670 results about "Uncertainty quantification" patented technology

A federated distributed computational system enables secure oncological therapy optimization through robotic integration. The system establishes a distributed graph architecture with secure communication channels connecting computational nodes, implementing encryption protocols for cross-institutional data exchange. Each node contains processing capabilities for fluorescence-guided imaging, uncertainty quantification, and expert knowledge integration while maintaining hierarchical knowledge graphs of oncological biomarkers, interventions, and outcomes. The system coordinates domain-specific knowledge through token-space communication and implements an advanced robotic integration system for surgical interventions using spatiotemporal tumor mapping, multi-modal fluorescence imaging, surgical robot coordination, and space-time stabilized mesh management. Key capabilities include wavelength-specific multi-modal fluorescence detection, combined epistemic and aleatoric uncertainty estimation, tensor-based data integration with adaptive dimensionality control, and light cone search for adaptive treatment optimization—all while maintaining strict privacy controls.

A deep learning system for time series prediction comprising a preprocessor that receives time series input sequences, truncates them by removing terminal values, and appends padding values to maintain the original sequence length. An encoder compresses these padded sequences into latent space representations, while a decoder reconstructs predicted sequences matching the original length, specifically trained to reconstruct values matching the removed terminal values in positions corresponding to the padding values. A training system optimizes the encoder and decoder by minimizing differences between original sequences and predicted sequences. The system can process multiple time horizons simultaneously while maintaining statistical properties and providing uncertainty quantification through confidence intervals. This approach enables accurate short-term forecasting while preserving both temporal patterns and statistical relationships in the predicted sequences.

The invention relates to a multi-source data fusion-based urban physical examination evaluation index calculation method and system. The method comprises the steps of extracting a multi-source data sequence; identifying a data source of the urban physical examination index set, and extracting an independent time sequence data sequence; calculating the information entropy of the independent time sequence data sequence, and distributing a basic fusion weight; calculating a dynamic state evaluation value of the independent time sequence data sequence, and performing weighted fusion on the basic fusion weight and the dynamic state evaluation value to obtain a comprehensive state evaluation value; obtaining a distribution variance of the basic fusion weight, inputting the distribution variance into the uncertainty quantification model, and obtaining an index calculation result containing uncertainty measurement; the real-time performance of the evaluation result is enhanced through an aging attenuation mechanism, and the latest state of the city system is accurately reflected; the output uncertainty measurement index provides a quantitative basis of result credibility for a decision maker, and the decision risk caused by a data fusion error is reduced.

The invention discloses a reservoir real-time scheduling simulation system based on a deep learning algorithm, and belongs to the technical field of intelligent water conservancy and artificial intelligence. Aiming at the problems of low prediction precision, poor multi-target coordination capability, weak coping uncertainty and the like of a traditional scheduling system, the system is designed to acquire hydrological, meteorological, water quality and engineering safety data through a multi-source data acquisition unit, and a multi-dimensional feature tensor is generated after preprocessing and fusion; the dispatching center server adopts an STGCN-LSTM mixed model to achieve high-precision prediction and uncertainty quantification of the water inflow process in the future 7-30 days, a reservoir hydrodynamic model and an MO-PPO algorithm are combined to complete multi-scene simulation and multi-target optimization decision, and an AF-DT mechanism dynamically adjusts the dispatching rule priority. According to the system, a sensing-decision-execution-feedback closed loop is constructed, the scheduling adaptive capacity and robustness are improved, the synergistic interaction of flood control, water supply, power generation and ecological protection is realized, and the system is suitable for real-time intelligent scheduling of large and medium reservoirs.

