126 results about "Mahalanobis distance" patented technology

The application discloses a marine buoy multi-source fusion positioning method and system based on a factor graph optimization, which acquires GNSS observation data, IMU measurement data and marine environment auxiliary data; a factor graph containing state nodes, GNSS position factors, IMU pre-integration factors and marine dynamics constraint factors is constructed, and wave and current theories are used to constrain buoy movement; in view of multipath effects, marine surface reflection geometry and marine root mean square wave height are combined to calculate a multipath weighting factor, and a GNSS covariance matrix is adaptively adjusted; according to IMU data, a sea state level is discriminated, and an edge window length and a trigger interval of incremental smoothing solving are adaptively linked and adjusted; through adjacent buoy ranging information, collaborative constraints are constructed, and based on Mahalanobis distance and chi-square distribution threshold value detection, abnormalities are detected and local reconstruction is performed. The application effectively suppresses marine surface multipath interference, slows down the accumulation of calculation errors during signal interruption, and realizes high-availability continuous positioning under limited computing power.

The present application relates to a single-beacon distance circle positioning auxiliary INS navigation method based on Mahalanobis distance constraint, and belongs to the technical field of underwater auxiliary navigation research, comprising: constructing a single-beacon ranging reference map, and converting single-beacon ranging values to a two-dimensional plane; based on the converted single-beacon ranging values, constructing a distance circle with the single beacon as the center, and combining the INS calculated displacement vectors at the previous and subsequent moments to construct a target function model; determining a positioning solution based on the target function model, and when there are two positioning solutions, using a Mahalanobis distance cost function to select an optimal point to obtain a positioning position. The present application can achieve high-precision positioning in a ranging effective area and effectively suppresses the divergence of INS position errors.

The application discloses a kind of underwater vehicle degradation characterization method, belong to underwater vehicle technical field, steps are as follows: the full life cycle data collected by sensor carried on underwater vehicle is collected, data is preprocessed;Feature extraction is carried out to the data after pre-processing;Design a kind of layered cooperation particle swarm optimization algorithm based on fuzzy analytic hierarchy process, the selected feature is obtained by screening the extracted feature, and the final optimal feature combination is obtained;Dynamic correlation mahalanobis distance is used to weight and fuse the selected feature, and the fusion feature is obtained;Using the UMAP dimension reduction method with degradation perception, the degradation process is divided into three stages of early, middle and late according to the full life cycle data, an independent UMAP submodel is trained in each stage, and then the degradation index is fused by transfer learning.This application breaks through the limitation of single signal, realizes multi-component coupling degradation recognition, strengthens early degradation capture, reduces the rate of missed judgment and fault risk, has environmental dynamic adaptability, and adapts to complex deep-sea working conditions.

The application relates to the field of image processing, in particular to an iris image matching method and device, equipment and medium, which are used to solve the problem of large calculation error in the iris image matching process. The method determines a plurality of target Mahalanobis distances based on each feature point of a to-be-detected iris image. It should be noted that each target Mahalanobis distance is determined based on the gradient parameters corresponding to any two target feature points of the to-be-detected iris image. Based on the sum of the plurality of target Mahalanobis distances and the sum of a plurality of standard Mahalanobis distances, the matching degree between the to-be-detected iris image and a pre-stored standard iris image is determined, wherein the standard Mahalanobis distance is determined based on the standard iris image. The above-mentioned iris image determination method based on Mahalanobis distance considers the internal relationship between the feature points, improves the matching accuracy between the to-be-detected iris image and the pre-stored standard iris image, and improves the reliability of the safe box in use.

The application discloses a kind of big data driven wind power assembly repeated quality intelligent determination method and system.Method includes setting sensor, automation equipment and environmental monitoring instrument in wind power assembly station, obtains multidimensional original data through edge computing node, realizes data alignment with precision time protocol, is converted into unified structured data stream and carries out denoising, and outputs the assembly signal data after denoising;Establish data infrastructure layer including distributed storage and containerization arrangement;Assembly signal data is processed, and time domain, frequency domain and time-frequency domain features are extracted, combined with environmental and equipment state parameters to construct assembly quality feature vector, process using quality determination model, calculate Mahalanobis distance and compare with preset threshold value, process drift is judged by Mann-Kendall test.The application can effectively identify the repeatability quality defects and process drift in wind power assembly, improve assembly quality consistency.

