20results about How to "Improve search ability" patented technology

The invention relates to the technical field of enterprise motorcade management, in particular to a motorcade dynamic scheduling and energy consumption collaborative optimization method and system based on digital twinning, and the method comprises the steps: building a motorcade digital twinning scheduling cloud platform, and accessing a plurality of motorcade participants cooperatively executing transportation tasks; the method comprises the following steps: carrying out space-time division on a transportation task according to a collaborative scheduling authority, generating and issuing motorcade scheduling blocks, carrying out initial parameter definition on key factors such as vehicle distribution, path planning, load optimization and dynamic road condition response by each participant based on block information, and constructing a plurality of motorcade dynamic scheduling modeling spaces by combining with traversal search of a scheduling parameter library; an improved teaching and learning optimization algorithm module is introduced, a dynamic competition optimization algorithm is embedded to enhance the adaptability, and a motorcade scheduling collaborative optimization algorithm module is formed. Global optimization is carried out in multiple modeling spaces based on the algorithm, an optimal scheduling parameter set is output, and dynamic scheduling and energy consumption collaborative optimization of transportation tasks are achieved.

The application discloses a kind of based on the improved NSGA-II algorithm abrasive belt grinding multi-objective process parameter optimization method, first establish the mathematical model of carbon emission, surface roughness and material removal rate of abrasive belt grinding process, then according to the improved NSGA-II algorithm multi-objective optimization model is established, and using the improved NSGA-II algorithm multi-objective optimization is realized the intelligent optimization of process parameter of grinding process.The method of the application fully considers the mutual influence between each process parameter in the process of abrasive belt grinding difficult-to-machine material, the improved NSGA-II algorithm proposed uses new sequencing method, improves the population diversity of algorithm, so that the algorithm has better solution set uniformity, and the searching ability of improved NSGA-II to global optimal solution is stronger, under the same condition, the number of Pareto optimal solution of improved NSGA-II algorithm is more than NSGA-II and MOPSO algorithm, which means that improved NSGA-II algorithm can find out better global optimal solution.

The application provides a combined cooling heating and power micro-grid system operation optimization method, first, an optimization objective function and constraint condition of the combined cooling heating and power micro-grid system operation are constructed, thereby a combined cooling heating and power micro-grid system multi-objective optimization model is established; then a target function of the combined cooling heating and power micro-grid system is determined, thereby the cost is reduced and the economic benefit is improved; secondly, an improved chameleon swarm algorithm is introduced in the traditional method in the combined cooling heating and power micro-grid system operation strategy to realize energy optimization management of the combined cooling heating and power micro-grid system, thereby problems such as population diversity attenuation and falling into a local optimal solution of the swarm intelligence optimization algorithm in the chameleon swarm algorithm are avoided; finally, a hybrid following heat load strategy operation strategy is provided, and the operation cost of the combined cooling heating and power micro-grid system is more effectively reduced. The application has the beneficial effects that the renewable energy is utilized, the stable operation of the power grid is maintained, and the operation cost of the combined cooling heating and power micro-grid system is effectively reduced.

The application provides a battery group arrangement equalization strategy optimization method based on a QTA-TLBO double-layer multi-objective algorithm, which comprises the following steps: establishing an upper-layer battery group optimization model comprising an upper-layer optimization objective function and an upper-layer optimization constraint condition, and obtaining an optimal single cell arrangement structure of the battery group; establishing a lower-layer battery group optimization energy scheduling model comprising a lower-layer optimization objective function and a lower-layer optimization constraint condition, and obtaining an optimal equalization strategy of the battery group; establishing a coupling optimization model between the upper-layer battery group single cell arrangement structure and the lower-layer battery group equalization strategy; and using the proposed quantum tunneling annealing-teaching and learning double-layer multi-objective optimization algorithm to optimize and solve the model, so as to obtain an optimal grouping scheme of the battery group and an optimal equalization strategy of each cycle. Through the application, the reasonable arrangement of the single cells of the battery group can be obtained, the long-term reliable operation of the battery group can be realized, and the energy scheduling strategy of the battery group between the single cells can be planned, so that the maximization of battery energy utilization is realized.

The present application relates to reservoir scheduling technical field, disclose a kind of cascade reservoir group scheduling trajectory dynamic optimization method, comprising the following steps: collecting scheduling basic data;Optimization function and constraint condition of cascade reservoir group scheduling are constructed and calculation parameter is set;Using artificial experience decision or conventional method, obtain the initial trajectory of each reservoir each stage;Start iteration, execute several times dynamic programming method and establish historical trajectory library;Continue iteration, execute multi-type flight mode dynamic optimization, randomly select lev flight, spiral flight or navigation flight mode combination historical trajectory optimization current trajectory, iteration until meeting termination condition output optimal scheduling trajectory.The present application also discloses a kind of cascade reservoir group scheduling trajectory dynamic optimization.The present application cascade reservoir group scheduling trajectory dynamic optimization method and system, break through the dimension disaster defect that dynamic programming exists in solving complex reservoir group scheduling trajectory optimization problem, present significant convergence ability and calculation precision.

