203results about How to "High solution accuracy" patented technology

The invention discloses an inertial microsystem thermal coupling analysis method based on a physical information neural network, and the method comprises the steps: S1, setting material parameters and boundary conditions of an inertial microsystem, and building a thermal coupling analysis model; s2, performing electrothermal coupling analysis to obtain temperature distribution of the inertial microsystem; s3, thermal stress distribution of the microsystem is obtained through thermal-mechanical coupling simulation analysis; s4, predicting a temperature field of the microsystem through the physical information neural network; s5, taking the temperature field as a boundary condition of mechanical simulation of the microsystem to obtain mechanical properties such as stress and strain of the microsystem; and S6, performing mechanical-electric coupling simulation analysis, and analyzing the influence of structural deformation on each parameter in electrical performance. According to the method, the neural network solving precision is improved through the improved adaptive weight strategy, the complete polynomial basis function is combined with the neural network, the state dimension is reduced by introducing the expansion basis function, the calculation cost and time are reduced, accurate prediction of the micro-system multi-moment temperature field is achieved, and the micro-system performance under electric heating power multi-physics field coupling is calculated.

The invention discloses an electric vehicle charging station layout optimization configuration method and system, and the method comprises the following steps: obtaining the traffic network information and power distribution network information of a planning target area, and determining the charging demand number of electric vehicles and the charging load demand distribution condition; according to the electric vehicle charging load demand distribution condition, determining the service range of each charging station, and constructing a proposed charging station capacity determination model; an upper-layer charging station site selection model is constructed, and the optimal site of each charging station is determined; establishing a lower-layer mixed integer programming model, and determining the configuration number of various charging piles of each charging station; solving the double-layer locating and sizing planning configuration model by using a hybrid genetic simulated annealing algorithm and an analytic hierarchy process to obtain an optimal locating and sizing scheme of the charging station; according to the method, the attraction of the charging station to the user and different types of charging pile configuration schemes are comprehensively considered, a bilevel planning configuration model is established, an optimal solution set is solved by using a hybrid genetic simulated annealing algorithm, and finally an optimal scheme is determined through an analytic hierarchy process.

The invention discloses a smart warehouse material sorting two-stage scheduling method based on an embedded neighborhood search strategy genetic algorithm, relates to the field of smart logistics scheduling, and is used for solving the problem of warehouse material sorting scheduling in enterprise production logistics links. The method comprises the following steps: under the condition of considering the heterogeneity characteristics of a production line, establishing an order task batching and batching path optimization two-stage optimization model taking the minimum total cost of order picking order delay as a target function, calling a channel type storage picking path strategy, and providing four neighborhood search strategies, and a traditional genetic algorithm is improved by embedding a neighborhood search strategy to solve problems. According to the method, to-be-sorted order batching and batch grouping path planning automation is realized, so that the total order sorting delay cost is minimized, and the problem of'order batching-path planning 'two-stage scheduling of storage sorting in the production material supply process of an enterprise can be solved, so that the comprehensive benefits of production logistics are improved, and the purposes of reducing cost and improving efficiency are achieved.

The invention discloses a scheduling optimization method for an aviation composite material manufacturing hot-press forming process, which comprises the following steps of: 1, establishing a hot-press forming production plan scheduling objective function by taking the minimum total delay time of a workpiece as an objective according to an aviation composite material manufacturing hot-press forming production plan; 2, establishing a two-dimensional hot press molding process batch scheduling model considering a workpiece release time window and machine applicability; and step 3, taking the objective function as an optimization objective, taking the two-dimensional hot-press forming process batch scheduling model as an optimization model, and utilizing a genetic algorithm embedded with a self-adaptive domain search strategy to solve and obtain a hot-press forming production plan scheduling scheme. According to the method, the total delay time of workpieces can be remarkably shortened while the machining batch of the workpieces is minimized, the occurrence of prepreg deterioration conditions is reduced, and conditions are created for improving the hot press molding production efficiency and promoting digital and intelligent transformation and upgrading of composite material manufacturing enterprises.

