37 results about "Unconstrained optimization" patented technology

The application provides a delay compensation control method for a double pendulum wave energy conversion device, which comprises the following steps: numerical modeling and hydrodynamic analysis are performed on the double pendulum wave energy conversion device, time domain motion equations are established, a time delay function is introduced into the time domain motion equations to simulate control signal transmission delay, and partial differential equations are used to simulate the execution delay of the brake; state space equations of the device are established, the convolution items in the time domain motion equations are replaced by the state space equations, and the motion state of the device is calculated; a Hamilton function is defined to convert a constrained optimization problem into an unconstrained optimization problem, the optimal control criterion considering the control delay is obtained by solving the Hamilton function, and the maximization of energy capture under the optimal control criterion is realized. The application truly reflects the operation characteristics of the physical system by introducing the control delay, so that the closed-loop control method is effectively implemented in the actual physical device, and the energy capture efficiency of the wave energy conversion device and the reliability of the system operation are effectively improved.

The application belongs to the technical field of wireless communication, and relates to a RIS-assisted integrated sensing and communication joint beamforming design method and system, which comprises the following steps: constructing an RIS-assisted ISAC system; initializing a digital beamforming matrix and a phase shift matrix according to a base station total power constraint; constructing an unconstrained optimization problem by using a penalty function method; designing a sending end phase shift matrix based on the unconstrained optimization problem; designing a sending end digital beamforming matrix based on the phase shift matrix; repeating the previous two steps until the change of the system objective function values before and after the two times is less than a preset threshold value, so that the optimal phase shift matrix and the corresponding digital beamforming matrix are obtained. The application effectively improves the performance of the overall system sensing mutual information by alternately optimizing the phase shift matrix and the digital beamforming matrix.

The application provides a kind of space target ISAR image component intelligent segmentation and attitude estimation method, through inverse synthetic aperture radar to space target is continuously observed, and utilize distance-Doppler imaging algorithm to the echo is sequentially imaged, obtain the ISAR image sequence of space target;Utilize deep learning network Pix2pixGAN to the ISAR image sequence is segmented, and the segmentation accuracy is higher;After removing the invalid connected region in each component segmentation result, obtain the final segmentation image of each component;Linear structure extraction is carried out to the final each component segmentation image using the minimum circumscribed rectangle method, and the method is lower to the image component segmentation accuracy requirement, and the robustness is stronger;Finally, according to the imaging principle of radar observation and ISAR image, an unconstrained optimization problem for solving three-dimensional attitude is constructed, and a particle swarm optimization algorithm is used for solving, and the solving efficiency is higher, to realize the attitude inversion of space target key component.

The application provides a kind of intelligent car multi-constraint trajectory planning method based on multi-dimensional laser radar point cloud information, it is related to intelligent car motion planning technical field, the method of the present application first constructs dense point cloud map using A-LOAM algorithm according to the point cloud information emitted by multi-dimensional laser radar, then on the basis of obtaining the dense point cloud map of surrounding environment, the method of curve fitting based on minimum jerk is used, the optimal trajectory is solved in state space by giving the planning starting point and end point position, velocity, acceleration, and the time is further discretized to generate front path point. The uniform B-spline curve without control points is used for curve fitting, and the unconstrained optimization problem about curve smoothness, intelligent car driving speed, intelligent car driving acceleration, obstacle avoidance distance, end point arrival distance is further constructed according to the existing dense occupancy grid map, the quasi-Newton method is used to solve the unconstrained optimization problem, and the optimal trajectory of the intelligent car in complex environment is obtained.

The present application relates to the technical field of power system simulation, and more particularly to a Thevenin equivalent parameter estimation method and system based on multivariate coefficient of variation, an electronic device and a medium; the method comprises: collecting the measured voltage and the measured current at the equivalent point in the target time window; based on the measured voltage, the measured current and the preset Thevenin equivalent impedance prediction value, an indirect statistical model is constructed; the multivariate coefficient of variation is set as an evaluation index for measuring the dispersion degree of Thevenin equivalent potential; an unconstrained optimization model is established; the unconstrained optimization model is solved to obtain the estimated value of Thevenin equivalent impedance, and the estimated value of Thevenin equivalent potential is determined based on the estimated value of Thevenin equivalent impedance. In this way, the technical problem of insufficient estimation accuracy of the existing Thevenin equivalent parameter estimation method when facing complex and variable load fluctuation conditions is solved, and the accuracy and reliability of parameter estimation are improved.

