347 results about "Simulated annealing" patented technology

The invention discloses a filling body multi-age strength prediction and material inversion model construction method, and belongs to the technical field of metal mine paste filling, and the method comprises the steps: carrying out the preprocessing operation according to the characteristic variables of a material ratio parameter and a tailing characteristic parameter, and obtaining a characteristic variable data set; performing data division on the characteristic variable data set according to a preset proportion in a preset multi-age period; constructing a multi-age strength prediction model, and training the model by using the training set to obtain an unconfined compressive strength prediction result in a preset multi-age; verifying the constructed multi-age strength prediction model by using a test set by adopting a Shapley addition explanation method; and adding a simulated annealing algorithm to the verified multi-age strength prediction model to obtain a reverse optimization model. The method has higher generalization ability and universality, and the filling design period is greatly shortened by combining model prediction of the multi-age strength prediction model with the simulated annealing optimization algorithm.

The invention provides a reinforcement corrosion electrochemical parameter inversion method based on LSTM (Long Short Term Memory) time sequence prediction, which comprises the following steps: S1, acquiring electrochemical time sequence data in a reinforcement corrosion process through an electrochemical workstation to form an original reinforcement corrosion electrochemical time sequence data set; s2, preprocessing is carried out to obtain a training set, a verification set, a test set and normalization coefficients of all parameters; s3, constructing and training an LSTM time sequence prediction model; s4, constructing and calibrating a steel bar corrosion electrochemical parameter forward modeling model; and S5, constructing an inversion framework fusing a particle swarm optimization algorithm, a simulated annealing algorithm and an Adam optimization algorithm, forming closed-loop cooperation by the particle swarm optimization algorithm, the simulated annealing algorithm and the Adam optimization algorithm so as to minimize an error between a target electrochemical response parameter and a theoretical electrochemical response parameter, and outputting an inversion result. According to the method, through organic combination of time sequence prediction and multi-algorithm cooperation, the problems that a traditional inversion method is low in precision and poor in stability are solved, and a reliable technical means is provided for reinforced concrete structure health monitoring.

The invention discloses a wing design optimization method based on agent-assisted multi-initial-point simulated annealing, and belongs to the technical field of optimization design. Comprising the steps of 1, initializing algorithm parameters and a training data set; 2, constructing an agent model; 3, executing multi-initial-point parallel simulated annealing, and generating a batch of candidate new solution sets; 4, executing a double-elite active learning strategy based on the new solution set, screening the most potential sample to carry out real evaluation, and updating the agent model; 5, cooling the temperature and reducing the step length; 6, judging whether the cumulative evaluation times of the expensive objective function reach the set maximum evaluation times or not; if not, returning to the step 2; if yes, optimization is stopped; and finally, traversing the training data set, and selecting a sample point with the minimum real objective function value as a global optimal solution. According to the method, a multi-initial-point parallel simulated annealing search mechanism and a double-elite active learning strategy are combined, and the global optimal solution is quickly approached under the limited simulation times.

The invention provides an aviation composite material hot-press forming workpiece loading method based on a hybrid optimization algorithm. The method comprises the steps that workpiece demand information and autoclave platform information in composite material hot-press forming manufacturing are obtained; minimizing the opening times of the autoclave as a target function; establishing a two-dimensional multi-layer platform hot press molding workpiece loading model, defining space constraints, distribution constraints, resource constraints and type constraints among workpieces, and incorporating the constraints into model constraint conditions; a GA-SP is adopted to optimize a workpiece loading sequence and a rotation state, an optimal layout is generated through chromosome coding, decoding, selection, intersection and mutation operations, a hybrid optimization algorithm is constructed in combination with a neighborhood search strategy, efficient arrangement of workpieces on different platforms is realized in combination with a simulated annealing criterion, and an optimized loading scheme is output. The production efficiency of the hot press molding procedure can be improved, the manufacturing cost is reduced, and efficient technical support is provided for intelligent manufacturing of aviation composite materials.