The invention provides a mold surface repairing method and system based on laser cladding, and relates to the technical field of laser cladding, the method comprises the following steps: selecting a matrix material with a proper size, and pretreating the surface of the matrix material; according to the actual process requirements, the value range of laser cladding process parameters is determined, and a response curved surface model of the microhardness and the dilution rate is established; optimizing the response curved surface model, and obtaining an optimized process parameter combination by taking maximization of microhardness and minimization of dilution rate as targets; according to the optimized technological parameter combination, the laser cladding process is carried out, and a cladding layer is formed on the pretreated base material; and performing performance detection on the formed cladding layer, and adjusting process parameters according to a performance detection result until an optimal process parameter combination is determined. By means of the method, it can be guaranteed that the hardness of the cladding layer is stabilized within the ideal range, the mold repairing quality is remarkably improved, and the service life of the mold is remarkably prolonged.

The invention provides a stratosphere aircraft cross-day and cross-night task trajectory planning method and system in a dynamic wind field environment. The method comprises the steps that a task target and task constraints are acquired; acquiring external wind field information; constructing a motion model and a cost function of the stratosphere aircraft in the dynamic wind field; and outputting the lowest feasibility requirement of the cross-day and cross-night task under the dynamic wind field condition and the optimal trajectory when the task is completed by using a level set method in combination with particle swarm optimization. The method has the advantages that a combination framework of the level set algorithm and the particle swarm algorithm is innovatively provided, the problem that the level set algorithm has strong dependence on initial conditions is solved, meanwhile, the search space dimension is reduced, and the probability that the algorithm falls into a local optimal solution is reduced; by flexibly designing a fitness function, conditions such as speed constraint, energy consumption constraint and task feasibility of a stratosphere aircraft cross-day and cross-night arrival or residence task can be comprehensively considered, and the globality and constraint compatibility of trajectory optimization are realized.

The invention discloses a deep learning-based pipeline structure stress proxy model construction method, which belongs to the field of engineering mechanics, energy transmission and artificial intelligence, and comprises the following steps of: firstly, establishing a numerical model of a pipeline, simulating different environmental conditions by applying different loads, and solving to generate a large amount of simulation data; then, feature unit extraction is carried out on the simulation data so as to compress feature dimensions; then, a deep learning initial proxy model of pipeline stress is constructed, and initial training is carried out through finite element simulation data; and finally, transfer learning is carried out based on the initial agent model, the transfer learning is divided into two stages, enhanced actual measurement sample data is used for training in the pre-training stage, and accurate actual measurement samples are used for further training and fine adjustment in the strengthening stage, so that the generalization ability of the model is improved. According to the method, the stress distribution can be rapidly and accurately solved by constructing the stress agent model, the generalization ability is high, and the problem that a traditional physical modeling method is insufficient in real-time performance and precision in stress monitoring and prediction can be solved.

The invention relates to a multi-stage collaborative scheduling method for a ship block assembly workshop, and belongs to the technical field of assembly workshop scheduling. The ship block assembly job shop scheduling modeling is an assembly job shop collaborative scheduling problem model considering three stages of processing, transportation and assembly; and solving an assembly job shop collaborative scheduling problem model of three stages of processing, transportation and assembly based on an improved genetic algorithm. Taking minimization of completion time as an optimization target, and converting a part integrity constraint in a machining stage, a time difference constraint of a part in a transportation stage and a flowing water blockage constraint in an assembly stage into control variable constraints in a mathematical model; the strategy is improved on the basis of the genetic algorithm, and the solving capacity of the genetic algorithm for the ship block assembly job shop scheduling problem is improved; the method effectively solves the problem of ship block assembly workshop scheduling, and has solving precision and stability.

