223 results about "Lagrange multiplier" patented technology

The invention provides a micro-grid cooperative scheduling method and device, and relates to the technical field of smart grids, and the method comprises the steps: obtaining historical operation data and real-time operation data of a micro-grid system, and data of an external information system; generating load demand and energy equipment output prediction information based on the historical operation data and the data of the external information system; constructing a layered multi-time-scale decision architecture, and performing decision optimization on each layer of agents by adopting a reinforcement learning algorithm; constructing a plurality of heterogeneous agents, and carrying out cooperative scheduling on the plurality of heterogeneous agents by adopting a centralized training and distributed execution multi-agent reinforcement learning algorithm; inputting the prediction information and the real-time operation data into a decision framework, and outputting a real-time control instruction; and setting a security constraint condition, and realizing optimization of the security constraint in combination with a Lyapunov function, a Lagrange multiplier method, a security layer mechanism and a reinforcement learning algorithm. According to the method provided by the invention, the safe, efficient and reliable operation of the micro-grid in the grid-connected / off-grid mode can be realized.

The invention discloses a data processing method based on multi-agent collaborative optimization, and the method comprises the following steps: building a multi-agent collaborative environment, and outputting a constraint threshold value; accessing multiple data sources according to the constraint threshold, and outputting a standardized input data set; distributing the input data set to each agent participating in collaboration, and outputting a processing suggestion set; performing cross evaluation and consensus formation on the processing suggestion set by each agent, and outputting a candidate scheme list; performing feasible region screening on the candidate scheme list, and outputting an optimized candidate scheme set; receiving an optimization candidate scheme set, carrying out joint optimization on candidate schemes by adopting a cooperation bidding rule simultaneously constrained by double Lagrange multipliers, and outputting a bid winning execution scheme; taking the bid winning execution scheme as input, and outputting execution state information; and receiving the execution state information, and outputting a final execution result when the system meets a preset termination condition. According to the invention, a collaborative optimization data processing method is realized.

The invention discloses a digital twinning multi-agent reinforcement learning intelligent decision-making system and method with a secure memory playback mechanism, and the system comprises a digital twinning module which is used for constructing a virtual model and synchronizing the virtual model with a physical entity in real time; the multi-agent reinforcement learning module is used for carrying out strategy learning based on a constrained Markov decision process and balancing performance and safety through a Lagrange multiplier; the safe memory playback module is used for weighting and playing back the experience samples according to the risk and the timeliness so as to improve the learning safety; the reversible grey influence network module is used for causal modeling and reasoning and enhancing decision interpretability; the double-loop self-constraint control module ensures that a control action is always in a physical safety boundary through a barrier function and safety projection; and the convergence and stability criterion module is used for verifying strategy security convergence and system asymptotic stability. According to the method, the problems of strategy border crossing, virtual-real mismatching and the like in the high-risk manufacturing process are solved, and multi-target optimal control under the safety constraint is realized.

The invention relates to a low-dimensional subspace clustering method based on projection matrix guidance, and the method comprises the steps: extracting a light response non-uniformity PRNU noise residual error from input image data through employing a denoising filter, and constructing a PRNU feature data set of an image; performing feature dimension reduction on the feature data set by adopting a projection matrix method, constructing a projection matrix maintaining a geometric structure, mapping the projection matrix to a low-dimensional potential subspace, and further constructing a model for the subspace by utilizing a sparse self-representation method; constraint is applied to sparse self-representation in the low-dimensional potential subspace, and joint optimization is carried out through an augmented Lagrange multiplier method ALM and an alternating direction minimization ADM strategy to be used for efficient clustering of data in the low-dimensional potential subspace. According to the method, the projection matrix maintaining the geometric structure is constructed, the high-dimensional PRNU features are mapped to the low-dimensional potential subspace, the local neighborhood relation and the global distribution structure are reserved in the dimension reduction process, the calculation cost is reduced, and the clustering robustness and performance are effectively improved.

