94 results about "Dung beetle" patented technology

The invention discloses a plant greenhouse intelligent monitoring and environment optimization management system and method. The method comprises the steps that a detection module obtains environment data, resource data and equipment feedback data of a vegetable greenhouse in real time; the acquisition module acquires vegetable types, growth days and growth parameters; the health prediction module calculates the current growth index according to the growth parameters and predicts the index of the next growth stage; the establishing module calculates a difference value between the predicted growth index and the standard growth index through a target function; the parameter optimization module adopts an improved dung beetle optimization algorithm, adjusts an optimization process according to equipment feedback and outputs optimal cultivation parameters; the condition generation module generates a resource scarcity state according to the resource data and provides adjustment limitation; the processing module adjusts a theoretical range based on the optimal parameter and the resource constraint; and the in-greenhouse adjustment module dynamically adjusts the greenhouse environment according to the optimization result. Through integration of sensor data and an optimization algorithm, dynamic adjustment of the resource ratio in the vegetable greenhouse is realized, and the vegetable growth efficiency is improved.

The invention relates to the technical field of underwater robots, in particular to an underwater robot cluster path planning method and system based on a dung beetle algorithm, and the method comprises the steps: obtaining a coordinate division region to construct an environment model, calculating and extracting an obstacle distance to fuse ocean current interference to generate a dynamic obstacle avoidance strategy, and evaluating the path speed similarity to generate a candidate path. And acquiring an offset angle difference, normalizing environmental factors to generate a correction path, and calculating a curvature fusion collision probability to generate a global path control instruction. According to the method, a dynamic model is constructed based on Cartesian coordinate division, the spatial analysis precision is improved, a sonar distance and ocean current interference are fused to generate a dynamic obstacle avoidance strategy, the trajectory smoothness is enhanced, candidate paths are screened by using vector similarity and Monte Carlo simulation, the collaboration is optimized, disturbance is reduced through coordinate offset and ocean current correction, and the accuracy of the dynamic obstacle avoidance strategy is improved. The curvature and collision probability are combined to balance safe energy consumption, and multi-dimensional parameter fusion improves cluster adaptability, precision, efficiency and energy utilization rate.

The invention relates to the technical field of mine gas disaster prediction, in particular to a gas concentration time sequence prediction method based on MSADBO-CNN-GRU-Attention. Firstly, dynamic Pearson correlation analysis is used, weighting is conducted on all indexes based on a time window of one hour, key factors leading gas concentration in different time periods are revealed, and therefore interference of irrelevant factors is weakened, and meanwhile the signal strength of the key factors is enhanced. Thirdly, performing local feature extraction on the data by applying a convolutional neural network (CNN), capturing multi-scale information, learning a time sequence data long-term dependency relationship and transmitting state information between time steps in combination with a gating cycle unit (GRU); an Attention mechanism is added to weight the hidden state output by the GRU so as to highlight the importance of key time nodes and improve the accuracy of multi-step prediction. And then, an improved sine algorithm, adaptive Gaussian-Cauchy mixed variation disturbance and a Bernoulli chaotic mapping improved dung beetle search algorithm are fused to obtain MSADBO, and then model hyper-parameters are globally and adaptively optimized. And finally, training the model, establishing a prediction model based on MSADBO-CNN-GRU-Attention, and verifying the performance of the prediction model by comparing the model. According to the gas concentration multi-index multi-step time sequence prediction method provided by the invention, parameter adaptability, feature mining and depth time sequence modeling are combined, the prediction performance of the gas concentration is improved, and a solution is provided for high-precision multi-step time sequence prediction of the gas concentration under complex working conditions.

The invention relates to the technical field of path planning, and provides a multi-strategy collaborative enhancement path planning method and navigation equipment. The path planning method comprises the following steps: acquiring an environment map comprising a starting position and a target position; initializing DBO algorithm parameters; initializing a dung beetle population based on Bernoulli chaotic mapping; calculating the fitness value of each dung beetle; determining the boundary of each dung beetle, and continuously iteratively updating the individual optimal fitness value and the global optimal fitness value of each dung beetle; and outputting the optimal path of the unmanned aerial vehicle until the number t of iterations is greater than the preset number T. According to the method, the initial solution is generated by introducing the chaos mapping based on Bernoulli distribution, so that the diversity and the ergodicity of the initial population are enhanced, premature convergence is effectively avoided, and the global search capability of the algorithm is improved.