The invention discloses an on-line estimation method and system suitable for cluster type intelligent electric meter error analysis, and the method comprises the steps: building an intelligent electric meter error on-line calculation model through an energy conservation principle based on the characteristic that most intelligent electric meters are distributed according to a tree topology structure in reality, and solving the model to obtain an error estimation value. On this basis, non-uniformity of error information contained in measurement data in time is considered, a weight coefficient represented by attenuation factors is introduced to construct a loss function of a calculation model, different attenuation factors are adopted according to the condition number of a coefficient matrix to improve the tracking capability of an algorithm, an error estimation value is obtained by deriving the loss function, and the tracking precision of the algorithm is improved. And the error estimation value of the electric energy meter is updated in real time through newly collected data, so that the solving precision of the error estimation value is improved.

The invention discloses a vegetable greenhouse environment management method and system, a storage medium and a program product, and the method comprises the steps: obtaining historical environment parameters of a vegetable greenhouse, vegetable growth data and the growth state of vegetables in the vegetable greenhouse at the current moment; establishing a multistable growth model according to the historical environmental parameters and the vegetable growth data, wherein the multistable growth model comprises a plurality of stable growth points; positioning a growth state in the multistable growth model, and determining a dominant stable growth point closest to the growth state; establishing an attractor potential field, setting an advantage stable growth point as an attractor center, and calculating a potential energy gradient from a growth state to the attractor center; based on the potential energy gradient, a progressive regulation and control path of vegetable greenhouse environment parameters is constructed, and a staged environment regulation and control instruction is generated; and the staged environment regulation and control instruction is sent to the environment control equipment, so that the environment control equipment carries out environment regulation according to the staged environment regulation and control instruction and the progressive regulation and control path, and the timeliness and the accuracy of farming operation and environment regulation are improved.

The invention discloses a calculation method for a nuclear reactor neutron transport equation, and belongs to the field of nuclear reactor core design and safety. According to the method, the problem that the convergence speed of an inner iteration process of a transport equation and a low-order equation in a traditional PI-CMFD method is low is solved. The method specifically comprises the following steps: step 1, reading a coarse mesh model, a fine mesh model, material information and boundary conditions of a nuclear reactor; step 2, establishing a numerical discrete model of a steady-state multi-group transport equation according to the fine grid model read in the step 1; 3, after boundary constraint and material constraint are applied to the established numerical discrete model of the steady-state multi-group transport equation, a discrete equation set is constructed by transforming a test function in the model; and 4, solving the constructed discrete equation set based on the grid mapping relation between the coarse grid model and the fine grid model by adopting a PI method and a CMFD method to obtain a neutron angular flux value and a characteristic value of the neutron transport equation. The method can be applied to calculation of the neutron transport equation of the nuclear reactor.

The invention relates to a special assembly workshop machine and AGV combined scheduling optimization method considering optimal path selection, and the method comprises the following steps: initializing configuration parameters according to a workshop assembly process; a general assembly workshop machine and AGV scheduling scheme is taken as a solution, and a machine and AGV combined scheduling multi-target optimization model considering an AGV transportation optimal path is established; designing a multi-objective learning type artificial bee colony algorithm; and optimizing the scheduling scheme through iterative computation, and finally obtaining a plurality of optimized scheduling schemes which accord with actual production. Compared with a traditional scheduling mode, the method considers the selection of the optimal path during AGV transportation, greatly improves the scheduling efficiency and accuracy of the special assembly workshop, reduces the scheduling time cost and energy cost while providing a reasonable and effective scheduling scheme for workshop scheduling, and improves the scheduling efficiency. The overall production efficiency of an assembly workshop is improved, the order delay condition is reduced, and consumption reduction and efficiency improvement of enterprises are achieved.

The invention discloses a manifold neural operator construction method for a boundary value problem, and relates to the technical field of machine learning, and the method comprises the following steps: S1, obtaining a geometric Laplacian operator feature function psi g where a solution function is located and a geometric Laplacian operator feature function psi b where a boundary condition function is located; s2, constructing a manifold neural operator based on the characteristic function psi g, and obtaining a geometric coding network so as to obtain a geometric embedding function group; s3, constructing a manifold neural operator based on the characteristic function psi b, and obtaining a boundary condition coding network so as to obtain a boundary condition embedding amount; and S4, embedding a combined approximation solution function of the vectors based on the geometric embedding function group and the boundary condition function so as to construct a boundary value problem-oriented manifold neural operator. According to the manifold neural operator construction method for the boundary value problem, the embedding of complex geometric information in the boundary value problem solving process is realized, and the difficulty of solving the boundary value problem by a network is reduced.