The application discloses a kind of meta-heuristic test design optimization methods based on matrix transformation, belong to computer-aided test design and statistical modeling technical field, this method uses a two-stage optimization framework: first, in global exploration stage, with minimizing global uniformity index as target to carry out unconstrained optimization, to obtain well space coverage sample set;Subsequently in local development stage, with minimizing adjacent distance variance as target, optimization is carried out under the constraint of maintaining the good global coverage obtained, to fine adjustment sample point local spacing distribution, improve uniformity;The application encodes test design scheme into matrix form individual, is updated iteratively by meta-heuristic algorithm, and adopts global normalization strategy to ensure that sample is always located in design space;The application can systematically consider the global coverage of sample and local uniformity, significantly improve the sample distribution quality in high-dimensional space, generate comprehensive performance excellent test design scheme.

The invention discloses a high-directivity phased array synthesis method based on circular polarization axial ratio control, and belongs to the technical field of satellite communication. The method comprises the following steps: firstly, establishing a one-to-one correspondence relationship between an axial ratio and an electric field; then, an array directivity coefficient maximization problem model with strict axial ratio constraint is established; a non-convex fractional programming problem is converted into a Rayleigh entropy form, axial ratio constraint is converted into linear constraint, the axial ratio constraint is replaced with first-dimension excitation through excitation dimension reduction, an original problem is converted into an unconstrained optimization problem, and the converted unconstrained optimization problem is further converted into the Rayleigh entropy form; and finally, carrying out eigendecomposition on the converted standard Rayleigh entropy form to obtain an eigenvector corresponding to the maximum eigenvalue, and recovering the excitation of the original problem according to the conversion form. According to the method, accurate axial ratio control can be achieved, meanwhile, the maximum directivity coefficient can be obtained under the condition that the current axial ratio is limited, and the iteration process is avoided.

The application discloses a power line channel estimation method, device and medium, and the method comprises the following steps: S1, a Vandermonde structure manifold matrix containing multipath delay information is constructed; S2, based on the Vandermonde structure manifold matrix, a super-complete manifold matrix containing all potential delay point positions is constructed, and a channel estimation problem is converted into a sparse representation problem; S3, an unconstrained optimization objective function is constructed; S4, singular value decomposition is performed on received OFDM pilot signal data of multiple time periods, a signal subspace is extracted, and compression and noise suppression of sampling data are realized; S5, the data compressed through step S4 is substituted into the optimization objective function constructed in step S3 to obtain high-precision multipath delay estimation; and S6, based on the multipath delay estimation, a complete power line channel response is reconstructed, and high-resolution and high-robustness channel estimation results are obtained in a power line channel environment with high noise and strong multipath interference at a relatively low calculation complexity.

Prior methods of state estimation rely on penalty-based heuristics to enforce inequality constraints, which can produce very large weight values, resulting in ill-conditioning of the gain matrix. Disclosed embodiments of state estimation convert the inequality-constrained optimization problem into an unconstrained optimization problem in which violated inequality constraints are represented as parameterized potential functions, each comprising a center-of-attraction parameter. This unconstrained convex optimization problem can be iteratively prepared, using successively updated values for the center-of-attraction parameters, and solved, until no inequality constraints are violated, to produce a final estimated state. This final estimated state may then be used to control the system being monitored, such as a power system.

The application discloses a low-complexity sparse array design method based on L 0 norm, and steps are as follows: based on Laguerre filter, an array signal model of a wideband beamformer is constructed, a mixed L 2,0 norm is taken as a target, an array sparsification optimization problem under a beam performance constraint is constructed, auxiliary variables are introduced, the array sparsification optimization problem is converted into an unconstrained optimization problem in a form of an augmented Lagrange, and based on an alternating direction multiplier method, the optimization problem is decomposed into a plurality of sub-problems about the beamformer weight, Laguerre poles and the plurality of auxiliary variables, and solutions of the sub-problems in step S3 are solved and iteratively updated respectively until a convergence condition is met, and the optimal weight matrix and the like are output. Compared with existing methods, the sparse performance of the application is better, especially in the case of a short tap, the number of array elements required by the system is less, and thus the application has lower implementation complexity.