The invention provides an LLM reasoning-oriented heterogeneous core particle architecture simulation and search method and system, and the method comprises the steps: constructing a heterogeneous core particle joint simulation platform which integrates behavior-level modeling aiming at various core particle types, simulates the calculation and data transmission behaviors of a heterogeneous core particle architecture and power consumption area characteristics, forms a simulation architecture, and carries out the simulation of the heterogeneous core particle architecture; carrying out performance evaluation on the simulation architecture; an improved simulated annealing search strategy is adopted to explore the design space of the simulation architecture, and the strategy comprises the following steps: configuring core particles of different types or scales for core particle groups executing tasks of different layers based on calculation and memory access characteristics of different network layers of LLM by adopting packet heterogeneous search, optimizing the search process by adopting a simulated annealing algorithm integrated with Pareto frontier optimization; a hybrid parallel strategy of TP, PP, DP and EP and grouping heterogeneous search are subjected to collaborative optimization, and optimal parallelism combination and task mapping based on core particle grouping are automatically explored.

The invention provides an FPGA parallel Isin model optimization method and system based on a GHMC simulated annealing algorithm, relates to the field of power system combination optimization, and solves the technical problem that an existing FPGA-based Isin model solver adopts a traditional Monte Carlo method and is low in convergence precision and solution quality. The method comprises the following steps: receiving a question input by a user through an upper computer, and mapping the received question into a Hamiltonian parameter of an Isin model; the Hamiltonian parameter is transmitted to an FPGA through a communication interface, and a mixed GHMC sampler and a temperature scheduling module are arranged in the FPGA; the hybrid GHMC sampler carries out parallel solution on Hamiltonian parameters; and the temperature scheduling module gradually reduces the system temperature according to a preset annealing curve, and drives the Isin model to converge to a global optimal solution. The method is used in the power system combination optimization process.

The invention discloses a five-axis machining cutter location linear interpolation optimization control method, which relates to the technical field of numerical control machining, and comprises the following steps: fitting a machining contour to generate a curve expression, determining an operation point sequence based on curvature distribution, and converting the operation point sequence into an actuator pose sequence; based on the model of a five-axis machining machine tool, a total transformation matrix from a base coordinate system to an actuator coordinate system is established through a D-H method, motion parameter changes caused by five-axis elastic deformation and inertia force are established based on the nonlinear beam theory and the Alembert principle, and a nonlinear axis body coupling motion equation is established; a correction expression is generated in combination with the Jacobian matrix, optimal unknown parameters in the correction expression are determined by introducing a quantum fluctuation simulated annealing algorithm, and a correction Jacobian matrix is generated; according to the actuator pose change of the adjacent operation points in the actuator pose sequence, the corrected Jacobian matrix is combined, the inverse kinematics algorithm is adopted to derive the motion parameter vector of the previous operation point, and higher-precision machining control is achieved.

The invention relates to an automatic driving test scene simulation generalization generation method and system based on knowledge distillation. The method comprises the following steps: acquiring real trajectory data, constructing a scene-level multi-agent trajectory generation framework based on a denoising diffusion probability model, and generating diversified and vivid agent trajectories through an iterative denoising process so as to realize modeling of multi-agent interaction behaviors in a complex traffic environment; a mixed knowledge self-distillation framework is further proposed, multi-level knowledge of a teacher model is migrated in a student model, and task loss and distillation loss are dynamically balanced in combination with a simulated annealing strategy, so that the cross-scene adaptability and generation stability of the model are improved; simulation verification shows that the generated intelligent agent track can effectively reduce the collision event rate and the retrograde event rate, and interaction coordination and traffic rule constraints are ensured. According to the system, the authenticity, diversity and cross-scene adaptive capacity of an automatic driving simulation scene can be improved.

