially designed for a complex network scene, is suitable for applications needing privacy protection and complex network topology, such as a smart power grid and energy management, and shows wide applicability and innovation in distributed optimization.

The invention discloses a satellite edge computing task scheduling method and system based on multi-agent deep reinforcement learning, and the method comprises the steps: S1, constructing a system model which comprises a user equipment model and a satellite edge computing server model; s2, constructing a target function, wherein the target is to minimize the total delay and total energy consumption of task processing of the user equipment and the satellite edge computing server; s3, modeling an original optimization problem into a decentralized partial observation Markov decision process, proposing an efficient cross-plot Transform multi-agent near-end strategy optimization algorithm, and training a task unloading and resource allocation model until the algorithm converges; and S4, the user equipment makes an appropriate task unloading and resource allocation decision based on the trained task unloading and resource allocation model according to the current satellite edge computing environment state and task requirements. According to the method, satellite movement and calculation and communication resource constraints of equipment in a satellite edge calculation environment are fully considered, joint optimization of task unloading and resource allocation strategies is realized through a multi-agent deep reinforcement learning algorithm, the total delay and total energy consumption of the system are effectively reduced, and meanwhile, the task completion rate is improved.

The invention provides an intelligent stowage method in a container wharf ship cabin. The intelligent stowage method comprises the following steps that S1, information of a container to be assembled and pre-stowage information of a target ship are obtained; s2, based on the information of the container to be assembled and the pre-assembly information of the target ship, establishing a multi-target optimization function including a dynamic weight adjustment mechanism; s3, carrying out iterative solution through an improved Monte Carlo tree search algorithm; and S4, when a preset number of iterations is reached, outputting an optimal stowage scheme. Through the Monte Carlo search algorithm for dynamic weight adjustment, the defect of parameter solidification in multi-objective optimization of a traditional method is effectively overcome, the convergence speed of the algorithm is increased, and meanwhile, a local optimal trap is avoided. According to the multi-target cooperation mechanism, core indexes such as box turnover operation, box area conflicts and field bridge movement are brought into dynamic optimization, the effects of reducing the box turnover amount, reducing the box area conflicts and reducing invalid field bridge movement are achieved, and the operation cost can be obviously reduced.

The invention relates to the technical field of robot path planning, in particular to a navigation method and device of a mobile robot based on Transform-DQN, and can solve the problems that an existing algorithm is slow in algorithm convergence time, poor in path planning strategy performance and the like in a complex dynamic environment to a certain extent. According to the method, environment information and state information are obtained through multi-sensor fusion sensing environment; obtaining an expected action of the current mobile robot by using an optimal strategy obtained by a DQN algorithm; and controlling the movement of the mobile robot according to the current expected action. According to the technical scheme, the reward function considering multiple factors is set to interact with the mobile robot, so that the accuracy of the algorithm is improved; in the training process, an attenuation mode of an adjustable greedy factor is set, exploration and learning of the mobile robot in environments with different complexity degrees are balanced, a Transform model is introduced into an experience playback mechanism, the long-term dependency relationship between experiences is captured, the learning effect of the robot is enhanced, and the training efficiency is improved.

The invention discloses a workshop layout optimization method for a discrete manufacturing system, and aims to construct a multi-row facility layout mathematical model considering a channel loading and unloading point mechanism aiming at the process storage behavior and cross-row logistics path problems in the manufacturing process. According to the method, on the basis of analysis of workshop parameters and logistics paths, reasonable assumed conditions are set, decision variables such as facility space positions and arrangement relations are defined, a constraint system meeting uniqueness, non-overlapping performance and boundary limitation of facilities is established, and material handling cost minimization is taken as a target. And a Manhattan distance and a Floyd algorithm are adopted to measure the same-row transportation distance and the inter-row transportation distance respectively. In order to solve the model, an improved genetic algorithm fusing bidding selection and a random immigrant mechanism is designed, and the algorithm convergence performance and the global search capability are improved. According to the method, the inter-bank logistics cost can be remarkably reduced, the compactness of the facility layout and the path continuity are optimized, and the method is suitable for manufacturing scenes with process storage characteristics such as welding, assembling and warehousing transfer.

