779 results about "Estimation result" patented technology

The invention relates to the technical field of bolt tightening, and provides an intelligent bolt tightening control method and system based on axial force measurement. Comprising the steps of collecting bolt identification and process parameter data, collecting temperature measurement data, and obtaining sound velocity compensation parameters and elastic modulus compensation parameters. And zero-load preloading data are collected and processed to generate zero-load baseline data, and a self-calibration model is obtained. Axial force data and ultrasonic echo data are collected, and an axial force fusion estimation result is obtained. And comparing an axial force fusion estimation result with target axial force data. And when in the target interval, fine twisting control is carried out based on model predictive control and a micro-stepping strategy, and the controllable damping unit is driven to carry out energy absorption and stopping. And acquiring an axial force fusion estimation result when the target axial force is reached, processing the data in the holding stage to obtain an axial force rebound check result, and if the axial force rebound check result exceeds the limit, performing secondary twisting control. According to the scheme, refinement and traceability of the bolt tightening process are achieved.

The invention relates to an intelligent measurement and control optimization method and device for dynamic parameter adaptive calibration, equipment and a medium. The method comprises the following steps: executing invariance causal test based on an external environment context to obtain a cross-environment invariant explanatory variable subset, and performing anti-fact simulation on each parameter in the cross-environment invariant explanatory variable subset to generate a causal attribution report; based on an under-excitation parameter subset and a cross-environment invariant explanatory variable subset in the baseline recognizable atlas, performing safe active excitation planning on the parameters to obtain a safe micro-perturbation excitation plan; and based on the residual error, the uncertainty estimation, the delay cross-correlation feature, the hysteresis loop area feature, the causal contribution score and the excitation-response fragment, performing calibration estimation on the target parameter by using a hierarchical estimator, and generating a calibration packet according to a calibration estimation result. By adopting the method, self-adaptive calibration of intelligent measurement and control dynamic parameters can be realized through residual attribution and cross-environment invariance test in combination with safe perturbation excitation.

The invention discloses a power distribution network topology state estimation method, electronic equipment, a medium and a product. The method comprises the steps of obtaining a topological structure and measurement data of a power system; constructing variable nodes and factor nodes according to the topological structure and the measurement data, and constructing a state-topological joint factor graph model according to the variable nodes, the factor nodes and the topological structure; based on the state-topology joint factor graph model, performing state estimation through a belief propagation algorithm to obtain an estimated value of state variable correction; if the estimated value of the state variable correction meets the convergence condition, correcting the topological state of the switch branch according to the active power and reactive power of the head end of the switch branch in the estimated value of the state variable correction; and outputting an estimation result of the topological state of the switch branch until the on-off state of the switch branch obtained according to the state variable is consistent with the original topological state of the switch branch. According to the method, asynchronous real-time updating of the topological state of the power system can be realized.

The invention discloses an Internet of Things equipment real-time early warning method and system based on digital twinning, and relates to the technical field of equipment operation management, and the method comprises the steps: collecting multi-modal original data of Internet of Things equipment, constructing a graph structure, and generating a semantic graph vector; obtaining a digital twinborn model state corresponding to the target equipment, forming an extended state vector by the digital twinborn state, the physical equipment state and the semantic map vector, and inputting the extended state vector into an extended Kalman filter for state fusion to obtain a state estimation result; and performing Monte Carlo simulation according to the state estimation result, generating a plurality of abnormal state samples, calculating a residual mean value between the abnormal samples and the current estimation result, correcting a covariance parameter of the extended Kalman filter, and generating an early warning tag. Fine estimation and risk level early warning of the state of the Internet of Things equipment are realized, and the state fusion precision and the abnormal response timeliness are improved.

The invention discloses a lightweight human body posture estimation method based on PLES-YOLO, and belongs to the field of computer vision, and the method comprises the following steps: carrying out the feature extraction of an input image through employing an improved down-sampling module, and obtaining an initial feature map; based on the initial feature map, a multi-scale feature fusion module is adopted to carry out progressive feature enhancement, and multi-scale fusion features are obtained; based on the multi-scale fusion features, performing feature optimization by adopting a spatial pyramid pooling module combined with an attention mechanism to obtain weighted multi-scale features; and on the basis of the weighted multi-scale features, a lightweight shared convolution detection head is adopted to predict human body key point coordinates, and a final attitude estimation result is output.