The application belongs to the technical field of spectral analysis, and relates to a honey purity identification method and system based on spectral data. The method comprises the following steps: collecting an original spectrum of a to-be-tested honey sample and performing serial pretreatment to obtain a pretreated spectrum matrix; dividing the pretreated spectrum matrix into two independent chemical semantic sub-windows, independently performing principal component analysis to extract principal component scores; calculating Mahalanobis distances of the to-be-tested honey sample relative to a pure honey reference distribution in each principal component space; performing cross-window statistical standardization on the Mahalanobis distances of each window, and fusing based on a pre-determined adaptive weight to obtain a comprehensive spectral deviation value; comparing the comprehensive spectral deviation value with a discrimination threshold value, and outputting a honey purity identification result. The application decouples sugar component information and moisture information, avoids dilution of low-concentration adulteration signals in full-spectrum background noise, and improves the recognition accuracy of low-concentration adulterated honey.

The application discloses a UAV robust path planning method and system for uncertain dynamic environment, relates to the field of path planning, and realizes real-time tracking of dynamic obstacles by using EKF, and constructs a probability repulsive field based on Mahalanobis distance, effectively solves the sensing vulnerability and static model limitation of a traditional APF algorithm, and provides a robust dynamic obstacle avoidance guide for random tree expansion; secondly, a fuzzy logic adaptive step (FLC-AS) module is designed; the module intelligently adjusts the expansion step according to the risk degree of a local environment and an exploration stage, and realizes dynamic balance of exploration safety and search efficiency; comparison and analysis of the method and various mainstream algorithms show that the PFLS-RRT* algorithm has excellent adaptability in a complex environment, and achieves the best comprehensive performance in key indexes such as path quality, planning efficiency and robustness.

This invention discloses a crowdsourcing testing platform system and method based on intelligent matching. The method includes: receiving test task requests containing task description text; using a hierarchical attention network model to perform semantic understanding of the task description text, generating structured skill tags, and dynamically updating the tag confidence of testers using a Bayesian probabilistic framework; calculating the initial matching degree using a cosine similarity algorithm that incorporates a recent task completion quality correction factor, and then filtering and constructing a candidate pool; for each candidate, constructing a dynamic feature matrix, and using an improved K-nearest neighbor algorithm based on Mahalanobis distance for ranking and recommendation, where the K value is dynamically determined based on the number of candidates in the pool and the task dwell time. This invention significantly improves the efficiency and accuracy of task allocation through a capability assessment mechanism, achieving optimized allocation of testing resources.

This invention provides a method and system for rapid online detection of fertilizer nutrients based on near-infrared spectroscopy. The method includes: acquiring the online near-infrared spectrum and corresponding nutrient concentration data of the fertilizer to be tested, constructing and preprocessing a calibration set; screening characteristic wavelengths through multiple rounds of iteration: in each round, a sample subset is generated by randomly sampling from the calibration set, and a partial least squares regression model is established; determining the importance weight of each wavelength, and determining the number of wavelengths to retain by combining an exponential decay function, and screening high-weight wavelengths to obtain a candidate subset; evaluating the accuracy of the candidate subset using optimized k-fold cross-validation: calculating the leverage value and Mahalanobis distance of all samples, mapping them to a two-dimensional space and dividing them into grids; sampling and grouping by grid as a stratum, and calculating the root mean square error of cross-validation; comparing all iteration results, selecting the candidate wavelength with the smallest error as the optimal characteristic spectrum; and using the optimal characteristic spectrum and nutrient concentration data, training a quantitative prediction model for fertilizer nutrients to achieve rapid detection.

The present application relates to the radar signal processing neighborhood, specifically to a kind of target detection method based on target space-time stability.The method includes: based on the time-domain signal representation of multiple frames sliding, generate subframe by dynamic matching filter, obtain subframe peak point information, including the energy, distance, doppler information of peak point on each subframe RD spectrum;Based on the spatial signal processing of single snap angle, generate multi-subframe peak point RDA spectrum, obtain the azimuth information of peak point on each subframe RD spectrum, utilize the feature information of each subframe peak point, remove false alarm point using false alarm suppression method based on mahalanobis distance;After false alarm suppression, the result is further removed discrete false alarm point using target track based on space-time stationarity, the method proposed in the present application improves the problem of too many false alarms in the RD spectrum after traditional clutter suppression algorithm;It can effectively reduce false alarm rate while retaining weak target signal, improve target detection capability;It is suitable for multiple system radars, and the application range is wide.

