88 results about "Bayesian algorithm" patented technology

The invention discloses a terminal meter reliability dynamic evaluation method, system and device based on multi-source data features and a medium, and relates to the technical field of terminal meter fault prediction.The method comprises the specific steps that multi-source data of a metering terminal are obtained, and the multi-source data are integrated to form a structured feature matrix; and introducing a mixed feature screening mechanism to carry out mixed feature screening to obtain a key feature set of the terminal meter. And carrying out weight distribution by adopting a Bayesian algorithm to obtain a comprehensive weight. And constructing a comprehensive reliability scoring model, and outputting a comprehensive reliability score of the terminal meter. And dynamically setting a risk threshold according to the environmental parameters, and outputting a comprehensive risk level of the terminal meter. According to the method, terminal meter reliability dynamic evaluation under multi-source data fusion is realized, the accuracy of reliability evaluation is improved through dynamic feature screening and an adaptive weight adjustment mechanism, and fault risks and operation and maintenance weak links under different scenes are effectively identified.

The invention relates to the field of coal mine geological disaster monitoring, in particular to a coal mine surface slope remote sensing data fusion monitoring method and system, and the method comprises the steps: collecting multi-source data through a satellite-unmanned aerial vehicle-ground three-stage network, and carrying out the cleaning, correction and standardization preprocessing; utilizing an improved LSTM model which introduces an attention mechanism and a geological parameter correction item to predict slope displacement and risk levels; distributing monitoring resources through a PSO (Particle Swarm Optimization) algorithm, dynamically adjusting an equipment state through a fuzzy PID (Proportion Integration Differentiation) algorithm, and fusing multi-source data through a Bayesian algorithm to generate a high-dimensional matrix; and finally, storing data based on the alliance chain and performing early warning based on a dynamic threshold value. The system correspondingly comprises six core modules. The problems of narrow coverage, poor timeliness and low data utilization rate of traditional monitoring are solved, millimeter-level precision monitoring is realized, the early warning response is less than or equal to 5 minutes, the cost is reduced by more than 40%, and the method is suitable for safety and ecological monitoring of various coal mine slopes.

The invention discloses a telescope parameter efficient optimization method and system based on a Bayesian algorithm and a fluctuation optical TTL coupling noise calculation model, and aims to solve the problem that a fluctuation optical high-precision calculation module is used for improving TTL coupling noise calculation precision in an existing telescope parameter optimization method. And due to frequent calling of a high-time-consumption module, the optimization time is sharply increased, and the efficient design requirement of a space gravitational wave detection task is difficult to meet. According to the method, on the basis of the principle of a Bayesian optimization algorithm, potential optimal to-be-evaluated telescope parameters are searched through an agent model, a collection function and the optimization function of Zermarkes software; and calculating TTL coupling noise of the telescope to be evaluated by combining a light field propagation calculation method based on a wave optics theory with a light field-phase resolving method, carrying out iterative optimization on telescope parameters, and outputting optimal TTL coupling noise and optimal telescope optical parameters.

The invention discloses an electric power field operation safety monitoring method and system based on AI driving. The method comprises the following steps: synchronously acquiring voice, operation video and equipment state identification information, and de-noising to generate a multi-modal sequence; using a multi-modal cross reconstruction model to reconstruct other modals for any modal, and identifying suspicious fragments according to reconstruction errors; multi-layer consistency matching is executed on the suspicious fragments, and the consistency matching degree and mismatch attribution are calculated through time soft alignment, semantic embedding unification and semantic graph reasoning; dispersing the voice, action and equipment state elements into an event sequence, and matching the event sequence with a preset process causal graph to position an abnormal event; and finally, abnormal nodes and induced nodes are analyzed in combination with a Bayesian algorithm, and whole-process safety monitoring is realized. According to the method, password inconsistency, action out-of-order, object mismatching and equipment response abnormity in electric power operation can be intelligently identified and traced, and the real-time performance and accuracy of operation safety are improved.

The invention discloses an intelligent inquiry method and device and electronic equipment, and relates to the technical field of intelligent inquiry and the technical field of data processing.The intelligent inquiry method comprises the steps that symptom information provided by a patient in the current round of inquiry is obtained, and the symptom information serves as latest symptom information; generating a current candidate disease set based on the latest symptom information; for each candidate disease in the current candidate disease set, calculating the posterior probability of the candidate disease after the current round of inquiry based on the latest symptom information by adopting a Bayesian algorithm; based on the posterior probability of each candidate disease in the current candidate disease set, the uncertainty entropy of the current candidate disease set is calculated, and the uncertainty entropy represents the uncertainty of the disease diagnosis result of the current candidate disease set; and determining whether to end the intelligent inquiry or not based on a size relationship between the uncertainty entropy and a preset entropy threshold value. By adopting the scheme, the inquiry efficiency and the inquiry integrity in intelligent inquiry are effectively balanced.

