553 results about "Statistical Confidence" patented technology

The invention relates to the technical field of wind power prediction. The invention provides a wind power prediction method and system. The method comprises the following steps: acquiring multi-dimensional meteorological time series data, three-dimensional elevation data and unit operation data of a target wind power plant; constructing a spatial-temporal feature fusion network, extracting time sequence dynamic features, and performing weighted fusion on the spatial correlation features and the time sequence dynamic features to obtain a fusion feature vector; establishing a hybrid prediction model, and taking the fusion feature vector as input to obtain a wind power initial prediction result; introducing a terrain correction factor, constructing a turbulence intensity compensation function, and performing micro-terrain disturbance correction on the wind power initial prediction result; and outputting a final power prediction curve and a confidence interval. The problems that in an existing wind power prediction method, a physical model is insufficient in complex terrain microclimate modeling precision, high in calculation complexity and difficult to meet the real-time requirement, a statistical learning method is limited in high-dimensional nonlinear time sequence feature expression capacity, and prediction errors are remarkably increased under the abnormal working condition are solved.

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.

An approach to time-series data point anomaly detection may be presented. Data point anomalies in time-series data can cause a cascade of incorrect predictions in a time-series data prediction model. Presented herein may be an approach to decompose a time-series training data set into elementary components, such as seasonal, trend and residual. The approach may determine one or more confidence intervals for elementary components of data points including level shift, variance, and outlier. From these confidence intervals, new data points can be analyzed and identified as anomaly data points. The approach may also prevent anomaly data points from being incorporated into a time series data prediction model, reducing prediction error in the prediction model.

The invention discloses a power plant equipment fault prediction method based on a time sequence large model, and the method comprises the following steps: S1, collecting and preprocessing the time sequence data of a multi-source sensor of a power plant, and generating a standardized time sequence data set; s2, constructing a time sequence large model, inputting standardized data, and outputting a future operation state predicted value; s3, comparing the running state prediction value with an actual measurement value to generate a prediction residual sequence; s4, constructing a Bayesian neural network model, inputting a prediction residual sequence, and outputting error probability distribution; s5, optimizing a Bayesian neural network structure and hyper-parameters by adopting an ant colony optimization algorithm; s6, confidence interval estimation is executed, and whether the state is a high-risk state or not is judged; and S7, outputting a running state label, and dynamically acquiring a data closed-loop updating model. According to the invention, high-precision prediction and uncertainty evaluation of the operation state of the power plant equipment are realized, so that the accuracy and response time efficiency of fault early warning are improved.

The invention provides a new energy output prediction method and system based on Monte Carlo Dropout, and the method comprises the steps: carrying out the probabilistic prediction of new energy output through a Monte Carlo Dropout technology, generating a dynamic prediction result containing a confidence interval, and quantifying the uncertainty of meteorological sudden change and equipment state; secondly, constructing a multi-stage random dynamic programming model, discretizing a prediction interval into multi-scene input, designing a non-linear objective function based on the discharge depth, and synchronously optimizing the electricity purchase cost and the energy storage aging cost; and finally, realizing rolling optimization of the system in combination with a model prediction control framework, and dynamically adjusting an energy storage aging cost weight by updating prediction data and a scheduling instruction on line and embedding an energy storage health state real-time feedback mechanism. The photovoltaic and wind power consumption rate can be remarkably improved, the full life cycle cost of an energy storage system is reduced, and meanwhile, the robustness of a scheduling strategy in extreme weather is ensured.

The invention relates to the crossing field of material design and artificial intelligence, in particular to a solid electrolyte intelligent inverse design method fusing a graph neural network and confidence analysis. According to the method, a prediction framework integrating multiple models is constructed, support vector regression, gradient boosting regression, a deep neural network and a graph neural network are included, component, process and structure parameter characteristics are fully fused, and the nonlinear mapping relation between input variables and performance parameters such as resistivity and conductivity is efficiently learned. In order to improve the credibility, a Bayesian neural network and a Monte Carlo method are further introduced, a confidence interval corresponding to each group of prediction results is output, and quantitative evaluation of the credibility of the prediction value is realized. In the inverse design module, high-dimensional submerged space parameters are generated based on a variational auto-encoder, and intelligent recommendation of parameter combination driven by target performance is realized in combination with strategies such as Bayesian optimization and a genetic algorithm. The design efficiency of the solid electrolyte and the success rate of material discovery can be effectively improved.