The invention belongs to the field of geotechnical engineering and engineering geological information modeling, and relates to a stratum-parameter coupling randomness three-dimensional random field modeling and shield construction ground surface settlement rapid prediction method and device based on multi-source data fusion. According to the method, a three-dimensional joint random field acting on stratum types and rock-soil key physical property parameters at the same time can be constructed under the joint constraint of multi-source data such as drilling, geophysical prospecting, geotechnical tests and terrains, and a calibrated, explainable and updatable geological section automatic generation and uncertainty quantification channel is formed; on the premise that geological rationality is guaranteed, section geometry and parameter distribution under the conditions of complex structures and lateral phase change are restored robustly, the accuracy, consistency and interpretability of the three-dimensional geological section are remarkably improved, and a combined uncertainty result which can be directly used for rapid prediction and risk assessment of shield construction settlement is output. The technical problems that a geological section generated by an existing method is not accurate enough, uncertainty is difficult to quantify, and the extrapolation capacity of a complex scene is weak are solved.

The invention discloses a digital twin-driven bridge full life cycle damage prediction and evaluation method and system, and belongs to the field of bridge structure health monitoring, and the method comprises the steps: obtaining a monitoring data set of a bridge structure; an initial digital twinborn model embedded with a micro physical layer is constructed and trained, the micro physical layer constructs a damage evolution model applied with monotonic physical constraint based on multi-source monitoring data, and a damage evolution trajectory of the bridge in a future time period is predicted through the damage evolution model based on the physical parameter vector; in combination with an uncertainty quantification method, generating a time-varying reliability index of the bridge in a future time period; and based on the time-varying reliability index, constructing and solving a maintenance decision optimization model to generate a maintenance decision of the bridge. According to the invention, the physical authenticity and reliability of the long-term prediction result are ensured.

The invention relates to the technical field of smart factory decision-making, and discloses a digital twin-driven smart factory AI intelligent decision-making system, which comprises a data acquisition and preprocessing module used for acquiring and preprocessing real-time and historical data of a production line; the twinborn modeling identification module is used for constructing a twinborn body and carrying out parameter identification and uncertainty quantification; the alignment evaluation credible module is used for comparing twin prediction data with real data and generating availability marks and trust scores; the strategy simulation optimization module is used for generating candidate strategies and risk evidences based on the constraints and the key performance indicators; the grayscale online publishing module is used for screening and grayscale publishing a strategy according to the trust score and the performance result; the operation evaluation auditing module is used for collecting operation data and generating an auditing packet; and the drifting detection updating module is used for detecting distribution drifting and recalibrating and updating the twinborn body and the strategy library. According to the invention, the reliability, robustness and continuous optimization of the production decision of the smart factory are realized.

The invention discloses a radar lifting control method and system based on meteorological monitoring, and relates to the technical field of radar lifting control, and the method comprises the steps: completing the switching of a power supply and communication after a radar is powered on, initializing a controller, collecting the data of a meteorological station, and generating a future fusion wind speed in real time through a Kalman filtering physical model and a residual neural network; future fused wind speed is converted into wind pressure for evaluation, the risk degree is judged according to the evaluation result, early warning is given out, and the controller is preheated to enter a lifting preparation state. The input stability is improved through meteorological data sliding window smoothing and feature extraction, wind speed dynamic prediction and uncertainty quantification are achieved through XGBoost prediction and residual variance estimation, the time sequence consistency and robustness are enhanced through remote API interpolation correction and adaptive extended Kalman filtering, residual correction is conducted through a neural network, the prediction precision is improved, and the prediction accuracy is improved. And a reliable decision basis is provided for radar lifting control.

The invention relates to the technical field of medical image processing, in particular to a CT image intelligent analysis system for pneumonia auxiliary screening. The method comprises the following steps: firstly, preprocessing a chest CT image and detecting a candidate focus area; secondly, extracting a topological feature, a deep convolution feature and a texture statistical feature based on a persistent coherence theory from each candidate focus, and performing feature fusion through a multi-head self-attention mechanism to generate a unified focus representation vector; mapping the lesion characterization vectors to a pre-constructed radiology knowledge graph, adopting a graph neural network for reasoning, and outputting the pneumonia suspected probability and lesion classification of each lesion; and finally, performing fusion and uncertainty quantification on the analysis results of the plurality of focuses by adopting an evidence theory, and generating a comprehensive screening report. According to the method, complex-form lesions are effectively identified through topological features, accurate identification of lesion types is realized through knowledge graph reasoning, and diagnosis uncertainty quantification is provided through an evidence theory.