Systems, methods, and computer-readable media are provided for determining matches between records of different systems based on aggregate record data, and graphically marking potentially matched groups of data along with predicted confidence levels. Preliminary matching tools may allow allow users to define various rules based on which a majority of the transactions can be matched and reconciled. However, remaining transactions are disposed of in an interactive matching process. The matches may be determined unidirectionally from a source transaction to transactions from a target ledger, or bidirectionally from transactions in the target ledger to transactions other than the source transaction. Transactions may be matched many-to-many, one-to-many, or many-to-one, and a proposed order of match selections may be presented in a user interface. Match metadata or insights may be displayed to show a confidence of the match, reasons for the confidence, and / or a confidence of other matches that may be more beneficial than a match with a source transaction. The confidence and match insights may be generated by a machine learning model with access to transactions from a source transaction ledger and a target transaction ledger. The machine learning model may be trained on manual activity for prior matches that have been made. Matches may be performed using a hybrid machine learning model that accounts for random forests, decision trees, neural networks, naïve bayes algorithm, and / or a generalized linear model. Machine learning models also incorporate ongoing feedback from the users who can either accept or reject suggested matches and hence the models undergo an evolution process and constantly update from user patterns.

This invention discloses an underwater acoustic anti-interference transmission method and system based on sparse time-frequency feature mapping. The method includes: at the transmitting end, adaptively generating a fractional-order linear frequency-modulated waveform with a specific time-frequency shear slope based on the Doppler state of the underwater acoustic channel, achieving physical-layer focusing of transmitted energy; at the receiving end, constructing a hybrid observation model containing wide-block sparse channel components and narrow-block sparse burst noise components, and using a dual-channel variational Bayesian algorithm to jointly iteratively infer the posterior probability distribution of environmental burst noise in the fractional-order domain; finally, recovering the original signal through soft-threshold interference cancellation and fractional-order channel equalization. This invention effectively solves the communication failure problem caused by high-dynamic Doppler diffusion and marine biological impulse noise interference in underwater acoustics by actively mapping the waveform and using heterogeneous sparse joint inference at the receiving end, significantly improving transmission reliability in harsh underwater acoustic environments.

The application belongs to the field of wireless communication and perception, and particularly relates to an environment map construction method for an arbitrary continuous irregular rough diffuse reflection scene. The application comprises: modeling a receiving end receiving signal with a continuous rough diffuse reflection probability model; using a two-dimensional off-network sparse Bayesian algorithm to extract channel parameter information from the receiving signal; perceiving the state of scattering points by using parameter information extracted from different observations; fusing the perceived scattering point information of multiple users and multiple base stations, performing data cleaning and clustering, and realizing perception of an arbitrary shape unknown environment including irregular scattering surfaces; and constructing a high-precision physical map by using a rotating polynomial fitting method. The application can greatly reduce the cost of environment map construction and prevent privacy leakage; can be applied to any unknown shape physical scattering scene, and can effectively extract and fuse a higher order of magnitude of environmental parameter state observations.

The invention discloses a carbon capture steam extraction and energy storage collaborative spinning reserve optimization scheduling method and system, and particularly relates to the technical field of comprehensive energy management, and the method comprises the following steps: building a carbon capture power plant flexible operation model, and coupling power adjustment and reserve capacity; steam extraction adjustment is executed to form a combined dispatching structure; the net output characteristic of the system is realized by introducing electric energy and heat energy storage; constructing a multi-time-scale low-carbon scheduling model; generating a multi-target solution set by using a multi-target Bayesian collaborative convergence optimization algorithm; screening an optimal solution based on an approximate ideal solution sorting method and outputting a scheduling instruction set; according to the invention, power regulation and spinning reserve of the carbon capture equipment are coupled, so that the system regulation capability is enhanced; a combined dispatching structure is formed by combining steam extraction regulation, deep peak regulation of a thermal power generating unit is achieved, a multi-time-scale low-carbon optimal dispatching model is constructed based on system net output, a multi-target Bayesian algorithm and an approximate ideal solution sorting method are adopted, low-carbon, economic and standby requirements are considered, and new energy consumption and system stability are improved.