The invention discloses an unmanned aerial vehicle area coverage flight path planning method and system based on graph segmentation, and relates to the technical field of unmanned aerial vehicle path planning. According to the method, a coverage point pool with high quality, comprehensive coverage and robustness is constructed for subsequent greedy selection through a strategy of adaptively generating candidate points; then, a greedy selection mechanism based on effective scores is adopted, the current optimal coverage point is accurately selected in each round of iteration, the new coverage area can be increased to the maximum extent, the overlapping area can be effectively controlled, and finally the whole target area is completely covered with the minimum number of circles. In the aspect of a path planning algorithm, a hybrid initialization mode of a greedy algorithm and a random generation strategy is innovatively combined, and the quality of an initial solution and population diversity are ingeniously balanced; meanwhile, in each generation of evolution of the genetic algorithm, a 2-opt local search strategy is embedded into a new non-elite individual, so that the convergence speed of the algorithm is increased, and the path optimization efficiency is remarkably improved. In conclusion, more efficient and more reliable planning of the unmanned aerial vehicle area coverage flight path can be realized.

The invention discloses a radar interference resource allocation method based on a grey wolf algorithm. The method mainly solves the problems that in the prior art, interference resource allocation efficiency is low, combination explosion occurs, and engineering implementation is not facilitated. The scheme comprises the following steps: 1) constructing an interference task scene, and constraining a solution space through a coding strategy optimization method; 2) constructing an interference resource allocation objective function, and initializing an allocation scheme according to a good point set theory; 3) on the basis of the grey wolf algorithm, a nonlinear convergence factor, a dynamic weight and a reverse learning method are introduced to complete updating of a grey wolf position, namely updating of a distribution scheme is completed; and 4) repeating the iterative updating process in the step 3) until the algorithm converges, and taking the wolf pack position corresponding to the currently obtained interference benefit as a final interference resource allocation result. The method can effectively improve the optimization speed in the resource allocation process, avoids falling into a local optimal solution, and can be used for improving the resource allocation task efficiency in a radar cooperative interference scene.

The invention discloses an improved moss growth algorithm-based assembly process parameter optimization method. The method comprises the following steps of (1) selecting a plurality of assembly precision indexes; (2) analyzing and evaluating the influence degree of each influence factor on the assembly precision index, selecting the influence factor with relatively large influence, inputting the influence factor into the improved support vector machine precision prediction model, and outputting an assembly precision prediction value; formulating a process optimization objective function by using the assembly precision predicted value; (3) selecting assembly process parameters needing to be optimized, formulating assembly process parameter optimization constraint conditions, and constructing a process parameter optimization model in combination with the process optimization objective function; (4) solving optimal assembly process parameters by the process parameter optimization model by using an improved moss growth algorithm; and (5) outputting the optimal assembly process parameters to form an assembly process adjustment scheme. According to the method, the convergence speed and optimization capacity of an existing algorithm are improved, the assembly precision and quality are improved, and the repair cost caused by trial and error and correction is reduced.

The invention provides a whole vehicle manufacturing coating resource scheduling method based on multi-agent deep reinforcement learning, and belongs to the technical field of artificial intelligence and intelligent manufacturing. The method is characterized by comprising the following steps: firstly, deeply analyzing whole vehicle manufacturing coating production characteristics and dynamic resource attributes in a cloud environment, and constructing a three-stage coating resource scheduling model considering manufacturing energy consumption and completion time; on the basis, through a multi-agent dynamic interaction mechanism in the cloud platform, a multi-agent near-end strategy optimization (MAPPO) algorithm is adopted to solve the whole vehicle manufacturing and coating resource scheduling problem in three stages; meanwhile, in order to enhance the interpretability of a scheduling strategy and ensure the convergence of the algorithm, KAN (Kolmogorov-Arnold Networks) is adopted as a neural network structure of an intelligent agent. The method is widely applied to finished vehicle manufacturing and coating production enterprises, the provided model and method can obtain a scheduling scheme meeting the requirements of energy consumption and completion time, and dynamic events such as resource maintenance and vehicle body return can be efficiently and autonomously processed.

The invention relates to an integrated energy system optimization scheduling method based on knowledge-guided reinforcement learning, and is suitable for the field of operation regulation and control of an integrated energy system. The method comprises the following steps: setting a state variable, an action variable and a reward function of reinforcement learning; acquiring a system operation state vector, and determining a control action vector corresponding to the state vector based on the strategy network; performing border crossing judgment on the control action vector; if the control action vector is judged to be border crossing, the control action influencing the operation cost is corrected, and a corrected control action vector meeting border crossing judgment conditions is obtained; based on the corrected control action vector, obtaining the reward result of the current round and the running state vector of the next round; storing a tetrad consisting of the running state of the current round, the control action, the reward result and the running state vector of the next round into an experience playback pool; and updating the policy network, the value network and the old policy network based on the data in the experience playback pool, and repeating the steps until the algorithm converges.