This invention relates to the field of CNC machine tool cutting, and particularly to a cutting force prediction method based on cutting parameter domain adaptive transfer learning. First, a dataset of cutting force signals and cutting parameters for both the source and target domains is constructed. Second, a dimensionless feature space for the target domain is established, the source domain cutting parameters are mapped, and the geometric centroid of the target domain is calculated. Then, combining Mahalanobis distance and entropy regularization distribution alignment algorithms, a transfer weight distribution between the source and target domains is generated based on an anisotropic metric matrix. Furthermore, using a cutting force prediction model and mechanical behavior feature parameters, a robust transfer objective function composed of weighted mean and weighted standard deviation is constructed. Finally, under physical property constraints, Bayesian optimization iteratively searches for the optimal feature parameters and outputs the predicted cutting force. This invention improves the generalization accuracy under varying working conditions, suppresses negative transfer, and achieves interpretability and reliable quantification of the prediction results.

The application discloses a soil drought monitoring method based on dynamic optimization of multi-source data, relates to the technical field of soil monitoring, and comprises the following steps: delimiting a target region according to a preset rule, and constructing a multi-dimensional drought feature vector by using multi-source observation data. The probability of each cause type is obtained by calculating the Mahalanobis distance between the vector and the preset vector set centroid corresponding to different stress cause types. The same cause probability difference between the target region and the adjacent region is compared. If all the difference values are less than a preset mutation threshold, the soil drought operation path graph is generated by traversing and connecting. If there is a difference value greater than or equal to the threshold, mutation detection and resegmentation are performed on the adjacent region, and the new region corresponding to the minimum probability difference is taken as a new target for iterative calculation, so that the monitoring path is dynamically optimized, the monitoring range and path can be dynamically adjusted according to the regional heterogeneity of drought characteristics, and adaptive tracking and visual operation guidance of the soil humidity condition under complex drought causes are realized.

The present application belongs to the technical field of industrial process monitoring and fault diagnosis, and particularly relates to a kind of multidimensional data monitoring and linkage early warning method for VIGA powder production process, comprising: obtaining multidimensional time series data and dividing it into multiple data sample matrices;Sparse autoencoder model is constructed, data sample matrix is input into the trained sparse autoencoder model, historical reconstruction error sequence is obtained, its covariance inverse matrix is calculated, and abnormality judgment threshold is determined;Real-time reconstruction error of real-time data sample is calculated, real-time Mahalanobis distance reconstruction error is calculated, and when it is greater than the abnormality judgment threshold, it is determined that the VIGA powder production process is abnormal;Partial derivative is calculated, and the absolute value of partial derivative is used as abnormal contribution degree;The variable set whose cumulative contribution degree meets the preset condition is identified, and early warning information is sent out.The present application solves the problems of insufficient early abnormality capture, difficult balance of false positives and false negatives, and low abnormality disposal efficiency of existing methods.

A man-machine collaborative quality detection and early warning system for intelligent factories, comprising an edge visual acquisition terminal, a cognitive anchor generation module and a hybrid intelligent inference engine, the hybrid intelligent inference engine extracts a high-dimensional feature vector of a workpiece image using a residual network and calculates a Mahalanobis distance. When the distance is in a fuzzy decision interval, a man-machine collaboration request is triggered, and a feature heat map is displayed on the terminal. The cognitive anchor generation module receives defect key pixel points labeled by an operator, maps them to a high-dimensional feature space to construct a feature repulsion sphere, and adds the feature repulsion sphere as a regularization term to the loss function of the residual network for online fine-tuning. The scheme corrects the feature boundary in a targeted manner without changing the weight distribution of the model main body, overcomes long-tail defect missed defects, and improves the feature boundary stability of the detection model under continuous production conditions.

This invention discloses an intelligent anti-jamming method based on radar-infrared heterogeneous fusion, comprising: radar and infrared sensors performing local filtering based on their respective measurements to obtain local state estimates; constructing a set space of track mapping relationships between radar and infrared sensors, and selecting the optimal track matching pair based on a minimum cost function; adaptively configuring the fusion weights of the heterogeneous sensors according to the optimal matching result to complete the radar-infrared anti-jamming fusion; deriving variable-dimensional Mahalanobis distance based on the projection of the reliable dimension measurement space to extract spatial statistical features, and constructing a main lobe active deception interference feature dataset in conjunction with the physical law features of the measurement itself; and building a deep learning model based on a long short-term memory network to achieve accurate identification of radar main lobe active deception interference types. This invention effectively suppresses main lobe active deception interference and achieves stable tracking of real targets through the designed distributed heterogeneous fusion criterion.