The invention discloses an FADS system data processing method, a data processing system and an FADS system. The FADS system data processing method comprises the following steps: S1, acquiring atmospheric pressure data measured by each measurement module of the FADS system; s2, performing fault analysis on the acquired data by adopting a fault detection method based on a principal component analysis method, and removing fault point data in the data; and S3, evaluating the credibility of the measurement data of each measurement module by adopting a trust calculation method based on an evidence theory, selecting the test data of the measurement module with high membership degree and high mutual support degree after being processed in the step S2, and carrying out atmospheric calculation to obtain atmospheric parameter data. By processing the atmospheric pressure measurement data, automatically removing fault point data in the atmospheric pressure measurement data and screening out data with high credibility for atmospheric calculation, atmospheric parameter information data obtained by calculation is more accurate, and the problem of FADS system failure caused by faults of an embedded pressure sensor in an FADS system is well solved.

The invention discloses an electric power system reactive power optimization method based on distribution interval optimization. The method comprises the following steps: S1, constructing a first model; the first model comprises an interval reactive power optimization model of the high new energy permeability power system; the interval reactive power optimization model comprises a target function, a first constraint and an interval power flow equation constraint; s2, obtaining a first state variable interval according to the interval power flow equation constraint in combination with a distribution interval power flow algorithm; s3, converting the first model according to the first state variable interval in combination with a security limit definition method to obtain a second model; the second model comprises a deterministic optimization model; and S4, obtaining a reactive voltage control strategy according to the second model in combination with a primal-dual interior point method. The precision, the practicability and the economical efficiency of the reactive power optimization method for the high-new-energy-permeability power system can be improved.

The invention discloses a micro-energy network shared energy storage configuration method and device and a storage medium. The method comprises the following steps: acquiring basic data of a micro-energy network and a shared energy storage system; constructing a double-layer optimization model based on the basic data, wherein the double-layer optimization model comprises an inner-layer optimization model and an outer-layer optimization model; according to the inner layer optimization model, the inner layer optimization problem is determined to minimize the annual operation cost under the given shared energy storage configuration; according to the outer-layer optimization model, determining that an outer-layer optimization problem is maximization of the consumption rate of photovoltaic power generation; and solving the double-layer optimization model based on the inner-layer optimization problem and the outer-layer optimization problem to obtain an energy storage configuration optimization scheme. According to the embodiment of the invention, the double-layer optimization model is constructed to optimize the operation of the micro energy grid and the shared energy storage system, the photovoltaic consumption rate can be effectively improved, the total cost can be reduced, a better energy storage configuration optimization scheme can be solved, and the energy storage optimization effect realized based on the energy storage configuration optimization scheme can be effectively improved.

The invention relates to an optimization design method of a multi-winding regulation and control transformer for flexible interconnection, which comprises the following steps: 1, according to a single-target optimization design mathematical model, constructing an optimization target function with the purpose of minimizing the sum of the material cost of the multi-winding transformer and the ten-year operation cost; 2, determining required constraint conditions according to basic electrical parameters of the multi-winding regulation and control transformer for flexible interconnection; under the action of the obtained optimization objective function, punishing a trend violating constraints by adopting a punishment function, so that non-constraint optimization is gradually close to a feasible region, a constraint optimization problem of the distribution transformer is adjusted into an unconstraint optimization problem, and an optimization design model of the amplitude-phase adjustment type multi-winding transformer for flexible interconnection is obtained; and 3, solving the optimal design model, obtained in the step 2, of the multi-winding regulation and control transformer for flexible interconnection by using a particle swarm optimization algorithm. According to the method, the local optimal solution and the global optimal solution of the individual can be solved, and higher solution precision can be obtained.