The invention relates to the technical field of exploration, and discloses a water depth inversion method and system based on a multispectral remote sensing image, which utilizes an independent verification sample set to carry out hierarchical precision evaluation, and analyzes model performance differences according to dimensions such as a water depth range and a substrate type. Error propagation of links such as atmospheric correction and water level correction is quantified through full-chain uncertainty analysis, an uncertainty quantification model of ensemble learning is constructed, and a pixel-level precision distribution diagram is generated. Therefore, according to the technical scheme, a closed-loop dynamic adaptation framework is formed by systematically integrating multi-temporal data dynamic modeling and an uncertainty quantification mechanism, a spatio-temporal variation compensation mechanism is embedded in the whole process from data acquisition to result verification, the interference of spatial-temporal heterogeneity of water optical characteristics on water depth inversion is effectively dealt with, and the accuracy of water depth inversion is improved. The problems of parameter mismatch and precision reduction of the water depth inversion model caused by dynamic change of optical characteristics of a coastal water body in seasonal and tidal scales are solved.

The invention discloses a hydraulic engineering construction operation parameter optimization and data management method and system. The method comprises the steps of 1, multi-source data access and vectorization; step 2, time sequence feature extraction and multi-modal fusion; step 3, identifying interpretable influence factors; 4, performing multi-task dynamic anomaly prediction; 5, risk weighted fusion and uncertainty quantification are carried out; 6, carrying out digital twinborn simulation verification; step 7, governance strategy optimization and security auditing; and step 8, feedback acquisition and model adaptive updating. The method has the advantages that multi-modal unified representation is constructed by fusing structured data such as water level and flow with unstructured information such as meteorological images and operation and maintenance logs, time sequence feature extraction is carried out in combination with the space-time diagram neural network, the dynamic sensing and prediction capability of the complex hydrological process is remarkably improved, and the method is suitable for being popularized and applied. According to the invention, the conversion from static threshold alarm to multi-task and prospective abnormal early warning is realized, and the adaptability of the system to multiple scenes is enhanced.

The invention provides an acoustic array adaptive calibration correction system applied to an underwater moving target, which relates to the technical field of marine equipment and comprises a multi-source excitation and environment perception module, an intelligent array perception and diagnosis module, an adaptive position inversion and uncertainty quantification module and a closed-loop calibration execution and self-learning optimization module. The multi-source excitation and environment perception module is responsible for providing reference signals required by calibration and establishing a correlation model of environment and formation distortion, and the intelligent array perception and diagnosis module realizes multi-modal data acquisition, array element health state monitoring and formation geometry self-perception. The adaptive position inversion and uncertainty quantization module completes signal processing, position estimation and error quantization propagation, and the closed-loop calibration execution and self-learning optimization module executes a compensation strategy, verifies a calibration effect and continuously optimizes system performance through online learning; the system solves the problem that a traditional method cannot process environment time varying, multi-sensor conflicts and uncertainty quantization.

The invention relates to the technical field of deep learning and small sample learning, in particular to a small sample capacity training method based on deep learning, which comprises the steps of 1, cross-domain data adaptation and feature alignment, 2, meta-knowledge distillation and prototype enhancement, 3, attention-guided small sample fine adjustment, and 4, model uncertainty quantification and iterative optimization. According to the small sample capacity training method based on deep learning, through cross-domain feature alignment, meta-knowledge distillation, prototype enhancement and dynamic iterative optimization, the problems of model overfitting and weak generalization ability in a small sample scene are solved, high-precision model training when the sample size is less than or equal to 50 is realized, and the training efficiency is improved. The method is suitable for data scarce scenes such as medical images and minority language processing.