The invention belongs to the crossing field of artificial intelligence and mechanical engineering, particularly relates to a micro-motor fault prediction and health management system, and aims to solve the problems that early faults of a micro-motor are difficult to recognize, degradation modeling is inaccurate and maintenance lags. The system collects multi-source data through high-density sensing, combines denoising reconstruction, composite feature extraction and time-varying weighted fusion to generate health indexes, identifies health stages by using a segmented hidden Markov model, iteratively updates residual life prediction based on a Wiener process, outputs an estimation result with a confidence interval, and links a hierarchical maintenance strategy. And continuous optimization of the model is realized through federal learning. The system improves the fault early warning accuracy and prediction reliability, and reduces the operation and maintenance cost.

The invention discloses a sparse regularization direction of arrival estimation method based on a risk minimization principle, and belongs to the technical field of array signal processing and underwater acoustic signal processing. The method comprises the steps of receiving array signals and establishing an observation model; constructing a sparse representation and over-complete dictionary; establishing and initializing a regularization optimization model; carrying out adaptive weight updating and risk-driven parameter selection; after regularization parameters are determined, a fast iterative shrinkage threshold algorithm FISTA is adopted to carry out optimization solution, and dictionary refinement is carried out on the detected direction after each iteration convergence so as to reduce off-grid errors; and after a small amount of outer layer iteration is repeated, outputting a final DOA estimation result and corresponding power. According to the method, self-adaptive selection of regularization parameters and noise levels can be realized, and the problem of precision degradation under complex conditions of low signal-to-noise ratio, limited snapshot number, signal source correlation, power imbalance and the like is effectively solved without manual parameter adjustment, so that the robustness and practicability of estimation are remarkably improved.

The invention provides a battery state-of-charge estimation method and system based on a physical gating neural network, and the method comprises the steps: obtaining battery operation data, and inputting the data to a data drive estimation module to obtain a preliminary SOC estimation value; meanwhile, the physical correction module performs integration on the battery operation data to obtain a physical estimation value, and generates a correction estimation value under physical constraint; calculating confidence through a confidence gating module to perform weighted fusion on the initial estimation value and the corrected estimation value, and outputting a final state of charge estimation result; and determining an optimal hyper-parameter through K-fold cross validation and completing network training to obtain a trained physical gating neural network, and predicting a state-of-charge estimation value of the battery based on the trained physical gating neural network. According to the method, high-precision and low-error SOC estimation can be realized under a complex multi-cycle charging and discharging working condition, and the stability and the reliability of an estimation result are remarkably improved.

The invention discloses a distribution network hot-line work robot pose estimation system and method, and belongs to the technical field of robot visual perception. The system comprises an input preprocessing module which is used for carrying out noise reduction and enhancement processing on an RGB-D image; the shared feature extraction module is used for extracting multi-scale universal features based on a lightweight convolution architecture; the 6D pose estimation module is used for processing the image based on the neural implicit field to obtain a pose estimation result; and the joint optimization module is used for realizing detection and pose estimation shared feature extraction through cooperation of a multi-task loss function and a pose estimation result. The system adopts adaptive median filtering and homomorphic filtering to eliminate noise and uneven illumination, and bilateral filtering optimizes a depth map; a bottleneck structure and cavity convolution are introduced into feature extraction, and a rank enhancement linear attention module is embedded; according to the pose estimation, a geometric field and an appearance field are modeled through a neural implicit field, and pose hypotheses are generated and optimized. According to the method, the problems of low pose estimation precision and poor real-time performance in the distribution network live working environment are solved, and the working safety and efficiency of the robot are improved.

The invention discloses an underwater target positioning method based on data-model dual drive. The method specifically comprises the following steps: data acquisition: acquiring initial data by using a receiver; performing sight distance reasoning: constructing and training a sight distance information reasoning neural network based on data driving, preprocessing the collected initial data, inputting the preprocessed data into the neural network, and outputting arrival time estimation of a sight distance path; joint estimation: adopting a model driving method, calculating the arrival time difference of sound signals received by a receiver by using the obtained sight distance arrival time, designing underwater target position and signal propagation speed joint estimation based on the arrival time difference, and calculating initial estimation values of the target position and the propagation speed by using a weighted least square method; and robust iteration: based on a maximum likelihood estimation function, performing robust iteration optimization on the obtained preliminary estimation value to obtain a stable and convergent final joint estimation result. The target positioning method is convenient to popularize and apply in different underwater environments, and has relatively high adaptability and expansibility.

