19results about How to "Avoid convergence" patented technology

The invention relates to the field of mechanical arm motion planning, relates to a multi-mechanical arm motion planning method based on an improved artificial potential field method and deep reinforcement learning, and aims to solve the problems that in a multi-mechanical arm system, early-stage rewards are sparse, the training speed is low, and effective strategies are difficult to learn in deep reinforcement learning. The invention provides an improved dynamic artificial potential field expert demonstration scheme, and in the training process, an artificial potential field reward function and a dynamic artificial potential field expert demonstration mechanism which dynamically change along with the training process are added, so that the mechanical arm obtains higher learning efficiency and more positive samples in the early-stage training process; in later training, the mechanical arm is assisted to reach a high-precision target, and then the learning speed of the mechanical arm is increased. The training process mainly comprises the following steps of constructing a simulation environment, describing and modeling a multi-mechanical-arm path planning task, generating a training sample, executing the training task and performing simulation, dynamically adjusting expert data according to a simulation result, collecting experience and updating a strategy. Compared with a traditional method, the method has the advantages that the convergence speed is higher, the training time is shorter, the precision is higher, and particularly, the early-stage convergence speed is higher, and the fitting precision is higher.

The invention discloses an AGV obstacle avoidance path planning method in an unmanned warehousing system, and the method comprises the steps: employing nested Logistic mapping and Skew Tent mapping to generate a chaotic initialization population to replace a population generation mode of a conventional differential evolution algorithm, carrying out the Levy flight operation after the selection operation, and carrying out the global path search on an environment map, thereby achieving the optimal path planning. And obtaining an AGV global feasible path avoiding obstacles in the environment map, and when the AGV has an unknown obstacle on the feasible path, re-planning the local path by adopting a dynamic window method so as to enable the AGV to realize an obstacle avoidance process in an interval where the unknown obstacle is located. The improved differential evolution algorithm enhances the global search capability through chaos initialization and a Levy flight strategy, and the AGV can quickly respond to an unknown obstacle through a dynamic window rule. The adaptability and the accuracy of path planning are improved, and the obstacle avoidance capability and the safety of the AGV in a complex environment are enhanced at the same time.

The invention discloses a three-dimensional medical image reconstruction pre-training method based on task perception, and the method comprises the steps: carrying out the preprocessing of an original three-dimensional medical image, and obtaining a preprocessed image; constructing a mask reconstruction main task, and establishing a main task network in the mask reconstruction main task; the main task network comprises a mask module, a reconstruction main task encoder and a reconstruction main task decoder which are sequentially connected in series; wherein the masking module is used for performing selective masking based on a high semantic information masking strategy on the preprocessed image; constructing a segmentation auxiliary task, and establishing an auxiliary task network in the segmentation auxiliary task to perceive a downstream segmentation task; the auxiliary task network comprises a segmentation task encoder and a segmentation task decoder; and performing joint learning on the mask reconstruction main task and the segmentation auxiliary task so as to optimize and train the main task network and the auxiliary task network at the same time. According to the method, the pre-training efficiency is improved, and the segmentation precision is improved under the condition that the downstream task complexity is not increased.

The invention discloses a big data analysis-based power distribution network planning decision optimization method and system, and relates to the technical field of power grids, and the method comprises the steps: constructing a system overall architecture, and carrying out the preprocessing of the constructed system overall architecture according to an improved deep learning preprocessing method; and a multi-source data fusion method is introduced, and the preprocessed system overall architecture is improved through a multi-objective optimization algorithm to complete power distribution network planning decision optimization. The training efficiency of the model is improved. The multi-target optimization algorithm processes multi-source data through a momentum modified Adam optimizer and an attention fusion network, and the feature expression ability and the model generalization ability are improved.

The invention discloses a time sequence perception knowledge graph reasoning method based on an attention network, and belongs to the technical field of artificial intelligence knowledge reasoning, and the method comprises the steps: inputting a historical event time sequence perception knowledge graph and an attribute time sequence perception knowledge graph; establishing a relation between a target entity and a high-order neighbor entity in the historical event time sequence perception knowledge graph by adopting a graph convolutional network; an attention mechanism is introduced, and influences of different relation types on the target entity are distinguished; adopting a layer of graph convolutional network without self-circulation to obtain embedding of each entity about attributes in the attribute time sequence perception knowledge graph; a time gate mechanism is introduced, and historical information embedded in the entity time sequence is screened; updating the relation embedding matrix under different timestamps by adopting a gating circulation unit; and entity prediction and relation prediction are realized. By the adoption of the method, reasoning precision and efficiency are improved, the processing capacity of the complex time sequence knowledge graph is improved, and accurate prediction of future events and the relation of the future events is achieved.