The invention discloses a lithium battery residual life prediction method and system based on an electrochemical model, and relates to the field of lithium ion battery life prediction, and the method comprises the steps: constructing an initial electrochemical model according to battery powder attribute parameters, internal structure parameters and empirical parameters of a lithium ion battery; the method comprises the following steps: respectively taking new lithium ion batteries of the same model and old batteries at different aging stages as experimental objects, obtaining respective corresponding battery aging characteristic data through experimental measurement and electrochemical model simulation, and then taking the minimum value of the difference between the measurement data and the simulation data as an optimization target; empirical parameters and battery recession parameters in the initial electrochemical model are identified through a simulated annealing intelligent optimization algorithm; and according to the identified empirical parameters and the battery recession parameters, constructing a lithium ion battery full-life-cycle electrochemical model, performing working condition analog simulation on the lithium ion battery full-life-cycle electrochemical model, and predicting the remaining life of the battery. The battery is modeled from the internal electrochemical reaction level of the battery, and the prediction precision of the residual life of the battery is improved.

The invention relates to the technical field of cloud computing, and provides a cloud native assembly type application construction method and device supporting dynamic combination. According to the method, through component standardized packaging and distributed warehouse management, the high component reuse rate is achieved, the repeated development workload is reduced, a visual arrangement tool and a process template are reused, the application construction period is shortened by 50% or above, business personnel can directly participate in development, the'business-technology 'communication cost is reduced, and the development efficiency is improved. And during dynamic combination, an optimal loading path is calculated by adopting an optimization particle swarm algorithm of global search of a particle swarm algorithm and local kick of a simulated annealing algorithm, so that intelligent dependency analysis and optimal path calculation are realized, and the complexity of manual dependency sorting is avoided.

The invention discloses an unmanned aerial vehicle arrival and departure joint scheduling method under a conical airspace structure, which solves the arrival and departure joint scheduling optimization problem by adopting a simulated annealing algorithm of a double-disturbance mechanism, balances the solving quality and convergence speed, provides a theoretical basis for vertical take-off and landing field unmanned aerial vehicle arrival and departure joint scheduling, and improves the unmanned aerial vehicle arrival and departure joint scheduling efficiency. The total operation cost of the vertical take-off and landing field is reduced, the guarantee efficiency is improved, and delay is reduced. Meanwhile, the optimal airspace structure design scheme and scheduling strategy are obtained by comparing the total cost under different airspace structure parameters, safety interval time and check time, a theoretical basis is provided for vertical take-off and landing field airspace arrangement and operation scheduling, and certain practical significance is achieved.

The invention relates to the field of intelligent optimization algorithms, and provides an antenna design method based on a collaborative hybrid electric eel algorithm. The method comprises three stages of interaction, rest and hunting: in the interaction stage, introducing a differential variation strategy of DE, generating a new solution in combination with a random direction vector to enhance the global search capability, and if the individual fitness is insufficient, executing random disturbance to expand the search direction; in the rest stage, a PSO speed-position updating formula is adopted, and an individual extreme value and a global extreme value are utilized to guide local fine search; in the hunting stage, a Metropolis criterion of SA is combined, an inferior solution is accepted by probability to avoid local optimum, and exploration intensity is controlled through dynamic annealing temperature. According to the algorithm, self-adaptive mode switching is achieved by dynamically adjusting an energy attenuation factor and a simulated annealing temperature, meanwhile, a boundary reflection method is adopted to ensure that a solution is in a feasible region, and stability is improved. Experiments show that SHEEA can quickly jump out of local optimum in a complex multi-peak function test, and performance indexes are remarkably improved in multi-frequency antenna design.

The invention provides an image segmentation method based on an improved parrot optimization algorithm and cross entropy multiple thresholds, and the method comprises the following steps: S1, converting a color image into a gray image, and carrying out the noise reduction processing; obtaining a corresponding image gray level histogram according to the gray level image; s2, constructing a target function of cross entropy multi-threshold segmentation based on the image gray histogram; independent variables of the objective function are a plurality of threshold values; s3, optimizing each threshold value by adopting an improved parrot optimization algorithm (IPO), and determining an optimal threshold value combination; wherein in the improved parrot optimization algorithm, the positions of individuals in the foraging behavior stage are updated by adopting a Leid flight strategy or particle swarm optimization (PSO); disturbing the current globally optimal solution by adopting a simulated annealing mechanism; and S4, segmenting the color image based on the optimal threshold combination. According to the method, the local search capability and the convergence speed are improved, so that the precision and robustness of image segmentation are improved.