The application provides an unmanned vehicle trajectory planning method based on energy optimization, comprising: updating complex irregular obstacle information of surroundings in the unmanned vehicle based on point cloud information; calculating posterior probability of a grid according to point cloud information fed back each time, and constructing an occupancy grid map in real time; searching for path points for avoiding obstacles by using an A* algorithm based on vehicle kinematics according to terrain and environment information constructed by a sensor; obtaining a series of relatively dense path points by using a path backtracking method, and performing curve fitting by using a uniform B-spline curve without control points; constructing an Euclidean distance map to further construct an unconstrained optimization problem about minimum energy consumption, driving speed, driving acceleration and obstacle avoidance distance, and solving the optimization problem by using an open source solver to obtain an optimal trajectory with optimal energy consumption, satisfying dynamic feasibility and being able to avoid obstacles; and performing time redistribution on the optimal trajectory, so that the speed and acceleration values corresponding to the trajectory points do not exceed a threshold value.

The invention discloses an LPI radar waveform design and resource allocation method based on manifold optimization, and aims to improve the target tracking precision of a radar. According to the method, the multi-target tracking performance is quantified through the target function based on the posterior Cramer-Rao lower bound. In order to improve accuracy and calculation efficiency, a manifold optimization framework is constructed to carry out optimization post-processing on a constructed objective function: firstly, an accurate penalty function is introduced, an LPI constraint condition is smoothly fused into the objective function, and conversion from a constraint problem to a penalty form is realized; constructing a volume manifold space based on resource constraint characteristics, and reconstructing an original optimization task into an unconstrained optimization problem on a manifold; meanwhile, a parallel conjugate gradient descent algorithm with a self-adaptive step length mechanism is adopted to execute optimization solution. According to the algorithm, parallel computing can be fully utilized to realize rapid convergence, and efficient exploration can be realized in a product manifold space through a self-adaptive step length strategy, so that a better solution and more stable optimization performance are obtained.

The invention discloses an unmanned aerial vehicle high-speed flight path planning method. According to the method provided by the invention, the physical authenticity of a high-speed flight path is remarkably improved by introducing a nonlinear wind resistance dynamic model, and a complex constrained optimization problem is converted into an unconstrained optimization problem in a flat output space by means of differential flat mapping in a dimensionality reduction manner; therefore, the calculation complexity is greatly reduced on the premise of ensuring the track precision. And in combination with construction of a safe flight corridor and gradient optimization solution, the optimal trajectory which conforms to dynamic characteristics, meets various constraints and is efficient in energy can be generated in real time in a complex environment, and cooperative improvement of trajectory planning precision and real-time performance under the condition of high-speed flight of the unmanned aerial vehicle is integrally realized.

The application discloses a kind of ultra-low range-doppler sidelobe Golay complementary waveform design methods, first, a kind of Pareto effective Golay complementary waveform design framework is proposed, the framework is jointly optimized to Doppler elastic transceiving sequence pair, to achieve the trade-off between SMR and SNR performance.This framework considers the unconstrained optimization problem with variable weight on these two indicators, a series of loss functions of Pareto multi-objective optimization problem are constructed using weighted sum method, and all possible Pareto optimal solutions are obtained.Secondly, in order to solve the optimization problem, a model-driven machine learning algorithm is designed to carry out multi-objective optimization.The method of the application can suppress the Doppler sidelobe to an extremely low level of-80.38dB, but the loss of signal-to-noise ratio is small, only 2.8dB, which is 5dB and 0.3dB higher than the traditional Doppler elastic scheme respectively.

This invention discloses a current optimization method for electrolytic copper based on a non-dominated sorting genetic algorithm. The method includes establishing a sub-model of a multi-objective optimization problem in the electrolytic copper production process; establishing a prediction model for the concentration of key ions in the electrolytic cell based on the principle of mass conservation; setting production process constraints, including at least the maximum rectifier current constraint and daily output target constraint, and transforming the constrained multi-objective optimization problem into an unconstrained optimization problem through a penalty function; and solving the unconstrained optimization problem using a non-dominated sorting genetic algorithm, outputting a sequence of optimal current values ​​for each time period within the next 24 hours, in units of a set time interval. This invention, by constructing a multi-objective model that integrates ion concentration prediction and employing an efficient algorithm for solving it, can achieve refined and collaborative optimization of the current in the electrolytic copper production process, thereby effectively reducing electricity costs while ensuring both output and quality.