A DBO-STN-Informer-based aquaculture water dissolved oxygen prediction method comprises the following steps: S1, adopting a dissolved oxygen sensor to collect dissolved oxygen data in aquaculture water online in real time, and dividing the data into a training set and a verification set according to a time sequence after preprocessing; s2, introducing a spatial transformation network STN on the basis of an Informer encoding mode to transform an input time sequence, constructing an STN-Informer prediction model, and performing spatial transformation and feature calibration on input time sequence data through the STN to help an encoder to understand a deep dissolved oxygen sequence; an attention mechanism parameter in the STN-Informer prediction model is optimized by adopting a dung beetle algorithm DBO; and finally, performing test scoring and optimization on the model by using the verification set. And S3, based on the trained and optimized model, outputting a dissolved oxygen concentration prediction value in a future time period. According to the method, the dissolved oxygen concentration in the future time period can be predicted according to the prior data, and the method has very high prediction accuracy, precision and efficiency.

The invention provides a photovoltaic output interval prediction method based on CEEMDAN-DBO-BiLSTM, and the method comprises the following steps: S1, decomposing a photovoltaic power sequence into a plurality of mode components through an adaptive noise complete set empirical mode decomposition method according to the nonlinear and non-stationary characteristics of distributed photovoltaic historical data; s2, carrying out secondary decomposition on the high-frequency non-stationary component obtained by primary decomposition, and reconstructing all components into a trend component and an oscillation component by adopting a sample entropy method; s3, optimizing parameters of the bidirectional long-short-term memory network based on a dung beetle optimization algorithm, and finally obtaining distributed photovoltaic point predicted values of the two components; and S4, probability density estimation is performed on the point prediction error of the oscillation component based on a kernel density estimation method, and the point prediction values are superposed to obtain an overall prediction interval result, so that the complexity of the original prediction component is significantly reduced, and the prediction precision of the model is further improved.

The invention relates to a micro-texture cutter alloy milling force multi-mechanism fusion prediction method under a heat-assisted condition, and belongs to the technical field of titanium alloy mechanical manufacturing. Comprising the following steps: S1, a milling vibration signal noise reduction method: optimizing a wavelet packet threshold noise reduction method of variational mode decomposition based on a dung beetle algorithm; and S2, real-time monitoring and prediction of the milling force: a regression analysis model based on Bayesian optimization, a convolutional neural network, a bidirectional long-short-term memory network and a multi-head attention mechanism. The DBO-VMD-WPT noise reduction method adopted by the invention has the advantages of high-precision noise reduction, high adaptability, wide applicability and the like, and is particularly suitable for processing non-stationary signals in a complex noise environment.

The invention discloses a combined model pollutant concentration prediction method and system based on multiple strategies, a storage medium and electronic equipment. The method comprises the following steps: firstly, performing multi-pollutant signal decomposition and feature fusion; then realizing data set division and standardization processing; time sequence window division and data tensor conversion are carried out; then training and preliminarily predicting an LSSVM (Least Square Support Vector Machine) model based on DBO optimization; and finally, carrying out residual error compensation and model performance improvement of an error correction module. According to the method, the hybrid kernel function least square support vector machine and the computational fluid mechanics correction model are innovatively combined, and the improved dung beetle algorithm is utilized to perform multi-objective optimization on the kernel parameters and the error compensation coefficient; and multi-modal feature mapping is realized through a dynamic weight distribution layer, and a photocatalytic reaction kinetic equation is introduced to implement prediction value inversion. The method successfully overcomes the technical bottlenecks that a traditional model lags in response to sudden emission and is insufficient in multi-pollution coupling effect modeling, and provides accurate decision support for air pollution prevention and control.

The invention relates to the technical field of equipment fault prediction, and discloses a low-voltage electrical equipment fault prediction system based on artificial intelligence, and the system comprises a data collection and preprocessing module, a feature engineering module, a prediction module, and an optimization hyper-parameter module. The system extracts time sequence features, frequency domain features and fault mode features by collecting electrical sensor and monitoring data, and based on an enhanced TCN-Learar-BiLSTM model, realizes accurate prediction of equipment health status and fault risk by combining alternate expansion convolution, trend and seasonal decomposition and linear modeling technologies; meanwhile, through joint optimization of an improved faecium beetle algorithm and an immune algorithm, hyper-parameter configuration of the model is dynamically adjusted, and prediction accuracy and stability are remarkably improved; the system is suitable for the field of electrical equipment operation and maintenance and intelligent power management, and can effectively improve the equipment fault early warning capability and the operation reliability.