The invention discloses a multi-unmanned aerial vehicle cooperative regional patrol path planning method based on hierarchical optimization, and the method comprises the steps: firstly, abstracting a task space containing a base station and a plurality of target points into a weighted undirected complete graph, and building a mathematical model with a target of minimizing the total completion time of a system and the standard deviation of task time; then solving is carried out through a hierarchical strategy; firstly, k-means clustering is adopted to carry out initial task allocation; solving a traveling salesman problem for each task cluster by using a simulated annealing algorithm, generating an initial path, and performing local optimization by using a 2-OPT algorithm; and finally, carrying out global collaborative optimization by adopting adaptive large-scale neighborhood search, dynamically adjusting task allocation and paths through a cross-unmanned aerial vehicle damage and repair operator, and carrying out iterative optimization according to a composite acceptance criterion and an adaptive mechanism to generate a near-optimal scheme. According to the method, through tight coupling of task allocation and path planning, the defect that a traditional method is prone to local optimization is effectively overcome, and joint optimization of completion time and load balancing is achieved.

The invention discloses a service scheduling method and system for a photoelectric hybrid low earth orbit satellite network, and relates to the technical field of satellite communication and network resource management.The method comprises the steps that the photoelectric hybrid low earth orbit satellite network is constructed, and topological information, node information and a to-be-scheduled service set of the photoelectric hybrid low earth orbit satellite network are obtained; establishing a mixed integer linear programming model containing node selection constraint, service scheduling sequence constraint and routing constraint by taking the minimum weighted sum of the total service completion energy consumption and the total service completion time as a target; in order to solve the problem of high model complexity, a heuristic algorithm based on simulated annealing is designed, and efficient solution is carried out by iteratively optimizing a scheduling sequence and a routing path of a service; and finally, implementing service scheduling according to the obtained optimal scheduling scheme. According to the method, heterogeneous characteristics of the photoelectric nodes and link resource conflicts are fully considered, dynamic balance of energy consumption and time delay is achieved, network energy efficiency and business service quality are remarkably improved, and the method is suitable for efficient operation of large-scale low-orbit satellite constellations.

The invention discloses a charging station network cooperative control method and system based on an improved particle swarm optimization algorithm, and the method comprises the following steps: S1, constructing a multi-dimensional feature fusion deep learning model, predicting a load demand of the charging station network in a future first preset time period based on a multi-dimensional feature fusion deep learning model according to the multi-source feature data, so as to obtain a short-term load demand result; s2, on the basis of a short-term load demand result, establishing a dynamic scheduling optimization model containing multiple constraint conditions; and S3, introducing an adaptive inertia weight adjustment mechanism into the improved particle swarm optimization algorithm, and cooperatively solving a short-term load prediction result and the dynamic scheduling optimization model in combination with a probability acceptance criterion of a simulated annealing algorithm so as to dynamically allocate and cooperatively control power resources in the charging station network in real time. Therefore, through the deep coupling prediction and scheduling process, global optimization and real-time response are balanced, and the operation efficiency of the charging station network and the compatibility of the power grid are improved.

The invention provides a self-adaptive intelligent scheduling optimization method for an industrial production line. The method comprises the following steps: constructing a production state model reflecting actual productivity and constraint conditions; establishing a multi-target scheduling optimization model including production efficiency, delivery date satisfaction degree and energy consumption level; based on the real-time production data, generating an optimal scheduling scheme by adopting a dynamic scheduling algorithm; an improved simulated annealing algorithm is introduced into the scheduling optimization process, and the solving efficiency is improved through a self-adaptive annealing strategy; scheduling execution data are collected for performance evaluation, and the scheduling rule base is updated in combination with a reinforcement learning mechanism, so that closed-loop feedback of scheduling optimization is realized. According to the method, collaborative optimization of multi-target scheduling performance can be realized, and the method has relatively high real-time performance and adaptivity and is suitable for intelligent scheduling requirements in a complex dynamic industrial production scene.