The invention relates to the technical field of computers, and discloses a nuclear power safety report examination method and system, electronic equipment and a storage medium, and the method comprises the steps: receiving an examination request, carrying out the intention recognition and entity extraction based on a nuclear power field large language model, and disassembling an examination task into a structured subtask sequence based on an intention type and an entity attribute; performing multi-modal retrieval based on the structured sub-task sequence, and outputting a multi-source retrieval result; calling time-space association information of the evolutionary knowledge graph, and outputting knowledge support data in combination with the time sequence model; fusing a multi-source retrieval result and the knowledge support data, performing risk value calculation and uncertainty quantification through a deep learning model, and outputting a risk assessment result; and based on the risk assessment result, carrying out federal learning model parameter adjustment, carrying out uplink evidence storage on the review conclusion, the risk assessment result and the evidence chain, and outputting the review result. The method has the advantages of being efficient, accurate, dynamic, safe and closed-loop during examination.

The invention discloses a reasoning optimization method and device for a code generation large model, equipment and a medium, and relates to the technical field of model reasoning, and the method comprises the steps: in the reasoning process of a code generation task of a target code generation large model, executing a multi-granularity uncertainty quantification step in parallel every time a new Token is generated, obtaining a multi-granularity uncertainty score; constructing a state space vector, and utilizing a preset reinforcement learning strategy network to evaluate the selection probability of a plurality of preset reasoning optimization strategies based on a preset smooth decision mechanism so as to determine a target reasoning optimization strategy; if the strategy is a preset reasoning acceleration strategy, optimization processing is carried out through speculation decoding; if the strategy is a preset exploration optimization strategy, performing optimization processing by using a preset multi-path sampling technology and a preset knowledge enhancement technology; if the strategy is the preset fuzzy processing strategy, taking the plurality of candidate outputs as target reasoning outputs for optimization processing; and evaluating the decision effect according to the reasoning result to optimize the preset reinforcement learning strategy network.

The invention provides a method for predicting the residual life of a power transformer based on digital-analog fusion, and belongs to the technical field of transformer detection.The method comprises the steps that multi-dimensional sensor data of the power transformer is collected, wavelet transform preprocessing is conducted, a normalized data matrix is established, a physical equation is established, and a deterministic physical model is formed; a data-driven model is established based on an improved adaptive multi-scale network to realize multi-scale feature adaptive extraction, a topological phase change algorithm is introduced to identify key transition points in an aging process, and a deterministic physical model and the data-driven model are fused to establish a digital-analog fusion prediction framework. A generative adversarial network is adopted to perform data enhancement to solve the problem of scarcity of fault samples, a Bayesian neural network and a Monte Carlo random inactivation technology are utilized to construct an uncertainty quantization framework to output a residual life prediction value and a confidence interval thereof, and the technical problem that the prediction precision of the residual life of the transformer is not high is solved.

The invention relates to the technical field of medical information, and discloses an internet-based remote medical inquiry system, which comprises a data acquisition and quality assurance module for acquiring multi-source heterogeneous medical data and performing time sequence alignment, quality monitoring and intelligent repair interpolation; the feature extraction and fusion module is used for performing deep feature extraction, cross-modal semantic alignment and hierarchical attention fusion; the complication association reasoning module is used for obtaining a deep complication association reasoning result by adopting a graph attention network and multi-hop reasoning; the complication progress prediction module is used for constructing a complication progress prediction model and carrying out meta-learning enhancement and uncertainty quantification; the intelligent medication decision module is used for generating candidate schemes and screening a Pareto optimal scheme; the compliance management module is used for carrying out compliance causal inference and closed-loop optimization; the effect evaluation module is used for carrying out effect evaluation and dynamic optimization; according to the method, a compliance improvement mechanism is established through causal inference and reinforcement learning, and interpretable man-machine collaborative decision and closed-loop optimization management are realized.