The invention belongs to the technical field of wind-solar power generation power monitoring, and particularly relates to a new energy wind-solar power data monitoring system and method. According to the method, power fluctuation characteristics and equipment state correlation indexes are extracted through abnormal value detection and time sequence analysis, so that the precision and efficiency of data processing are improved, and in the aspect of prediction, dynamic comparison between a historical operation data set and the current power fluctuation characteristics is utilized, and environmental parameter change trends are combined. A power prediction curve and a confidence interval are generated, so that the system can recognize potential abnormal operation in advance, decision support time is provided for operation and maintenance personnel, in addition, the system has corresponding fault diagnosis and optimization capabilities, when the prediction deviation degree exceeds a preset threshold value, an early warning mechanism is automatically triggered, a fault source is positioned through a fault diagnosis process, and the fault diagnosis efficiency is improved. And finally, according to a fault diagnosis result, a power prediction curve is corrected and optimized to form a closed-loop optimization mechanism, and the prediction precision and the operation efficiency of the system are continuously improved.

The invention provides a cigarette abnormal flow standard risk prediction method and system. The method specifically comprises the steps of collecting multi-source data to construct a causal feature set, generating a causal graph according to domain knowledge and algorithm mining, quantifying an average processing effect through a dual machine learning method, constructing a risk model to position a root cause, simulating risk change after intervention through anti-fact inference, and outputting a result. Through the dual machine learning and anti-fact inference technology, the causal effect is accurately quantified, the intervention effect is simulated, the confidence interval is dynamically adjusted, and the risk prediction and decision support capability can be remarkably improved.

The invention relates to the technical field of information retrieval, in particular to an artificial intelligence digital science and technology platform based on big data analysis, which comprises a data uncertainty modeling module for receiving a big data stream, determining a confidence interval boundary for each data item to represent the uncertainty of the data item, generating a data item uncertainty parameter set, and combining each data item with the corresponding data item uncertainty parameter set, and then storing the data item and the corresponding data item uncertainty parameter set to form a structured probability data record. According to the method, by independently establishing an uncertain parameter structure for each data item in the data stream, tight binding of the data items and the corresponding uncertain parameters is realized, a structured probability data record is generated, the precision and reliability of the data in the query and calling process are guaranteed, and retrieval errors caused by isolated storage of the data items are avoided; through probability attribute grouping of a preset space and a numerical range and establishment of a multi-dimensional probability index structure, the search space and the filtering difficulty of probability data are reduced.

The invention discloses a Bayesian neural network-based concrete durability prediction method, which is characterized in that durability prediction is carried out by designing a multilayer Bayesian neural network model and combining data such as a concrete mix proportion, external environment conditions and material attributes. The Bayesian neural network updates the weight and bias through random sampling, and can quantify the uncertainty of prediction and provide a prediction confidence interval. The method comprises the specific steps of data preprocessing, network training, sampling, calculating and outputting a mean value and a standard deviation, optimizing model parameters through a gradient descent method, and finally evaluating model prediction performance. According to the method, the uncertainty in concrete durability prediction can be effectively quantified, more scientific and accurate decision support is provided for building engineers, and the cost and time of experimental testing are reduced.

The invention relates to the technical field of wind speed prediction, in particular to a wind speed prediction method and system based on entropy clustering, and the method comprises the following steps: carrying out the multi-scale decomposition of a wind speed sequence through a permutation entropy algorithm, generating subsequences, carrying out the sliding window probability distribution calculation of a plurality of subsequences, setting a dynamic classification threshold value based on a normalized entropy value, and carrying out the calculation of the sliding window probability distribution. And dividing the sub-sequence set into an entropy classification result set. According to the method, a classification threshold value is dynamically set through sliding window probability distribution, the sensitivity of fixed entropy division to data complexity change is overcome, nonlinear mapping between an original sequence and entropy components is established through GRU training, the feature extraction depth and low component error transmission are enhanced, high, medium and low entropy components are modeled through Bi-RNN, LSTM and SVR, feature extraction with different complexities is matched, and the accuracy of feature extraction is improved. Chaotic mapping optimization fusion weight, multi-target optimization balance component complementarity and dynamic error reference are combined with feedback to adjust a confidence interval, error distribution adaptive tracking is realized, and prediction reliability is enhanced.

