35 results about "Differential evolution" patented technology

This invention addresses the challenge of complex scheduling tasks in industrial manufacturing, where multiple tasks exist simultaneously with coupled constraints, leading to high optimization difficulty. It proposes an intelligent multi-task optimization method based on constraint coupling strength indices. This method aims to minimize the number of vehicles used and the total transportation cost. First, a knowledge graph network is constructed to store task information and constraints. Then, a constraint coupling strength index is calculated based on the relationship between constraints and decision variables. Subsequently, during the multi-task differential evolution search, candidate solutions are grouped according to constraint coupling strength, and differentiated cross-tabulation, mutation, and cross-task knowledge transfer strategies are employed to guide the search process towards efficient convergence. This method effectively characterizes complex constraint structures, enhances multi-task collaborative optimization capabilities, and provides an efficient and feasible optimization solution for transportation scheduling in industrial manufacturing.

This invention relates to a method for optimizing process parameters of enameled wire stranding based on particle swarm optimization (PSO). The method includes collecting process parameters to construct a multi-objective prediction model, using a dynamic weight fitness function to adapt to different operating conditions, employing a hybrid PSO-ADE optimization approach, verifying the closed-loop and re-searching based on sensitivity, and outputting the optimal control signal. This PSO-based method for optimizing enameled wire stranding process parameters achieves nonlinear mapping by collecting process parameters to construct a multi-objective prediction model, setting dynamic weights and adaptive penalties to adjust the optimization objective according to operating conditions. It uses particle swarm optimization as the main loop, condition-triggered differential evolution to enhance diversity, balance exploration and development, introduces a verification closed loop, and re-searches based on the deviation direction and sensitivity when the target is not met. It determines variable priority based on sensitivity, granting greater search freedom. This method solves problems such as difficulty in describing multi-variable coupling, incompatibility of fixed weights with disturbances, premature convergence of single algorithms, prediction errors leading to non-compliance, and ambiguity in the direction of secondary optimization.

The application relates to the technical field of geotechnical engineering construction, and discloses a high-altitude rotary drilling bored pile construction parameter dynamic optimization method based on big data, wherein the method comprises the following steps: acquiring multi-source construction data and historical working condition data from a construction big data platform; performing data-driven calibration on activation energy parameters and coalescence rate constants by using a Bayesian parameter estimation method; establishing an axisymmetric two-dimensional finite difference grid and calculating absolute static liquid pressure values of each layered unit; performing bidirectional coupling iterative calculation of a temperature field and a bubble volume distribution in each time step; extracting local comprehensive volume correction factor time series data and melting front surface radial thickness time series data; determining multiple safety constraint conditions; outputting an optimal pouring rate control scheme through a multi-constraint differential evolution optimization solver; and monitoring in real time and triggering online recalculation and scheme correction during pouring execution.

An improved differential evolutionary sparse distribution optimization method based on virtual interference patterns is proposed. This invention relates to sparse distribution optimization methods for spaceborne antennas. The purpose of this invention is to solve the problem that the limited number of uniform phased array elements due to the limited load of spaceborne antennas restricts the antenna performance. The process is as follows: 1. Create an initial population, with each population having N... p An individual represents one of the M radii corresponding to the antenna array ring; the population represents the N radii corresponding to the antenna array ring. p ×M radii; N p For all individuals in a population; 2. Calculate the fitness value of each individual; Fitness value F(d1,d2,...,d...) N The value is defined as the average of the main lobe and side lobe gain ratios on the plane and the θ = 0° plane; III. Repeat step II to obtain N. p The population is analyzed by first determining the fitness value of each individual, then retaining the individual with the optimal fitness value; fourth, a differential operation is performed on the population to obtain the optimal individual, which is the optimal antenna array. This invention is applicable to the field of aerospace technology.

This invention discloses an adaptive differential evolution cooperative position estimation method for meteor radar phase calibration, comprising: acquiring meteor trail angle of arrival (AHA) data and meteor trail distance data; constructing a composite objective function based on the meteor trail AHA and distance data; using the composite objective function, employing adaptive differential evolution to search for multi-channel phase deviations, and iteratively performing virtual half-wavelength baseline inversion of meteor trail positions until the composite objective function converges to a global minimum, ultimately obtaining high-precision multi-channel phase calibration results. This method requires no external reference signal, is stable and usable in all weather conditions, continuously and automatically updates calibration parameters, is simple to implement and low in cost, and has higher receiving channel phase calibration accuracy than existing internal calibration methods.