The invention discloses a digital twinning driven steel rail state transition diagnosis method, which belongs to the field of rail traffic fault diagnosis, and comprises the following steps: establishing a digital twinning model of a vehicle-rail coupling system; performing simulation by using a digital twin model to obtain a plurality of groups of vibration response signals; performing time-frequency analysis on each group of vibration response signals and each group of actually collected axle box vibration signals through wavelet transform to obtain a time-frequency diagram of each group of vibration response signals and a time-frequency diagram of each group of axle box vibration signals; taking the time-frequency diagram of each group of vibration response signals as source domain data of a sub-domain alignment migration network, and taking the time-frequency diagram of each group of axle box vibration signals as target domain data of the sub-domain alignment migration network to obtain a trained sub-domain alignment migration network; and utilizing the trained sub-domain alignment migration network to predict a to-be-detected axle box vibration signal, and completing diagnosis and identification of different steel rail states. The problem that the steel rail state diagnosis precision is insufficient under the condition that sample labels are scarce is solved.

The invention discloses a power system dynamic economic dispatching decision-making method and system oriented to reliability improvement. The method comprises the following steps: constructing a Markov decision-making process of dynamic economic dispatching; constructing a reinforcement learning environment; updating the neural network of distributed reinforcement learning; obtaining feasible power output under the constraint condition; obtaining the total power generation cost through an average consensus algorithm; a greedy strategy epsilon-greedy algorithm is introduced, and the intelligent agent is utilized to maximize a reward which can be obtained currently, so that the intelligent agent is ensured to learn an optimal strategy in a complex environment; and defining # imgabs0 # as a historical optimal strategy, and updating a local operation strategy, so that the optimal scheduling strategy is monotonically decreased, and finally, the optimal scheduling strategy is achieved. The method has high robustness under the condition of fluctuating power demand.

The invention discloses a main distribution micro multi-level collaborative optimization regulation and control method and system adapting to non-smooth characteristics. The method comprises the following steps: constructing a converter equivalent model and a power grid topological relation according to power grid measurement data; obtaining a distributed energy three-phase reactive power piecewise function based on the converter equivalent model and a droop control principle, and performing approximate fitting by using a fitting function to obtain a droop control function; micro-grid decoupling is realized by using a node replication method and a micro-grid adjacent relation; constructing a multi-level collaborative optimization scheduling model by using a droop control function, micro-grid decoupling and an optimization objective function; and outputting a main and distribution micro-grid regulation and control strategy by using an interior point method according to the real-time data of the power grid and the multi-level collaborative optimization scheduling model in combination with a time sequence consistency strategy. The method has the advantages that it is ensured that the final regulation and control result is based on the characteristics of the distributed energy and the global characteristics of the distributed energy while the iterative calculation amount is reduced, and both pertinence and efficiency are considered.

The invention discloses an intelligent control method and system for a mobile lighting device, and relates to the technical field of mobile lighting. An intelligent control system of a mobile lighting device comprises a lighting target preprocessing module, a lighting target identification module, a lighting scheme output module and a lighting device intelligent control module. According to the invention, through combining a plurality of image processing layers of the trained residual learning network and the deep convolutional network, image enhancement operation is carried out in the illumination target preprocessing model, which is helpful for identifying a dynamic target object under various environmental conditions; by using the illumination target identification model, motion prediction can be carried out on an identification target, accurate positioning information is output, and necessary target positioning information is provided for intelligent illumination control; the optimal intelligent control scheme of the lighting device is calculated and output by adopting an improved group optimization algorithm, so that intelligent control of the lighting device is realized.