The embodiment of the invention provides a barrel service life prediction method and device based on gradient enhancement and a quantile recursive network, and the method comprises the steps: collecting the multi-source sensor data of the whole life cycle of a barrel, and carrying out the preprocessing, and forming a standardized data set; constructing an XGBoost model, performing feature importance analysis on the standardized data set through the XGBoost model, screening key features based on an analysis result to obtain a data set after feature selection, and performing optimization training on the XGBoost model through gradient lifting and regularization methods; dividing the data set after feature selection into a training set and a test set; in combination with a quantile regression method, constructing a life prediction model based on a quantile recurrent neural network, training the life prediction model by using the training set, and training and optimizing model parameters through a bifurcated sequence to obtain an optimized barrel life prediction model; and inputting a test set into the model, outputting a residual service life prediction result containing a prediction value and a confidence interval, and evaluating the prediction performance.

The invention relates to the technical field of industrial information and data processing, in particular to a cutting fluid multi-parameter self-adaptive monitoring and early warning method and system based on a dynamic threshold value, and aims to obtain and standardize multi-modal data of a cutting fluid in real time, construct a coupling attenuation prediction model in combination with processing working condition parameters, and predict a joint attenuation trend under a specific working condition. A cutting fluid performance time sequence is modeled through a Gaussian process, a confidence interval boundary is dynamically adjusted, and a self-adaptive single parameter dynamic threshold value is calculated. And a Copula function is used to learn a non-linear dependence structure among multiple parameters, a combined overrun risk is identified, and a multi-parameter combination threshold value is dynamically adjusted according to a preset rule. The system monitors data in real time and triggers early warning when abnormity is found, a digital computer is used for intelligent decision support processing, a maintenance knowledge base and a process optimization rule are combined, and accurate maintenance suggestions are generated. In addition, the edge intelligent unit ensures the independent operation capability of the system when the communication is interrupted.

The invention discloses a statistical analysis-based engineering cost dynamic adjustment method and system, and aims to solve the problems of many errors and poor accuracy and reliability when the engineering cost is changed due to factors such as material price fluctuation, the method comprises the steps of obtaining a price change message and extracting related data, matching an engineering material data table by using a preset template, and obtaining an engineering material data table; the system queries and processes price data according to a change material identifier, carries out source diversification processing on the change price data, and also relates to initial construction and dynamic updating of an engineering cost template, the system is composed of a price change module, an engineering material data table module, a to-be-changed module, a to-be-replaced module and other modules, and all the modules work cooperatively to realize corresponding functions. The method has the following advantages that on the aspect of data processing, multi-channel data are automatically integrated, prices are fused, and the operation risk is reduced; in the aspect of template construction and updating, historical data and algorithms are utilized, and the material matching accuracy is improved; during price adjustment, the confidence interval is calculated based on statistical analysis, and the accuracy and reliability of the project cost are effectively guaranteed.

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 design and application of two-dimensional materials, and discloses a design and simulation method of a two-dimensional semiconductor nanometer transistor, which comprises the following steps: collecting multi-source data of design and simulation of the two-dimensional semiconductor nanometer transistor, and screening through a data quality evaluation model to obtain a layered data structure; constructing and training a Bayesian neural network model; key influence parameters are identified through a multi-scale feature extraction algorithm and a parameter correlation analysis algorithm, and an attention algorithm is applied to pay attention to an important parameter combination; meanwhile, the uncertainty is predicted, a sampling point with the most information content is generated, and a prediction confidence interval is provided; through active learning feedback optimization circulation, high-value data points are selected based on prediction uncertainty for verification, and the model is updated until preset precision or resource constraint is achieved; according to the method, through multi-scale feature representation and parameter correlation analysis, invalid parameter exploration is reduced, and meanwhile, the model interpretability is improved through integrated physical constraint and uncertainty quantification.

A system and method for predictive analysis, scenario simulation, and decision optimization is provided. The system includes a prediction management system executed on a distributed computing infrastructure, and a prediction engine configured to receive input data, including event parameters, user-defined constraints, real-time data feeds, and historical trends. The prediction engine generates predictive models using algorithms trained on historical event outcomes, assigns probability scores and confidence intervals to potential outcomes, and dynamically updates the models based on new input data. Actionable insights are generated and ranked according to predefined success criteria. A non-transitory computer-readable medium is used to store the predictive models, outcome probabilities, and actionable insights for subsequent analysis and reporting. This system facilitates enhanced decision-making by offering real-time insights and continuously refined predictions, thereby optimizing responses to complex events and scenarios.