This application discloses a method, system, device, and medium for generating game parameters, relating to the technical field of game design. The method includes: performing correlation mining on the multidimensional behavioral data to obtain an emotional state feature sequence; constructing a personalized emotional response model for the target player based on the emotional state feature sequence, and generating a target emotional state feature trajectory for the target player based on an emotional change template and the personalized emotional response model; acquiring historical game interaction data and constructing an emotional state prediction model based on the historical game interaction data; calling the emotional state prediction model and searching in the game plot parameter space using a Bayesian algorithm to generate target game plot parameters, such that the emotional state feature prediction sequence corresponding to the target game plot parameters matches the target emotional state feature trajectory. This application has the effect of enhancing the personalized immersive experience of players in the game plot.

The invention relates to the technical field of power systems and automation thereof, and particularly discloses an energy scheduling and decentralized transaction management system based on a battery energy storage system. The method comprises the following steps: collecting battery multi-mode health data through a sensor, and calculating and updating the health state of each battery module by using a Bayesian algorithm; system-level virtual charge state equalization is realized based on a chemical neutral virtual battery abstraction layer; predicting energy surplus or deficit of each node through a causal state space model; for deficit nodes, calculating an optimal energy supply path by a multi-hop energy balance controller; and in combination with a battery health state, an operation condition and the like, a transaction price is generated through a personalized energy token pricing engine, and finally, automatic settlement is performed through a block chain smart contract. According to the invention, the health and chemical characteristics of the heterogeneous battery can be deeply perceived, the asset life and the system safety are improved, and the economy and reliability of the distributed energy storage network are enhanced.

The application discloses an energetic material processing parameter optimization method and system based on a force-heat coupling model, and relates to the technical field of intelligent simulation optimization based on specific calculation models. In view of the problems that 3D printing and mechanical processing data are disconnected, and common force-heat coupling models are not suitable for energetic materials in the prior art, the method of the application first collects 3D printing operation and initial state data of the grain, then constructs a force-heat two-way coupling intelligent calculation model special for energetic materials, adopts a Bayesian algorithm to multi-objective optimize processing parameters based on the model, and carries out model-driven closed-loop dynamic processing control. The method of the application realizes full data connection and adaptation to material characteristics, takes into account safety, precision and efficiency, and improves the processing stability and consistency of the energetic material.

The application discloses a kind of terminal meter reliability dynamic evaluation method, system, equipment and medium based on multi-source data characteristics, relating to terminal meter fault prediction technical field, its specific steps are: obtaining the multi-source data of metering terminal, integrates multi-source data and forms structured feature matrix.Introduce mixed feature screening mechanism to carry out mixed feature screening, obtain the key feature set of terminal meter.Bayesian algorithm is used for weight distribution, and the comprehensive weight is obtained.A comprehensive reliability score model is constructed, and the comprehensive reliability score of the terminal meter is output.According to the dynamic setting of the risk threshold value according to the environmental parameters, the comprehensive risk level of the terminal meter is output.The application realizes the terminal meter reliability dynamic evaluation under the multi-source data fusion, improves the accuracy of reliability evaluation through dynamic feature screening and adaptive weight adjustment mechanism, effectively identifies the fault risk and operation weak link in different scenarios.

The application discloses an intelligent health monitoring system based on electroencephalogram signals, and relates to the technical field of intelligent medical treatment, comprising the following steps: constructing a user personalized neural baseline model through small sample calibration and meta-learning; carrying out daily monitoring based on the model, and dynamically updating the model by using an online Bayesian algorithm to track long-term physiological drift of the individual; when significant neural baseline drift is detected, automatically matching and triggering intervention measures; constructing an anti-fact causal inference model to quantify the net effect of the intervention measures on the neural baseline; generating a personalized health insight report based on the net effect; and driving the iterative evolution of the neural baseline model through reinforcement learning by using closed-loop data containing drift, intervention measures and net effect, so that the application realizes intelligent health management with long-term self-adaptation, accurate quantitative intervention effect and self-evolution ability.