The invention discloses a narrow environment high-precision laser inertial navigation and SLAM (Simultaneous Localization and Mapping) method based on adaptive parameters. According to the method, firstly, radar and IMU data are collected and preprocessed to form a unified input data stream; obtaining a pose prediction result by using the data stream, constructing an observation model, and obtaining a laser observation residual error; calculating a characteristic value proportion in the matching process of the point cloud and the sub-map, and judging a geometric degradation scene; when degradation is detected, adaptively adjusting a voxel filtering radius and a loopback detection threshold value; fusing the pose prediction result and the laser observation residual error by adopting a Kalman filtering model to obtain an optimal pose estimation result, and carrying out loopback detection and back-end map optimization under a dynamic threshold value to correct accumulated drift and update a voxel map; and finally outputting a continuous pose track and a three-dimensional voxel map. According to the method, the robustness and the positioning precision of the laser inertial navigation fusion SLAM in narrow scenes such as pipe galleries, tunnels and chemical plants are effectively improved.

The invention provides a radar-based human skeleton estimation method, system and product, and the method comprises the steps: carrying out the target detection of collected radar echo data, and generating a target four-dimensional point cloud containing distance information, speed information and angle information based on a target detection result; dividing the target four-dimensional point cloud into a plurality of human body topology point cloud blocks based on the velocity direction similarity of each point in the target four-dimensional point cloud; and inputting the human body topology point cloud block into a human body skeleton estimation network for human body skeleton estimation to obtain a human body skeleton estimation result. According to the human skeleton estimation method provided by the invention, human topology priori can be constructed from sparse millimeter wave radar point clouds, point cloud block features sensed by a structure are extracted, the modeling capability of a model for the spatial relationship of key parts of a human body is enhanced, diversified and natural daily human behaviors in a non-inductive monitoring scene can be adapted, and the human skeleton estimation accuracy is improved. The human body skeleton estimation with higher generalization ability is realized, and the accuracy and robustness of human body posture prediction can be effectively improved.

The invention discloses a power grid power flow real-time calculation and state estimation method and system based on a PMU, and belongs to the technical field of electric measurement and electric fault positioning. The method comprises the following steps: synchronously measuring electrical variables, including a voltage phasor and a current phasor, of a power grid node through PMU equipment to obtain synchronous phasor data, and verifying time and topology consistency; the power grid observability grade is judged based on PMU configuration node distribution corresponding to the verified electric measurement data; directly generating a real-time state estimation result through linear calculation based on PMU electric measurement data if the whole domain is observable; and if a part is observable, fusing PMU and SCADA data, carrying out nonlinear state estimation through a weighted least square method, distributing a high weight for the PMU electrical measurement data, and dynamically adjusting the SCADA weight to suppress bad data. According to the method, through observability adaptive judgment, the precision and efficiency of state estimation are improved, a data basis is provided for power grid fault positioning, and the method is suitable for practical application scenes of various PMU coverage degrees.

The invention discloses a dual-path non-cooperative spacecraft pose estimation method based on uncertainty perception, and belongs to the technical field of spacecraft pose estimation. According to the method, a dual-path prediction framework based on a shared backbone network is constructed and comprises a geometric reasoning path and a global context sensing path. In the training stage, prediction results of the two paths are aligned through a geometric consistency loss function, and joint optimization is carried out by combining multi-task losses such as key point regression, classification, rotation and translation regression and the like. In the inference stage, the pose estimation result is adaptively fused according to the predicted variance output by each path, when the variance is low, the output of the global context sensing path is directly adopted, otherwise, the key point projections of the two paths are combined, and the final pose is recovered. The method has higher estimation precision, robustness and interpretability in complex space environments such as shielding, illumination variation and large-scale variation, and provides reliable visual navigation support for on-orbit autonomous tasks.

The invention relates to a bridge crane game model-free optimal control method based on event triggering, and the method comprises the steps: collecting a state vector of a bridge crane in real time, and building a nonlinear multi-player system model of the bridge crane; estimating an unknown dynamic function and an input gain matrix on line in the input identifier neural network; according to an event triggering mechanism, whether triggering is conducted or not is judged based on the error between the current state vector and the state vector of the recently-triggered sampling; if so, triggering a dynamic updating instruction; under a non-zero sum game framework, obtaining an optimal value function gradient based on an estimation result and a current state vector through a self-adaptive evaluator network, and generating an event triggering optimal control law of each player based on a sampled state vector; and the event triggering optimal control law is processed by a zero-order retainer and then is output as a physical driving signal to control the operation of the bridge crane. Compared with the prior art, the method has the advantages of high applicability, high disturbance resistance, high accuracy and the like.