This invention discloses a health assessment method and system for ultrasonic flowmeters based on Mahalanobis distance and Bayesian smoothing, belonging to the field of industrial measurement instrument operation status monitoring technology. The method includes: acquiring multidimensional operating status data of the flowmeter and fluid temperature and pressure data; extracting common-mode difference and mechanism residual features based on acoustic mechanisms to construct a high-dimensional feature vector; calculating the squared Mahalanobis distance between this vector and the healthy baseline to quantify the degree of nonlinear coupling degradation among multiple variables; mapping the distance to the original health index, then introducing a Bayesian model to perform smoothing updates based on historical priors and current observations, outputting a posterior smoothed health index; classifying health levels accordingly, and using standardized deviation (Z-Score) to extract dominant factors and trace faults when degradation occurs. This invention overcomes the shortcomings of black-box models lacking interpretability and traditional threshold methods prone to false alarms, and significantly enhances noise resistance by utilizing Bayesian smoothing, effectively reducing the false alarm rate in industrial settings and achieving accurate early fault detection and physical source tracing.

This invention provides a method and apparatus for predicting the success rate of oil and gas exploration. The method includes: quantitatively evaluating multiple oil and gas accumulation geological conditions in a study area to obtain multiple single-factor geological evaluation value maps; extracting the single-factor geological evaluation value of each well from each single-factor geological evaluation value map based on the location of multiple exploration wells in the study area; combining the single-factor geological evaluation value of each well and the type of each well into training set data; calculating the logarithmic Mahalanobis distance from each well to each well type in the training set data; drawing a two-dimensional Mahalanobis distance grid map based on the calculated logarithmic Mahalanobis distance; and calculating the oil and gas exploration success rate of each grid in the two-dimensional Mahalanobis distance grid map. This invention can accurately predict the success rate of oil and gas exploration.

The application provides a four-legged robot adaptive terrain recognition and navigation method for an explosion-proof environment, and relates to the field of high-definition positioning technology.The application quantifies endogenous disturbance and sensing uncertainty of an actuator by synchronously extracting electromagnetic torque pulsation entropy and point cloud shielding entropy rate;cross-modal feature space alignment is achieved by using bilinear interpolation, and matching is performed based on Mahalanobis distance and a high-precision semantic map;by using semantic space consistency score and a left multiplication disturbance model in a Lie group space, a pose correction vector is output to perform manifold projection correction, thereby eliminating nonlinear drift caused by skidding;high-definition navigation or a tactile stepping strategy is triggered according to positioning reliability, and driving gain is dynamically optimized in combination with energy evolution attenuation gradient.The application effectively solves the problems of sensing non-determinacy and positioning misalignment under explosion-proof working conditions, and improves the navigation robustness and sub-centimeter positioning resolution of the robot in an extreme environment.

The application relates to a rotating machinery sample unbalanced fault diagnosis method based on a latent diffusion model, characterized by comprising the following steps: obtaining a vibration signal of a rotating machinery to form a sample set; constructing and training an attention variational autoencoder to perform feature learning on the sample set, obtain an encoder and a decoder, and map a time-frequency diagram sample to a latent space by using the encoder to obtain a latent feature representation; constructing a diffusion model in the latent space to learn the feature distribution of a minority class sample and generate a preset number of minority class synthetic samples; performing sample screening, including: performing principal component analysis on the real minority class samples to construct a principal component subspace, projecting the generated samples to the principal component subspace, and adopting Mahalanobis distance to perform distribution consistency measurement, and retaining the generated samples with Mahalanobis distance not exceeding a preset threshold; and constructing a class distribution balanced enhanced data set.

