48 results about "Noise sensitivity" patented technology

The invention particularly relates to a binocular vision-based three-dimensional reconstruction method, which comprises the following steps of: calibrating a binocular camera based on an improved Zhang Zhengyou calibration method to obtain internal and external parameters and a distortion coefficient of the camera; performing stereo correction on the image by using the internal and external parameters of the camera and the distortion coefficient obtained by calibration, so that the binocular image meets an epipolar constraint condition; a multi-strategy optimized semi-global stereo matching algorithm is adopted to process the image after stereo correction, and a disparity map is generated; based on the generated disparity map, generating a three-dimensional point cloud through a triangulation principle; carrying out anti-interference processing and registration optimization on the three-dimensional point cloud; and performing global splicing on the three-dimensional point clouds subjected to anti-interference processing and registration optimization based on a sequential registration error sharing strategy to complete three-dimensional reconstruction. According to the method, the key problems of large calibration error, weak texture matching failure, point cloud noise sensitivity and registration accumulative error in a traditional method are solved, and the reconstruction precision and stability are remarkably improved.

The invention provides a video content enhancement method for a low-illumination environment, and the method comprises the steps: achieving the data preprocessing based on an original low-illumination video frame sequence through frame synchronization, color space conversion and local brightness analysis, generating a noise sensitivity thermodynamic diagram through multi-feature unsupervised learning, and constructing a noise perception gating mechanism through the combination of affine transformation. Dynamic modulation of the characteristic channel is realized; in the multi-scale network structure, a channel attention module is used for carrying out layer-by-layer self-adaptive adjustment on a noise sensitive area; a basic illumination image and an edge enhancement image are generated through double-branch decoding, and then weighted fusion is carried out in combination with a noise thermodynamic diagram, so that brightness balance and detail enhancement are realized; a noise smoothing regular term is introduced during end-to-end training, so that the network achieves dynamic balance between an enhancement effect and noise control.

The application relates to the technical field of system-in-package, and discloses a functional chip SIP (System in Package) system-in-package method and system. The method constructs a reduced-order discrete thermal state predictor through multi-order exponential attenuation fitting, generates a DVFS gear-noise hazard degree spectrum mapping table based on a synchronous switching noise spectrum and an ADC noise sensitivity curve, generates a multi-DVFS working condition robust grounding network topology by optimizing a narrow bridge connection structure parameter by using a sequential quadratic programming, quantizes equivalent noise interference amounts of each DVFS gear on an ADC chip, and jointly optimizes DVFS gear selection and power consumption upper limit distribution under a rolling time domain mixed integer quadratic programming framework, simultaneously performs online model correction through exponential weighted moving average and Kalman filtering, and realizes cooperative satisfaction of thermal constraints and noise constraints.

A kind of atomic gyroscope pumping rate stable composite control method based on phase reshaping extended state observer and power approaching sliding mode control.Aiming at the problems that standard linear extended state observer has steady-state estimation error under the action of ramp disturbance, disturbance estimation phase lag and it is difficult to balance between observation bandwidth improvement and noise sensitivity, a composite corrector composed of lead network and lag network is cascaded at the output end of disturbance estimation of extended state observer, the disturbance estimation channel is shaped in frequency domain, phase lead is provided in mid-frequency band to reduce compensation delay, amplitude lag characteristic is used to suppress high-frequency noise, and parameter constraint design is used to realize zero-error estimation of ramp disturbance;At the same time, a power approaching sliding mode controller is constructed to improve the adaptability to the nonlinear, internal and external coupling and parameter uncertainty of atomic gyroscope system, and the phase reshaping extended state observer is combined to effectively estimate and feed forward compensate the lumped disturbance, so as to improve the stability and accuracy of pumping rate control.The present application can balance dynamic anti-disturbance performance, steady-state control accuracy, convergence speed and noise robustness without significantly improving the observation bandwidth, and is suitable for atomic gyroscope precision control system affected by ultra-low frequency slowly varying disturbance.

The invention provides a medical invoice edge detection model construction method and device, equipment and a medium, and the method comprises the steps: obtaining a medical invoice image set, and marking the invoice semantic anchor point of each medical invoice image in the medical invoice image set, so as to construct a sample set; the mask auto-encoder is improved, and an optimized mask auto-encoder is obtained; performing iterative training on the optimized mask auto-encoder by using the sample set to obtain a trained mask auto-encoder, and extracting a multi-layer residual network from the trained mask auto-encoder; constructing an initial edge detection model based on a multi-layer residual network and a double-branch attention fusion module; and training the initial edge detection model by using the sample set to construct a medical invoice edge detection model. By adopting the medical invoice edge detection model construction method and device, the equipment and the medium, the noise sensitivity is reduced, the edge feature extraction capability is improved, and the image detection precision is improved.