This invention belongs to the field of wireless communication technology, specifically relating to a beamforming method for cellless massive MIMO. The invention proposes a cascaded maximum-minimum user-access point association and beamforming method, decomposing the problem into an association stage and a beamforming stage. In the association stage, the maximum-minimum user-access point association is solved to obtain a user-access point association scheme that satisfies backhaul constraints. In the beamforming stage, the maximum-minimum beamforming problem is solved under a fixed association scheme to maximize the minimum user rate. A precise penalty function method is proposed, unifying the two stages within a binary threshold search and feasibility determination paradigm, transforming the feasibility determination problem into an unconstrained optimization problem. Finally, to avoid complex parameter tuning issues, an adaptive gradient descent algorithm is introduced to solve the unconstrained optimization problem. This invention significantly reduces complexity and enhances engineering implementability.

This invention proposes a Riemann expansion network security waveform design method for intelligent reflector-assisted communication, belonging to the field of wireless communication technology. This invention innovatively reconstructs the security rate maximization problem, which involves jointly optimizing the normalized transmit beamforming matrix and the reflection coefficient vector, into an unconstrained optimization problem on a product Riemann manifold. This invention designs an efficient product Riemann gradient descent algorithm to solve this problem, and further expands the iterative physical process of this algorithm into a trainable neural network layer. Specifically, this expanded network adaptively optimizes the descent step size of each iteration through unsupervised learning, not only strictly preserving the inherent geometric structure of the constant modulus constraint of the intelligent reflector, but also possessing clear interpretability. This invention has extremely fast convergence speed and extremely low online computational complexity, meeting real-time requirements. This invention avoids local optima traps and significantly improves the security rate performance of the system.

This invention discloses a multi-agent safety reinforcement learning method and system for AGV charging scheduling, relating to the field of intelligent logistics scheduling technology. The method includes: constructing an AGV transportation system environment model in an aviation equipment logistics environment, collecting real-time status data, and setting operating parameters. Each AGV is modeled as an independent decision-making agent, and the charging pile is modeled as a resource regulation weak agent, forming a multi-agent collaborative scheduling system. The AGV charging scheduling problem is modeled as a constrained Markov decision process, setting a multi-objective reward function and charging safety constraints, transforming it into a cost constraint function, and modeling it as a constrained optimization problem. This is further transformed into an unconstrained optimization problem, and the multi-agent decision network is trained until the parameters converge to obtain the optimal policy network. Finally, it is deployed to the AGV scheduling system to achieve real-time collaborative scheduling of transportation and charging tasks.

The invention belongs to the technical field of large-span space structure design, and provides a non-linear form optimization method and system for a free-form surface single-layer latticed shell structure, which takes the minimum overall strain energy of the structure as an optimization target and coordinates of latticed shell nodes as optimization variables to construct a non-linear optimization equation of a single-layer latticed shell form and convert the non-linear optimization equation into an unconstrained optimization equation. Solving an optimization problem by adopting a conjugate gradient method; based on solution of a conjugate gradient method, the sensitivity of strain energy to optimization variables is determined; obtaining a nonlinear strain energy gradient based on the sensitivity so as to determine a conjugate gradient direction; based on the conjugate gradient direction, carrying out line search according to a preset load and a step length until the line search in the conjugate gradient direction meets a convergence condition; the overall strain energy minimization, obtained based on nonlinear calculation, of the structure serves as an optimization target, coordinates of latticed shell nodes serve as optimization variables, a conjugate gradient method serves as an optimization algorithm, and the influence of geometric nonlinearity of the structure under the load effect is fully considered.

A probabilistic transient stability constrained optimal power flow (TSCOPF) method considering the uncertainty of power sources and loads is proposed, which includes the following steps: Step 1: initialize the system power flow parameters and establish the probability distribution model of the uncertainty variables; Step 2: convert the static security inequality constraints and transient stability constraints into the form of probability constraints, and build the TSCOPF model based on the chance-constrained optimization theory; Step 3: convert the sampling matrix in the independent standard normal space to the original space; Step 4: perform multiple deterministic power flow calculations on the sampling matrix based on the point estimate method (PEM), and combine the Cornish-Fisher series to determine whether the probability constraints of each output variable are out of limits; Step 5: convert the original optimization problem into an unconstrained optimization problem, and initialize the parameters of the moth flame optimization (MFO) algorithm; Step 6: calculate the fitness value of the moth, and output the moth with the best fitness value as the optimal solution of the model.