This invention discloses a UAV 3D trajectory planning method based on expensive multi-objective optimization, comprising: initializing parameters and constructing a static physical neighborhood; establishing a multi-objective function of flight energy consumption and threat probability and initializing the trajectory population; determining whether the number of actual evaluations has reached a soft-start threshold, and if not, using the static physical neighborhood; otherwise, entering the evolutionary stage; selecting the dominant subproblem and constructing a dynamic cooperative neighborhood using a confidence upper bound strategy; training a proxy model and generating candidate trajectories through differential evolution; evaluating the actual fitness of the candidate trajectories and updating the population; updating the dynamic cooperative proxy model based on the local fitness improvement gains; repeating the evaluation until the maximum number of times, and outputting the 3D trajectory solution set. This invention can quickly generate globally optimal 3D trajectories that balance low energy consumption and high safety with a very small number of actual evaluations, significantly improving the efficiency and survival probability of UAVs in complex airspace missions.

This invention discloses a wind power generation prediction method based on a variable-priority adaptive grey model. The method involves collecting annual wind power generation data for a target area and establishing an original sequence; introducing weight parameters and an adaptive variable weight function to construct a variable-priority accumulation operator; calculating a variable-priority accumulation sequence using the original sequence and the variable-priority accumulation operator; introducing the variable-priority accumulation sequence and a double nonlinear term to improve the grey discrete model, thus constructing a variable-priority adaptive grey discrete model; optimizing the nonlinear parameters of the model using a hybrid algorithm of social spider and differential evolution to obtain optimal nonlinear parameter values; and then solving the parameters of the model's time response equation using the least squares method to obtain the optimal model; finally, using the optimal model to predict future wind power generation. The introduction of a variable-priority accumulation operator adaptively adjusts the data priority to reduce the impact of uncertainty in new wind power data, thereby improving the prediction accuracy of wind power generation.

The application discloses a kind of attention mechanism LSTM fan blade fault diagnosis method, device, electronic equipment and medium based on differential evolution optimization.The method can include: collecting SCADA data, determining feature dataset;LSTM neural network is trained by feature dataset, and output state is obtained;Output state is input to attention mechanism model, and output result is obtained;Output result is obtained by output module to obtain prediction result, and prediction result is compared with fan actual state, and output error is calculated;According to output error, differential evolution calculation is carried out, and the parameters of LSTM neural network and attention mechanism network model are updated;Fan data to be tested is input into the model after training, and the diagnosis result of fan blade fault is obtained.The application has higher comprehensive performance and generalization ability, and has the advantages of improving the accuracy and speed of fan blade fault diagnosis.

Embodiments of the present application provide a data optimization method, device and equipment and a storage medium. The method comprises: obtaining an initial population data set, the initial population data set comprising at least one individual data, the individual data comprising at least one design parameter; performing reverse learning processing on the initial population data set to obtain a first population data set; performing differential evolution processing and crossover processing on the first population data set to obtain a second population data set; performing non-dominated sorting processing and clustering processing on the second population data set to obtain a target population data set, the target population data set being used for multi-objective optimization. Through multi-working-condition constraint processing and multi-modal solution set maintenance, the output target population data set can meet the design requirements under different working conditions, provide diversified candidate schemes for engineers, shorten the design cycle and improve the comprehensive performance of the suspension system.

This invention relates to the fields of computer vision and artificial intelligence, and discloses a sign language recognition method based on multi-level state feature optimization. The method includes acquiring a sign language video sequence and extracting original visual features; constructing a semantic potential energy field, calculating the potential energy value of the current frame features and their gradient vector relative to the feature space; constructing a local orthogonal basis based on the gradient vector, and orthogonally decoupling the features into normal transition components along the gradient direction and tangential steady-state components along the equipotential surface direction; performing differential evolution processing on the normal transition components based on multi-level dynamic states, using graph networks to repair transition features, and smoothing the tangential steady-state components; finally, reconstructing features and temporally decoding the processed components to obtain the sign language text. This invention utilizes the geometric properties of the potential energy field to achieve physical-level decoupling between core semantics and transitional actions, effectively solving the feature drift problem caused by action switching in continuous sign language, and significantly improving recognition accuracy.