The invention discloses a radar short-time heavy rainfall estimation method based on classification echoes and environmental physical constraints, and belongs to the technical field of meteorological detection, and the method comprises the following steps: S1, multi-source data integrated fusion and cooperative gridding preprocessing; s2, rainfall type dynamic identification and Z-R relation self-adaptive primary selection based on multi-feature fusion; s3, adaptive correction of the estimation result driven by the environmental physical process is carried out; s4, estimating sequence optimization and systematic deviation correction based on a sliding time window and live feedback; and S5, multi-source information optimal fusion and refined heavy rainfall product generation. According to the method, the problems that a traditional fixed Z-R relation and single data source estimation method is insufficient in precision and insufficient in physical mechanism consideration are effectively solved, the accuracy of short-time heavy rainfall estimation is remarkably improved, and the method has obvious service application value.

The invention relates to the technical field of robot positioning and mapping, and discloses a positioning and mapping method and device and a storage medium. The method comprises the following steps: performing motion distortion correction on point cloud data of a current frame collected by a laser radar to obtain corrected point cloud data of the current frame; constructing a local sub-map of the current frame, calculating a degradation probability of a unit direction vector of the local sub-map, correcting a Hessian matrix of an iterative nearest point algorithm according to the degradation probability, and determining a pose estimation result of the corrected point cloud data relative to the local sub-map according to the corrected Hessian matrix; and fusing the pose estimation result and an IMU predicted value through a Kalman filter, calculating to obtain optimal pose estimation, and inserting the corrected point cloud data into a global map based on the optimal pose estimation. The problems of point cloud distortion and scene degradation in a dynamic scene are solved, and high-precision and robust positioning and mapping are realized.

The invention discloses a target detection and pose estimation method and system for a robot, and the method comprises the steps: collecting an RGB image and a depth image in a scene, and constructing a data set; a WD-DETR model based on the RT-DETR-R18 is established; the WD-DETR model is trained through the data set, and the trained WD-DETR model is obtained; the method comprises the following steps: preprocessing an output result of a WD-DETR model trained by an RGB image and a depth image in a scene collected in real time, inputting the preprocessed output result into a Foundation Pose 6D pose estimation model, and outputting a 6D pose estimation result; the method has the advantages that a detection method capable of effectively dealing with complex environments, diversified objects and small-size targets is provided, high-precision target detection and category matching are achieved, and finally 6D pose information of the objects is output.

The invention provides a working condition lithium battery SOH estimation method based on improved cordyceps sinensis correction-visual Transform, belongs to the technical field of battery health state estimation, and aims to solve the problems that the existing lithium battery capacity estimation depends on experimental data, the experimental data and working condition data have huge difference, and a real SOH label is lacked. The method comprises the following steps: acquiring lithium battery charging cycle and SOC change data, and selecting data sampling points; calculating a battery capacity estimation result, and carrying out statistical analysis on the battery capacity estimation result to obtain a distribution condition and statistical characteristics of a capacity estimation value; correcting the battery capacity estimation result after statistical analysis; and establishing an SOH estimation model, taking the corrected lithium battery capacity estimation result and the corresponding voltage, current and temperature data as input, and outputting a final lithium battery SOH estimation result.

The invention discloses a method and a system for presuming a correction coefficient of the strength of a standard test piece by adopting a small core sample test piece, and belongs to the technical field of concrete strength detection. The method solves the problems of large error and high discreteness of a presumption result caused by factors such as size effect, aggregate constraint and process difference when the standard strength is directly presumed by adopting the strength of a small core sample in the prior art, constructs a historical sample library containing multi-dimensional characteristics, calculates an initial correction coefficient and a size ratio, and obtains the presumption result of the standard strength. Key factors such as the small core sample size, the coarse aggregate particle size, the water-binder ratio, the curing age and the height-diameter ratio are comprehensively considered, an intelligent correction model is established by utilizing algorithms such as a gradient boosting decision tree and a random forest, and a comprehensive correction coefficient can be scientifically and accurately output, so that the actually measured strength of the small core sample is reliably converted into the strength of a standard test piece; and the presumption precision and the result stability are greatly improved, so that reliable technical support is provided for safety and durability evaluation of an engineering structure.