The invention belongs to the field of uncertainty quantification and robustness design optimization of aero-engine air-cooled turbines, and particularly discloses a one-dimensional uncertainty design optimization method and system for a reverse cooling turbine based on a one-dimensional aerodynamic analysis method for the reverse cooling turbine. Forming an augmented space by the optimization variables and the uncertainty parameters, and generating a sample set; establishing a Kriging global agent model, and generating an uncertainty parameter sample set; an ASPC model is established, and one-dimensional uncertainty quantification of the reverse cooling turbine is completed; an NSGA-II multi-objective optimization algorithm is coupled, and one-dimensional robustness design optimization of the reverse cooling turbine is completed. The one-dimensional uncertainty design optimization method and system framework of the reverse cooling turbine are provided and established, aerodynamic performance analysis of the reverse cooling turbine can be completed through simple parameters, a geometric entity is not needed, and tasks such as one-dimensional uncertainty quantification and robustness design optimization of the reverse cooling turbine can be achieved.

The invention discloses an aero-engine residual life prediction method based on multi-modal deep learning, and relates to the field of aero-engine prediction and health management. The method comprises the following steps: acquiring and preprocessing multi-sensor time sequence data; constructing a degradation sensitive feature set through multi-scale analysis of a time domain, a frequency domain and a time-frequency domain; constructing a multi-modal deep learning model comprising an original data processing module and a multi-scale feature processing module, and introducing an attention mechanism and an uncertainty quantization module into the model; the model is subjected to lightweight processing to support embedded deployment. According to the method, multi-scale features and multi-modal deep learning are fused, the uncertainty quantification capability is achieved, high-precision and interpretable residual life prediction with uncertainty quantification is achieved, and reliable support is provided for engine maintenance decision making.

The invention relates to the technical field of hydrological prediction, in particular to a drainage basin distributed runoff prediction method and system based on a graph neural network, and the method comprises the following steps: obtaining a drainage basin multi-source runoff data set to construct a multi-relation dynamic graph structure, and extracting node feature vectors; based on the node feature vector, obtaining a watershed evolution trend forward feature by establishing a watershed diffusion fitting architecture; constructing a distributed runoff probability prediction model, and taking the watershed trend forward features as model input to obtain runoff initial condition probability distribution of each sub-watershed in multiple periods in the future; establishing a mixed loss function, and performing physical constraint optimization on the runoff initial condition probability distribution to obtain distributed runoff optimization probability distribution; and performing uncertainty quantification on the distributed runoff optimization probability distribution to obtain a drainage basin distributed runoff prediction result. According to the method, the hydrological process simulation capability of the complex watershed is improved, and accurate prediction of the distributed runoff volume is realized.

The invention discloses a thermal spraying coating thickness online optimization control method based on digital twinning, and relates to the technical field of intelligent manufacturing, and the method comprises the steps: synchronously collecting multi-modal online observation data and process control observation data in a thermal spraying process, carrying out the time-space alignment, and generating a multi-modal observation set; performing adaptive optimization of multi-modal uncertainty gating on the candidate control set according to the credible thickness field confidence distribution map to generate a control instruction sequence; and the control instruction sequence acts on the thermal spraying process, response feedback data are continuously collected in the execution period, a new multi-mode observation set is generated according to the response feedback data, and real-time closed-loop optimization control is kept. According to the method, the thickness field with high credibility and the credible thickness field confidence distribution diagram can be generated through forward generation and uncertainty quantification of physical guidance, and depth coupling of multi-modal data and physical rules and accurate mapping of uncertainty are achieved.