The present application belongs to the field of project risk prediction, and particularly relates to a project risk prediction avoidance method and system fusing deep learning, comprising: acquiring project reports and overall personnel configuration data, using a relation extraction decomposition model to extract project decomposition configuration data, secondly, constructing a project implementation node chain according to graph theory, thirdly, obtaining a set of correlated and non-correlated single sub-project from single sub-project implementation planning data in the node chain through a correlation algorithm, and then constructing a configuration risk model based on a particle swarm algorithm-optimized Bayesian algorithm, inputting the above-mentioned sub-project set to obtain single and correlated configuration risk probabilities, and finally constructing a personnel configuration adjustment factor according to the two risk probabilities, configuring the adjustment factor to the node chain connection relationship, and dynamically adjusting the initial configuration of personnel of each single sub-project until all nodes satisfy a preset risk probability threshold, so as to effectively cope with risks caused by personnel configuration in project implementation.

The invention relates to the technical field of data processing, and discloses a modular new energy automobile motor dismounting and detection teaching method and system. The method comprises the steps that motor parameters are recognized through RFID, student ability is tested to generate an initial scoring matrix, ability portrait vectors are constructed, a personalized training sequence is generated through collaborative filtering and a Bayesian algorithm, a visual algorithm is adopted to recognize component superposition guide animation, and operation data are collected; and a rack test injection fault is controlled, a detection data update capability vector is collected, a weak knowledge point backtracking dependency relationship is identified, training sequence matching resources are adjusted, and a file is generated through cyclic execution. According to the method, self-adaptive training sequence generation based on student ability portraits, accurate operation guidance assisted by augmented reality, intelligent analysis and evaluation of multi-dimensional learning data and targeted intensified training driven by a knowledge graph are realized.

The application discloses a gear design optimization method based on a Bayesian algorithm, and relates to the technical field of gear design. A tooth surface geometric model is established based on the pure rolling relationship of a rack and a gear, a load stiffness coupling model is constructed by combining meshing partition and a tooth direction slicing method, contact and bending stress are obtained, and drive and non-drive side pressure angles, addendum height coefficients, dedendum fillet radius coefficients, radial variables and tooth widths are taken as design parameters. A multi-objective function of minimizing maximum dedendum bending stress, maximum contact stress and maximizing average overlapping degree is set. A Markov blanket structure is introduced to screen key variables, a Gaussian process is used to establish a proxy model, and an improved acquisition function based on an expected hypervolume is used for iterative optimization. The number of iterations, the improvement amplitude and the running time limit are taken as termination conditions. The optimal parameters are screened by combining a normalized comprehensive score. The gear design optimization method based on the Bayesian algorithm can improve the design accuracy of asymmetric high-overlapping gears and the efficiency of design parameter optimization.

This invention discloses a fault identification method for underwater thrusters based on channel expansion and sequence fusion. The method acquires time-domain sequences of several dynamic signals from an underwater robot. Each time-domain sequence is sequentially processed using mean removal, wavelet decomposition, modified Bayesian algorithm, and evidence theory fusion. Then, each processed sequence undergoes a Fourier transform to obtain corresponding frequency sequences. These frequency sequences are arranged and fused to obtain a two-dimensional matrix. Using this two-dimensional matrix as input, a fault diagnosis model is used to classify fault levels and determine the degree of thruster fault. The fault diagnosis model is established through underwater thruster fault experiments. The time-series channels are expanded, and the diagnostic effects of the expanded frequency sequences are ranked and fused into a two-dimensional matrix for hyperparameter learning, significantly improving the convergence speed and accuracy of fault degree identification.

The application discloses a watch spare part defect classification and identification method and system based on visual technology, acquires watch spare part image data, introduces an adaptive light correction algorithm, eliminates light reflection interference through histogram equalization and enhancement technology, establishes a double-path convolutional neural network to extract local texture features and global geometric features in the processed image data, performs weighted fusion of the features through an SEBlock attention mechanism to obtain fusion feature data, establishes a lightweight classifier based on a neural network, inputs the fusion feature data into the lightweight classifier for classification, and outputs a preliminary classification result; generates a defect sample through a GANs generative adversarial network based on the preliminary classification result, calculates a posterior probability through a Bayesian algorithm, and outputs a target classification result. The accuracy and completeness of classification and identification are improved.