The application discloses a two-stage multi-form differential evolution method for mine integrated energy system scheduling, and belongs to the technical field of intelligent scheduling. First, under the multi-form optimization framework, two alternative tasks of electricity-heat and electricity-cold are constructed in combination with field knowledge, and a feasibility-driven knowledge transfer mechanism is introduced to realize efficient transfer of knowledge between the two tasks. Then, a two-stage optimization strategy is designed, and a neighborhood double mutation mechanism is proposed. In the first stage, the diversity-driven neighborhood double mutation strategy is used for parallel evolution of the populations corresponding to the two alternative tasks. In the second stage, the convergence-driven neighborhood double mutation strategy is used for evolution of the original task, and an optimal feasible solution set is obtained. Finally, the time complexity is analyzed to illustrate the rationality of the method for optimizing mine integrated energy system scheduling. The application can overcome the limitations of existing optimization methods in dealing with strong coupling constraints and multiple uncertainties, and improve the economy, energy utilization rate and scheduling stability of the system.

This application discloses a multi-objective optimization method, apparatus, equipment, and storage medium for logistics vehicle scheduling, relating to the field of tobacco technology. The method obtains a multi-source initial logistics dataset through multi-source data acquisition, providing a complete data foundation for subsequent optimization; it preprocesses the multi-source initial logistics dataset to obtain a standardized logistics dataset; it constructs a multi-objective optimization model and uses a weighted Chebyshev decomposition method to obtain a set of decomposed subproblems; it uses the MOEA / D framework combined with differential evolution operators to collaboratively solve for a multi-objective optimization solution set; it obtains timeliness preference, cost preference, and capacity preference, sets weight vectors, and selects the optimal vehicle allocation instruction set from the multi-objective optimization solution set; it pushes the optimal vehicle allocation instruction set to logistics vehicles and obtains execution feedback data to learn and iterate the weight parameters of the multi-objective optimization model online, obtaining an iteratively optimized multi-objective optimization model and achieving continuous optimization of algorithm parameters.

The application discloses a water quality clustering method based on an improved snow melting algorithm, utilizes the improved snow melting optimization algorithm to cluster water quality, finds the optimal division of clustering by using a heuristic algorithm according to a clustering evaluation index, and analyzes and mines multiple groups of related water quality physicochemical indexes covered by water quality data by introducing Latin hypercube sampling to initialize a population, a positive greedy strategy, a self-adaptive differential evolution strategy based on population division and a reverse learning strategy based on average centroid to improve the ability of the method in the clustering problem. The method can not only improve the division precision of water quality, well divide drinkable water and non-drinkable water with different characteristics, realize unsupervised learning of water quality, and has good interpretability.

The application relates to an asymmetric fault evolution model establishment and diagnosis method of a ceramic rolling bearing, which comprises the following steps: S1. signal acquisition; S2. data preprocessing; S3. defect geometry modeling; S4. dynamic response simulation; S5. feature extraction; S6. feature matching and fault stage identification; and S7. fault early warning output. The application also provides an asymmetric fault evolution model establishment and diagnosis system of a ceramic rolling bearing. The application introduces asymmetric geometry representation and establishes a differential evolution model on both sides of a defect, so that the model can depict the profile difference between the entering side and the leaving side of the defect and the evolution law of the profile difference under different working conditions, thereby improving the representation capability of the real defect morphology of the ceramic bearing. The application provides a modeling and diagnosis method and system which can describe the asymmetric defect evolution law and is coupled with the vibration response characteristics, and the precision of the fault prediction and diagnosis of the ceramic bearing is improved.