The invention discloses a sparse view angle indoor reconstruction method based on uncertainty perception depth supervision. The method comprises the following steps: acquiring multi-view angle image data; solving a camera pose based on the SFM; a neural radiation field model based on uncertainty perception is constructed, and modeling is carried out on volume density, color and depth uncertainty parameters of space points; introducing a depth uncertainty synthesis formula into the volume rendering framework; constructing luminosity loss fused with random structure similarity; designing a self-adaptive deep optimization mechanism of uncertainty perception, and optimizing a training process through a progressive uncertainty learning strategy; and applying the trained model to a sparse view angle indoor scene to generate a high-quality three-dimensional reconstruction result and an uncertainty quantization graph. According to the invention, by introducing a fusion method of uncertainty perception and adaptive depth supervision, the problems of poor reconstruction quality and detail missing under a sparse view angle are effectively solved, and the precision and robustness of indoor scene three-dimensional reconstruction are significantly improved.

The invention discloses a knowledge-data dual-drive urban inland inundation simulation method considering uncertainty. The method comprises the following steps: acquiring basic hydrological elements and geographic information data to construct a feature input set; constructing an urban inland inundation physical model based on a hydrological hydrodynamic principle; the physical model parameters are iteratively corrected based on actually measured rainfall-inundation data, and a water depth data set with parameter uncertainty constraints is output; correcting data uncertainty, and constructing an urban waterlogging data set; generating and training a sub-model group through self-service sampling, and fusing structural uncertainty and weight uncertainty by adopting an integration strategy; and quantifying the uncertainty of integrated prediction, outputting a prediction result with a confidence interval, and verifying the precision. According to the method, the interpretability of a physical model and the feature learning ability of a data model are effectively fused, high-resolution and interpretable waterlogging water depth prediction in a complex urban scene is realized through a multi-source uncertainty quantification mechanism, and reliable support is provided for early warning and intelligent scheduling of urban flood.

The invention discloses a generator state estimation method and system considering noise and parameter uncertainty constraints. The method comprises the following steps: acquiring model parameters and dynamic state vectors of a generator, and establishing augmented state vectors; performing unscented transformation on the augmented state vector to obtain a particle set; improving to obtain robust mixed Kalman particle filtering, and in the process of performing unscented Kalman filtering on an augmented state vector, taking correlation entropy maximization of a measurement information sequence as a target function, and solving by adopting a fixed point iteration method to obtain a filtering gain; determining a filtering gain according to the updated state of the measurement information; robust mixed Kalman particle filtering is executed, physical constraints of model parameters serve as a feasible region, after resampling, projections of the model parameters in new-generation particles exceed the feasible region, the model parameters are set to be closest boundary points, and then resampling is conducted again; a weighted average value of the particle set is an optimal joint estimation value, a dynamic state estimation value and a model parameter identification result are separated, and reliable uncertainty quantization is provided for state and parameter estimation.

The invention discloses a pre-stack seismic elastic parameter inversion method based on a conditional diffusion model, and the method comprises the steps: obtaining a pre-stack CMP multi-angle seismic trace set and a well data low-frequency trend, mapping seismic data and an elastic parameter model to a potential space, training the conditional diffusion model in the potential space, carrying out the step-by-step denoising in order to recover the distribution of the elastic parameter, and carrying out the inversion of the elastic parameter. In the sampling process, Aki-Richards equation physical constraint is introduced, and uncertainty quantization is realized through transverse constraint and multiple sampling. According to the method, the spatial continuity of an inversion result can be ensured, uncertainty quantification can be realized, and reliable confidence evaluation is provided for geological interpretation. The method is wide in applicability and high in calculation efficiency, and the pre-stack elastic parameter inversion result with higher precision and higher credibility can be quickly obtained in actual three-dimensional seismic data processing.

The invention relates to the technical field of engineering structure health monitoring, and discloses a method for evaluating the fatigue life of a main beam based on sample continuous increment, which comprises the following steps: acquiring multi-modal monitoring data including physical parameters of strain, displacement and acceleration and external factor data of environmental temperature and humidity and traffic flow information; performing multi-source data fusion by using an adaptive feature extraction network; constructing a dual-knowledge consolidation incremental learning framework, and keeping the memory of historical knowledge when newly added data is processed; performing uncertainty quantification on a prediction result based on Bayesian deep learning, and establishing a risk early warning mechanism; according to the method, the problem of disastrous forgetting in the model updating process is effectively solved, and a relatively high historical knowledge retention rate is kept; a scientific basis is provided for bridge maintenance and maintenance decision making, and maintenance resource allocation is optimized; the method has excellent adaptability and generalization ability, and realizes continuous monitoring and evaluation in the whole life cycle.