The invention discloses an intelligent portfolio management method and system based on a Bayesian neural network, and belongs to the field of machine learning and financial investment management. In order to flexibly optimize the optimal investment portfolio under the conditions of risk avoidance and transaction cost change, the financial market investment income is maximized. By acquiring market financial data and processing information, a stochastic gradient variational Bayesian algorithm (SGVB) is adopted to solve the problem of uncertainty of stock income probability distribution parameters and an investment portfolio model structure, and parameter estimation errors are effectively solved. And then, the system combines the SGVB and a neural network to construct a probability deep learning framework, so that the model latent variables are modeled as probability distribution, and efficient investment portfolio model training is realized through stochastic gradient optimization. The method has outstanding feasibility and stability in the aspect of financial investment portfolio, reduces the transaction cost, improves the investment income, and adapts to a dynamic and complex financial market investment decision-making environment.

The invention discloses an MOBO algorithm-driven key enterprise energy-saving and carbon-reducing multi-objective auxiliary decision-making method, system, equipment and medium, and belongs to the technical field of industrial energy saving and emission reduction, and the method comprises the steps: carrying out the data reading and preprocessing, generating an initial sample, and constructing an objective function based on energy saving and carbon reduction; performing multi-target Bayesian optimization initialization on the preprocessed data, and dynamically allocating weights; and performing iterative optimization through multi-objective Bayesian to generate a candidate decision scheme, and performing constraint check. The method responds to the time-of-use electricity price, the carbon factor and the load state, and the problem of time-of-use electricity multi-target separation is solved; an MOBO algorithm is adopted, a target function is modeled through a Gaussian process regression model, external condition mutation can be quickly responded, complex constraints can be effectively processed, the performance of multi-target optimization in a dynamic energy-saving and carbon-reducing scene is remarkably improved, the convergence speed is higher, and the optimization effect is better.

This invention discloses a probability tensor CPD algorithm based on dynamic and static Lagrange multipliers and orthogonal factors, comprising the following steps: (1) constructing a complex-valued tensor model; (2) preprocessing the complex-valued tensor model using the FF-SVD algorithm based on static Lagrange multipliers; (3) further updating the FF-SVD algorithm parameters based on dynamic Lagrange multipliers; (4) transforming the complex-valued tensor model into a probability model; and (5) solving the probability model using the μ-VB algorithm. This invention introduces the influence of Lagrange multipliers from both static and dynamic dimensions on existing variational Bayesian algorithms, automatically determining the tensor rank, reducing running time, and improving the accuracy of the algorithm. Furthermore, this invention is applied to wireless communication technology and linear image coding technology.

The application discloses a kind of optical port degradation analysis methods, comprising: step 1: obtaining fiber storage switch data, including the equipment range needing to execute degradation analysis, the optical port model and parameter used and the alarm threshold of different optical ports;Step 2: obtain the monitoring data of optical port;Step 3: cache optical port data;Step 4: based on dynamic bayesian algorithm, degradation analysis is executed to each optical port, and then the time remaining when the each optical port distance fault occurs is obtained;Step 5: output analysis data.The application solves the fiber port power degradation analysis problem of fiber communication relay equipment based on bayesian, fully extracts the information contained in existing data, accurately fits the actual degradation path, so that the model well describes the degradation trend of optical port power, so as to obtain accurate fault diagnosis and the estimation result of remaining usable life, which provides a new idea for degradation modeling and remaining usable life prediction of this kind of problem.

The application discloses a software grouping method based on a Web component, an electronic device and a storage medium. The method comprises the following steps: acquiring a personal computer end software information list according to user permission information; performing multi-level grouping on to-be-grouped software by using a Web component according to the personal computer end software information list and a user grouping request; performing an installation or uninstallation operation on grouped software according to state information of the grouped software displayed according to a grouping result and in response to a trigger event of an icon of the grouped software by the user; re-grouping grouped software in the same level in response to a user drag grouping request, and automatically naming a folder name of the re-grouped software by using a naming model based on a naive Bayes algorithm; and moving selected grouped software from the grouping result to a preset position of the personal computer end in response to a software removal request of the user.

The invention discloses a method for constructing a prediction model of compound retention time in high performance liquid chromatography, which relates to the technical field of machine learning and comprises the following steps: generating a candidate sample data set; the candidate sample data set serves as input to train a lightweight gradient elevator regression model, and an optimal hyper-parameter combination corresponding to the data set is found in combination with a Bayesian algorithm; training the lightweight gradient elevator regression model under the corresponding optimal hyper-parameter combination by using the candidate sample data set and adopting a 10-fold cross validation method to obtain an evaluation index; and taking the model corresponding to the optimal evaluation index as a prediction model for the retention time of the compounds in the high performance liquid chromatography, and retaining the group of candidate sample data sets. According to the method, the multi-strategy data configuration pool is constructed, the LightGBM regression model is combined with the Huber Loss objective function, hyper-parameter efficient optimization is achieved based on Bayesian optimization, and finally the model stability is guaranteed through cross validation.