A high-precision external rotor permanent magnet motor stray magnetic field analysis method relates to the field of external rotor permanent magnet motor magnetic field calculation, and comprises the following steps: S1, dividing an external rotor permanent magnet motor into 5 + n subdomains according to a structural equivalence principle under a two-dimensional polar coordinate system; s2, establishing a Laplacian equation or a Poisson equation of each sub-domain, and solving a vector magnetic potential of each sub-domain through a variable separation method and boundary conditions of an interface of a ferromagnetic material and a non-ferromagnetic material; s3, listing a constraint equation according to boundary conditions, and solving a harmonic coefficient of each vector magnetic potential; s4, collaboratively integrating the sub-domain model and an iterative convergence algorithm, and automatically iteratively updating the rotor unsaturated permeability at different radiuses of the iron core of the motor under various working conditions; and S5, solving partial derivatives of the vector magnetic potential of the external air domain to obtain radial and tangential components of the stray magnetic field. The method can accurately predict the unsaturated permeability of the iron core at different working conditions and different radiuses of the iron core of the motor, and improves the calculation precision of the stray magnetic field.

The invention relates to a distributed system for solving a large-scale mathematical optimization problem and an implementation method, and aims to improve the calculation efficiency and the solving capability so as to meet the requirements of enterprises on efficient operation and accurate decision-making under the background of digitization, globalization and double carbon. According to the system, a complex optimization problem is decomposed into a plurality of small sub-problems, and the sub-problems are processed in parallel on a plurality of computing nodes, so that the solving process is accelerated. The system also adopts an innovative synchronization and communication mechanism to ensure the data consistency and calculation accuracy among the nodes. In addition, the invention further provides a self-adaptive load balancing strategy so as to optimize resource allocation and further improve the overall calculation efficiency. According to the method, data analysis, knowledge discovery and interdisciplinary research innovation are promoted while high-performance computing power is provided, and the method has important significance on improvement of enterprise competitiveness and scientific research.

The invention relates to the technical field of neutron diffusion characteristic values, in particular to a method for solving multi-group neutron diffusion characteristic values by adopting a decoupling residual error loss function, which comprises the following steps of: randomly taking points on a calculation area, and dividing the points into a boundary point set, an interface point set and a residual error point set; determining the number of neurons of an output layer according to the number of group neutron fluxes and the number of materials in the calculation area; neurons of the output layer are subjected to weighted summation through an indicative function to obtain a neural network numerical solution; constructing a corresponding loss function; constructing a decoupling loss function containing the characteristic function information of the previous step; and optimizing the neural network by using an optimization algorithm, obtaining a numerical result when the loss function reaches a preset condition or the neural network completes a given number of training times, and according to the method, a neutron diffusion characteristic value equation source iteration solving method is absorbed, the characteristic function information of the previous step is inherited in an iteration form, and a new decoupling residual loss function is constructed. And the solving precision of the multi-group neutron diffusion characteristic value problem is improved.

The invention discloses a permanent magnet synchronous motor speed regulation control method based on an improved hawk algorithm. The method comprises the following steps: acquiring permanent magnet synchronous motor data; inputting the permanent magnet synchronous motor data into a pre-trained permanent magnet synchronous motor speed regulation control model, and outputting a speed regulation result of the permanent magnet synchronous motor; and the permanent magnet synchronous motor speed regulation control model is trained by using an improved Tianying algorithm. According to the method, the problem of controller parameter adjustment in a permanent magnet synchronous motor speed regulation control model is solved, the improved hawk optimization algorithm is introduced, the algorithm realizes optimal configuration of global search and local search capabilities by virtue of the characteristics of rapid convergence, high global search capability and high solving precision, and the optimal configuration of the global search and local search capabilities is realized in the parameter optimization process. A dynamic simplex method strategy and an annealing simulation-gold sine updating strategy are utilized to expand the optimal selection range, the algorithm shows excellent performance, and the labor intensity of researchers for adjusting parameters is remarkably relieved.