This invention relates to the field of power transmission line technology, providing a method and system for power transmission line parameter identification based on differential evolution and bi-layer optimization. The method includes constructing a lumped-parameter power transmission line model with a π-type equivalent circuit based on the transmission line topology; outer-layer optimization searches for optimal line parameter values ​​within a given range and outputs them to the inner layer; inner-layer optimization solves for the corresponding optimal error compensation amount under the given line parameter conditions from outer-layer optimization. This method can suppress the interference of measurement errors on weak signals, reduce the systematic bias of the line parameter identification results, and improve the stability and engineering applicability of the identification results.

The application relates to the technical field of flotation process, and discloses a flotation pH adjustment process model prediction parameter identification method improved based on differential evolution and a partial least square method. The method is aimed at the key link of lead-zinc metal flotation, namely, dosing regulation, and pH of ore pulp is controlled through accurate process model analysis and parameter identification to realize efficient separation and extraction of lead-zinc metal. The process model is a mathematical tool for describing the dynamic behavior of the pH dosing regulation of the ore pulp, and the interaction and influence of internal and external variables in the dosing process are deeply analyzed. The model fuses a mechanism model and a data-driven model, simultaneously adopts an adaptive optimization mechanism, realizes closed-loop control, and thus can systematically understand and predict the dynamic trend of the pH value of the ore pulp with the change of the type, dosage and time of the dosing agent, and further realize accurate regulation of the dosing process, and ensure the efficiency and stability of the flotation process.

The application discloses a kind of heterogeneous compact reservoir difference evolution model construction methods, belong to oil and gas geological exploration technical field, this method includes five core steps: first, core, experiment, well logging and seismic multi-source data are standardized and preprocessed;Then quantitative analysis reservoir porosity, permeability temporal and spatial variation and pore throat characteristics;Then dynamic source rock diagenesis process and quantize its intensity;Further, key factors such as sedimentary microfacies, diagenetic transformation intensity, tectonic activity frequency and burial depth are coupled, and the correlation function between them and reservoir densification degree is established;Finally, a visual model is constructed and optimized by validation data and regional geological background factors.The application solves the problems of multi-source data integration, evolution law quantization and poor model applicability, realizes the integrated dynamic characterization from micro-pore throat to macro-reservoir, significantly improves the prediction accuracy of high-quality reservoir, and provides reliable technical support for compact oil and gas reservoir exploration and development.

This invention discloses an adaptive anomaly removal method and system for flow calibration. The method includes: performing adaptive water level segmentation processing on a cleaned historical water level and flow dataset to obtain several segmented historical water level and flow datasets and constructing several corresponding local calibration models; optimizing the parameters of the several local calibration models according to an improved differential evolution method to obtain their respective optimized local calibration models; inputting each segmented historical water level and flow dataset into its corresponding optimized local calibration model for processing to obtain the calibrated flow sequence for each segment; performing multi-criteria statistical testing on each segmented deviation sequence; if the test is successful, the calibrated flow sequence for each segment is taken as the successfully calibrated flow sequence for that segment; if the test fails, adaptive removal processing is performed until the test is successful. This invention enables automated and high-precision calibration of flow data output by automatic flow meters.

The application discloses a kind of multi-path optical fiber fault identification positioning method and system.The method is aimed at the high dimension of optical fiber signal feature space, strong nonlinearity, large noise interference and the problem that random forest model hyperparameter optimization is easy to fall into local optimum and search space coverage is insufficient, introduce chaotic white shark optimization algorithm to carry out global adaptive optimization to random forest parameter.Optimization process utilizes chaotic mapping to generate uniformly distributed chaotic sequence, drives population initialization, global search and local fine tuning, and combines elite reservation, chaotic disturbance, differential evolution and simulated annealing mechanism, improve the efficiency and accuracy of parameter optimization.Based on the optimized random forest model, the robustness and generalization ability of the model are effectively improved for realizing the rapid identification and positioning of optical fiber faults.The method provides an efficient and reliable technical approach for optical fiber fault intelligent diagnosis, and has high engineering application value.

