26results about How to "Quantitative uncertainty" patented technology

The invention discloses an urban flood prediction method based on a Bayesian convolutional neural network, and the method comprises the steps: collecting historical rainfall events of a research region, simulating different rainfall events through hydrodynamic simulation software, and obtaining the maximum submerging water depth; selecting characteristic variables influencing waterlogging water depth, wherein the characteristic variables comprise 10 rainfall characteristic variables and 10 spatial characteristic variables; considering uncertainty to construct a Bayesian convolutional neural network prediction model; training the model based on a loss function MAE; and inputting the data in the verification set into the trained model, and calculating the mean value of the output approximate posteriori distribution as the predicted value of the water depth. The method is proposed on the basis of calculating and analyzing the relationship between the characteristic variables and the target variables, effectively fusing different data and considering possible uncertainty sources, not only realizes the prediction of the size and range of the submerged water depth of the research area, but also quantifies the prediction uncertainty, so that the prediction accuracy is improved. And support is provided for real-time flood disaster management.

The invention discloses a cable corrosion steel wire service life evaluation method and system, and the method comprises the steps: obtaining corrosion steel wire fatigue test data and corrosion related parameters, building a data set based on the corrosion steel wire fatigue test data, building an initial prediction model, training the initial prediction model based on the data set, and obtaining a target service life prediction model. The physical parameters of the to-be-predicted cable are input into the target life prediction model for life prediction, corrosion steel wire life evaluation is conducted on the to-be-predicted cable based on a life prediction result, and the life prediction result comprises a fatigue life prediction value and the confidence coefficient corresponding to the fatigue life prediction value. The target life prediction model is constructed based on the corrosion related parameters and data of multiple dimensions, life prediction of the cable steel wire is realized based on the target life prediction model, the uncertainty of the prediction result is quantified, the accuracy of life evaluation is ensured, and a reliable evaluation result is provided for cable maintenance.

The invention discloses an energy storage battery capacity attenuation short-term prediction method and system based on multi-model fusion, relates to the technical field of battery management, and aims to solve the problem that short-term capacity attenuation prediction of an energy storage battery is difficult in the prior art. Taking the battery parameter variable data of the to-be-tested time period as input, and obtaining a plurality of machine learning model prediction results based on the output of the plurality of machine learning models; averaging and splicing a plurality of machine learning model prediction results to obtain a preliminary battery energy storage capacity attenuation prediction result; and taking the preliminary battery energy storage capacity attenuation prediction result as input, and obtaining a battery energy storage capacity attenuation short-term prediction result based on linear regression model output. According to the method, the instantaneous characteristics in the operation of the battery are used as input, short-term prediction of capacity fading can be reasonably and accurately carried out, and a new basis is provided for real-time control and strategy adjustment of energy storage.

The invention discloses a multi-sensor signal anomaly detection method, electronic equipment and a medium. The method comprises the steps of obtaining a first confidence interval and a second confidence interval based on historical measurement data of a target sensor; taking the sum of the first confidence interval and the second confidence interval as an overall dynamic threshold interval; when the sum of the 2 norm of the first output data corresponding to the to-be-detected data of the sensor and the 2 norm of the difference between the second output data and the first tensor does not belong to the total dynamic threshold interval, outputting a first abnormal label; and / or acquiring historical measurement data of T sensors around the target sensor; calculating a sample mean value corresponding to the measurement data of the T sensors, calculating a sample standard deviation, and calculating a standard error so as to obtain a confidence interval; and when the real-time measurement data of the ith sensor around the target sensor does not belong to the confidence interval, judging that the ith sensor is abnormal at the moment, and outputting a second abnormal label.

The invention relates to a distribution network maintenance topology identification system based on multi-source data fusion, and the system achieves the effective integration and precise processing of multi-source power distribution network data through the cooperative work of a multi-source data collection module, a data preprocessing module and a measurement generation module, and remarkably improves the temporal-spatial resolution of the state quantity of a distribution network. According to the method, a confidence evaluation system is constructed, and an algorithm confidence evaluation system is used for carrying out confidence scoring on an output identification structure, so that the uncertainty of an identification result can be quantified, and the availability and reliability of the system in an actual complex environment are greatly improved; through seamless connection and data interaction between a database and a marketing system and a scheduling system, the applicability and effectiveness of the system in an actual maintenance scene are ensured, accurate and reliable topology identification support can be provided for power distribution network maintenance, and the maintenance efficiency and the power supply reliability are improved; the method has the advantages of being high in self-adaption, accurate and reliable.