The invention relates to the technical field of ocean monitoring and data processing, in particular to a sea condition estimation method based on multi-source information fusion. The method comprises the following steps: emitting electromagnetic waves to a target sea area by using a radar, receiving a sea clutter reflection signal and converting the sea clutter reflection signal into a digital image signal to obtain a sea clutter image, and after preprocessing and sea wave edge feature extraction, calculating to obtain a first meaningful wave height parameter of sea waves in the sea area through a preset formula based on extracted sea wave edge discrete points; collecting the surging data of the ship in the target sea area in real time through RTK GPS equipment, performing preprocessing and spectral analysis to extract frequency components related to the sea waves, and calculating a second meaningful wave height parameter of the sea waves in the sea area based on the frequency components; and effectively fusing the two types of parameters, performing deviation correction on the first meaningful wave height parameter by using a fusion result, and outputting a sea condition estimation result. The method can improve the accuracy and reliability of sea condition estimation, can adapt to different marine environments and weather conditions, and is wide in application prospect.

Disclosed are a method for distribution of PHASE to monitor the operating state of a power system by using heterogeneous data obtained from measurement of SCADA and a time synchronized PMU and a method for processing defect data in mixed DSE by using same. The method for distribution of PHASE to monitor the operating state of a large scale power system includes the steps of: defining an extended state variable and an extended state variable set for each region; performing a SCADA-based DSE by using a SCADA measurement value for each region and a covariance matrix thereof, and parallelly performing a PMU-based DSE by using a PMU measurement value for each region and a covariance matrix thereof; and mixing the estimation results of the SCADA-based and the PMU-based DSE algorithms so as to perform a phasor-aided normalized residual test and a general normalized residual test.

The invention discloses a rainstorm flood risk early warning method and system based on machine learning and multi-source data fusion, and belongs to the technical field of flood prediction.The method comprises the steps that multi-source sample data is constructed based on flood disaster historical data; the multi-source sample data type comprises rainfall characteristic data, hydrological characteristic data, landform characteristic data, earth surface attribute characteristic data and social economic characteristic data; an XGBoost ensemble learning algorithm is adopted to construct a risk prediction model, and training and evaluation are carried out based on multi-source sample data; historical rainstorm flood event records are taken as labels in the training process; performing quantitative and application verification on the risk prediction model, and calibrating a risk level probability output by the risk prediction model based on a risk level distribution probability of historical disaster situation data; performing real-time estimation based on the optimized risk estimation model; and generating a spatial refined rainstorm flood risk grade early warning map in a future preset time period according to an estimation result in a rolling manner.

The invention discloses an overwater combined inertial navigation positioning method based on self-adaptive interactive multi-model, which comprises the following steps: S1, establishing SINS / DVL interactive multi-model according to an interactive multi-model algorithm; s2, according to the SINS / DVL interaction multi-model, firstly inputting interaction, then carrying out model filtering, then carrying out model probability updating and finally carrying out hybrid estimation, and taking an estimation result as combined navigation output; s3, feeding back an error term of updating feedback filtering calculation to inertial navigation; through the interactive multi-model algorithm, rapid adaptation can be achieved when the system state changes, the switching probability of each filtering model is adjusted in a self-adaptive mode, the matching precision between the SINS and the DVL is improved, and the challenges of DVL measurement abnormity and SINS noise fluctuation can be effectively coped with; meanwhile, the AIMM algorithm of the adaptive transition probability is adopted, and the optimal filtering model can be recognized in time in a fast changing environment, so that divergence of system errors is effectively inhibited, and the reliability and precision of a navigation result are improved.

The invention discloses an equipment health monitoring method based on multi-modal data fusion, and the method comprises the following steps: carrying out the preprocessing and feature extraction of collected multi-modal monitoring data, and constructing a cross-modal pairing feature sample; a deep canonical correlation analysis model is adopted to model correlativity among different monitoring data, and multi-modal features are mapped to a unified potential health representation space; and further combining with a hidden variable Gaussian process model, carrying out probability modeling and posterior inference on the potential health representation to obtain a continuous estimation result of the equipment health state changing along with time, and generating a health degradation track. The method is suitable for various equipment operation scenes with noise, missing or asynchronization of monitoring data.