The invention discloses a large-scale ad hoc network multipoint relay selection method based on ant colony optimization, and the method can effectively reduce the size of a selected MPR set, thereby reducing the packet loss rate of a network, and improving the throughput of the network. Firstly, an ant colony algorithm is introduced into a selection process of an MPR set, secondly, a local three-hop neighbor database and speed measurement are added into a path selection decision of a node, and then for updating pheromones, a global pheromone updating rule is adopted to update the pheromones on a path so as to prevent the algorithm from being converged to a local optimal solution. According to the method provided by the invention, the problem that the traditional MPR selection algorithm is easy to generate redundancy and the difficulty that the traditional MPR selection algorithm cannot adapt to the existing large-scale ad hoc network are well overcome.

The present application belongs to the technical field of artificial intelligence and multi-modal large language model, and particularly relates to a hallucination reduction method and device for multi-modal large language model. The method comprises the following steps: obtaining multi-expert visual tokens of an original image and text tokens of a text prompt, and inputting the connection of the two into a multi-modal large language model; calculating a similarity matrix of the multi-expert visual tokens and an adaptive clustering threshold, performing hierarchical clustering on the multi-expert visual tokens, merging redundant tokens and retaining complementary visual evidence; constructing a negative sample pool and distributing it to an auxiliary expert with the largest feature difference through a CLIP anchored complementary rejection fine-tuning strategy, and performing specialized training on the corresponding projectors of each expert; and inputting the clustered and fused visual tokens and the text tokens into the multi-modal large language model to generate target text output. The present application solves the problems of information redundancy, large computational overhead and insufficient exertion of expert advantages in the existing multi-expert multi-modal large language model hallucination reduction method.

This invention provides a method for extracting image watermarks based on a single-step inversion diffusion model, comprising: acquiring a synthetic image, wherein the synthetic image is generated by a VAE decoder based on the latent variables output by multi-step denoising of initial noise according to the diffusion model, and the symbol of the initial noise is a symbol mask obtained by encrypting the watermark information used for tracing through an encryption algorithm; mapping the synthetic image to the latent space where the diffusion model denoising operation is located to obtain latent space coding features; performing a symbol classification task based on the latent space coding features without using continuous initial noise regression to predict the symbol mask prediction value of the initial noise; acquiring the decoding algorithm corresponding to the encryption algorithm; and extracting watermark information from the symbol mask prediction value according to the decoding algorithm.

The invention relates to a cloud resource real-time scheduling technology, which is used to solve the problem that it is difficult to effectively balance the two conflicting goals of energy consumption and computing time during cloud computing resource scheduling, resulting in extended task execution time; the problem that traditional bee colony algorithms have slow convergence speed and limited solution accuracy in cloud computing resource scheduling applications, specifically a cloud resource real-time scheduling method based on an improved bee colony algorithm, including a master module and a slave module; the invention constructs an objective function, continuously adjusts the allocation scheme of tasks to servers, finds a resource allocation method that achieves a balance between energy consumption and computing time, and improves the overall efficiency and sustainability of the cloud computing system; introduces a solution retention strategy based on a dominance relationship in the bee hiring stage, so that solutions in the population can evolve faster towards a better direction; in the solution filtering stage, fast non-dominated sorting and crowding distance calculation are used to screen solutions, retain uniformly distributed high-quality solutions, and avoid the population from converging to a local optimal solution too early.

The invention discloses a power distribution area voltage imbalance treatment method and system based on a phase-change switch and an SVG. The method comprises the steps that firstly, a power distribution network full-node voltage imbalance optimization multi-objective function and a phase-change switch phase sequence and SVG compensation instruction current optimization model are established; calculating a node three-phase voltage by adopting a three-phase unbalanced load flow, and optimizing the obtained phase-change switch phase sequence and SVG compensation instruction current optimization model by using a fast non-dominated sorting genetic algorithm to obtain a Pareto leading solution set of phase-change switch phase sequence optimization and SVG negative sequence compensation current; screening the obtained Pareto leading-edge solution set, and selecting a result which not only meets the national standard but also can reduce the commutation frequency of the commutation switch and the negative sequence compensation current of the SVG as an optimal instruction; according to the obtained optimal instruction, a commutation instruction and a compensation current instruction are issued to a commutation switch and an SVG in the power distribution network respectively, and comprehensive treatment of the voltage unbalance of all nodes of the power distribution network is achieved.