A kind of iron concentration prediction method based on water supply pipeline wall layered structure and automatic calibration, comprising: integrated pipeline hydraulic model, iron concentration release model and microscopic electron microscope layered observation result, construct pipe network iron concentration layered multi-species reaction model, simulate the migration and transformation of iron ions between corrosion base layer, loose porous layer, hard shell layer and surface layer;Multi-objective comprehensive error function is constructed, and the difference between simulation result and observation data is evaluated;Three-stage differential evolution calibration is executed: the model is used as water quality simulation engine, the comprehensive error function is used as optimization target, and the model parameters are optimized by iteration method;First stage global search locates advantage area, second stage local optimization, third stage fine tuning, and after each stage ends, the subsequent parameter search boundary is dynamically contracted based on optimal solution and boundary tightening coefficient;Iron concentration spatiotemporal distribution prediction is output.The method of the application realizes high-precision prediction of complex pipe network iron concentration and efficient automatic calibration of model parameters.

The application relates to an energy-driven crowd optimization method and device, electronic equipment and a readable storage medium, which comprises the following steps: generating an initial population corresponding to a robot obstacle avoidance path, initializing each individual in the initial population; determining the individual fitness of each individual, determining an elite set and an exploration set, and determining the dynamic role parameters of each individual; determining the first target orientation of the individual in the elite set and the second target orientation of the individual in the exploration set, thereby adjusting the development direction and the exploration direction corresponding to the elite set and the exploration set; selecting a differential evolution strategy or an energy-driven behavior strategy to update the individual position with a preset probability, obtaining an updated individual position; updating the energy value corresponding to the individual based on the updated individual position, determining an optimal population corresponding to a global optimal solution, and obtaining a robot obstacle avoidance path. Through the method provided by the application, the global exploration and local development capabilities are enhanced, and the adaptability and search efficiency in a dynamic environment are improved.

The application discloses a kind of redundancy mobile manipulator heuristic linkage trajectory planning method.For the linkage control problem of the mobile platform and manipulator of redundancy mobile manipulator, platform path and joint trajectory are encoded into upper and lower layer population respectively, and multidimensional conflict target is decomposed into several subproblems;Through the collaborative evolution mechanism under the neighborhood constraint of subproblem, it is forced to match combination under the same preference of upper and lower layer, to ensure that search direction is consistent;Fusion differential evolution parameter self-adaptation and problem-specific local search, periodically optimize solution set;And according to the population state dynamic adjustment neighborhood scale and local search intensity.The application can efficiently generate uniform distribution optimal trajectory solution set, improve the quality of trajectory planning of redundancy mobile manipulator.

The application discloses a method and device for characterizing the viscoelasticity of an egg cell based on a nonlinear Maxwell model, a medium and a product, and relates to the field of the viscoelasticity of an egg cell. The method acquires a force-time curve sample set of a shellfish egg cell; a Maxwell model with a nonlinear index parameter is constructed; according to the force-time curve sample set, a differential evolution global optimization algorithm is used to optimize a unified parameter in the Maxwell model, with the maximum minimum determination coefficient in all samples as an optimization target, so that the optimized unified parameter is obtained; the Maxwell model with the optimized unified parameter is fitted and verified, so that it is determined that all samples reach a fitting standard, and a verified Maxwell model is obtained; and the verified Maxwell model is used to describe the nonlinear viscoelastic behavior of the shellfish egg cell. The application can accurately and universally describe the viscoelastic mechanical behavior of the shellfish egg cell.

The application provides a method for dynamic three-dimensional modeling of earthmoving equipment operation scene based on multi-source data fusion, comprising the following steps: deploying a heterogeneous sensing network for air-ground cooperation, dynamically obtaining engineering physical basement data corresponding to soil compaction degree and organic matter content by using microwave radar and hyperspectral sensor; constructing a unified space-time reference; outputting three-dimensional point cloud with shape and depth coupling; giving time sequence dynamic weight constrained by equipment operation cutting and medium partial differential evolution; reconstructing a predictive three-dimensional model according to physical properties, and constructing a dynamic three-dimensional model directly predicting materials. The soil compaction degree measured by the microwave and the organic matter content measured by the hyperspectral are used as physical constraint factors and directly placed into the three-dimensional partial differential reconstruction equation, so that the 3D model can automatically calculate the real mechanical form of gravity pulling, shearing, sliding and local collapse according to the hardness and softness of the soil, and the deviation between dynamic simulation and actual working condition is avoided.