The application provides a clutch damping control method for a wave energy device, considers the survival problem of the wave energy device in actual sea conditions, establishes a time domain motion equation and a state space equation, simplifies the time domain motion equation by using the state space equation, rewrites the time domain motion equation into a linear differential equation, represents whether the inner oscillator and the wave energy device are connected by loading and unloading control commands in the linear differential equation, and obtains the motion state of the wave energy device by solving the motion differential equation with the control. A Hamilton function about the control command is defined, a constraint problem of displacement minimization is converted into an unconstrained optimization problem, the Hamilton function is expanded according to the state space equation of the wave energy device, the Hamilton function is solved, the optimal control sequence of the displacement of the optimized wave energy device in the extreme environment is obtained when the Hamilton function is minimum, the motion of the wave energy device is adjusted by using the optimal control sequence, and the effect of maximizing the survival ability of the optimized wave energy device is realized.

The invention is suitable for the field of hydraulic structure design of water conservancy and hydropower engineering, and provides a gravity dam economic section automatic design method and system based on an intelligent optimization algorithm, and the method comprises the steps: inputting design parameters, and initializing an algorithm population; performing stability calculation and constraint verification on each candidate section in the population; the candidate sections are evaluated through a preset fitness function, the function applies a great penalty value to the sections which do not meet the stability constraint, and the volumes of the sections which meet the constraint are directly used as fitness values; the population is iteratively evolved by using an intelligent optimization algorithm, and individuals with better fitness values are continuously screened out; and finally outputting an economic section which meets all safety constraints and has the minimum concrete volume. According to the method, a complex constrained engineering optimization problem is converted into an unconstrained optimization problem, automation and intellectualization of gravity dam section design are achieved, the design efficiency is greatly improved, and the engineering amount of a dam body can be remarkably reduced on the premise that safety is guaranteed.

This invention relates to the field of energy-saving retrofitting of high-pressure water descaling systems, and discloses a multi-objective energy-saving control method for accumulators in descaling systems. For high-pressure water descaling systems in steel rolling, the basic parameters of the descaling system and accumulator are first determined. Simulations are used to obtain the steel plate energy consumption, the minimum system pressure, and the accumulator cost. Relevant performance indicators and core accumulator parameters are selected as variables to be optimized. Then, with the goal of minimizing steel plate energy consumption and accumulator cost, a penalty function is introduced to transform constrained optimization into unconstrained optimization. A multi-objective intelligent particle swarm optimization algorithm is executed. After multiple iterations, including particle swarm initialization and objective function evaluation, the non-dominated solution of the external archive set is output as the optimal parameters for the accumulator. This method achieves the optimal match between the energy consumption of the descaling system and the cost of the accumulator, while ensuring that the system operating pressure meets the standard, thus improving the economy and reliability of the descaling system operation.

The invention relates to the technical field of spectral imaging, in particular to a spectral data demodulation method, which comprises the following steps of: 1, providing an imaging spectrometer, acquiring a plurality of images of the same target point by using the imaging spectrometer, and outputting an electron number expression of a modulation curve corresponding to each image by the imaging spectrometer; step 2, obtaining an optimal solution x0 of a least square problem of an electron number expression by using singular value decomposition; 3, constructing an unconstrained optimization function based on an electron number expression; 4, the optimal solution x0 serves as an initial value of iteration input of the unconstrained optimization function, the minimum solution x of the unconstrained optimization function is obtained through an LM algorithm, and x is spectral data obtained through demodulation. The method is at least beneficial to improving the demodulation precision of the spectral data.

The present application relates to the technical field of power system simulation, and more particularly to a Thevenin equivalent parameter estimation method and system based on multivariate coefficient of variation, an electronic device and a medium; the method comprises: collecting the measured voltage and the measured current at the equivalent point in the target time window; based on the measured voltage, the measured current and the preset Thevenin equivalent impedance prediction value, an indirect statistical model is constructed; the multivariate coefficient of variation is set as an evaluation index for measuring the dispersion degree of Thevenin equivalent potential; an unconstrained optimization model is established; the unconstrained optimization model is solved to obtain the estimated value of Thevenin equivalent impedance, and the estimated value of Thevenin equivalent potential is determined based on the estimated value of Thevenin equivalent impedance. In this way, the technical problem of insufficient estimation accuracy of the existing Thevenin equivalent parameter estimation method when facing complex and variable load fluctuation conditions is solved, and the accuracy and reliability of parameter estimation are improved.