The invention relates to a fault early warning method, device and equipment for an energy storage system. The method comprises the following steps: acquiring target data of a target parameter; the target data is generated by preprocessing real-time operation data and real-time environment data of the energy storage system; extracting a target feature corresponding to each target parameter based on the target data; calculating a feature confidence interval of each target parameter based on the historical data of the target parameters, and marking suspected abnormal features based on the feature confidence intervals; identifying at least two fault types based on the suspected abnormal features; based on the current environment data, the load power of the energy storage system and the historical operation and maintenance data of the energy storage system, carrying out fuzzy reasoning on the risk membership degree corresponding to each fault type and dynamically adjusting the basic weight coefficient corresponding to each fault type; and determining a comprehensive risk index based on the risk membership degree corresponding to each fault type and the dynamically adjusted dynamic weight coefficient, and performing fault early warning analysis processing based on the comprehensive risk index. The method can improve the accuracy of fault early warning.

The invention discloses a physical field solving method based on a Bayesian physical information extreme learning machine, and the method comprises the steps: constructing a single-layer full-connection neural network, carrying out the random initialization, and fixing the weight of an input layer; based on a partial differential equation of a physical system and boundary conditions thereof, defining a training loss item containing physical information; a physical system solving problem is converted into a linear least square problem, and a linear equation set is constructed; supposing that an output layer weight parameter obeys Gaussian prior distribution with the mean value being zero, and controlling a covariance matrix by an adjustable hyper-parameter; constructing a Gaussian likelihood function based on the observation data, and calculating posterior distribution of the output weight in combination with the prior distribution; carrying out iterative optimization on the hyper-parameter by adopting an evidence maximization method to obtain a mean value and a covariance of posterior distribution; based on posterior distribution, adopting a Monte Carlo integral method to generate prediction output of the physical system; and performing uncertainty quantization based on the variance of prediction output, and outputting a prediction value and a confidence interval thereof.

The invention discloses a heavy duty gas turbine compressor scale deposition detection method based on a liquid neural network, and relates to the technical field of anomaly detection, and the method comprises the following steps: collecting operation data for correlation analysis; the selected feature data is preprocessed; extracting time characteristics of the operation parameters of the gas compressor; calculating weights of interaction among the parameters, and outputting spatial correlation; constructing a space-time fusion model, and inputting normal operation data to train the model; and a parameter prediction sequence is output, a multi-dimensional residual vector of a predicted value and an actual value is calculated, and by constructing a dynamic threshold function, when the model converges and residual distribution deviates from a normal working condition confidence interval, a gas compressor fouling anomaly detection result is output. According to the invention, through the dynamic topological structure of the liquid neural network and in combination with a spatial-temporal characteristic collaborative mining mechanism, quantitative evaluation of the scale deposition degree of the gas compressor is realized, and the precision and robustness of gas compressor scale deposition anomaly detection are improved.

The invention belongs to the technical field of wind power weather forecasting, and provides an all-region three-dimensional wind speed correction method and system, and the method comprises the steps: constructing a weather numerical forecasting model, and obtaining wind field forecasting data; fusing the preprocessed multi-source data by adopting an optimal interpolation method to obtain three-dimensional space-time continuous wind field analysis data; based on the wind field forecast data and the wind field analysis data, features are extracted and fused, then a historical forecast error sample set is constructed, a wind speed correction model is constructed, and the historical forecast error sample set is utilized to train the wind speed correction model; introducing an initial value, a physical parameter and boundary condition disturbance, calculating a mean value and a standard deviation of each set result, extracting a probability distribution feature of a wind speed, constructing a confidence interval, estimating a probability density function, and quantifying an occurrence probability of an extreme wind speed event; and the prediction result of the wind speed correction model and the multi-source wind field observation data are fused to generate final three-dimensional wind field data, so that the actual requirements of wind power prediction and power grid dispatching can be met.