Based on the improved grey wolf optimization algorithm, the PMU optimal configuration method for distribution network is proposed. Under the condition of system full observability, the PMU optimal configuration mathematical model is established. Considering the influence of zero injection node and the system observability under single PMU interruption and single line outage, the constraint conditions of the established PMU optimal configuration mathematical model are modified. On the basis of grey wolf optimization algorithm, the population initialization, nonlinear convergence factor and position update weight coefficient are improved. The improved grey wolf optimization algorithm is used to solve the PMU configuration model under different scenarios. The method builds the optimal configuration model under different scenarios to achieve the goal of system full observability, and uses the improved grey wolf optimization algorithm to solve the PMU optimal configuration scheme. Compared with other algorithms, the method has better optimization effect.

The invention provides a blast furnace molten iron silicon content prediction method based on an improved grey goose algorithm, and relates to the technical field of intelligent prediction, and the method comprises the following steps: collecting multi-dimensional process parameters in a blast furnace operation process, and synchronously recording corresponding silicon content data; performing abnormal value elimination and normalization processing on original parameter data, dividing a training set and a test set, constructing an initial prediction model of the BP neural network, optimizing training parameters of the BP neural network by using an improved grey goose algorithm, and dynamically adjusting step parameters in the algorithm along with the distance between an individual and a global optimal solution. Fusing a velocity field constructed based on a local curvature factor and a local density factor, updating an individual position in a global search stage, reconstructing a final prediction model according to an optimization result, and performing convergence training by using a training set; and finally inputting the test set into the prediction model, and outputting a blast furnace molten iron silicon content prediction result. The method is suitable for blast furnace molten iron component control and has the advantages of being stable in optimization, small in error and high in real-time performance.

The application discloses a quad-rotor formation obstacle avoidance control method based on an improved DDPG algorithm, and belongs to the technical field of unmanned aerial vehicle formation control. The method adopts an improved DDPG reinforcement learning algorithm to plan an obstacle avoidance path of the quad-rotor. When the improved DDPG reinforcement learning algorithm is executed, the priority weight of each quadruple experience in the experience replay pool is initialized. After the quadruple experience in the experience replay pool is sampled and trained, the priority weight of each quadruple experience is recalculated based on a TD error, and a Sum_Tree structure is updated. The method effectively alleviates the training instability caused by hyperparameter sensitivity, the misleading of policy updating caused by overestimation of Q values, and the problem that key experiences are not sufficiently learned, accelerates the convergence speed of the quad-rotor formation obstacle avoidance training, and improves the obstacle avoidance effect.

This invention discloses a path optimization method based on cooperative aggregation and branch deviation, comprising the following steps: (1) Initialize the population and variables, and divide the population into two subpopulations s1 and s2; (2) Calculate the fitness of individuals in subpopulations s1 and s2 according to the fitness function; sort the fitness of individuals in the two subpopulations from smallest to largest, and select the optimal individual; (3) Keep the i1 and i2 individuals with the highest fitness in subpopulations s1 and s2 respectively, and take the remaining individuals as clustered individuals; (4) Apply the cooperative aggregation strategy to the clustered individuals; (5) Take the top m1% and m2% of s1 and s2 respectively according to fitness to synthesize a new population s3; (6) Update the individuals in s3 randomly using the replacement strategy, and update the global optimal individual; (7) Determine whether the termination condition has been met. If not, increase the population diversity using the crossover operator and mutation operator; (8) Iterate according to steps (2)-(7) until stopping, and output the optimal path.

This invention discloses an improved near-infrared spectral wavelength selection and modeling method for artificial bee colony algorithms, comprising the following steps: data preparation, chaotic initialization, fitness evaluation, establishing a PLS model based on wavelength subsets, using the regularized fitness function of RMSECV as the fitness Fitnessxi of nectar source xi; searching for foraging bees; searching for observation bees; searching for scout bees; outputting the optimal wavelength subset Sbest and establishing the final PLS model. The beneficial effects of this invention are: the method effectively improves convergence speed and accuracy; chaotic initialization improves the quality of the initial population, avoiding the algorithm from prematurely falling into local extrema; the adaptive perturbation factor balances the algorithm's global search and local exploitation, improving the ability to find the optimal wavelength combination in high-dimensional discrete space, and the selected wavelength subset has stronger representativeness, resulting in a final PLS model with lower RMSEP (root mean square error of prediction) and better robustness.