The invention discloses a silence cabin intelligent control method and system based on an AI digital matrix, relates to the field of silence cabin intelligent control, and constructs a high-dimensional silence cabin multi-modal feature tensor, namely the AI digital matrix, by obtaining multi-source heterogeneous data such as environment, biological features and equipment states and using time synchronization, matrix construction and normalization cleaning technologies. On the basis, performing user activity scene semantic analysis on the feature tensor to generate an activity weight vector reflecting the current demand of the user; and then prediction modeling of the acoustic-thermal coupling effect is carried out based on the weight vector, optimization is carried out in a prediction result set by using a multi-target Pareto optimal algorithm, and optimal control parameters giving consideration to noise sensitivity, thermal comfort and energy consumption are calculated. And finally, a PWM signal is generated through closed-loop feedback to drive a fan and light, so that the breathing effect of the fan is eliminated on the physical level, and active precise regulation and control of the environment of the mute cabin are realized.

This invention relates to an efficient particle sphere generation method based on principal component analysis (PCA), belonging to the field of quantum computing. It solves the problem of low data representation efficiency caused by excessive segmentation and noise sensitivity in existing particle sphere algorithms. The technical solution includes: initializing the particle sphere set using a parallel sampling strategy; calculating the splitting gain and setting a threshold; calculating the optimal splitting direction based on the PCA core sample set; splitting the particle spheres along the principal direction and iteratively updating the set. This method achieves efficient data compression, reduces computational complexity, enhances the representation ability of complex geometric structures, and has strong robustness.

This invention discloses a method for estimating the speed and position of a permanent magnet synchronous motor (PMSM) based on a third-order switched extended state observer. Specifically, based on the mathematical model of the PMSM, a back-EMF observer based on a sliding mode observer is constructed to obtain the estimated back-EMF. Further, the estimated back-EMF signal is processed using a low-pass filter and amplitude normalization. The processed back-EMF is then used as the input signal to a position estimation scheme based on the third-order switched extended state observer, achieving accurate estimation of the PMSM's speed and position under different operating conditions. This invention is simple in principle and easy to implement. It combines the advantages of both third-order linear and third-order nonlinear extended state observers, improving estimation accuracy and dynamic performance while reducing the adverse effects of noise on the estimation scheme. This solves the technical problems of low estimation accuracy, high noise sensitivity, and difficulty in parameter tuning in existing estimation schemes.

The invention discloses an energy storage converter virtual inertia control method based on a heterogeneous second-order generalized integrator-frequency locked loop (HSOGI-FLL), and aims to solve the problems that in virtual inertia control of an existing energy storage converter, power grid angular frequency operation often needs to be depended on to provide control input, and noise interference is easy to introduce in frequency differential operation, and implementation is complex. The invention discloses the energy storage converter virtual inertia control method based on the heterogeneous second-order generalized integrator-frequency locked loop (HSOGI-FLL). According to the method, on the basis of a typical SOGI-FLL control structure, different SOGI output signals are adopted to construct an FLL control loop, an HSOGI-FLL structure is formed, power grid angular frequency differential signals can be directly and accurately extracted, and power grid angular frequency differential operation does not need to be carried out. According to the method, noise sensitivity and implementation complexity caused by power grid angular frequency differential operation can be avoided, reliable input signals are provided for virtual inertia control of the energy storage converter, then the energy storage converter can effectively provide virtual inertia support for a power grid, and the method can be suitable for the field of grid-connected control of various energy storage converters.

The invention discloses a crack three-dimensional accurate quantification method and system based on semantic point clouds, which are used for solving the problems of skeleton extraction distortion, tail end missing, noise sensitivity and insufficient multi-scale fusion in the existing crack quantification method, and the method comprises the steps: obtaining three-dimensional point cloud data with crack semantic tags, and carrying out the denoising and smoothing preprocessing; segmenting independent crack individuals through a density-based clustering algorithm; dynamically extracting skeleton points by adopting a curvature weighted L1 median algorithm, and adaptively adjusting the point density according to the curvature; skeleton end points are complemented from the original point cloud through main direction projection; calculating crack length, width, direction and type parameters based on the complete skeleton point set; the system correspondingly comprises a point cloud preprocessing module, a segmentation module, a skeleton extraction optimization module, a parameter calculation module and the like. According to the method, high-precision and automatic three-dimensional quantification of a crack structure with complex bending and strong noise interference is realized, and the accuracy, the integrity and the anti-noise capability of skeleton extraction are remarkably improved.