The invention provides a deep learning-fused power demand multi-algorithm collaborative demand prediction method and system, and the system comprises a short-term power demand prediction platform, a medium and long term power demand prediction platform, a collection management platform, and a display analysis platform. According to the whale optimization algorithm, the generalization ability is improved by introducing chaotic mapping and a nonlinear convergence factor, the weight is optimized in combination with a multi-scale graph convolutional network, the number of nodes, the learning rate and the number of iterations of a model are optimized in combination with a simulated annealing algorithm, the model is constructed, and by setting a medium-and-long-term power demand prediction platform, the power demand prediction efficiency is improved. Based on the Tent chaotic mapping and the dynamic step length factor optimization standard sparrow search algorithm, the prediction result is accurate and reliable by optimizing the key parameters of the composite model combining the convolutional neural network and the bidirectional long and short term memory network with the attention mechanism, and the power demand prediction cost is reduced.

The invention discloses a container scheduling optimization method for improving a cluster resource utilization rate, and relates to the technical field of container scheduling, the method comprises the following steps: S1, collecting resource utilization rate data of a computing server in a cluster in real time, and cleaning and standardizing the collected data to form a standardized resource vector; s2, calculating a real-time comprehensive health score of each calculation server based on the standardized resource vector; s3, aiming at the to-be-scheduled job, constructing a comprehensive scheduling cost function to calculate a cost value deployed to each candidate server; s4, based on a simulated annealing algorithm, performing joint scheduling decision on the jobs in the current scheduling queue, and searching for a deployment scheme with the lowest total cost; and S5, executing container scheduling according to a decision result, and optimizing the scheduling model based on job operation feedback data. According to the method, the cluster state can be perceived, and a scheduling decision is made through an optimization algorithm, so that the resource utilization rate of the whole cluster is maximized.

The invention relates to the technical field of thermal power generating unit operation optimization, and particularly discloses a thermal power generating unit operation optimization method, device and equipment and a storage medium, and the method comprises the steps: determining a target optimization function of a thermal power generating unit and a target constraint condition corresponding to the target optimization function; obtaining a nonlinear mapping function, and converting the target optimization function into representation of the nonlinear mapping function to obtain a target mapping function; determining a current initial operation parameter of the target mapping function in the target constraint condition based on a simulated annealing algorithm; iteratively optimizing the current initial operation parameter by adopting a trust region inner point method to obtain a current target optimization parameter of the target mapping function; updating the current operation parameters of the thermal power generating unit based on the current target optimization parameters to obtain current target operation parameters; and controlling the thermal power generating unit to operate based on the current target operation parameters. According to the scheme, the operation accuracy of the thermal power generating unit is improved by optimizing the operation data of the thermal power generating unit.

The invention provides a man-machine collaborative dynamic scheduling method fused with a double-layer optimization mechanism, and relates to the field of man-machine collaborative dynamic scheduling. According to a double-layer optimization mechanism provided by the invention, an offline optimization layer and an online real-time scheduling layer are organically combined: firstly, the offline optimization layer is based on a workpiece set, stations and robot resources, and is combined with a simulated annealing algorithm for adaptive optimization to obtain a global optimal solution; and then, taking a global optimal solution output by the offline optimization layer as an initial scheduling scheme of the online real-time scheduling layer, and performing real-time adjustment by adopting a multi-agent adaptive near-end strategy optimization algorithm. According to the method, the low efficiency of online scheduling from zero exploration is avoided, and the high efficiency of decision making is ensured. Besides, the online real-time scheduling layer constructs a collaborative decision-making system composed of a task allocation agent, a resource scheduling agent and a disturbance response agent, decision-making dimension pressure faced by a single agent is remarkably reduced through specialized labor division, and a complex interaction relation in man-machine collaborative scheduling is delicately processed.

The invention discloses an agent path planning method based on dual-archive multi-target Harris eagle optimization. The method comprises the following steps: firstly, constructing a three-dimensional environment model and defining a multi-target optimization problem; then, the paths are coded, populations are initialized, and a double-archive mechanism of convergence archives and diversity archives is introduced innovatively; in iterative optimization, dynamically switching a global exploration stage and a local development stage according to an improved nonlinear energy model, respectively guiding search by utilizing double archives, and enhancing the optimization capability in combination with Levy flight, Cauchy variation and a simulated annealing mechanism; and finally, selecting a path from the Pareto optimal solution set, smoothing and verifying the path, and outputting the path. According to the invention, through the dual-archive cooperation strategy and the improved Harris eagle optimization algorithm, the convergence speed and the diversity of solution sets are effectively balanced, the quality, efficiency and robustness of path planning in a complex constraint environment are significantly improved, and the method can be widely applied to autonomous navigation tasks of intelligent agents such as unmanned aerial vehicles, automatic guided vehicles and rescue robots.