The invention relates to the technical field of target tracking, and discloses an LSTM-KF hybrid tracking method based on parameter adaptation, which comprises the following steps: acquiring target position measurement data of a moving target, and extracting dual-channel characteristics of the target position measurement data through a sliding window; inputting the dual-channel features into a pre-trained dual-channel LSTM network to obtain a target position prediction result and a target speed prediction result; analyzing target motion characteristics based on a prediction result, selecting a corresponding dynamic model according to a motion mode, and performing target state estimation on the dynamic model through a Kalman filter; and finally, optimizing noise parameters of the Kalman filter by adopting an expectation maximization algorithm, carrying out weighted fusion on a prediction result of the dual-channel LSTM network and a target state estimation result, and outputting a final target state. According to the invention, high-precision and high-robustness target tracking in a complex environment is realized.

The invention discloses an automatic driving safety state estimation method and system based on statistical similarity, and the method comprises the steps: firstly constructing a sensor network for sensing the two-dimensional position information and speed information of a moving target: building a system state equation and an observation equation based on the dynamic characteristics of a target vehicle; constructing a local optimization objective function on each distributed node, deducing a local posteriori mean value and covariance update formula, and realizing high-precision state estimation of a two-dimensional target; an alternating direction multiplier method is adopted as a distributed information processing strategy, consistency constraint conditions are introduced, estimation result fusion and global state consistency estimation between nodes are achieved, and vehicle safety state estimation is completed. According to the method, high-precision state estimation and fusion of the two-dimensional target can be realized in a complex environment of non-Gaussian noise and hostile attack, the state estimation precision and the system robustness of the automatic driving vehicle are improved, and the method has a relatively high engineering application value.

The invention discloses a clamping force estimation method for a data and model dual-driven electronic mechanical braking system, and relates to the technical field of intelligent vehicle brake-by-wire. The method comprises the following steps: establishing electronic mechanical braking system models and state observers thereof under different precisions; designing a clamping force estimator of the model-driven electronic mechanical braking system by combining an extended Kalman filtering method; after the input features are screened, designing a clamping force estimator of the data-driven electronic mechanical braking system in combination with a time sequence convolutional neural network; estimating values of the model driving estimator and the data driving estimator are fused in real time based on an adaptive weight fusion mechanism, and finally an estimation result with higher precision and higher robustness is obtained. According to the method, the interpretability and real-time advantages of a model driving method and the adaptive capacity of a data driving method to complex non-linear working conditions are fused, and the precision and robustness of clamping force estimation under multiple working conditions and noise interference are effectively improved under the condition that a force sensor is not needed.

The invention relates to the technical field of data filtering, and provides a sliding window robust adaptive cubature Kalman filtering method and device and a medium, and the method comprises the steps: obtaining an observation vector of a sensor for a tracked target at a current moment; estimating a current state and an error covariance matrix by using a volume Kalman filtering algorithm based on the observation vector and the previous moment information; performing reverse smoothing on an estimation result at each moment in the sliding window by using a volume Kalman smoother to obtain a state smooth vector and a corresponding matrix; and finally, determining a current noise covariance matrix by variational Bayesian inference based on the information, wherein the current noise covariance matrix is used for correcting a prediction error covariance matrix at the next moment. According to the embodiment of the invention, the sliding window mechanism and the volume Kalman smoother are introduced to carry out reverse smoothing on the historical state, and the variational Bayesian inference is combined to carry out online joint estimation on the time-varying noise covariance matrix, so that the uncertainty of the model and the filtering divergence caused by noise abrupt change can be effectively inhibited, and the state estimation precision and robustness are improved.

The invention discloses a power distribution network state estimation method and system based on a fine tuning large language model, and belongs to the field of power system state estimation. The method comprises the steps of collecting node data of a power distribution network, constructing a power distribution network state estimation data set which is suitable for a large language model and comprises measurement information, topological information and constraint information, and dividing the data set into a training set, a verification set and a test set; training the large language model by using the training set data, finely adjusting parameters of the large language model to obtain a power distribution network state estimation model, and verifying the power distribution network state estimation model by using the verification set; inputting the test set data into the power distribution network state estimation model to obtain a power distribution network state estimation result; the method comprises the following steps: integrating unstructured power distribution system information with measurement data; the effectiveness and the robustness of the method are verified on an IEEE (Institute of Electrical and Electronic Engineers) 33-node power distribution network; compared with the prior art, the method provided by the invention shows the most advanced performance on all verification indexes.