The invention belongs to the technical field of coal mining settlement prediction, and particularly relates to a coal mining settlement prediction model parameter inversion method based on an improved dung beetle optimization algorithm, and the method comprises the steps: obtaining coal mine geological mining parameters and the actual measurement data of an earth surface observation point; logistic chaotic mapping is adopted to initialize a dung beetle population, and the dung beetle population is divided into four classes of roll dung beetles, breeding dung beetles, small dung beetles and theft dung beetles; the method comprises the following steps: improving position updating of roll dung beetles through a global exploration strategy fused with an eagle algorithm, updating a breeding dung beetle spawning area by adopting a dynamic boundary strategy, introducing an adaptive t distribution disturbance strategy to optimize foraging behaviors of small dung beetles, and randomly disturbing and updating positions of stolen dung beetles near an optimal solution; and finally, constructing a fitness function according to the sum of squares of errors of the measured value and the predicted value, and carrying out iterative optimization until an optimal parameter solution is obtained. According to the method, the convergence speed and the global search capability of the algorithm are remarkably improved, and the problems that a traditional method is prone to falling into local optimum, poor in anti-interference capability and the like are effectively solved.

The invention discloses a threat entity recognition and intelligence processing method based on BERT assistance, and the method comprises the following steps: S1, collecting and preprocessing threat intelligence text data, and constructing an input corpus data set; s2, inputting to a BERT encoder, extracting context semantic vectors, and obtaining a semantic feature vector sequence; s3, inputting the semantic feature vector sequence into a gating recursion unit, modeling time sequence features, and outputting a hidden state sequence; s4, based on the hidden state sequence, performing threat entity label labeling through a decoding layer; s5, adopting a dung beetle optimization algorithm to optimize BERT and gating recursive unit parameters; and S6, performing reasoning prediction by using the optimal parameter, and outputting and storing structured threat entity information. According to the method, the BERT encoder, the gating recursion unit and the improved dung beetle optimization algorithm are fused, so that high-precision recognition and structured extraction of the threat entities in the threat intelligence text are realized.

The invention discloses a multi-unmanned aerial vehicle flight path planning method based on a multi-mode cooperative dung beetle optimizer. The method comprises the steps that 1, a dung beetle optimization algorithm is initialized; 2, updating the position of the dung beetle; 3, mapping position elements exceeding the upper and lower bounds back to the effective search area to obtain a dung beetle position updating result and calculating a population fitness value; 4, updating the position of the dung beetle and calculating a population fitness value; 5, updating the position of the small dung beetle and calculating a population fitness value; step 6, updating the position of dung beetle theft and calculating a population fitness value; 7, comparing population fitness values, and recording a maximum value, a minimum value and corresponding position results; and step 8, iterating to obtain a final position result. Compared with DBO, QHDBO and route planning, the total cost of the method is respectively reduced by 80.78% and 63.8% in a simple scene, and is respectively reduced by 83.96% and 68.89% in a complex scene, and high efficiency and practicability of the method are proved.

The invention discloses a strip mine slope stress prediction method and system based on VMD-DBO optimized GRU, and relates to the technical field of mine engineering safety monitoring. According to the method, VMD (variational mode decomposition), a dung beetle optimization algorithm (DBO) and an improved gating cycle unit (GRU-A) are combined, and decomposition and noise reduction are performed on stress data through the VMD so as to extract key features; dBO is utilized to optimize and improve hyper-parameters of a gating cycle unit GRU-A, and the learning ability of the model is enhanced; and in combination with a self-attention mechanism, key features of the stress time sequence are dynamically captured. According to the strip mine slope stress prediction method and system based on VMD-DBO optimization GRU, the prediction result is more accurate compared with a traditional method, and an efficient and reliable solution is provided for surface mine slope stress prediction and landslide disaster early warning.

The present invention discloses a method for optimizing spray quenching process parameters, comprising the following steps: Step 1: Establishing a three-dimensional spray quenching finite element model; Step 2: Embedding an improved quenching factor method into the finite element model; Step 3: Processing the simulation results; Step 4: Establishing a multi-objective optimization model; Step 5: Establishing a single-objective optimization model; Step 6: Solving the multi-objective and single-objective optimization models using a non-dominated genetic algorithm and a dung beetle algorithm, respectively. This method for optimizing spray quenching process parameters is an efficient research method based on existing experimental data, providing methodological and theoretical support for the selection of quenching process parameters.