A model prediction-based control method for grid forming of multi-port autonomous reconfigurable solar plants includes: estimating and predicting system parameters by establishing a multi-port autonomous reconfigurable solar plant and a dynamic model of a synchronous generator model; converting an objective function into an unconstrained optimization problem, using Newton's method to achieve minimum computational burden within each calculation time step to find a solution in real time for obtaining an optimal angular frequency; based on results of the optimal angular frequency, updating an output voltage and a dq-axis current of the multi-port autonomous reconfigurable solar plant, and changing an arm modulation index of the plant, thereby realizing the plant's inertia and primary frequency modulation support. The model prediction-based control method provided by the present invention achieves rapid prediction during operation and improves frequency response, rapidity and system stability.

The application discloses a SAR interference self-elimination method based on weak background prior, constructs an interference suppression optimization model based on weak background prior by detecting homologous weak background prior interference to be suppressed, protects useful signals by sparse regularization with hyperparameters, constructs an equivalent unconstrained optimization model by using a Lagrange, obtains an iterative relationship by an alternating direction multiplier method, and calculates a closed-form solution of a low-rank component of the interference suppression model to the useful signals by a soft threshold operator. The method can well utilize information of homologous interference to complete interference suppression on a specified area in SAR data polluted by interference, and has a certain energy protection for useful signals.

The application discloses a kind of based on short-time variational modal decomposition electric signal decomposition method, comprising: step 1, obtaining initial electric signal, using pre-constructed window function to the electric signal is carried out sliding window operation, obtain the signal segment corresponding to the electric signal;Step 2, set reconstruction mode number, using variational problem to describe the mode constraint condition of each mode under sliding window signal segment, obtain constraint optimization function;Step 3, using augmented Lagrange function to carry out equivalent transformation to constraint optimization function, solve and obtain unconstrained optimization function;Step 4, reconstruct to unconstrained optimization function, obtain the instantaneous frequency-time function corresponding to each mode electric signal.This application provides a kind of electroencephalogram signal decomposition device.The method provided by the application does not need to define base function in advance, is completely driven by original signal data decomposition, can eliminate mode aliasing and edge effect problem, to obtain the complete electric signal corresponding to each rhythm.

This invention discloses a finite element method for finding the shape of a multi-span transmission line based on the BFGS optimization algorithm. The method includes the following steps: discretizing the transmission line with insulator strings using finite element methods to obtain multiple two-node rod elements; defining the endpoints of the two-node rod elements as discrete nodes, and forming a node set based on the multiple discrete nodes; constructing a total potential energy function of the system based on the node set, and using the total potential energy function as the objective function to transform the transmission line shape finding problem into an unconstrained optimization problem; iteratively solving the objective function to output the set of node coordinates that minimizes the total potential energy; calculating the axial stress of each two-node rod element by combining the material parameters and cross-sectional parameters of the transmission line and insulator strings; and using the axial stress and the final set of node coordinates as the finite element shape finding result of the transmission line.

The invention relates to the technical field of power distribution network fault positioning, and discloses a multi-scale residual convolutional neural network new energy power distribution fault positioning method and system, and the method comprises the steps: carrying out the feature extraction of a zero-sequence current, decomposing an original signal into a plurality of intrinsic mode functions through a variational mode decomposition method, and carrying out the feature extraction of a zero-sequence current; constructing an expanded Lagrange unconstrained optimization problem, and searching an optimal center frequency to minimize the bandwidth; based on a traditional convolutional neural network structure, constructing a multi-scale dynamic adaptive convolutional neural network; and combining the multi-scale dynamic self-adaptive convolutional neural network with residual learning, constructing a multi-scale dynamic self-adaptive residual convolutional network, and carrying out fault positioning. Through variational mode decomposition, a feature mode function is obtained, fault data is extracted, a multi-scale adaptive residual convolutional neural network dynamically adjusts the size of a convolution kernel, and the network learning ability is improved through residual convolution. And different faults can be accurately positioned for the new energy access power distribution network.