The invention relates to an adaptive Layered Threshold Min-Sum (ALTMS) decoding method for an LDPC (Low Density Parity Check Code) code, which is characterized in that the adaptive Layered Threshold Min-Sum (Amplitude Layered Threshold Min-Sum) decoding method is provided; according to the method, the advantages of a threshold normalized minimum sum decoding algorithm and a threshold offset minimum sum decoding algorithm are combined, correction factors under different iterations are dynamically adjusted, and check node information updating in each iteration is adapted, so that the algorithm convergence speed and the decoding performance are effectively improved. Simulation results show that compared with three threshold minimum sum decoding algorithms under hierarchical scheduling, the ALTMS decoding algorithm provided by the invention realizes certain performance gain, and compared with a fixed parameter minimum sum decoding algorithm, the ALTMS decoding algorithm provided by the invention has better error correction performance.

The invention discloses an underwater multi-target routing method based on an improved non-dominated sorting genetic algorithm. The method comprises the following steps: firstly, arranging sensor nodes in a target water area, networking, and encoding a feasible path from a source node to a target node by adopting a segmented structure; secondly, constructing a routing multi-target fitness function, and introducing a dynamic weighting function to form a comprehensive fitness index; and finally, grading the population by using an improved non-dominated sorting genetic algorithm, and exploring a better path through crossover and mutation operations. And designing a reference point elite selection strategy, improving the coverage of the solution set in the target space, and outputting an optimal routing path until the algorithm converges. According to the method, the dynamic balance among different optimization targets can be realized, and the link quality is considered while the energy consumption and the time delay are reduced, so that the network routing performance is improved.

The invention discloses an arm-hand robot grabbing method based on deep reinforcement learning. The arm-hand robot grabbing method comprises the following core steps: 1) providing a strategy network structure based on a sparse causal time self-attention mechanism; (2) a post experience recombination method is provided, so that the utilization efficiency of successful samples by the algorithm is improved; 3) designing a self-adaptive conservative Q learning value network updating method, and dynamically adjusting the intensity of a regularization item through a self-adaptive adjustment mechanism based on a time sequence difference error and an average reward; the method can effectively improve the convergence speed of the algorithm, balance exploration and stability requirements in the training process, and improve the stability of the algorithm. In addition, according to the strategy network structure of the method, through local window sparse connection and an LSTM series structure, the modeling capacity of single-step, local and overall action characteristics is effectively enhanced, and finally the success rate of the grabbing task can be effectively improved.

The invention discloses a finite block length secure transmission method and system based on communication perception integration, and relates to the technical field of communication. Comprising the following steps: S1, constructing a system model, determining an optimization problem, analyzing a safe transmission rate capable of reaching a limited block length, and constructing a safe rate maximization problem; s2, designing an optimization scheme: decomposing the non-convex optimization problem in the S1 into three sub-problems, namely uplink transmission power distribution of IoE equipment, sensing signal design and joint sensing and communication receiving beam forming optimization, converting each sub-problem into a solvable convex optimization problem, and respectively solving the solvable convex optimization problem, and obtaining the solution of the original problem through an alternate iteration method until the algorithm converges or reaches the maximum iteration times. According to the method, a potential threat source is identified more accurately by utilizing a sensing data auxiliary system, and the technologies of beam forming, artificial noise and the like are utilized, so that the secure transmission between legal users is ensured, the quality of a received signal of an eavesdropper is reduced, and the secure fusion of a communication function and a sensing function is realized.

The present invention relates to the technical field of wireless communications, and in particular to an intelligent reflecting surface-assisted group selection beamforming method. First, a raccoon position is initialized, and an RIS phase shift matrix is selected. Then, users are grouped on the basis of spatial correlation, and a beamforming matrix and an overall system rate are computed. The RIS phase shift matrix is updated on the basis of an obtained result by means of a raccoon optimization algorithm. The proposed algorithm is iterated multiple times to obtain the maximum overall system rate and a corresponding beamforming matrix. The intelligent reflecting surface-assisted group selection beamforming method provided by the present invention achieves joint optimization of the RIS phase shift matrix and the beamforming matrix by introducing the raccoon optimization algorithm, and solves the problems of slow convergence and susceptibility to local optima of other algorithms. By grouping the users when computing the beamforming matrix, the computational complexity of the system is reduced while inter-user interference is reduced, thereby improving the overall system rate.