The invention discloses an engineering machinery industry green factory evaluation method and system. The method comprises the steps of obtaining a pre-formulated green factory evaluation index system; calculating the subjective weight of each secondary index relative to the target layer; introducing a Monte Carlo simulation algorithm, and calculating an objective weight and an evaluation matrix of each secondary index corresponding to each Monte Carlo simulation relative to the target layer; based on a minimum relative information entropy principle and a Lagrange multiplier method, combined with the subjective weight and the objective weight of each secondary index relative to the target layer, calculating the comprehensive weight of each secondary index relative to the target layer corresponding to each Monte Carlo simulation; on the basis of the comprehensive weight and evaluation matrix of each secondary index relative to the target layer, constructing a fuzzy comprehensive evaluation matrix corresponding to each Monte Carlo simulation; and obtaining a green factory grade evaluation result based on the fuzzy comprehensive evaluation matrix corresponding to each Monte Carlo simulation and a preset score interval corresponding to each comment grade. According to the method, the accuracy and objectivity of green factory evaluation can be remarkably improved.

The invention provides a large model training data desensitization protection method and system based on differential privacy, and relates to the technical field of artificial intelligence security, and the method comprises the steps: calculating a differential privacy parameter, mapping training data to a feature subspace, and constructing a dimension reduction manifold projection operator; solving an optimal disturbance vector by using a Lagrange multiplier method to form a de-sensitization feature set; probability distribution is constructed based on kernel density estimation, and Gaussian noise is injected; and dynamically adjusting a parameter group updating strategy in model training. According to the method, data utility and privacy protection can be effectively balanced, the large model training safety is enhanced, and the model convergence efficiency is improved.

The invention discloses a mixed regular variational mode decomposition method, device and equipment suitable for an unsteady flow field of an aircraft and a storage medium, and relates to the technical field of flow analysis, and the method comprises the steps: determining a bandwidth estimation value and a frequency separation weight coefficient based on the unsteady flow field, an expected mode number, a spatial mode and a time evolution coefficient, constructing a first regular term and a second regular term, weighting to obtain a mixed regular term, introducing a flow field reconstruction term to establish a flow field modal decomposition variational optimization problem, converting the problem into a frequency domain optimization problem through Fourier transform, and simplifying the problem into a sub-convex optimization problem by adopting an alternating direction multiplier method; an analytic solution is obtained through a variational method and iteratively updated to obtain a flow field space mode, a time evolution coefficient frequency domain representation, a center frequency and a Lagrange multiplier, the time evolution coefficient is obtained through inverse Fourier transform, a mode decomposition result is obtained, and therefore high-precision mode separation of the unsteady flow field is achieved. And the calculation efficiency and the iteration convergence speed of the variational optimization problem are improved.

The invention discloses a low-altitude edge network anti-fault task migration and DNN adaptive segmentation method, which comprises the steps of constructing a multi-unmanned aerial vehicle auxiliary MEC system, and performing DNN task division through a DNN adaptive division strategy; constructing a fault migration model, and migrating an uncompleted DNN task on the failed unmanned aerial vehicle to a normal unmanned aerial vehicle; the weighted energy consumption minimization problem of the multi-unmanned aerial vehicle assisted MEC system is reconstructed into a Markov decision process, and an optimal strategy is learned through interaction with the environment; a DKSAC-PER joint optimization framework is constructed, transmission power is optimized through the DKSAC-PER, calculation resource allocation optimization is performed through a Lagrange multiplier method, a reward value of a current step is calculated through an SAC-PER algorithm, network parameters are updated, and a complex mixed decision space is solved. According to the invention, the flight paths of the remaining unmanned aerial vehicles can be automatically adjusted, the calculation load is redistributed, and the survivability of the system in a severe environment is greatly improved.