This application provides a hierarchical sensitivity-adaptive model smooth annealing quantization training method and apparatus, relating to the field of artificial intelligence technology. The method includes: determining quantization noise sensitivity based on the trace of the Hessian matrix; determining the annealing temperature based on the quantization noise sensitivity and the current training step number; determining multiple logical values ​​based on the distance between the weights to be quantized and multiple discrete quantization center points; converting the logical values ​​into a probability distribution based on the annealing temperature and a normalized exponential function; and obtaining the quantization weights by weighted summation of the multiple discrete quantization center points based on the probability distribution. The method and apparatus provided in this application determine the sensitivity of each layer through the trace of the Hessian matrix and adaptively adjust the annealing rate, solving the problems of low optimization efficiency and accuracy loss; by fitting the quantization function using a normalized exponential function, a smooth gradient path is constructed, solving the gradient mismatch problem; enabling large language models to have high model performance at extremely low bit compression rates.

The invention relates to the technical field of medical imaging, in particular to a self-supervised deep learning magnetic resonance image reconstruction method and device and electronic device.The method comprises the steps that multi-channel k-space data are acquired, the multi-channel k-space data comprise multiple pieces of parallel magnetic resonance acquired k-space data, and the k-space data comprise magnetic resonance images; and based on the multi-channel k space data, carrying out self-supervised training on a pre-established expanded neural network. In the training process, a single-channel image is generated, an under-sampling mask is applied to a discarded coil, the single-channel image and the under-sampling mask serve as network input, and a network is supervised and trained through an under-sampling matrix. And reconstructing a magnetic resonance image by using the trained expanded neural network. Therefore, the problems of complicated calculation, sensitivity to noise, dependence on a large amount of full sampling data and the like in related technologies are solved.

This invention relates to a weakly supervised video anomaly detection method based on a label noise perception strategy, comprising the following steps: S1, video feature extraction; First, 16 consecutive frames of a video are input as a segment into a feature extractor to generate a feature map of size 32×256×512. Subsequently, the text information of the anomaly type is encoded into a 32×256×14 text embedding, wherein there are 14 anomaly types. By matching the text embedding of the anomaly type with the corresponding video frame features, and inferring pseudo-labels based on the matching similarity, this invention breaks through the limitations of the traditional self-training paradigm from the perspective of label noise learning, breaks the inherent mode of the traditional video anomaly detection self-training framework, and proposes a method for generating pseudo-labels online in an end-to-end manner, solving the problems of error accumulation and noise sensitivity in video anomaly detection pseudo-labels.

This invention discloses a method and system for calculating the sensitivity of an electromagnetic environment monitoring system based on link configuration in low-temperature environments, belonging to the field of electromagnetic environment monitoring technology. The method includes: determining the monitoring scenario and link configuration of the electromagnetic environment monitoring system, and selecting a calculation method based on the determined monitoring scenario and link configuration; collecting parameters of each component of the electromagnetic environment monitoring system; if the monitoring scenario is an extreme environment, determining the correction coefficient kt corresponding to the ambient temperature and the actual operating temperature of each component of the electromagnetic environment monitoring system; and calculating the sensitivity of the electromagnetic environment monitoring system using the selected calculation method, the component parameters, the correction coefficient kt, and the actual operating temperature. This invention solves the problem that existing calculation methods do not distinguish between signal sensitivity and noise sensitivity calculation scenarios, leading to insufficient monitoring accuracy in special fields.

The invention discloses a high-order phase velocity frequency dispersion calculation method, which comprises the following steps: after obtaining subarray background noise cross-correlation function data, calculating a high-order phase velocity frequency dispersion spectrogram through a CCBF algorithm, retaining causal part signals and removing aliasing, and obtaining a CCBF spectrogram after aliasing removal; performing non-uniform sampling on the CCBF spectrogram by combining a compressed sensing theory according to the sparse characteristic of effective frequency band signals in the dealiasing CCBF spectrogram to obtain under-sampling data; reconstructing the undersampled data according to an iterative shrinkage threshold algorithm of a multi-scale hybrid wavelet basis function to obtain a reconstructed wavelet domain CCBF high-order phase velocity spectrogram; and threshold processing of incompressible random noise is carried out on the reconstructed wavelet domain CCBF high-order phase velocity spectrogram, and a final CCBF high-order phase velocity frequency dispersion calculation result is obtained. According to the method, the resolution and the signal-to-noise ratio of the frequency dispersion spectrogram are remarkably improved, and the noise sensitivity is reduced.