The invention belongs to the technical field of thunder and lightning signal noise reduction, and particularly relates to a noise reduction method and noise reduction system for very low frequency thunder and lightning signals and a storage medium. The noise reduction method comprises the steps of obtaining a plurality of position points of a current mixed lightning signal in a dung beetle algorithm after the mixed lightning signal is obtained; after a position point corresponding to the minimum envelope entropy in the current mixed lightning signal is calculated based on a VMD algorithm, the abscissa and the ordinate of the position point corresponding to the minimum envelope entropy are respectively recorded as an optimal decomposition mode number and an optimal penalty factor; decomposing the current mixed lightning signal into a linear superposition form of a plurality of decomposed signals by using a VMD algorithm based on the optimal decomposition mode number and the optimal penalty factor; after the decomposition signals representing the noise are removed, linear superposition of the remaining decomposition signals is reconstructed, and the very-low-frequency thunder and lightning signals are obtained. According to the method, the noise signal deeply coupled with the very low frequency lightning signal can be efficiently and accurately removed, and the real very low frequency lightning signal is restored.

The invention belongs to the technical field of robot motion control, and discloses a hybrid multi-strategy dung beetle optimization algorithm-based aircraft control parameter setting method, which is characterized in that a hybrid multi-strategy dung beetle optimization algorithm is designed based on a traditional dung beetle optimization algorithm, and an optimization algorithm of population initialization and population position updating is provided. A population position in an initialization stage is uniformly generated by introducing a good point set theory so as to improve diversity of an initialized population, and meanwhile, gravity center reverse learning is added to search global and dimension-by-dimension Gaussian variation after the position is updated so as to improve the global search capability and the convergence speed of the algorithm. The method is suitable for parameter setting optimization of the ADRC controller, the diversity of position updating modes of the water-air amphibious vehicle can be improved, the global search capability and convergence speed of the algorithm can be improved while the algorithm is prevented from falling into a local optimal solution, and therefore the position and attitude control performance of the water-air amphibious vehicle is further improved.

The invention relates to the technical field of wireless sensor networks, in particular to a heterogeneous wireless sensor network coverage method for a mountain new energy construction site, which comprises the following steps of: constructing a three-dimensional mountain monitoring area, inputting related parameters and establishing a multi-target optimization model taking the non-coverage rate, the reciprocal of the connectivity rate and the minimum total energy consumption as targets; initializing a dung beetle population, dividing the dung beetle population into four classes, obtaining an initial coverage scheme, and screening a non-dominated coverage scheme solution set for storage; iteratively updating the positions of various types of dung beetles based on a multi-target dung beetle optimization algorithm; the current coverage scheme and the archive set are combined, the archive set is updated after non-dominated sorting, and dense solutions are discarded to guarantee diversity when the scale is over-scale; and outputting a solution set after the maximum number of iterations is reached, and selecting a target scheme to complete node deployment. The method is adaptive to complex mountain scenes, network coverage and communication quality are improved, energy consumption is reduced, local optimum is avoided, and mountain monitoring effects of high coverage, low energy consumption and strong adaptation are achieved.

This invention relates to a 3D UAV path planning method based on an improved gray wolf optimization algorithm, comprising: acquiring a 3D environment model; setting the start and end positions of the UAV based on the 3D environment model; employing the improved gray wolf optimization algorithm, using the objective function as the fitness function; updating the positions of all gray wolves synchronously during the iterative process; and outputting the optimal path. This invention introduces a circle chaotic mapping to the gray wolf optimization algorithm to increase population diversity; introduces an adaptive exploration factor to increase the balance between global and local search; combines the global and local development formulas of the dung beetle optimization algorithm to compensate for the slow convergence speed of the traditional gray wolf optimization algorithm; subsequently introduces a sine and cosine strategy to help the algorithm search for potential optimal solution regions, thus better exploring the global optimal solution; and finally introduces a pooling mechanism to randomly recombine stored historical poor solutions to generate new solutions, accelerating the convergence speed and improving the robustness of the algorithm.

The application provides a signal denoising method based on a dung beetle optimizer (DBO) optimized wavelet threshold, and belongs to the technical field of signal processing. The method comprises the following steps: firstly, performing CEEMDAN decomposition on a signal to obtain a plurality of IMF components; adopting a dung beetle optimizer (DBO) to select an optimal threshold for a wavelet threshold denoising method; for an IMF component with a relatively small correlation coefficient in CEEMDAN decomposition, adopting the threshold selected by the dung beetle optimizer to perform wavelet threshold denoising; and reconstructing signals of the denoised IMF component and other IMF components to obtain a denoised signal. The application has applicability, can effectively solve the problems of threshold selection difficulty and signal noise removal, retains useful information in the signal, and improves the effectiveness of the signal.