The invention discloses an electric vehicle collaborative optimization scheduling method based on a'network-station-vehicle 'layered architecture. The method comprises the following steps: constructing a double-layer distributed scheduling model; in the upper-layer model, modeling is carried out on aggregation flexibility of the charging stations, and an aggregation charging and discharging plan of each charging station is formulated by taking maximization of the total benefit of the system as a target; in the lower-layer model, the charging and discharging behaviors of the individual electric vehicle are scheduled by following an upper-layer plan instruction and taking the comprehensive satisfaction degree of a vehicle owner as a target; a second-order cone programming relaxation technology is adopted to convert a non-convex power flow constraint equation in the upper-layer model into convex constraint; decomposing the global optimization problem into a plurality of independent sub-problems which can be solved by each charging station in parallel by adopting an improved Lagrange relaxation dual method; and iteratively updating the Lagrangian multiplier through a sectional self-adaptive step length strategy until the algorithm is converged and a global optimal scheduling plan is generated. According to the method, the scheduling effect close to centralized optimization can be obtained while the privacy of the user is protected; and the problem of curse of dimensionality is effectively solved.

The invention discloses a main lobe gain maximization method for an analog-digital hybrid array of a radar communication system. According to the method, the ratio of the maximum minimum main lobe level to the peak side lobe level is used as a target function, and under the main lobe ripple constraint, the simulation weight constant modulus constraint and the digital weight power constraint, the ADMM (Alternating Direction of Multiplexing) is used for carrying out joint design on the simulation weight and the digital weight. In the ADMM framework, a Riemann conjugate gradient method is adopted to solve a simulation weight subproblem with constant modulus constraint; and solving a digital weight by adopting a Lagrange multiplier method. A numerical result shows that the method can generate better main lobe ripples and lower peak side lobe level, and has good beam directional diagram accurate control performance.

The application discloses a kind of anti-saturation preset performance despun control methods of failed satellite and related devices, the method includes: obtaining the attitude of service spacecraft and failed satellite, establishes the dynamics model of service spacecraft and failed satellite;According to the dynamics model of service spacecraft and failed satellite, the flexible operating rod dynamics model of service spacecraft is established, the large deformation dynamics characteristics of despun brush are obtained, under the framework of the dynamics model of service spacecraft and the large deformation dynamics characteristics of despun brush, the rigid-flexible coupling dynamics model of service spacecraft is established by Lagrange multiplier method;Based on the rigid-flexible coupling dynamics model of service spacecraft, an anti-saturation preset performance controller is designed, and an anti-saturation full-state constraint control strategy is used for despun control.The application is aimed at service spacecraft with flexible operating rod, realizes efficient and accurate despun process, and greatly improves control performance.

The invention discloses an electric vehicle charging station safety scheduling method and device based on PID-Lagrange deep reinforcement learning, and a medium, and relates to the technical field of intelligent power grid and artificial intelligence crossing. The method comprises the following steps: firstly, constructing a constrained Markov decision process model of a charging station, and defining a reward function containing a power grid tracking error or economic profit and a cost function based on distribution transformer physical capacity limitation and user satisfaction; in a deep reinforcement learning training process, a PID control mechanism is introduced to dynamically update a Lagrange multiplier, and a penalty weight is adjusted by using a proportion, an integral and a differential term of a security constraint violation quantity. The method solves the problems that when a traditional Lagrange relaxation method is used for processing hard constraints, multiplier oscillation is violent, and the convergence speed is low. Experiments show that the method can strictly ensure that the transformer is not overloaded while maximizing the operating benefit of the charging station, effectively considers the charging demand of a user, and has the advantages of stable convergence, high safety, strong adaptability and the like.