This invention provides a hate video detection method based on a multimodal pattern library and a hierarchical complementary gating mechanism, belonging to the field of multimodal learning technology. The method includes: acquiring textual, visual, and audio features of a video through a multimodal feature extraction module and mapping them to a unified space; constructing a multimodal pattern library using a large language model, refining massive training samples into a compact and interpretable high-level semantic prototype set; injecting semantic priors through a pattern library retrieval and feature enhancement module; employing a hierarchical complementary gating mechanism to dynamically allocate modal weights with text as the semantic anchor, achieving selective fusion of audio and visual features; and finally training the model using a composite loss function to complete hate video detection. This invention solves the problems of modal competition, visual noise sensitivity, semantic ambiguity in instance-level retrieval, and high computational overhead caused by symmetric fusion in existing methods, significantly improving detection accuracy and efficiency, and enhancing model robustness and generalization ability.

This invention relates to the field of microgrid operation anomaly monitoring technology, and in particular to a method, device, equipment, and computer storage medium for monitoring microgrid operation anomalies in industrial parks. The method for monitoring microgrid operation anomalies in industrial parks proposed by this invention includes: firstly, constructing a spatiotemporal coupling matrix to achieve collaborative analysis, accurately characterizing the dynamic coupling relationship between power load and pedestrian flow distribution in the park; secondly, designing an anomaly detection model based on bidirectional LSTM to reduce false alarms and missed alarms caused by noise sensitivity in complex spatiotemporal coupled data; and finally, proposing a dual-modal training and dynamic threshold generation scheme to solve the problem that fixed threshold mechanisms cannot be adjusted according to changes in park activity scenarios, effectively improving the accuracy of the algorithm.

This invention relates to the field of computer vision technology, specifically disclosing a robust point cloud registration method and system based on block-aware serialization spatial learning. Addressing the problems of high computational complexity, noise sensitivity, and poor registration performance in partially overlapping scenes, existing methods employ a point cloud registration network comprising a segmentation and serialization module, a backbone network (encoder-decoder structure), and a dual-dominating head. The segmentation and serialization module divides the point cloud into multiple independent blocks and serializes them to maintain spatial locality; the encoder extracts multi-scale block-level features layer by layer; the decoder further aggregates contextual information; and the dual-dominating head predicts rotation quaternions and translation vectors respectively. Experiments show that this invention outperforms traditional iterative methods and existing deep learning models in registration accuracy, maintains stable performance in noisy environments and low-overlap scenes, and possesses high inference efficiency and low memory usage.

The invention belongs to the field of signal processing, and discloses an analog signal valley point mode recognition method and a related system.According to the method, through multi-dimensional feature extraction, first-order difference, short-time energy, cepstrum analysis and other methods are complementarily fused, the richness of feature representation is enhanced, and the recognition accuracy is improved. And the limitation that a single feature is sensitive to noise or depends on window parameters is relieved. In the core candidate detection link, an improved wavelet modulus maximum method is adopted, a self-adaptive threshold value is combined on the basis of multi-scale decomposition, screening conditions can be automatically adjusted according to the signal noise level, noise interference is effectively filtered out, real feature points are reserved, and therefore the detection robustness is remarkably improved. According to the method, pseudo valley point elimination is carried out on candidate valley points by using the bidirectional LSTM network, so that screening of the candidate points is not limited to single-point amplitude comparison any more, comprehensive discrimination is carried out through learning of context time sequence features, and the reliability and accuracy of a final identification result are greatly improved.

The application provides a photometric curve anomaly detection method based on a long short-term memory network and relates to the technical field of intelligent perception of space targets. In view of the problems of dependence on labeled data, noise sensitivity and insufficient local anomaly capturing capacity in the prior art, a high-precision anomaly recognition is realized through the construction of an unsupervised learning framework. The long short-term memory network is used for modeling the time sequence dependence relationship, and a time attention mechanism is introduced to dynamically focus on key time steps, so that the anomaly detection precision of the model is improved. The application provides an efficient solution for space target abnormality perception and is suitable for real-time monitoring of complex scenes such as geosynchronous orbits and earth-moon space.