The application discloses a 'rolling-grinding-honing' multi-process parameter collaborative optimization and decision method, which comprises the following steps: 1) according to the characteristics of gear machining process in the automobile high-speed gear machining process, selecting process parameter variables to be optimized, and constructing a 'rolling-grinding-honing' process optimization model; 2) using a multi-objective snake optimization algorithm to iteratively solve the 'rolling-grinding-honing' process optimization model, and obtaining a Pareto collaborative process parameter solution set; 3) based on an entropy weight-TOPSIS decision method, evaluating and sorting the Pareto collaborative process parameter solution set, and obtaining optimal process parameters. The application solves the problem of how to obtain the overall optimal solution in the machining process rather than a single process optimal solution in the new energy automobile high-speed gear machining process.

This invention discloses a lens design method based on deep learning, belonging to the fields of optical design and deep learning. The method includes: constructing a dual-channel neural network; adjusting task indicators in real time according to the current state using a dynamic task generator; inputting the task indicators into the dual-channel neural network for joint training; calculating aberration sensitivity based on Zernike aberration coefficients from real-time ray tracing verification feedback; and outputting a lens design result that meets both optical performance and manufacturing feasibility requirements when the closed-loop iteration formed by dual-channel joint training, real-time ray tracing verification, and dynamic optimization strategy adjustment satisfies a preset convergence condition. This invention uses a dynamic task generator to adjust the optimization path in real time, physically constrains channels to block unmanufacturable structures, and prioritizes suppressing dominant aberrations through aberration sensitivity feedback; it embeds lightweight ray tracing into the training loop, provides real-time feedback of Zernike aberration coefficients, and uses manufacturing feasibility scoring to drive design iteration.

The invention relates to the technical field of motor optimization design, in particular to a motor performance and efficiency optimization method and system based on a bee colony algorithm, and the method comprises the following steps: determining an optimization target and a design variable; an improved bee colony algorithm module is constructed, and the following steps are executed: a nectar source is initialized; calculating the fitness; performing screening; a global optimal nectar source and an individual historical optimal nectar source; the employed bees calculate random disturbance of honey source position updating based on the global optimal honey source and the individual historical optimal honey source; constructing a motor optimization model, and calculating a nectar source optimization target value; and the improved bee colony algorithm module and the motor optimization model are subjected to collaborative iteration solution, and an optimal nectar source design variable combination is output. According to the method, disturbance memory and a global extreme value guiding mechanism are fused in an employed bee stage, so that historical search direction information can be reserved while the search process of a nectar source is accelerated, and the optimization capacity and the stability and convergence efficiency of the search process are improved.

This application belongs to the field of zero-sequence current transformer optimization design technology, specifically disclosing a multi-objective optimization design method and system for zero-sequence current transformers. The method includes: taking the relative error of the secondary output voltage, manufacturing cost, and overall weight as optimization objectives; selecting core parameters, winding parameters, and structural parameters as design variables; establishing constraint conditions and cost / weight calculation models; constructing a multi-objective optimization mathematical model; using a mixed real-number and integer encoding method to encode the design variables to generate an initial population; iteratively optimizing based on a multi-objective optimization algorithm to obtain a Pareto non-dominated optimal solution set; verifying the electromagnetic characteristics and engineering feasibility of the optimal solution set; eliminating invalid solutions to obtain an engineering-feasible Pareto optimal solution set; selecting the final design scheme according to the objective weights of the engineering scenario and outputting all design parameters. This application can achieve coordinated optimization of the accuracy, cost, and weight of zero-sequence current transformers.

The present application relates to the technical field of cascade reservoir flood control scheduling, and discloses a cascade reservoir flood control storage capacity joint operation method based on approximate equal proportion impoundment, comprising the following steps: collecting basic data; carrying out equal proportion impoundment joint flood control scheduling to obtain an initial trajectory; introducing a deviation coefficient to obtain an approximate equal proportion distribution coefficient, constructing an objective function and a constraint condition; taking a step-by-step optimization method as a framework to decompose into two-stage sub-problems, embedding a variable spiral search strategy to optimize, and iteratively outputting a final scheduling trajectory. The cascade reservoir flood control storage capacity joint operation method based on approximate equal proportion impoundment solves the strictness and mechanicalness of the equal proportion impoundment distribution coefficient, improves the flexibility and variability of the cascade reservoir flood control storage capacity joint operation, and overcomes the defects of dimension disaster and insufficient search capability faced by POA when solving the cascade reservoir flood control storage capacity optimization operation problem.