The invention provides a micro-grid energy storage optimization scheduling method based on predictive control, and belongs to the technical field of micro-grid energy storage, and the method comprises the steps: building a state space mathematical model containing dynamic characteristics through collecting the operation parameters of energy storage equipment, building a double-layer game optimization framework to coordinate multiple physical constraints of the energy storage equipment, and achieving the optimal scheduling of the energy storage equipment. A rolling time domain prediction control strategy is established to process dynamic response requirements of energy storage equipment, an adaptive power adjustment model based on a graph convolution network is established to realize accurate prediction and dynamic adjustment of energy storage power, an energy storage equipment constraint processing mechanism is established, and a Lagrange multiplier method is adopted to process multiple physical constraint conditions. A prediction error compensation algorithm is established to monitor the operation state of the energy storage equipment in real time and dynamically correct a control instruction, an energy storage scheduling instruction is executed, closed-loop feedback control is carried out, and the technical problem that the energy storage equipment is difficult to realize dynamic response under multiple physical constraint conditions is solved.

The invention discloses a permanent magnet synchronous motor current harmonic suppression method based on model prediction control, and the method comprises the following steps: S1, building a mathematical model of a permanent magnet synchronous motor in a rotating coordinate system, and carrying out the discretization through an Euler discretization method, and obtaining a prediction model for predicting the state of the permanent magnet synchronous motor at a future moment; s2, designing and constructing a cost function including a fundamental current tracking item and a high-order current harmonic suppression item in the prediction model; calculating a current harmonic term factor; s3, traversing voltage vectors corresponding to all switching states of the inverter, calculating predicted current and a cost function under the action of the voltage vectors, selecting an optimal voltage vector enabling the cost function to be minimum, and generating a switching signal to drive the permanent magnet synchronous motor to operate; according to the method, the prediction model containing fundamental wave tracking and high-order harmonic suppression is constructed, and the harmonic suppression factor is optimized in real time by using the Lagrange multiplier method, so that current harmonic suppression and system loss reduction are realized.

The invention relates to the technical field of power system operation and control, and discloses an active power distribution network distributed reactive power optimization control method, which comprises the following steps: independently establishing a second-order cone branch power flow model by each regional controller, and constructing an augmented Lagrange objective function based on an alternating direction multiplier method; and executing a distributed iterative solution process. The process comprises the following steps that: a region controller executes local optimization solution to obtain a local boundary coupling variable; executing an information exchange operation, and exchanging the boundary coupling variable with an adjacent region; dual variable updating operation is executed, and the Lagrange multiplier is updated according to the residual error of the consistency constraint; and executing convergence discrimination, and outputting a reactive power optimization control strategy if the condition is satisfied. A non-convex problem is converted into a convex optimization problem by adopting second-order cone relaxation, the solution optimality is ensured, and a distributed node decoupling architecture is combined, so that the communication burden is reduced, and the expandability and robustness of the system are improved.

The invention relates to the field of multi-mode collaborative transportation and logistics, in particular to a collaborative distribution optimization method and system for taking off, landing and synchronous recovery of a vehicle-mounted unmanned aerial vehicle on the way (in the advancing process). According to the method, a layered decoupling framework is adopted; in the first layer, subsection division is performed on a road network, taking-off and landing positions are continuously optimized in candidate taking-off and landing subsection pairs based on a Lagrange multiplier method and geometric synchronization constraint, and a client cluster candidate set is formed; the second layer performs joint optimization on selection of a single take-off and landing sub-segment pair in each client cluster and a global path of a ground vehicle to construct a generalized traveling salesman variant, and designs a sub-segment distance measurement and an overlapping deduction strategy to deal with any continuous take-off and landing distance calculation and multi-unmanned aerial vehicle cooperation problem. Experiments show that compared with a fixed stop point or discretization in-transit strategy, the method can significantly reduce the total delivery cost and the completion time, and has robustness and expandability for customer scale, distribution, unmanned aerial vehicle speed and road network density change.