The invention relates to the technical field of intelligent medical treatment, and discloses a cataract surgery navigation control method based on multi-modal fusion, which comprises the following steps: carrying out lightweight preprocessing on an eye fundus image, ultrasonic probe data, a corneal topographic map and intraocular pressure parameters through an edge computing architecture, and constructing an efficient feature extraction network by adopting a knowledge distillation technology; self-adaptive feature fusion is realized based on an uncertainty quantification mechanism, real-time structure recognition is provided by utilizing an augmented reality technology, an intelligent navigation strategy is generated by pre-training a reinforcement learning model, an instrument control system with multilayer safety guarantee is established, and continuous optimization of the system is realized by adopting an online learning mechanism. According to the invention, the precision and safety of the operation are effectively improved, and an effective technical scheme is provided for intelligent navigation control of the cataract operation.

The invention discloses an intelligent fishing point dynamic prediction method and system based on multi-source marine environment data fusion. The method comprises the following steps: step 1, access, space-time alignment and pre-screening of multi-source heterogeneous marine environment data; step 2, priori knowledge base construction and suitability modeling based on target fish ecological habits; 3, constructing a fishing point prediction model fusing the multi-time-sequence environmental characteristics and deep learning; step 4, fusing two-channel prediction results under the Bayesian framework and quantifying uncertainty; 5, generating a dynamic mask of a real-time sea condition safety threshold value and fishery regulation space constraint; 6.1, constructing a comprehensive scoring function of the risk perception function. According to the method, multi-source heterogeneous data is constructed, a target fish ecological suitability model and a depth time sequence prediction model are combined, the fishing point posterior probability is generated through a Bayesian fusion mechanism, the prediction uncertainty is quantified, and dynamic fishing point recommendation with risk perception and compliance safety is realized.

The invention discloses an energy efficiency optimization control method for a heterogeneous computing power cluster, and particularly relates to the technical field of energy efficiency optimization control. According to the method, a unified time reference with a high-precision energy consumption anchor point as a reference is constructed, and residual error construction is carried out on power consumption data of a multi-source sensor; and a Bayesian online change point detection mechanism based on risk scoring is introduced to identify sensor drift. The system further adopts a multi-sensor Kalman filtering algorithm to carry out joint estimation on a real power consumption state and a channel bias state, and the fusion precision is improved through bias backtracking correction and observation noise self-adaptive adjustment. In order to improve the adaptive capacity to cross-source interference and structural change, the system constructs a dynamic graph structure in a sliding window, topology-time joint modeling and self-supervised correction are performed in combination with a graph convolutional neural network, and fine-grained adjustment and uncertainty quantification of observation values of each channel are realized.

The invention discloses a leg health state evaluation and fault tracing system and method based on a time sequence large model, and the method comprises the steps: an input layer is responsible for carrying out the synchronous collection, normalization and time alignment of various sensor signals, and constructing time sequence input data in a unified format; the feature fusion layer adopts a sliding window mechanism to carry out Patch segmentation on an original signal, and local representation is enhanced in combination with feature engineering; a channel attention mechanism is further introduced, the weight of each channel is adaptively adjusted according to the dynamic relevance between the sensors, and information fusion and feature screening are achieved; the model layer constructs a long-term dependence modeling framework based on a time sequence large model and is integrated with an LoRA low-rank adaptation module, and the prediction layer performs uncertainty quantification on a health state prediction result through dynamic confidence interval estimation; and the application layer completes fault tracing and key component positioning according to time sequence attention distribution and channel weight change, and synchronously generates a health trend curve, confidence interval distribution and a visual early warning interface.