The invention discloses a tire three-way force prediction method based on a piezoelectric type intelligent tire technology and a BKA-GPR. A finite element model of a tire and a PVDF (polyvinylidene fluoride) sensor is constructed, and a piezoelectric type intelligent tire model is established in combination with an Inp fusion method; through global sensitivity analysis, sensitivity of changes of a longitudinal force (Fx), a lateral force (Fy) and a vertical force (Fz) to voltage output of the PVDF sensor at different positions in the tire is evaluated, and the optimal installation position of the sensor is determined. A Sobol method is used for collecting a voltage-tire force data set, and extraction and normalization processing are carried out on signals of the ground mark area; the method comprises the following steps of: designing a tire force Gaussian process regression (GPR) model according to data characteristics, and optimizing hyper-parameters of the model through a black-wing kite algorithm (BKA); the optimal input features and the data scale are determined through a random forest (RF) algorithm, and a tire three-way force prediction model which is low in cost, high in precision and good in stability and generalization performance can be obtained by retraining the model.

The invention discloses a user electric energy use data prediction method and device and electronic equipment, the method is applied to the field of data processing, and the method comprises the following steps: collecting target electric energy data of a target user; inputting the target electric energy data into the target prediction model, and calculating target probability distribution of the electric energy use data after the target user responds to the electric power regulation request; and predicting electric energy use data of the target user according to the target probability distribution. Through the method and the device, the problem of relatively low prediction accuracy caused by high sample acquisition cost and limited training sample capacity in the process of predicting the electric energy regulation capability when the user responds to the electric power dispatching request through a neural network model in the related technology is solved.

The application discloses a power distribution network topology fast adaptive inference method and device based on meta learning, and belongs to the technical field of smart grids. The method comprises the following steps: acquiring a first data set; the first data set comprises a plurality of groups of first topology data and first measurement data of the power distribution network; the first topology data represents the connection relationship between nodes in the power distribution network, and the first measurement data represents the operating state of each node; the first topology data is taken as the label of the first measurement data, and a meta initial model is trained; second measurement data and topology label data of a target power distribution network are acquired; the topology label data represents the connection relationship between part of nodes in the target power distribution network; the topology label data is taken as the label of the second measurement data, the meta initial model is trained, and a target topology inference model is obtained; real-time measurement data of the target power distribution network is acquired, the real-time measurement data is input into the target topology inference model, and target topology data is obtained. The application can improve the efficiency of power distribution network topology inference.

The invention provides an aircraft space-time probability envelope determination method and system, and belongs to the technical field of trajectory prediction, and the method comprises the steps: inputting a data set of an aircraft into a Gaussian process regression model, and obtaining a prediction mean value and a prediction covariance of each prediction space position of the aircraft after a future moment; wherein the data set comprises a plurality of current flight data and a plurality of current environment data; based on each prediction mean value and each prediction covariance, calculating the probability that the aircraft appears at each prediction space position after the future moment; and gathering all the predicted spatial positions of which the probabilities are greater than a preset probability threshold to obtain a space-time probability envelope of the aircraft. According to the method, the spatial position and the uncertainty of the aircraft at the future moment are predicted based on the Gaussian process regression model by using the current flight data and the environmental data, and the high-probability region is screened out by setting the probability threshold value to form the spatial-temporal probability envelope of the aircraft, so that the spatial position of the aircraft at the future moment is accurately predicted.

The invention relates to a fault classification and pole selection method for a flexible direct-current power transmission system, which realizes fault classification and pole selection according to the difference of high-frequency components of bus and line fault voltages when a fault occurs, and comprises the following steps: S1, when the system has a fault, collecting bus and line fault voltage data of a single converter station, constructing a data set and dividing the data set into a training set and a test set; s2, decomposing the fault voltage by adopting discrete wavelet transform, and extracting bus and line fault voltage characteristics; s3, calculating a fine composite multi-scale discrete entropy; s4, taking an extreme random tree model as a data mining model, and taking the calculated RCMDE value as the input of an ET classifier; after data in the training set and the test set are processed through the steps S2-S3, the extreme random tree model is trained and evaluated, and the trained extreme random tree model is obtained and can be used for fault classification and pole selection. According to the method, the fault detection precision and reliability can be improved, and accurate classification and pole selection of different fault types are realized.