The present application relates to a kind of pasteurized milk, high-temperature sterilized milk and formula milk powder fast identification method, which comprises that pasteurized milk, high-temperature sterilized milk and formula milk powder are made into samples to be detected respectively;Under different current frequency, the dielectric properties of the sample to be detected are collected using LCR tester, and dielectric property spectrum data are obtained;Select the dielectric property data of several frequency points, and carry out dimension reduction processing by principal component analysis;After dimension reduction, the data is divided into training set and test set according to the principle of random sampling;On the training set, Gaussian naive bayes algorithm is used to establish the mathematical model for distinguishing pasteurized milk, high-temperature sterilized milk and formula milk powder.The method uses simple LCR measurement, quickly obtains the dielectric property spectrum of milk, the dielectric property spectrum has numerous independent information, can establish milk type identification model under very small sample size, greatly reduces detection time and detection cost.

Disclosed in the present application are a method and apparatus for intelligent judgment of a shield tail seal failure. The method comprising: acquiring gap data between segments and a shield tail, external soil pressure data and grease state data; inputting the gap data into a shield attitude anomaly warning model, and outputting a first prediction result; inputting the external soil pressure data into an external soil anomaly warning model, and outputting a second prediction result, the external soil anomaly warning model being used for determining the turning point of a sudden change of an external soil pressure; inputting the grease state data into a grease anomaly warning model, and outputting a third prediction result, the grease anomaly warning model being used for determining, on the basis of the grease state data, whether grease contains water, whether the grease temperature is abnormal, and whether the grease pressure is abnormal; and on the basis of a Bayesian algorithm, fusing the first prediction result, the second prediction result and the third prediction result to output an overall prediction result.

The application relates to the technical field of production quality control, and discloses a silver powder production quality control method and system fusing multiple technologies and a storage medium. The method comprises the following steps: collecting silver powder production data through a distributed sensor to obtain a quality characteristic correlation matrix, adjusting a gamma distribution hyperparameter to obtain an adaptive parameter by using a self-adaptive Bayesian algorithm based on a defect rate parameter, generating a device cooperative control instruction set by optimizing a control strategy through a decision fusion algorithm, performing linkage control on a ball mill, an atomization drying tower and a grading screening device to obtain an execution result, evaluating the execution result to obtain a performance index, and correcting the control instruction set according to the performance index. The application solves technical problems such as performance degradation of a traditional Bayesian control under a large defect rate parameter condition in a silver powder production process, insufficient control precision caused by a lack of cooperative decision fusion of multiple quality characteristics, and an influence on overall quality control effect caused by a lack of cooperative linkage control among production devices.

This invention provides an AI-based multimodal network information operation and maintenance system, belonging to the field of network information operation and maintenance technology. The system collects heterogeneous operation and maintenance data such as network traffic, device status, audio alarms, and thermal imaging through a data acquisition unit. It utilizes a multimodal feature extraction module to extract various features in parallel, forming a unified multidimensional feature vector. A hierarchical anomaly detection architecture is established, deploying lightweight and deep anomaly detection models at the edge and cloud respectively. A multimodal feature fusion model intelligently fuses different modal features through an attention mechanism. An adaptive threshold dynamically adjusts the Bayesian algorithm to optimize the detection threshold in real time based on network status. A multimodal fusion decision engine is constructed to weight and fuse anomaly detection results and dynamically adjust modal weights, thus solving the technical problem of insufficient accuracy in multimodal operation and maintenance data fusion processing.

The application provides a rail transit station distribution transformer power quality comprehensive evaluation method and system, comprising: acquiring power quality index data within a given time; constructing a segmented nonlinear single score model according to the preprocessed power quality index data, and obtaining power quality single score according to the single score model; wherein the single score model is constructed based on the historical deviation data of each power quality index collected in the preset sliding window; the initial weight corresponding to each index is determined by the entropy weight method, and the Bayesian algorithm is used to fuse each initial weight to obtain the final weight; based on the final weight and the power quality single score, the comprehensive score result is obtained through the pre-constructed comprehensive score model, and the power quality comprehensive evaluation is carried out according to the comprehensive score result. The application comprehensively measures the power quality from multiple dimensions, and realizes objective and dynamic evaluation of the power quality of the rail transit station distribution transformer.