According to the TBM full-circumference supporting shoe based on the cam hinge mechanism, a motor is used for driving a cam plate to rotate and driving a sliding pin and an ejector rod to move, unfolding and folding of the hinge mechanism are achieved, and when the hinge mechanism is unfolded, a hinge can make full contact with a full-circumference rock wall to serve as the supporting shoe to disperse supporting pressure and provide tunneling counter force. By the adoption of the technical scheme, rock supporting in the full-circumference range of a tunnel can be achieved, tunneling counter-force is dispersed to large-area surrounding rock, and the pressure acting on the surrounding rock is effectively reduced, so that the supporting device can be applied to soft and broken surrounding rock zones; and in addition, the occupied space in the machine is small, and the device can be carried in a small-diameter or ultra-small-diameter TBM (Tunnel Boring Machine).

The invention discloses a membrane unit correction constitutive method for explicit dynamic analysis. The method comprises the following steps: providing a tension state stiffness matrix for a data inspection stage; officially calculating, assuming that each integration point is in a tension state at first, and calculating the assumed stress and strain of the integration points by using a tension state stiffness matrix; calling a tool subprogram to calculate principal stress and principal strain of the assumed stress and strain; judging whether the integral point is actually in a tensioned state, a folded state or a relaxed state by adopting a stress-strain combination judgment criterion according to the magnitude relationship between the principal stress and a preset threshold value and the magnitude relationship between the principal strain and the preset threshold value; if the integration point is in a tension state, the actual stress is equal to the assumed stress; if the integral point is in a wrinkle state, calculating the actual stress by adopting a wrinkle state stiffness matrix; if the integral point is in a relaxed state, the actual stress is calculated by adopting a relaxed state stiffness matrix. The method considers the wrinkle and relaxation characteristics of the film, can be used for explicit analysis and calculation, and avoids the problem that the implicit analysis is not easy to converge.

This invention discloses an optimized cell layout structure for a trench MOSFET and its fabrication method. The optimized cell layout structure of the trench MOSFET includes an epitaxial layer, within which multiple trench structures extending in the thickness direction and of different depths are formed. The trench walls are provided with a gate oxide layer and filled with a polysilicon gate. A first well region and a second well region with different extension depths are formed between the trenches, and a corresponding conductivity-type doped region is formed on the surface of each well region. By constructing trench and well region structures of different depths, this invention enables the formation of channel units with different conduction characteristics inside the device, achieving current distribution and flow when the device is turned on, improving current density concentration, enhancing current distribution uniformity, and improving device reliability.

The invention discloses a unit layout optimization structure of a trench MOSFET and a preparation method thereof, the unit layout optimization structure of the trench MOSFET comprises an epitaxial layer, a plurality of trench structures which extend in the thickness direction and are different in depth are formed in the epitaxial layer, the trench wall of each trench structure is provided with a gate oxide layer and is filled with a polycrystalline silicon gate, and the gate oxide layer and the polycrystalline silicon gate are formed in the epitaxial layer. A first well region and a second well region which are different in extending depth are formed between the grooves, and corresponding conductive doped regions are formed on the surface layers of the well regions respectively. According to the invention, channel units with different conduction characteristics are formed in the device by constructing grooves and well region structures with different depths, so that current distribution flow is realized when the device is conducted, the current density concentration phenomenon is improved, and the current distribution uniformity and the device reliability are improved.

The invention relates to the technical field of underground garage safety management, in particular to an underground garage iron nail safety inspection method and device. The method comprises the following steps: S1, constructing a training data set containing three marked values of normality, iron nail throwing and iron nail throwing; s2, importing the training data set into a YOLOv8 target detection model for training to obtain an iron nail recognition model; a round hyper-parameter and a batch hyper-parameter in the YOLOv8 target detection model are determined through a speed delay particle swarm algorithm, and the rest hyper-parameters use default values; according to the speed delay particle swarm optimization, speed delay parameters are increased to serve as a third state option of the particles, so that the speed of the particles at the next iteration times is kept unchanged; s3, obtaining and preprocessing an original video image to obtain an input video image; s4, inputting the input video image into the iron nail recognition model, and outputting a recognition result; and S5, when the identification result is that the iron nail is thrown or the iron nail is thrown, the intelligent inspection vehicle is controlled to process the iron nail, and real-time early warning monitoring and processing can be carried out on the iron nail.