This invention specifically relates to a method for analyzing the structural strength sensitivity of automotive generator assemblies. The method first constructs a finite element model of the generator assembly and calculates its unit radial and torsional stiffness coefficients; then, it constructs an acoustic simulation model and obtains a dataset of the full-frequency sound transfer function of the structural surface through full-band frequency sweep simulation; next, it calculates the single-frequency noise sensitivity coefficient and combines it with the stiffness coefficient to obtain the overall noise sensitivity coefficient; finally, it completes the sensitivity analysis and performance level assessment of the structural strength's impact on noise through preset rating rules. This invention eliminates the need for complex multi-physics coupling simulations and physical prototypes, enabling fully digital analysis and risk prediction to be completed early in the design process, significantly shortening the product development cycle and providing standardized support for low-noise forward design of generators.

This invention belongs to the field of proton exchange membrane fuel cell (PEMFC) state monitoring technology, and discloses a method for reconstructing the internal current density distribution of a PEMFC based on a physical information neural network. The method includes constructing an electro-magnetic dataset of the internal current distribution and external magnetic field distribution of the PEMFC under different operating conditions; constructing a physical information neural network model, embedding Biot-Savart's law as a physical loss into the network loss function; training the physical information neural network model using the loss function, and obtaining the trained physical information neural network model when the loss function converges. In practical applications, the current external magnetic field distribution of the PEMFC is input into the trained physical information neural network model to obtain the reconstructed internal current density distribution. This invention solves the problems of ill-posedness and noise sensitivity of traditional inversion methods, and achieves high-precision, non-invasive real-time monitoring of the internal state of the PEMFC.

The application discloses a dynamic scene visual SLAM method based on a Transformer and multi-modal fusion, and relates to the technical field of real-time positioning and map construction. The method extracts an initial semantic mask by using a semantic segmentation network based on the Transformer, and performs time sequence consistency optimization through a ConvLSTM; then, a light flow dynamic mask is generated by using adaptive morphological erosion; meanwhile, a geometric consistency mask is constructed based on a re-projection error, a triangulation error and a depth consistency error; finally, the masks of the three modes are weighted and fused according to the accuracy of a verification set, and a high-reliability dynamic region mask is generated through a multi-condition judgment rule. Through the complementation and fusion of multi-modal information, the defects of single mode in the dynamic scene, such as inaccurate recognition, noise sensitivity and insufficient stability, are effectively overcome, and the positioning robustness and mapping precision of the visual SLAM in a complex dynamic environment are significantly improved.

The invention belongs to the technical field of proton exchange membrane fuel cell state monitoring, and discloses a proton exchange membrane fuel cell internal current density distribution reconstruction method based on a physical information neural network, and the method comprises the steps: constructing an electric-magnetic data set of PEMFC internal current distribution and external magnetic field distribution under different working conditions; constructing a physical information neural network model, and embedding the Biot-Savart law into a network loss function as physical loss; and training the physical information neural network model by adopting a loss function, and when the loss function converges, obtaining a trained physical information neural network model. And during practical application, inputting the external magnetic field distribution of the current PEMFC into the trained physical information neural network model to obtain reconstructed internal current density distribution. According to the method, the problems that a traditional inversion method is not qualitative and sensitive to noise are solved, and high-precision and non-intrusive real-time monitoring of the internal state of the PEMFC is achieved.

The application relates to the technical field of infrared thermal wave nondestructive testing and material thermal physical property measurement, in particular to a high-precision thermal diffusivity inversion method based on a multi-terminal deep neural network. The application aims to solve the problems of low calculation efficiency, strong noise sensitivity and insufficient robustness in the traditional thermal diffusivity measurement method, and proposes a high-precision thermal diffusivity inversion method based on a multi-terminal deep neural network for materials containing damage defects. Specifically, the application uses a phase-locked thermal imaging technology to extract the amplitude and phase of the thermal wave, and obtains stable characteristics describing the thermal diffusion process. A deep learning network is constructed with spatial coordinates, excitation frequency, surface temperature information, amplitude and phase as inputs. Through multi-modal data fusion, advanced direct current component removal technology and multi-terminal deep neural network architecture, efficient and accurate measurement of the thermal diffusivity of complex materials is realized.