The present application belongs to the technical field of linear cutting blanking processing, and discloses a wire oblique cutting blanking method based on a parallel grouping genetic algorithm, which adopts the parallel grouping genetic algorithm for solving, adopts an elite selection strategy to reserve some best solutions in a population, adopts a grouping coding mode according to the characteristics of the problem, with one coding sequence representing one solution, considers wire cutting matching, proposes a BFD algorithm, converts the coding sequence into a blanking scheme of the wire parts on the raw material and calculates the fitness value of the individual, adopts an Exon crossover mode for adaptive crossover operation, adopts adaptive probability and a novel mutation site selection for adaptive mutation operation, and adopts population drift operation to exchange excellent individuals of each sub-population in the initial number of iterations. The wire oblique cutting blanking method can effectively solve the actual wire oblique cutting blanking optimization problem, can improve the wire blanking efficiency and material utilization rate, and can produce good economic benefits.

This invention discloses an intelligent emergency lane opening system based on traffic flow prediction and its implementation method. The system includes a data acquisition module, a data processing module, a central control module, a power supply module, and a display module. The method includes collecting and processing traffic flow over a period of time to construct a spatiotemporal feature matrix of traffic flow; constructing a CNN-GRU-Attention prediction model; optimizing the parameters of the CNN-GRU-Attention prediction model, including the weight matrix and bias vector, using the improved Big Cane Mouse algorithm IGCRA; obtaining traffic flow prediction results based on the optimized model; and determining whether to open the emergency lane based on the obtained traffic flow prediction results. This invention can accurately predict traffic flow, promptly identify and open emergency lanes before congestion occurs, provide additional passage space for vehicles, avoid excessive traffic concentration, thereby effectively alleviating traffic congestion, reducing vehicle waiting time, and improving overall traffic efficiency.

The invention discloses a flexible workshop scheduling optimization method based on a process perception adaptive genetic algorithm, and relates to the technical field of intelligent production scheduling. According to the method, aiming at a production scene considering a machine and a workpiece, minimization of the maximum completion time is taken as a core optimization target, and a dynamic coding mechanism of process constraint perception and an adaptive genetic manipulation strategy are fused; the problems of coding redundancy, evolution blindness, local convergence and the like of a traditional genetic algorithm in flexible job shop scheduling are solved. According to the method, the workpiece process constraint depth is creatively embedded into the coding design, and the adaptive adjustment mechanism of the adaptive genetic operation of the genetic algorithm is combined, so that the optimization efficiency and the global optimization capability of the scheduling scheme are remarkably improved, the production cycle can be effectively shortened, and the method is suitable for flexible manufacturing scenes with small batches of various varieties and high process complexity.

The application provides a power distribution network fault reconstruction method and system, the method comprising: dividing load nodes into different psychological account types; constructing a power distribution network fault reconstruction objective function based on psychological accounts and constraint conditions corresponding to the psychological account types; constructing a TLBO-SNS optimization algorithm, and recombining imitation, dialogue, argumentation and innovation in social behavior into two selectable parallel exploration branches: branch one is a convergent process of teaching-imitation and mutual learning-dialogue, and branch two is a divergent process of teaching-innovation and mutual learning-argumentation; the power distribution network fault reconstruction objective function is solved as a fitness function of the TLBO-SNS optimization algorithm, a branch is randomly selected from branch one and branch two to execute in each iteration until a stop condition is met to obtain an optimal feasible solution of the power distribution network fault reconstruction objective function; and based on the optimal feasible solution, a corresponding power distribution network fault reconstruction topology structure is output.

The application provides a diesel engine cold test fault detection method and system based on a hybrid Bayesian network, which comprises the following steps: acquiring parameter values in a diesel engine cold test process in real time, wherein the parameter values comprise exhaust valve opening pre-leakage values, exhaust valve closing post-leakage values, minimum intake vacuum values, intake valve opening pre-leakage values, intake valve closing post-leakage values, maximum crankshaft torque values and maximum exhaust pressure values; obtaining a diesel engine fault detection result by using an optimized hybrid Bayesian network model based on the obtained parameter values; wherein the optimized hybrid Bayesian network model takes the exhaust valve opening pre-leakage values, the exhaust valve closing post-leakage values, the minimum intake vacuum values, the intake valve opening pre-leakage values, the intake valve closing post-leakage values, the maximum crankshaft torque values and the maximum exhaust pressure values as nodes of a Bayesian network structure; and the Bayesian network structure is optimized by using a glowworm swarm optimization algorithm based on a preset fitness function to obtain an optimized Bayesian network structure; wherein in the glowworm swarm optimization algorithm, the three glowworms with the highest fitness are used to guide the movement of other glowworms.