The invention discloses a gas insulation cabinet partial discharge monitoring method and device based on edge calculation, and relates to the technical field of gas insulation cabinets. The method comprises the following steps: collecting environmental data and background electromagnetic noise signals of the gas insulation cabinet, calculating an environmental noise correlation coefficient by using a maximum information coefficient method, combining an environmental deviation value to obtain a comprehensive environmental disturbance index, and correcting a preset background noise threshold value to obtain a corrected noise threshold value; if the real-time electric signal amplitude exceeds the corrected noise threshold, marking the data as partial discharge signal data; denoising the partial discharge signal data by adopting an improved ensemble empirical mode decomposition adaptive noise method, and extracting a discharge feature vector; calculating the mahalanobis distance of each feature vector in the discharge feature vector sequence, obtaining the discharge similarity, obtaining a homologous discharge link, extracting the feature data of the homologous link, inputting the feature data into a BP neural network model based on a dung beetle optimization algorithm, outputting the type of partial discharge, and carrying out the early warning, thereby achieving the monitoring of the partial discharge of the gas insulation cabinet.

The invention discloses a teenager long-distance running strategy method fusing deep learning and an improved swarm intelligence optimization algorithm, and the method comprises the following steps: collecting multi-dimensional time sequence features in the historical training and competition process of athletes, and constructing and training a CNN-LSTM-Attention prediction model based on the multi-dimensional time sequence features; establishing an integral form long-distance running strategy optimization model framework with the goal of minimizing the game completion time; dividing the long-distance running process into a plurality of continuous time sequence windows, calling a CNN-LSTM-Attention model at the starting moment of each window to generate a state prediction result as a dynamic constraint, and constructing a state transition equation; and based on the state transition equation, solving the optimal speed under the current time sequence window through an improved dung beetle optimization algorithm, rolling to the next window after execution, and carrying out iterative execution until the optimal speeds under all time sequence windows are output.

The invention relates to the technical field of building environment and energy utilization, in particular to an air conditioning system cooling load prediction method and related equipment, and the method comprises the steps: firstly obtaining related data of an air conditioning system, inputting the data into a pre-trained improved LSTM load prediction model, and obtaining a cooling load prediction result; the construction process of the improved model comprises the steps that historical air conditioner system related data is obtained, and a data set is formed through screening by means of a random forest algorithm; constructing an LSTM load prediction model, and updating hyper-parameters in the model based on a dung beetle optimization algorithm; performing iterative training on the LSTM load prediction model by using historical cold load data in the data set to obtain an optimal hyper-parameter; and finally, the obtained optimal hyper-parameter is updated to the LSTM load prediction model, so that construction of the improved LSTM load prediction model is completed for subsequent cold load prediction.

This application relates to the field of rolling force prediction technology, and particularly to a method and apparatus for predicting rolling force in cold continuous rolling mills based on IDBO-SA-LSTM. The method includes: optimizing a dung beetle optimization algorithm based on a preset rolling force calculation model, a Circle chaotic mapping strategy, a golden sine strategy, and dynamic weight coefficients to construct an improved dung beetle optimization algorithm; performing performance tests on the improved dung beetle optimization algorithm using various benchmark test functions to obtain an improved dung beetle optimization algorithm that meets preset performance test requirements; automatically optimizing a preset adaptive long short-term memory network based on the improved dung beetle optimization algorithm, and constructing a target SA-LSTM rolling force prediction model using the automatically optimized adaptive long short-term memory network, so as to use the target SA-LSTM rolling force prediction model to predict the rolling force in real time during the online prediction stage. This solves the problem that existing mechanistic models contain many difficult-to-determine empirical parameters, which cannot guarantee the generalization performance and accuracy of cold continuous rolling mill rolling force prediction.