The present application relates to the technical field of industrial equipment state monitoring, in particular to a multi-working-condition mechanical equipment anomaly detection method based on Gaussian mixture variational autoencoder. It comprises the following steps: synchronously collecting vibration signals and key phase information, segmenting the vibration signals according to sliding windows and performing fast Fourier transform, logarithmic compression and sample-by-sample standardization; performing aggregation, step value merging, adaptive midpoint boundary discretization and minimum residence de-bouncing on the working condition signals; constructing a Gaussian mixture variational autoencoder model based on one-dimensional convolution, and completing health period training through a loss function; in the detection stage, establishing a health baseline according to working conditions in the latent space, and taking Mahalanobis distance as an anomaly detection index; and adopting a 3σ principle to adaptively construct a threshold to realize anomaly judgment. The method can decouple working condition changes and health degradation without fault labeling, and improves the stability and engineering deployability of anomaly detection in multi-working-condition scenarios.

The application provides a kind of converter transformer fault prediction method based on deep neural network, it is related to power equipment state monitoring technical field, the steps of the method include obtaining the time series data of the concentration of dissolved gas in oil in a historical period of converter transformer, and pretreatment is carried out;Using fixed-length sliding window mechanism, the data is mapped into a supervised learning sample set, and divided into training set and test set;For the minority class samples containing fault samples and fault precursor samples in the training set, a multivariate dynamic time warping method based on Mahalanobis distance is used for time series sample enhancement, and an enhanced training set is obtained by screening;Based on the enhanced training set, a multi-class deep neural network model is constructed and trained, and the single-window prediction probability of each type of fault is output;After the data preprocessing and window division consistent with the training phase, the real-time time series data of the concentration of dissolved gas in oil is input into the trained multi-class deep neural network model, and the final fault type is output.

The application discloses a sparse positive sample risk discrimination method and system based on cluster analysis, relates to the technical field of data processing, and comprises the following steps: obtaining positive samples and negative samples of a historical clinical data set, performing double evaluation on the historical clinical data through a feature evaluation model to obtain a target feature subset; projecting the negative samples to the target feature subset to obtain a feature space, performing cluster analysis to determine a plurality of data subgroups and a plurality of cluster centers, determining a corresponding anomaly detection model for each data subgroup, determining the local anomaly scores of the corresponding data subgroups through the anomaly detection model; calculating the Mahalanobis distance between the to-be-tested sample and each cluster center, determining the main subgroups and adjacent subgroups corresponding to the to-be-tested sample; determining the anomaly scores corresponding to the main subgroups and the adjacent subgroups; determining a verification set according to the positive samples, performing index maximization processing according to the verification set to determine a decision threshold, comparing the anomaly scores with the decision threshold, and obtaining a risk discrimination result.

The application discloses a marine buoy multi-source fusion positioning method and system based on a factor graph optimization, which acquires GNSS observation data, IMU measurement data and marine environment auxiliary data; a factor graph containing state nodes, GNSS position factors, IMU pre-integration factors and marine dynamics constraint factors is constructed, and wave and current theories are used to constrain buoy movement; in view of multipath effects, marine surface reflection geometry and marine root mean square wave height are combined to calculate a multipath weighting factor, and a GNSS covariance matrix is adaptively adjusted; according to IMU data, a sea state level is discriminated, and an edge window length and a trigger interval of incremental smoothing solving are adaptively linked and adjusted; through adjacent buoy ranging information, collaborative constraints are constructed, and based on Mahalanobis distance and chi-square distribution threshold value detection, abnormalities are detected and local reconstruction is performed. The application effectively suppresses marine surface multipath interference, slows down the accumulation of calculation errors during signal interruption, and realizes high-availability continuous positioning under limited computing power.

The technology described herein is directed towards workload prioritization (ranking) in a cloud (e.g., private / hybrid) environment based on multi-criteria decision analysis using Mahalanobis distance-based variance-covariance matrix that takes into account the pair-wise correlation between criteria attributes from a dataset. The technology described herein calculates relative closeness values for alternatives (e.g., virtual machines), and can perform a final ranking of a group of virtual machines based on their associated relative closeness values. The workload prioritization process can be incorporated into a decision engine. The decision engine can be used in various use cases, including backup prioritization, shutdown prioritization during power failures, workflow scheduling prioritization, and the like.

A method and system for identifying the critical transformation risk of an ecosystem based on multi-source remote sensing vegetation indicators are disclosed. The method includes: S10: acquiring and preprocessing vegetation time-series data of the study area; S20: performing signal separation based on multiple time-series decomposition methods; S30: selecting the best separation result from the multiple time-series decomposition methods; S40: calculating statistical indicators for early warning of critical transformation; S50: performing linear trend analysis on the time series of early warning indicators for each pixel, and calculating the slope b of the indicator value changing over time using the least squares method; S60: directly summing the trend values ​​b of each indicator obtained in step S50 to obtain the pixel-scale consistency score CS; S70: constructing a multi-indicator covariance matrix; calculating the standard deviation MS of the Mahalanobis distance time series; S80: constructing a critical transformation risk index R, and judging the critical transformation risk of the ecosystem in the study area based on R.