The invention discloses an attitude self-constrained RTK image attitude optimization method, a storage medium and a device, and relates to the technical field of real-time dynamic differential localization, and the technical scheme is characterized in that the method comprises the following steps: S1, feature point extraction; s2, feature point matching; s3, triangularizing the feature points; s4, constructing visual constraint information; s5, constructing attitude self-constraint information; and S6, performing nonlinear optimization. According to the method, the camera attitude is used as constraint information, so that attitude excessive optimization caused by visual information is inhibited.

The invention discloses a seabed inversion method, device and equipment based on genetic clone selection and a medium, and the method comprises the steps: carrying out the initialization to obtain a first population, and taking the first population as a target population; performing inversion and evaluation based on the inversion parameters of the target population to obtain a root-mean-square value corresponding to each individual; setting random parameters based on the minimum root-mean-square value and population iteration times; performing population updating based on a random parameter improved genetic algorithm; when the root mean square value in the updated population accords with the iterative optimal threshold value, taking the corresponding individual as a target individual; otherwise, population updating is carried out circularly until the target individual is obtained, or the number of population iterations is equal to the preset maximum number of population iterations; and finally, according to the submarine topography data corresponding to the target individual, determining a submarine inversion result of the to-be-inverted region. The method can accurately realize seabed inversion, and can be widely applied to the technical field of data processing.

The invention provides an active power distribution network strategy reconstruction method based on an improved grey wolf algorithm, and the method comprises the following steps: stage 1, reading the electrical data of a power distribution network, confirming the switching state and the access position and constraint conditions of a distributed power supply, and carrying out the reconstruction of a power distribution network strategy on the premise of meeting the power flow constraint, operation constraint and topological structure constraint of the power distribution network; and constructing a mathematical model for static reconstruction of the multi-target active power distribution network. Stage 2: then improving the GWO algorithm, the improved strategy including using improved Tent chaotic mapping to perform population initialization, improving a convergence factor and an adaptive t distribution disturbance variation position updating strategy, and obtaining a TGWO algorithm, according to the method, improved Tent chaotic mapping is introduced to carry out population initialization, an attenuation factor updates an alpha wolf position, and a disturbance variation strategy of adaptive t distribution is improved. The improved grey wolf algorithm is improved in operation speed, solving precision and robustness.

The invention belongs to the technical field of steering pull rod design, and particularly relates to a steering pull rod mechanism design method based on analytic geometry and a steering pull rod mechanism. The steering pull rod mechanism is simplified into a plane connecting rod mechanism, and four key hinge points are marked; establishing a coordinate system by taking P1 as an original point; the length, the initial angle and the P4 coordinate of the front steering swing arm are obtained; calculating two coordinates of a P2 point when the front steering swing arm rotates to a limit position; generating P2 ''and P2'' ''points by rotating P2 'P4 and P2'' P4 line segments; and connecting the line segments and constructing perpendicular bisectors, and determining the position of a P3 point by solving the intersection point of the perpendicular bisectors. According to the method, the steering pull rod mechanism is designed through analytic geometry and coordinate transformation, the accuracy of hinge point positioning is improved, and structural deviation caused by empirical estimation is reduced; the design complexity is reduced through standardization steps, the development period is shortened, the motion coordination of the steering system is optimized, and the method is suitable for the field of automobile chassis and the like needing high-precision motion control.

The embodiment of the invention provides a power system robust optimization method and device considering meteorological uncertainty. The method comprises the steps of obtaining historical wind and light output data, historical load power consumption data, historical meteorological data and day-ahead meteorological data of a power system; carrying out serialization processing on system elements of the power system to obtain a serialization processing result; based on the serialization processing result and the equivalent reliability index of the electric power equivalent system, determining the credible capacity of the electric power system; performing point prediction on the wind and light output and the load power to correspondingly obtain a wind and light output prediction result and a load prediction result; fitting the wind and light output prediction result and the load prediction result to correspondingly obtain an output prediction power interval and a load prediction power interval; constructing a day-ahead scheduling planning model; performing correction processing on the day-ahead scheduling planning model to obtain an intra-day scheduling optimization model; and solving the day-ahead scheduling planning model and the intra-day scheduling optimization model to obtain a power optimization strategy of the power system.