The invention relates to a three-dimensional cargo boxing method and platform based on path planning and order splitting and a medium, and the method comprises the steps: carrying out the initial planning of a distribution path of a to-be-distributed cargo according to preset distribution resource information and a distribution planning strategy, and generating initial planning information; based on the logistics path corresponding to the initial planning information, path construction iteration and simulated annealing optimization iteration are carried out by using an ant colony and simulated annealing hybrid algorithm, and current planning information is generated; determining a distribution sequence corresponding to a logistics path corresponding to the current planning information and pre-distributed goods corresponding to each node, and performing three-dimensional boxing planning on all the pre-distributed goods based on a preset three-dimensional boxing strategy and an inverted sequence of the distribution sequence, and determining whether the planned current three-dimensional boxing planning information meets the requirement of boxing all the pre-distributed cargos into the corresponding distribution vehicles or not, and repeatedly executing to generate the current planning information and plan the current three-dimensional boxing planning information until the boxing requirement is met.

The invention belongs to the technical field of satellite communication, and particularly relates to a beam position scheduling method based on a hopping beam, which systematically solves the core bottleneck in hopping beam resource scheduling through a double-stage collaborative optimization mechanism: breaking through the limitation of single-slot scheduling by adopting cross-slot global beam position planning, and realizing the space-time balanced allocation of resources in a hopping beam period; non-uniform user distribution is dynamically matched based on density self-adaptive beam position clustering and iterative optimization, so that the high-density area coverage capability and the system load balance are remarkably improved; and internal and external interference of the system is effectively suppressed by combining minimum beam spacing constraint and a hybrid optimization strategy (greedy algorithm + simulated annealing). According to the method, the resource utilization rate is improved, the communication quality robustness is synchronously enhanced, and a high-reliability and self-adaptive beam scheduling solution is provided for a heterogeneous satellite network.

The invention relates to an intelligent prediction method for a sub-terahertz propagation coefficient of a dual-algorithm optimized DNN, and belongs to the field of communication technologies and deep learning. The technical problems that a traditional propagation model depends on actual measurement and is poor in generalization ability are solved. High-frequency electromagnetic waves and materials are complex in action; artificial setting of the neural network is easy to fall into local optimum. The method specifically comprises the following steps: constructing a DNN model to capture a nonlinear relationship between electromagnetic waves and a material; actually measuring the reflection / transmission coefficient of the sub-terahertz frequency band material to construct a data set; fusing a simulated annealing algorithm to optimize a network structure; optimizing a weight initial value by a genetic algorithm; and training the model and evaluating the performance based on MAE, RMSE, MAPE and error probability. According to the invention, the prediction precision and the model generalization ability are significantly improved through a dual optimization mechanism; limitation of a traditional simplified model is broken through; complicated electromagnetic characteristics are autonomously learned; and environment modeling and beam management of the 6G communication perception integrated system are supported.

The invention discloses a neural network optimization method for predicting the photosynthetic rate of protected grapes, and belongs to the crossing field of artificial intelligence and agriculture. In order to solve the problem that random initialization of a neural network is easy to fall into local optimum, the method adopts a swarm intelligence optimization algorithm combined with a simulated annealing algorithm to perform global optimization before training so as to determine an optimal initial connection weight and an optimal node threshold. In the optimization process, a Huber loss function is taken as fitness, and a poorer solution is accepted according to Metropolis criterion probability, so that the global search capability is effectively improved. And after the optimal initial parameters are obtained, training and predicting a neural network in which environmental factors such as carbon dioxide concentration, temperature and the like are input. According to the method, the local optimum problem is effectively avoided, and the precision and stability of the prediction model are remarkably improved.