The invention discloses a verification system and method for a material formula through a confidence interval, and relates to the technical field of material informatics and intelligent research and development decision. Comprising a data acquisition module used for acquiring candidate formula basic data, historical experiment basic data, environment associated data, material recessive data and equipment state data and preprocessing the acquired data; according to the method, the final error value is obtained through fusion, the adjusted final credible interval is constructed, the problems that an existing material performance prediction tool can only output a point prediction result and lacks a stable credible interval, and engineers are difficult to assess that performance reaches the standard and actually and successfully grasp are solved, the coverage rate is verified through the verification set, the error scale is scaled, and the reliability of the material performance prediction tool is improved. It is ensured that the credible interval meets the preset coverage requirement, successful mastering of performance standard reaching can be quantified, an engineer does not need to depend on experience judgment any more, and the accuracy of performance evaluation is improved.

The invention relates to a power capacity evaluation method based on a dynamic confidence interval and double-layer optimization, which solves the problems of inappropriate single-side modeling, static evaluation, source-load coupling modeling data processing mode and the like in the prior art, and adopts the technical scheme that a prediction error of wind power output is obtained based on historical data and a prediction value of the wind power output; based on the prediction error, determining an influence parameter generating the error; creating a power supply side model based on the prediction error and the influence parameter; obtaining a demand response sensitivity coefficient and a time-varying adjustment parameter based on the historical load data, the demand response execution record and the external influence factor; creating a load side model based on the demand response sensitivity coefficient and the time-varying adjustment parameter; creating a source-load joint scene model based on the power supply side model and the load side model; optimizing the source-load joint scene model through a double-layer robust optimization model; an assessment risk probability index and a capacity vacancy expectation are determined based on the optimized source-load joint scenario. The method has the advantages that a source-load joint scene model is created, and the coverage range and precision of an evaluation result in time and space dimensions can be remarkably improved; meanwhile, by means of a dynamic confidence interval adjustment mechanism and a double-layer optimization strategy, effective balance between the electric power market economy and the operation safety is achieved.

The invention discloses a power grid dispatching scheme generation method and system based on load optimization, and the method comprises the steps: predicting a reference load change curve and a confidence interval of each node in a future set time period according to the load data and meteorological data of each node in a power grid topological graph in a corresponding time period; continuously determining a risk area based on the risk assessment model and determining a predicted load offset and a standard deviation so as to correspondingly optimize and broaden a reference load change curve and a confidence interval of each node in the risk area; and constructing an uncertain scene set based on the reference load change curve and the confidence interval, then constructing an objective function, and solving the objective function based on the uncertain scene set to generate an elastic scheduling scheme with the minimum power generation cost and the minimum load vacancy in the worst load scene. According to the invention, through supplementing the prediction load offset and the standard deviation, the prediction precision of the short-term load change under the condition of sudden power consumption peak or extreme weather is obviously enhanced, and the power grid dispatching level is improved.

The invention discloses a fault-tolerant reconstruction method for sensing faults of a spatial dexterous hand, and relates to the field of robot control. In order to solve the defects that in the prior art, a dexterous hand on-orbit sensor is weak in fault-tolerant capability, insufficient in model generalization capability and incapable of being adaptive to complex space environment changes, the technical scheme provided by the invention comprises the following steps: constructing a conditional variation auto-encoder model, inputting a joint position and a rope length sequence, and constructing a model; time sequence features are extracted, and a reconstructed joint position mean value and a prediction variance are output; the reconstructed joint position mean value is compared with actual joint data, a dynamic confidence interval is generated, and whether the data breaks down or not is judged; for the data judged to be normal, information entropy is calculated based on the prediction variance, and data samples with the information entropy exceeding a set threshold value are screened and written into a dynamic buffer area; and when the buffer data is fully loaded, incremental learning is triggered, and model parameters are updated by utilizing the buffer data. The method is suitable for real-time detection and fault-tolerant reconstruction of sensor faults in the long-term on-orbit operation process of the space dexterous hand.