The invention provides a distribution network-micro-grid multi-agent distributed collaborative optimization method and equipment, and the method comprises the steps: constructing a safe operation model of a distribution network-micro-grid system, and building a multi-stage optimization model with the minimization of the operation cost as a target based on the model, a multi-stage optimization model is decomposed into an active power distribution network operator optimization sub-problem and a plurality of micro-grid operator optimization sub-problems, and a distributed optimization algorithm is designed based on an augmented Lagrange function and a consistent alternating direction multiplier method, so that each main body iteratively updates a local decision variable, a shared variable copy and a Lagrange multiplier, and the optimal power distribution network operator optimization sub-problem is obtained. Collaborative optimization solution is realized; based on a distributed optimization algorithm, a rolling time domain optimization framework is adopted to realize real-time cooperative operation and reactive power support regulation and control of the distribution network and the microgrid. Based on the method, the invention further provides distribution network-microgrid multi-agent distributed collaborative optimization equipment. According to the invention, safe operation of the distribution network and the micro-grid is guaranteed, the reactive power support capability of the system is improved, and the operation cost is reduced.

The application discloses a kind of double-channel label guide multi-label feature selection method and system, belong to feature engineering technique.Method mainly includes: obtaining the feature matrix and positive label matrix of multi-label data set, by performing logical negation to positive label matrix, generate mirror negative label matrix, and construct graph Laplacian matrix based on feature matrix;Based on the data after pre-processing, a multi-label model is constructed, and the objective function of the multi-label model includes at least positive label regression loss term, negative label regression loss term, label alignment constraint term, graph regularization term and sparse constraint term;The constraint is processed by relaxation, and the optimization function is constructed by combining the Lagrange multiplier method, and then the objective function is iteratively solved according to the KKT condition, and after iterative convergence, the feature importance is evaluated based on the projection matrix used to associate features and positive labels;The application meets the demand of multi-label learning for accurate and efficient feature selection, can fully utilize label information, enhance anti-interference ability and consider efficiency.

The application discloses a TBM tunneling parameter abnormal data identification method and system, and belongs to the technical field of data processing. The application constructs a polynomial chaos expansion regression model through polynomial chaos expansion, identifies abnormal data in TBM tunneling parameter data by using data clustering and polynomial chaos expansion regression error, depicts the correlation between TBM tunneling parameters through polynomial chaos expansion, compares the difference between data by using the correlation between TBM tunneling parameters, constructs a clustering objective function based on polynomial chaos expansion regression error, optimizes and solves the clustering objective function by using a Lagrange multiplier method, and obtains a TBM tunneling parameter membership degree matrix. Whether the data is abnormal is determined by using the TBM tunneling parameter membership degree matrix, and accurate identification of abnormal data of TBM tunneling parameters is realized.

The application discloses a kind of gas-electricity-water system combined scheduling distributed solution method, comprising the following steps:1, obtain the initial value of boundary variable and Lagrange multiplier, obtain penalty parameter, correction factor and convergence accuracy;2, by sequentially solving natural gas, power and water supply system optimization model, update corresponding boundary variable;3, update Lagrange multiplier, and correct the boundary variable corresponding to power and water supply system;4, stop updating when boundary variable and Lagrange multiplier no longer change, obtain gas-electricity-water system combined scheduling scheme.As an independent operation subject, gas, electricity, water three systems exist respective privacy, unwilling to share all data information, while centralized solution needs all data information, at the same time, three systems cannot be independently solved, so as to guarantee each dispersed autonomy right.The application protects the data privacy of gas, electricity, water three systems to a great extent, and guarantees the dispersed autonomy right of each system.

The invention relates to the technical field of image processing, in particular to a silicon carbide tray defect detection method and system based on image recognition, and the method comprises the steps: obtaining a gray image of a silicon carbide tray to construct an observation matrix, and initializing a low-rank matrix, a sparse matrix and a Lagrange multiplier matrix for representing error accumulation; iterative optimization is executed; and repeating the iteration steps until a termination condition is met, and taking the final sparse matrix as a defect detection result. Through the technical scheme of the invention, the problems of false detection and missing detection caused by misjudging the background texture as the defect can be reduced, and the accuracy and robustness of the defect detection result of the silicon carbide tray are improved.