The present application relates to geological exploration and three-dimensional modeling technical field, disclose a kind of fluorite ore three-dimensional exploration modeling and analysis system, the system includes: data preprocessing and metallogenic period definition module, space-time geological structure tensor field construction and dynamic updating module, dynamic geodesic distance field calculation module, and multi-stage feedback driven level set modeling module.The present application is evolved by executing multi-stage time sequence, the model boundary of previous geological period evolution convergence is used as the starting boundary of current period, and the inheritance type mineralization is simulated.In evolution, the system also performs dynamic feedback: narrow band area near the current evolution surface is identified, the tensor field module is instructed to update locally in the narrow band, and the geodesic distance field is recalculated to guide the next evolution.The present application can also generate a three-dimensional boundary probability volume by applying a disturbance to the input parameters and repeating the modeling to quantify the uncertainty of the model.

The invention discloses an offshore wind power project soil space variability analysis method. The method comprises the steps that drilling data and CPT data of an offshore wind power project are collected and preprocessed; a mathematical model is established, a correlation function of drilling and CPT is constructed, and distribution characteristics of model parameters are obtained; taking the obtained distribution as initial estimation, and for any to-be-predicted point, obtaining an optimal predicted value of the point in a spatial domain according to the known data points and spatial distribution characteristics of the to-be-predicted point; the prediction result is verified and corrected by using actually measured data obtained in the actual construction process; and a high-precision soil body spatial variability prediction model is obtained through repeated iterative optimization and is used for guiding fan foundation construction scheme formulation, optimization and engineering risk assessment. The method provides data support for the whole wind power plant.

The present invention discloses a fragment cumulative damage assessment method and system, which belongs to the technical field of warhead blasting. The method comprises step S1: setting a fragment warhead for experiment, presetting the parameters of the fragment warhead, and constructing a fragment warhead damage capability matrix function; step S2: setting a simulated target area, defining that the performance of each part in the target area being damaged by the blow is uniform, and calculating the core damage area in combination with the material, shape and anti-destructive property of the target material; step S3: constructing a fragment cumulative damage model, combining the damage capability of the fragments, the regional characteristics of the target and the error factors of the shooting, and calculating and predicting the cumulative damage probability caused by the warhead fragments to the target in a single shot and multiple shots.

The application discloses a kind of based on artificial intelligence's consumer goods harmful substance intelligent screening method, it is related to artificial intelligence technical field, it is difficult to effectively identify and analyze the technical problem that a large number of natural language, commercial name or commonly known as etc. non-standardized description exists in ingredient list, it is also difficult to accurately convert these fuzzy text information into the standardized terminology that can be accurately matched by regulation database;Including the following steps: the fuzzy ingredient list containing natural language or commercial name description is preprocessed by multi-task text regularization model;Then, utilize embedding semantic similarity model and the multi-evidence fusion presumption unit of improved attention mechanism, fuzzy component is intelligently analyzed and matched, and standard substance identification and confidence are output;Finally, through multi-agent risk decision framework combines real-time regulation database, dynamic compliance screening and risk assessment are carried out;The application improves the intelligent level of consumer goods safety compliance management.

This application discloses a method, apparatus, and electronic device for predicting user electricity usage data. The method, applied in the field of data processing, includes: collecting target electricity data from a target user; inputting the target electricity data into a target prediction model to calculate the target probability distribution of the target user's electricity usage data after responding to a power dispatch request; and predicting the target user's electricity usage data based on the target probability distribution. This application solves the problem in related technologies where, due to high sample acquisition costs and limited training sample capacity, prediction accuracy is low when using neural network models to predict a user's ability to regulate electricity in response to a power dispatch request.

The invention discloses a domestic sewage yield prediction method and system based on machine learning, and belongs to the technical field of intelligent sewage management, and the method comprises the steps of data collection, data preprocessing, water demand prediction, domestic sewage yield prediction and sewage yield comprehensive prediction. According to the method, the water demand is predicted by adopting the convolutional bidirectional long-short term conformal prediction model, the prediction interval can be adaptively adjusted through quantile regression and a conformal prediction technology, the coverage rate and the reliability of the prediction interval are ensured, the prediction uncertainty is quantized, and the support for a subsequent sewage treatment decision is enhanced; a time convolution long and short term network model is adopted to predict the yield of the domestic sewage, and a time convolution network and a long and short term network are combined, so that the complex dependence of a time sequence is better captured, the prediction capability of seasonal fluctuation and long-term trend is improved, the robustness of the model to abnormal data is enhanced, and the prediction efficiency is improved. And high prediction accuracy can be kept in the face of sudden water use.