The invention relates to the technical field of metal smelting, and particularly discloses a mechanism data co-driven metal smelting process key process index sensing method, which comprises the following steps of S01, carrying out mechanism modeling in a smelting process, and providing a mechanism model for key process indexes to predict a key process index preliminary interpolation; s02, key process index accumulative error compensation: after a key process index preliminary interpolation is obtained through a mechanism model, spatial feature extraction is carried out on collected operation variables by introducing a CNN model, accumulative errors output by the mechanism model are compensated, and a complete key process index historical data sequence is obtained; and S03, based on probabilistic prediction of the compensation sequence, carrying out time sequence modeling and bidirectional feature capture on the sequence subjected to error compensation, improving the prediction precision in combination with an attention mechanism, and realizing prediction of each confidence interval and single-value prediction by adopting a mixed quantile regression mode. According to the method, the problem that the accuracy and the reliability of process index sensing in the traditional metal smelting process are low is solved.

The invention discloses a power equipment health evaluation method and system based on time sequence analysis and probability modeling, equipment and a medium, and relates to the technical field of power equipment state monitoring and fault prediction, and the method comprises the steps: obtaining and preprocessing multi-source operation data of power equipment, outputting a predicted value and a confidence interval of a future parameter through a time sequence prediction model, calculating a residual sequence of an actual observation value and a predicted value, fitting distribution through a probability distribution model, establishing a statistical characteristic model of a normal operation state of the equipment, performing anomaly judgment, calculating a health degree index of the equipment based on a deviation degree and a dynamic weight of a monitoring parameter and weighted accumulation, and dividing equipment state grades according to the index. Quantitative evaluation of the health state of the equipment is realized. According to the method, accurate quantification and early abnormity identification of the health state of the power equipment are realized, a reliable basis is provided for predictive maintenance, and the intelligent level and the safety guarantee capability of power grid operation and maintenance are remarkably improved.

The invention relates to a community demand response carbon emission reduction data monitoring method based on the Internet of Things technology, and the method comprises the following steps: S1, collecting multi-source heterogeneous data of community carbon emission data, and carrying out the preprocessing, and obtaining a basic data set; s2, performing feature engineering and depth representation according to the basic data set, and constructing a high-dimensional feature vector set; s3, constructing a new energy output prediction model, and predicting a new energy output confidence interval based on the high-dimensional feature vector set; s4, constructing a load demand elastic prediction model, and predicting a rigid load and flexible load adjustment boundary based on the high-dimensional feature vector set; s5, based on the predicted new energy output confidence interval and the rigid load and flexible load adjustment boundary, adopting multi-objective optimization control to obtain an optimal equipment control instruction set; and S6, performing control based on the optimal equipment control instruction set, obtaining the verification emission reduction amount and a user response log, and generating a carbon perbenefit integral. According to the invention, the community can flexibly adjust the energy supply strategy according to the new energy volatility and the user demand.

The invention provides a high-speed rail insulation joint health monitoring and early warning method and system, and relates to the technical field of joint health monitoring, and the method comprises the steps: carrying out the dimension reduction of resistance data and environmental influence factors through a random projection algorithm, carrying out the anomaly detection of the resistance feature data after the dimension reduction through an isolated forest algorithm, and carrying out the early warning. And through weight adjustment and path length optimization, a resistance abnormal point is marked. Using an empirical mode decomposition method to carry out constrained decomposition on the abnormal point data, and extracting multi-scale intrinsic mode function feature data; and performing resistance change trend prediction by using a Gaussian process regression model to obtain a resistance change prediction value and a confidence interval thereof. And inputting the predicted value and the confidence interval into a fuzzy reasoning model to obtain a graded early warning result of the high-speed rail insulated joint. Through multi-level data processing and analysis, the accuracy and reliability of fault early warning are improved, and safe operation of a high-speed rail steel rail system is ensured.

The invention discloses a machine learning-based flight wheel block removal time prediction method, and relates to the technical field of flight prediction, and the method comprises the steps: collecting flight preorder state data, airport resource distribution data and meteorological data in real time, and generating an original data set through multi-source heterogeneous data fusion; constructing spatio-temporal features including a preorder flight delay propagation chain, a stand-vehicle conflict energy matrix and a meteorological attenuation factor, and screening and optimizing a feature set through distribution drift detection; training and verifying the Bayesian depth quantile regression model, and outputting a prediction result with a confidence interval; and combining the airport Internet of Things positioning feedback optimization feature set and parameters to generate a prediction deviation diagnosis report. According to the method, a preorder flight delay propagation chain and a stand-vehicle conflict energy matrix are constructed, flight dynamics, resource allocation and weather attenuation factors are embedded into a unified spatial-temporal feature space, and the problem of feature information loss caused by data isolation is solved.