The invention discloses a cold-heat-electricity flexible resource cooperative regulation and control method and system for a low-carbon park. The method comprises the following steps: constructing a park operation model; constructing a park optimization scheduling model, and taking the minimum park operation cost and carbon emission as a target function; solving a dual-objective optimization problem by adopting augmented epsilon-constraint to obtain a Pareto frontier solution set; carrying out evaluation analysis on the solution set by sampling a TOPSIS method and a grey correlation analysis method to obtain an optimal solution; and scheduling the park according to the optimal operation scheme. By optimizing cold-heat-electricity resource regulation and control of the park, dual optimization of the operating cost and the carbon emission of the park is achieved. And an augmented epsilon-constraint method and a TOPSIS method are adopted, so that the solving efficiency of a multi-objective optimization problem and the precision of a solution set are improved, and an optimal regulation and control scheme is finally selected. Meanwhile, carbon capture and electricity-to-gas technologies are combined, so that carbon emission is effectively reduced, and low-carbon transformation and sustainable development of the park are facilitated.

The invention discloses an electromagnetic wave rain attenuation prediction method based on nonlinear regression, and belongs to the technical field of communication. The method is based on a classical ITU-R rain attenuation model, and comprises the following steps: constructing a training and testing data set for fitting model parameters k and b by collecting rainfall rate and attenuation data; a nonlinear regression method in deep learning is adopted, a model containing k and b parameters is designed and trained, a mean square error is used as a loss function, and parameter solving is carried out through a gradient descent optimization algorithm; and when the similarity between the fitting result on the test set and the real attenuation value reaches a specified threshold value, stopping training and outputting an optimal parameter. According to the method, automatic solving of the rain attenuation model parameters is realized, human intervention is reduced, the calculation precision and the generalization ability of the model are improved, and the method is suitable for electromagnetic wave propagation research in various rain attenuation scenes.

The invention discloses a collaborative planning method and system for accessing a charging infrastructure to a power grid, and relates to the technical field of electric vehicle charging, and the method comprises the steps: building an upper optimization model based on the position and number of charging stations, building a lower optimization model based on the traffic flow and a user charging and discharging strategy, an improved particle swarm algorithm is constructed by dynamically adjusting an inertia weight factor and learning factor mechanism, and global search and local search are balanced; and based on an improved particle swarm algorithm, carrying out bilevel programming model solution, and formulating a charging station configuration optimization scheme. According to the method, an efficient and dynamic charging infrastructure planning method is jointly formed, efficient cooperation of the charging station and the power grid is achieved by comprehensively considering multiple factors, and the operation efficiency and economical efficiency of the whole electric vehicle charging system are improved.

The invention discloses an electric power system real-time low-carbon economic dispatching method and device based on a parallel distributed flexible action device-evaluator, electronic equipment and a storage medium, and the method comprises the steps: jointly participating in the real-time optimal dispatching information of an electric power system according to large-scale new energy and a carbon transaction mechanism; and constructing a real-time low-carbon economic dispatching model of the power system based on the Markov decision process. According to the model, a parallel distributed flexible action device-evaluator algorithm is proposed to train an agent offline to learn a low-carbon economic dispatching strategy; and integrating the trained intelligent agent into a power system dispatching device for application, and deciding a dispatching scheme of each generator set according to the real-time state information of the system. According to the method, on the basis of the real-time low-carbon economic dispatching requirement of a power system, the continuous action space of the dispatching problem is processed through a flexible action device-evaluator; and a distributed flexible strategy iteration framework and a parallel technology are utilized to improve a flexible action device-evaluator, so that the solving speed and precision are improved.