This invention provides a method for generating an integrated OFDM communication and sensing signal with low sidelobes and PAPR characteristics, relating to the fields of communication and radar technology. The method includes: constructing an OFDM time-domain signal with N subcarriers; constructing an integrated communication and sensing frequency-domain signal, the integrated frequency-domain signal including a set of communication subcarriers and a set of radar sensing subcarriers; constructing a mathematical model of the integrated communication and sensing signal; constructing a Lagrange augmented function; updating the OFDM time-domain signal; updating the communication subcarriers; updating the radar subcarriers; updating the Lagrange multipliers; and repeating the above update steps to obtain the optimal result. This invention optimizes both radar sensing and communication performance under PAPR constraints, solves the non-convex problem, and achieves a good balance between sensing and communication performance.

This invention discloses a soft tissue modeling method based on constrained energy functions and the finite element method. First, a corresponding constrained energy function is constructed for the specific interaction effects between soft tissue and surgical instruments. Then, the constructed constrained energy function is integrated into the total energy function of the soft tissue. The continuous variational expression of the total energy is discretized into nodal displacement functions. Next, the displacement field is initialized, and the initial solution and iteration direction are calculated based on the gradient and Hessian matrix of the total energy function. By iteratively updating the displacement field and Lagrange multipliers, the optimal solution is gradually approximated. Finally, the convergence condition is checked; if the preset criteria are met, the iteration terminates; otherwise, the gradient and Hessian matrix are updated until the expected solution is reached. This method significantly improves computational efficiency while enhancing the accuracy of soft tissue deformation simulation, making it suitable for real-time simulation and interactive operation in complex surgical scenarios.

The invention discloses a station micro-grid optimization scheduling method and system considering internal and external double circulation, and belongs to the field of micro-grid operation optimization. According to the method, an internal circulation model is established based on classification of power load data of a thermal power plant and in combination with the start-stop sequence and process of equipment and the stoppable interval of power generation, the internal circulation model comprises economical efficiency, operation time sequence and environmental protection modules, and coordinated optimization is realized through a dynamic adaptive weight adjustment mechanism. An embedded optimization method is adopted, dynamic programming and mixed integer linear programming are combined, an equipment start-stop path and load distribution are optimized, loads are further reduced and transferred, and economic benefits are improved. The outer circulation comprises wind power, photovoltaic and energy storage devices, is responsible for scheduling optimization, and is coupled with the inner circulation through energy storage discharge. On the basis of independent optimization, an internal and external loop optimization problem is decomposed into parallel sub-problems, each iteration is independently optimized and a Lagrange multiplier is updated, power distribution and target coordination are dynamically adjusted, and global optimization is realized.

The invention discloses an intelligent household module dynamic management system based on cloud-side cooperation, and the system comprises the following modules: a sensing preprocessing module which is used for collecting data and generating an operation log and a resource portrait through Kalman filtering; the intention arrangement module is used for generating a task graph by adopting graph pointer decoding under graph constraint to obtain a service index weight and a strategy threshold value; the segmentation and interface module is used for outputting a cloud edge segmentation scheme, an intermediate interface specification and a segmentation version based on a multi-target Lagrange cost model; the execution and exploration module is used for connecting the edge end and the cloud end execution subgraph and combining an improved context dobby machine with PPO online evolution; the alarm and revision module is used for generating an alarm by residual prediction and accumulation and minimizing the influence on rerouting; and the adaptive optimization module is used for updating the weight, the threshold value and the Lagrange multiplier by Bayesian optimization. According to the invention, interpretable arrangement and self-optimization of tasks of the smart home module are realized, time delay energy consumption is reduced, and reliability is improved.

The application provides a kind of energy storage participation multi-dimensional power market optimization control method based on quantification attribution.The application carries out initial configuration, constructs energy storage participation multi-dimensional power market clearing model, obtains benchmark scheme and optimal scheme, quantification attribution based on path integral, optimizes control energy storage decision according to attribution result.The application specifically designs the path construction method for mapping marginal benefit using optimal Lagrange multiplier information, proposes the benefit decomposition attribution scheme of riemann approximation based on the path construction method, and generates the power distribution instruction and declaration strategy of energy storage system in the next scheduling period by taking the attribution result as feedback signal.The application can solve the decoupling problem of energy storage value under the coupling of complex physical and market constraints, clearly quantifies the contribution share of energy storage in multi-dimensional power market, optimizes the energy storage scheduling scheme, and provides support for energy storage investment decision and safe and economic operation of new power system.