The application relates to the technical field of SCGD-OES online detection, and specifically provides a multi-element online quantitative method, system, equipment and medium of a high-salt matrix solution, which comprises the following steps: synchronously collecting multi-modal data; constructing a state vector according to the multi-modal data; calculating a stability index through robust principal component analysis and Mahalanobis distance; combining with working condition parameters to distinguish the working condition and the stability state; and adaptively selecting a quantitative analysis mode; under the working condition constraint, inputting spectral line characteristics into a segmented weighted least square regression model which is fused with monotonicity constraint, multi-spectral line consistency and self-absorption / quenching penalty term, compensating for the matrix effect and calculating the concentration; and finally, fusing the stability index, spectral line consistency deviation and model residual error to calculate the comprehensive confidence, and outputting the concentration and the confidence. The application improves the accuracy, robustness and result reliability of multi-element online analysis under high-salt, dynamic and nonlinear complex working conditions.

According to one aspect, a computer-implemented method for generating an anomaly detection model in a system is proposed. The method comprises: - obtaining (10) a training data matrix corresponding to the normal operation of said system, - decomposing said training data matrix into singular values ​​(11), - calculating (12) a new basis (V'), - defining (16) a maximum Mahalanobis distance threshold representing a limit of the normal operation of said system, - defining an anomaly detection model (MDL) from said new basis (V') and said maximum Mahalanobis distance threshold (MTS). Figure for the abstract: Figure 1

The application relates to a single-phase ground fault early warning method and system based on dynamic clustering analysis, in the system, a data acquisition module collects real-time recording wave data of three-phase current and zero sequence current, and a characteristic waveform is constructed based on the recording wave data; a multi-scale feature extraction module calculates a plurality of dimensions of current feature vectors based on the characteristic waveform, normalizes the plurality of dimensions of current feature vectors, and generates a high-dimensional feature vector; an adaptive dynamic clustering module performs offline spectral clustering based on historical data to obtain an initial cluster; a local neighborhood graph is established with the initial cluster center as a node; a mode migration tracking module captures the dynamic change path of a new sample in a feature space based on the high-dimensional feature vector, calculates a mode migration recognition index and a Mahalanobis distance value; and a multi-level early warning decision module executes multi-level early warning determination based on the mode migration recognition index and the minimum Mahalanobis distance value, and generates corresponding early warning events when different early warning conditions are met.

This invention relates to the field of computational toxicology, and in particular to a precise method for comparing the consistency of animal and non-animal toxicity evaluation results. This method acquires in vivo baseline data from animals and in vitro test data from non-animals. It employs a dynamic time warping algorithm and radial basis function kernel function to construct correction coefficients and perform equivalent mapping to generate a converted sequence. Based on a binary classification mapping of toxicity thresholds, a confusion matrix is ​​constructed to calculate sensitivity, specificity, and predicted values. Each indicator is treated as an independent source of evidence, and the Mahalanobis distance is calculated using the covariance matrix to generate a basic probability allocation function. The D-S evidence theory combination rule is applied for fusion, and a secondary factor allocation is introduced when there is conflict. Finally, the result is compared with a preset threshold to determine the feasibility of substitution. This invention adaptively eliminates the nonlinear misalignment difference between in vivo and in vitro dose responses, providing an objective quantitative judgment standard for toxicological substitution verification.

The equal-potential grounding grid anomaly detection method based on dynamic weighted Mahalanobis distance provided in the application relates to the technical field of power system safety monitoring. The method collects current data of each monitoring point to establish a time series data set, uses the 2 sigma criterion to clean up the data and calculate the relative deviation rate, eliminates the dimension difference through normalization, designs fluctuation weight coefficient, single-point abnormality variable weight coefficient and global same-direction attenuation weight coefficient to construct a composite weight system, and combines iterative optimization to determine a dynamic threshold, so as to realize accurate identification of the abnormal state of the grounding grid. The application can effectively distinguish normal load fluctuation from a real abnormal state, and improve the accuracy and reliability of the grounding grid anomaly detection.