The present application relates to a pathological whole slice image classification method based on multi-branch independent mask and Dirichlet evidence fusion, belonging to the cross field of biological information and artificial intelligence. In view of the defects of traditional multi-instance learning method in weakly supervised classification task of pathological whole slice image, such as excessive attention concentration and static fusion, the present application sets dynamic mask parameters through multi-branch independent setting, forces different branches to pay attention to different pathological regions, and solves the problem of insufficient feature diversity caused by attention concentration; combining the confidence and uncertainty of Dirichlet distribution quantization branch prediction, the branch fusion weight is dynamically adjusted based on evidence theory, and the fusion robustness of multi-branch prediction result is improved. The experiment is verified on the public pathological data set such as CAMELYON-16, compared with the MIL method, the present application improves the AUC index by 1.1-2.4%, and significantly enhances the accuracy and generalization ability of pathological WSI classification.

The application provides a spatio-temporal joint planning and decision-making method and system based on uncertainty perception, which obtains a detection result of detecting a moving target in a preset range of an autonomous vehicle, and static map data in the preset range of the autonomous vehicle, generates a spatio-temporal probability occupation heat map of the moving target, fuses the static map data and the spatio-temporal probability occupation heat map, updates an occupation probability distribution at a current time based on a probability propagation mechanism, constructs a three-dimensional probability occupation grid, maps a value in the three-dimensional probability occupation grid and a collision time to a risk field, performs opportunity-risk analysis on a preset candidate strategy, determines an output decision, determines a planning space, and determines an optimal perception trajectory in the planning space; the application can avoid blind passing in a high-uncertainty condition, effectively transfer perception uncertainty to a planning layer, and significantly improve the robustness and safety of an autonomous driving system in a long-tail scenario.

This invention provides a method and system for adaptive elastic scaling of ruggedized computers based on a domestically developed platform, relating to the field of computer resource management technology. The method includes: collecting computing unit operating state parameters to construct a multi-dimensional state tensor; identifying key driving characteristics through tensor decomposition and causal inference analysis; establishing a mapping relationship between load characteristics and resource requirements; quantifying uncertainty to obtain capacity demand prediction results and confidence intervals; and finally determining the execution strategy for scaling decisions. This invention improves the accuracy of resource allocation and the reliability of scaling decisions, reduces resource waste, and enhances system stability.

The present application relates to the technical field of engine life prediction, in particular to an engine life prediction method based on multi-head attention, which first normalizes the original data of the aero-engine sensor and eliminates redundant features; then realizes time-space double-dimension adaptive weighting through the multi-head attention mechanism, and strengthens the key degradation information; then inputs the weighted data into the long short-term memory network to learn the long-time dependence relationship, and completes the preliminary prediction of the remaining useful life; finally, combining Monte Carlo regularization and kernel density estimation, multiple prediction values are generated and the uncertainty is quantified, and the mean value is taken as the final prediction result. Experimental verification shows that this method effectively highlights the key degradation features, reduces the influence of uncertainty, and significantly improves the prediction performance under single working condition and multiple fault modes, providing reliable data support for preventive maintenance of aero-engines.

The invention provides a pore pressure prediction model based on a knowledge perception time fusion converter. According to the model, the prediction accuracy of the pore pressure is effectively improved by integrating field professional knowledge and time sequence data. In the data processing stage, firstly, original logging data are preprocessed, including abnormal value detection, missing value filling and data segmentation, so that the quality and integrity of the data are ensured. In the feature extraction stage, time sequence statistical features, rock physical characteristics and empirical formula parameters are extracted from logging data by using a knowledge extraction method, and the features cover physical parameters, mechanical properties and fluid properties of a stratum. Through feature screening, key features which have great influence on pore pressure prediction are reserved. In the model training and evaluation stage, the model is trained by using training set data, and the generalization ability and robustness of the model are verified on an independent test set. The method not only improves the prediction precision of the model, but also obtains an excellent result in practical application, so that the method becomes an effective choice for replacing the traditional technology.