The invention discloses a heterogeneous computing spatio-temporal joint optimization task scheduling and resource allocation method and system, and relates to the technical field of heterogeneous computing scheduling optimizing.The method comprises the steps that a spatio-temporal joint optimization cost function is constructed; a projection value is generated through dot product projection operation of the task demand vector and the resource capacity tensor, a target calculation unit is selected according to the minimum value of the projection value, and the smaller the projection value is, the higher the matching degree of the task demand and the resource capacity is; a scheduling scheme is generated by adopting a particle swarm optimization algorithm, the inertia weight of the scheduling scheme is nonlinearly decreased along with the number of iterations, and a simulated annealing mechanism is introduced in the position updating process to receive a degradation solution with a preset probability. According to the method and the system provided by the invention, through multi-dimensional collaborative optimization, the overall performance of the heterogeneous computing environment is effectively improved, and the space-time joint optimization cost function constructed by the method comprehensively considers key factors such as task execution time, energy consumption, resource fragmentation and the like, so that multi-objective balance optimization is realized.

The application discloses a full life cycle management system and method for a smart park based on digital twinning and the Internet of Things, relates to the technical field of smart park management, and comprises a sensing edge module, a data management module, an intelligent analysis module, a life cycle module and a twinning modeling module.The application supports multi-protocol access and edge computing capability, greatly improves data transmission efficiency and stability, the intelligent analysis module outputs accurate analysis results by constructing a multi-class feature matrix and a deep multi-task joint modeling mechanism, and provides data support and model guidance for park dynamic management and intelligent decision-making, the life cycle module fuses Kepler optimization algorithm, multi-agent reinforcement learning and simulated annealing algorithm, establishes a collaborative optimization mechanism, realizes the combination of global search and local fine-tuning of resource scheduling, and effectively optimizes energy consumption, response time, space utilization and safety risks, and the twinning modeling module constructs a three-dimensional model of the park, improves system interactivity and operability.

The invention provides a design method of a replaceable anti-falling beam device for improving transverse anti-seismic performance of a bridge, and relates to the technical field of design of anti-falling beam devices.The method comprises the specific steps that parameters of the bridge without an anti-falling beam and regional historical seismic parameters are collected; different earthquake scenes are simulated, and pier bottom reference anti-seismic performance indexes are output when no anti-falling beam exists; a group of anti-falling beam parameter combination is randomly set, a coupling model is constructed, an earthquake scene in the same S2 is simulated, and an anti-seismic performance index in the presence of an anti-falling beam is output; s5, calculating a performance comprehensive difference value by taking the reference index as a reference, calculating a comprehensive matching degree after the performance comprehensive difference value exceeds a performance threshold value, and entering S5 when the comprehensive matching degree exceeds a matching degree threshold value; and taking the selected parameters as initial solutions, and carrying out iterative optimization by using a simulated annealing algorithm to obtain an optimal combination. Through double-model linkage, a double-screening mechanism and algorithm optimization, the problems that in the prior art, adaptation verification is missing, and a device is prone to failure are solved, the anti-beam-falling protection effect is quantified, and the transverse anti-seismic reliability of a bridge is improved.

The application relates to the field of 5G communication technology, in particular to a 5G base station site selection method and system taking a convergence device as a center, which comprises setting candidate base stations, convergence device and link related parameters and decision variables; enabling the candidate base stations and connecting the nearest convergence device in a high demand area, calculating the total cost, the time delay of each service and the utilization rate at this time; using the evaluation function of the simulated annealing algorithm to calculate the total cost, the time delay and the utilization rate to obtain the current solution; randomly exchanging the convergence device allocation of the base station or adjusting the link path until the constraint condition is met, recalculating the total cost, the time delay and the utilization rate and substituting them into the evaluation function to obtain a new solution; judging whether to accept the new solution according to the simulated annealing algorithm criterion, constantly updating the temperature and iterating until the maximum running number is reached, and finally forming a convergence device deployment scheme and a link planning. The application is used for reasonably planning the base station site under the conditions of multi-site, multi-convergence device and multi-target optimization.