A CO2 injection capability prediction method for optimizing a BP neural network based on a dung beetle algorithm comprises the steps that S1, data collection and preprocessing are carried out to obtain an optimal sampling point set, and the optimal sampling point set comprises a verification set and a training set; carrying out data collection by adopting an optimal Latin hypercube sampling strategy; s2, constructing a BP neural network model; s3, inputting the training set into the BP neural network model, and randomizing a weight value and a threshold value in the BP neural network model to realize initialization of the weight value and the threshold value of the BP neural network model; s4, optimizing the BP neural network model by adopting a dung beetle algorithm; s5, further training the optimized BP neural network model; and S6, evaluating the training effect of the BP neural network model and determining whether to output or not. The method has the advantage of high prediction accuracy.

The present invention is a composition for inhibiting PTEN dephosphorylation enzymes, and specifically, the present invention is characterized by presenting a composition in which a CopA3 peptide derived from the small horned dung beetle binds to a PTEN enzyme via a covalent bond, thereby enabling inhibition of PTEN dephosphorylation enzymes.

The invention provides a Fuzzy-Smith-LADRC coagulation dosing control method based on an improved dung beetle algorithm, and the method comprises the steps: firstly obtaining a transfer function of a coagulation dosing system through an alum consumption rising experiment data result, then applying the LADRC to the system, estimating and compensating the disturbance in the coagulation control system through an expansion observer, and finally obtaining a final control result. Meanwhile, a self-adaptive Smith controller combining a Smith predictor (Smith) and a fuzzy controller (Fuzzy) is designed to eliminate the influence of a large time lag link in the coagulation dosing system on the control effect, a Fuzzy-Smith-LADRC control method is proposed, and an improved dung beetle algorithm is introduced for parameter setting for the difficulty in controller parameter adjustment. Effective adjustment of the coagulation dosing system can be achieved under the conditions that the model is uncertain and external disturbance is unknown, and the safety of drinking water is ensured.

The invention discloses a grain storage environment prediction method based on an optimized extreme learning machine, and the method comprises the following steps: obtaining granary environment information, and generating an input layer parameter according to the granary environment information; predicting the input layer parameters by using a pre-trained extreme learning machine to generate a prediction result; the method for training the extreme learning machine comprises the following steps: generating original parameters based on an input layer weight matrix and a hidden layer threshold vector of the extreme learning machine; using the original parameters as position information, and using a dung beetle algorithm to carry out iterative optimization to obtain optimization parameters, wherein the optimization parameters comprise an optimization weight W and an optimization threshold b; training an extreme learning machine according to the optimization parameters; the prediction performance of the extreme learning machine is improved.

This application belongs to the field of truss boom parameter optimization technology, specifically involving a multi-objective optimization design method and system for port crane truss booms. First, the minimum set of parameters that determine the boom structure is selected as the design parameters. The design space is sampled based on the optimal Latin hypersolution method. Computational fluid dynamics-static fluid-structure interaction calculations are carried out taking into account the characteristics of the shore wind field to obtain the wind resistance, strength, and stiffness indices of each sampling point. A surrogate model is constructed using the deep learning DAL algorithm, with dimensions as input and wind load, strength, stiffness, and other indices as outputs. Furthermore, the optimal design value within the design space is obtained by improving the dung beetle optimization algorithm, and the optimal design value that satisfies the premise of strength, stiffness, and stability is constructed and output.

The invention discloses a WSN coverage optimization method and device based on an improved dung beetle algorithm, equipment and a medium, and relates to the technical field of wireless communication, and the method comprises the steps: initializing algorithm parameters and setting the maximum number of iterations, employing a Single chaotic mapping strategy to initialize a population, calculating an individual fitness value, and determining a preset individual position, according to the method, individual positions are updated by using crisscross and random inertia weight strategies, an optimization result is finally output, and a WSN coverage scheme is generated, so that the global search capability and the optimization precision are improved, local optimum is effectively avoided, and the network coverage rate and the node energy efficiency are improved.

The invention discloses a same-protocol network flow privacy protection method based on flow-level statistical enhancement, and belongs to the technical field of network flow privacy protection. According to the method, flow-level multi-dimensional feature representation is constructed, a flow feature sample with both endogenous stability and extrinsic dynamics of a target flow sample is generated based on a steady-state variation generation model, and representative samples are selected based on feature state difference minimization to construct optimal target distribution. A confusion strategy optimization model oriented to flow-level multi-dimensional feature difference minimization is established, a global confusion strategy is solved by adopting a multi-strategy dung beetle optimization algorithm, and real-time fitting of flow-level features is realized through a packet-by-packet confusion method based on a real-time receptive field. According to the method, a deep learning identification method based on flow-level statistical characteristics can be effectively resisted, and privacy protection of network flow of the same protocol is realized under controllable cost.