In order to solve the problems that according to an existing energy storage converter virtual inertia control method, a power grid angular frequency differential signal needs to serve as input, noise is likely to be introduced in a differential operation link, and implementation complexity is high, the invention discloses a virtual inertia implementation method based on a reconstructed second-order generalized integrator-frequency locked loop (RSOGI). According to the method, on the basis of a typical SOGI-FLL control architecture, the mathematical operation relation of output signals of the typical SOGI-FLL control architecture is reconfigured, a frequency-locked loop control loop is constructed, an RSOGI-FLL architecture is formed, power grid angular frequency differential signals can be accurately extracted, and therefore differential operation does not need to be carried out on the power grid angular frequency. According to the method, the problems of noise sensitivity and implementation complexity caused by angular frequency differential operation are effectively avoided, reliable input signals are provided for virtual inertia implementation of the energy storage converter, the energy storage converter can effectively provide virtual inertia support for a power grid, and the method can be widely applied to grid-connected control scenes of various energy storage converters.

The application discloses a vehicle drivable area segmentation method and related device. The vehicle drivable area segmentation method comprises: segmenting current frame visual data collected by a vehicle to obtain boundary positions of drivable areas and non-drivable areas in the current frame visual data; obtaining current signed distance of each data point in the current frame visual data from the boundary positions to constitute a current frame signed distance field, the numerical sign of the current signed distance corresponding to the drivable data point being opposite to that of the current signed distance corresponding to the non-drivable data point; fusing the current frame signed distance field with a previous fusion signed distance field to obtain a current fusion signed distance field, the previous fusion signed distance field being obtained based on at least one previous frame visual data collected by the vehicle; and segmenting the current fusion signed distance field to obtain a current fusion drivable area. The above scheme can improve the drivable area accuracy, the adaptability to dynamic obstacles and the noise sensitivity.

The invention belongs to the field of thermal management of direct-current charging equipment, and particularly relates to a charging pile and a noise reduction control method and system thereof. Comprising the following steps: controlling a system fan of the charging pile to be switched to a noise control mode and a standard mode according to the noise sensitivity level of the current time period; in the standard mode, obtaining a first duty ratio value and a second duty ratio value corresponding to the current environment temperatures at the air inlet and the air outlet of the charging module and obtaining a total duty ratio value according to the first relation and the second relation between the environment temperatures at the air inlet and the air outlet corresponding to the standard mode and the duty ratios; in the noise control mode, according to the relation between the environment temperature corresponding to the noise control mode and the duty ratio, a third duty ratio value corresponding to the environment temperature at the current air outlet of the charging module is obtained, and the total duty ratio value is obtained; controlling the cooling fan to operate according to the total duty ratio value; a relation interval in which the duty ratio is increased along with the increase of the environment temperature exists in the relations; the total duty ratio in the standard mode is larger than that in the noise control mode and is smaller than or equal to 100%.

The invention relates to the technical field of computers, in particular to a deployment method and device of a neural network on a simulation, storage and calculation integrated system, and the method comprises the steps: calculating the Hessian trace of a neural network model according to the type, parameter scale and topological structure information of each layer of the neural network model, so as to obtain a layer noise sensitivity sorting list; executing a preset self-test process on a cross array of the target simulation storage and calculation integrated system according to the hardware configuration information to obtain an array noise level sorting list of the cross array; and mapping the neural network model to at least one cross array according to the layer noise sensitivity ranking list and the array noise level ranking list to complete deployment of the neural network model on the target simulation storage and calculation integrated system. Therefore, the problem that available storage and calculation resources are idle and wasted due to the fact that part of storage and calculation arrays cannot participate in a neural network calculation task due to the fact that the storage and calculation arrays are screened and shielded through a fixed threshold value in correlation calculation is solved.

To solve the problems of traditional virtual synchronous generator (VSG) such as insufficient disturbance rejection ability, noise sensitivity and limited dynamic performance under complex working conditions, a control strategy combining linear active disturbance rejection control (LADRC) and improved adaptive filter algorithm is proposed. By establishing the equivalent model of VSG, virtual inertia and droop control are introduced to reconstruct the operation characteristics of inverter synchronous generator. LADRC is used in the voltage loop to estimate and compensate the internal and external disturbances of the system using the extended state observer, thereby improving the robustness of the system. To solve the noise amplification problem caused by the increase of the observer bandwidth, an LMS adaptive filter is introduced to preprocess the error signal, and a variable step-size LMS algorithm based on the optimized Sigmoid function is used to balance the convergence speed and steady-state accuracy. Finally, a "VSG+LADRC+improved LMS" integrated control architecture is constructed. The simulation and experimental results show that the proposed method significantly improves the disturbance rejection ability and dynamic response under off-grid and on-grid switching and load disturbance, and has good engineering application value.