The method comprises the following steps: in the device layer, the action prediction of a single distributed energy device is performed with a confidence interval, the action prediction is constrained in a physically executable range through a feasibility mapping function, and a device prediction result is formed; in the cluster layer, the distributed energy devices are divided into multiple clusters according to an electrical topology by using a graph neural network, and the power adjustable interval and the stability boundary of the clusters are extracted as cluster characteristics; in the system layer, the device prediction result and the cluster characteristics are jointly input into a physical information neural network, and the running data of the power distribution system is output through simulation deduction; a virtual energy pheromone network is constructed based on the topology of the power distribution system, the node pheromone and the edge pheromone in the sampling field are sensed and sampled to obtain a sensing value, the action prediction of each distributed energy device in the cluster with a confidence interval is spliced, and a coordination strategy of each cluster is formed, so that the anti-disturbance ability under uncertainty is improved.

The invention discloses a diffusion model radar track information probability prediction method based on conditional prior. The method comprises the following steps: acquiring historical track information of a target; inputting the historical track information into the trained condition prediction network to obtain predicted track information of the target; wherein the condition prediction network is used for extracting non-stationary factors and potential variables when the target moves to obtain non-stationary features and potential variable information, and predicting a future track of the target according to the non-stationary features and the potential variable information; the predicted track information is input into the trained diffusion model to generate a plurality of possible predicted track sequences through random sampling and gradual denoising processes, predicted track distribution of the target is obtained, and the predicted track distribution further comprises uncertainty information of each predicted track sequence. The prediction information provided by the invention is more and comprises the quantitative information of the uncertainty of each prediction track, and reliable probability reference and firm decision support can be provided for subsequent decision tasks.

The invention relates to the technical field of grain storage monitoring, and particularly discloses a processing characteristic monitoring and analyzing system for early indica rice for rice noodles in a storage process, which comprises the following steps of: generating a three-dimensional quality deterioration risk map according to storage environment data, and performing layered space sampling according to the three-dimensional quality deterioration risk map to obtain a sample set with coordinate identification; performing differential scanning calorimetry analysis on the sample to obtain gelatinization enthalpy value data, and integrating the gelatinization enthalpy value data with space coordinates and risk levels of the sample into a structured database; by taking the space coordinate as a position variable, the gelatinization enthalpy value as a target variable and the risk value as an auxiliary variable, processing by adopting a covariant Kriging algorithm, and generating a continuous aging degree prediction curved surface covering the whole storage space and corresponding uncertainty evaluation data; and finally, constructing a three-dimensional visual distribution map based on a prediction result, calculating a whole warehouse statistical index, identifying a high-confidence local deterioration region, and forming a quality decision report. The problem of monitoring distortion of a traditional method is effectively solved.

The application discloses a kind of main beam performance evaluation method and system based on vehicle-induced deflection over-limit probability, related to structural performance evaluation field, by collecting deflection and vehicle monitoring data and preprocessing, separate vehicle-induced deflection component;Adopting moving block self-help method, block self-sampling is retained, data autocorrelation;Combined with POT method and generalized Pareto distribution, determine the optimal threshold by multiple testing, calculate single test point over-limit probability;Again through hierarchical sampling, Monte Carlo simulation and Gaussian kernel density estimation, quantize single test point and main beam overall time-varying over-limit probability and 95% confidence interval, combine with specification to evaluate stiffness performance and identify high-risk cross section.The application can accurately calculate the over-limit probability distribution of time-varying vehicle-induced deflection, quantify over-limit risk and uncertainty.Not only improve the utilization degree of monitoring data, but also provide theoretical support for the optimization of bridge maintenance strategy and the improvement of service safety, which has important technical significance for bridge life prediction and long-term structural safety evaluation.

A multi-model power system inertia probabilistic prediction method based on porcupine optimization and adaptive kernel density estimation includes the following steps: acquiring power system inertia-related characteristic variables, constructing a data sample set for inertia prediction, and building a CNN-BiLSTM-MHAM deep learning model based on the data sample set; optimizing key hyperparameters of the model using the porcupine optimization algorithm based on the constructed CNN-BiLSTM-MHAM deep learning model to obtain optimized model structure parameters and inertia prediction results; constructing an error database based on the error between the inertia prediction results and actual values; and using the constructed error database, probabilistically modeling the prediction error using the adaptive bandwidth kernel density estimation method, and generating the probability interval for inertia prediction by combining the Bootstrap resampling method, thereby realizing the quantification and probabilistic expression of the uncertainty of the inertia prediction results. This method not only significantly improves the accuracy of power system inertia prediction but also more effectively characterizes the uncertainty and probability distribution characteristics of inertia fluctuations.