This application relates to the field of power system technology and discloses a branching method and apparatus for accelerating the solution of power system safety-constrained unit combinations. During the branching process, if the relaxation problem of the target node is unsolvable, instead of simple single-point pruning, a network constraint minimum violation model is constructed. If the network constraint results in no solution, a globally feasible cut is generated using the Lagrange multiplier at the optimal solution. This globally feasible cut represents the constraint condition of a specific unit combination mode that leads to the unsolvability of the relaxation problem. Adding the globally feasible cut to the branching cut pool allows for the removal of infeasible solutions for similar specific unit combination modes in the future, avoiding a large number of repetitive and invalid explorations during the branching process, thereby accelerating the solution and ensuring the safety and economy of power grid dispatch. In this application, the globally feasible cut is strictly based on strong duality theory, ensuring that feasible or optimal solutions are not erroneously removed, fundamentally guaranteeing the feasibility and optimality of the solution results for safety-constrained unit combinations.

The present application relates to the technical field of image processing, and particularly relates to an infrared image stripe removal method, comprising: providing an infrared image I; establishing a structure tensor matrix based on the infrared image I, and obtaining an edge preserving operator matrix based on the structure tensor matrix; constructing a target function Y(S) for solving stripe noise S based on the edge preserving operator matrix; converting the target function Y(S) into an augmented Lagrangian function, iteratively solving each auxiliary variable and the Lagrange multiplier corresponding to each auxiliary variable to obtain a plurality of parameter combinations; performing Fourier transform on the augmented Lagrangian function to obtain a function of the stripe noise S, and iteratively solving the function of the stripe noise S by using the plurality of parameter combinations to obtain the stripe noise S; and removing the stripe noise S in the infrared image I to obtain a clear image B. The present application is at least beneficial to obtaining an infrared image with better quality after removing the stripe noise.

The invention discloses a sample labeling resource allocation method and electronic equipment, and the method comprises the steps: obtaining a comprehensive value score of each sample in a to-be-labeled sample set, the comprehensive value score being a weighted sum of an uncertainty score, a diversity score, a time correlation score and a domain migration cost score; based on data distribution of the to-be-labeled sample set, adjusting weighting coefficients of the uncertainty score, the diversity score, the time correlation score and the domain migration cost score to obtain a target weight parameter group; updating the comprehensive value score of each sample according to the target weight parameter group, and determining a to-be-labeled sample set with the maximum comprehensive score sum under the labeling budget constraint as a target to-be-labeled sample set based on a Lagrange multiplier method; the sample set with the maximum comprehensive value sum is optimally selected under the constraint of the marking budget, accurate and efficient allocation of marking resources is achieved, and the selected sample can better meet the requirement of model training for high-value data.

This invention discloses a high-resolution range image feature preservation and enhancement method based on a deep unfolded network, comprising: preprocessing radar echo data into an initial feature tensor; constructing a low-rank sparse decomposition model and mapping the iterative solution process of the model to a deep neural network containing cascaded networks, with each layer corresponding to one iterative optimization step; in each layer, a low-rank near-end mapping module captures the global correlation between the range dimension and the Doppler dimension through a dual-path axial attention mechanism to update the low-rank clutter component matrix; a sparse near-end mapping module updates the sparse target component matrix using a complex soft thresholding operator to maintain target phase information while suppressing clutter; and a Lagrange multiplier update module is used to update the Lagrange multipliers. This invention overcomes the limitations of manual parameter tuning by introducing a deep neural network and a dual-path axial attention mechanism, enabling the acquisition of structurally complete and phase-accurate high-resolution range image features while effectively suppressing clutter.