79 results about "Univariate" patented technology

Systems and methods of anomaly detection in time-series are disclosed. A time-series dataset is received and a set of segments is iteratively defined from the time-series dataset by identifying a set of changepoints in the time-series dataset based on a changepoint type and a sensitivity parameter, determining whether the set of segments defined by the changepoints satisfy at least one threshold criteria, and modifying the sensitivity parameter when the threshold criteria is not met or outputting the set of segments when the threshold criteria is met. A segment-specific anomaly detection threshold is determined for each segment in the set of segments and a set of anomaly-flagged segments is generated. The set of anomaly flagged segments are generated by an anomaly detection process based on the segment-specific anomaly detection threshold for a corresponding segment. An anomaly-flagged time-series is generated by combining the set of anomaly-flagged segments.

The invention discloses a microservice system time sequence anomaly detection method and device, equipment, a medium and a product, and the method comprises the steps: carrying out the preprocessing of original multivariate time sequence data, converting the data into a sliding window sequence, carrying out the channel independent division of the sliding window sequence into a univariate time sequence of a plurality of channels, carrying out the periodic coding, and carrying out the calculation of the univariate time sequence; the method comprises the following steps: generating a periodic coding sequence, carrying out feature analysis on the periodic coding sequence, obtaining local features and global features, carrying out feature fusion on the local features and the global features, decoding, generating reconstructed time sequence data, and carrying out mean square error calculation on the reconstructed time sequence data and original multivariate time sequence data. According to the method, the abnormal score of each time step is obtained, anomaly detection is carried out based on the abnormal scores, semantic differences of different variables in multivariate time sequence data are accurately distinguished, relation characteristics of the different variables in the micro-service system are fully extracted, and abnormal fluctuation in the time sequence of the micro-service system is accurately detected.

The invention relates to a high-dimensional statistics and hydrodynamic force coupled flood risk assessment method and system. The method comprises the following steps: acquiring historical observation data covering river flow, tide level and rainfall events; constructing a univariate marginal distribution function; connecting the univariate marginal distribution functions of the river flow, the tide level and the rainfall event, and simulating a joint probability distribution function; coupling the joint probability distribution function with the mechanism model to obtain a probability-mechanism coupling model; inputting the determined joint probability boundary condition into a probability-mechanism coupling model, simulating to obtain composite flood scenes in different return periods, and comparing the composite flood scenes with single variable flood scenes in different return periods; and quantizing the contribution of each variable to the change of the submerging area by using the obtained submerging area and the corresponding rainfall event, river flow and coastal tide level data. According to the method, the defect that traditional single-factor evaluation cannot capture multi-factor interaction is overcome, and the accuracy of flood disaster evaluation is greatly improved.

The invention discloses a univariate ultra-short-term wind power prediction method based on two-stage trend decomposition, and the method comprises the steps: carrying out the multiple times of trend decomposition of historical wind power time series data, and generating a macroscopic trend component, a mesoscale trend component and a residual component; performing exponential distribution initialization causal convolution kernel extraction on the decomposed macroscopic trend component and the mesoscale trend component to extract multi-scale trend characteristics, and keeping time sequence causality by adopting a proportional normalized adaptive weight; residual modeling is enhanced by adopting a loop reconstruction attention mechanism, and residual component dynamic features are obtained through sequence splicing and double residual connection; and performing linear processing on each component and performing result fusion to generate an ultra-short-term wind power prediction value. And precise prediction of ultra-short-term wind power can be realized.

This invention provides a method and system for univariate time series prediction of process parameters based on knowledge transfer, belonging to the field of process industry technology. The method includes: collecting basic univariate time series information and preprocessing the basic information to obtain training basic information; pre-training a knowledge-embedded DKN network based on the training basic information to obtain denoising parameters; performing secondary training of the knowledge-embedded DKN network based on the denoising parameters and the basic information to obtain a trained network; and performing time series prediction under unstable operating conditions based on the trained network. This invention solves the problems of generalization performance degradation in traditional data-driven univariate time series prediction models under uncertain input scenarios, and the slow convergence and false saturation of traditional DKN networks due to the time-varying characteristics of process industry operating conditions.

The invention relates to the technical field of electric power, and discloses an electric energy meter measurement missing data complementing method based on univariate dynamic time warping, which comprises the following steps: constructing an initial time sequence INP from normal no-missing electric energy meter data, and determining missing data of a missing sequence; according to the length T of the missing data, combining with the new time sequence INP'to adaptively create a query subsequence, and based on the initial time sequence INP, constructing a reference database; calculating the similarity between the query sub-sequence and each candidate sub-sequence in the reference database by adopting a dynamic time warping algorithm so as to obtain a candidate sub-sequence most similar to the query sub-sequence; and filling missing data with the last T adjacent data of the most similar candidate subsequences. According to the method, the complex dynamic change of the data can be better captured, and a reliable result can still be obtained under the condition that nonlinear fluctuation is possibly caused by factors such as faults and interference in the measurement of the electric energy meter.

The invention relates to a time sequence prediction method based on an adaptive multi-scale Transform, and belongs to the field of time sequence prediction. The method comprises the following steps: carrying out preprocessing and seasonal trend decomposition on multivariable time series data; predicting a trend term based on a linear model; splitting a seasonal item into a univariate sequence, performing fast Fourier transform, and extracting main periodic components; carrying out multi-scale fragment division on each variable time sequence, and distributing a corresponding global Token; on the basis of a cross attention mechanism, correlation among variables is calculated; on the basis of a self-attention mechanism, calculating the correlation of the multi-scale sequence fragments of the variables; constructing a clustering distributor based on the global Token; and performing weighted fusion on the multi-scale output of each variable, and combining with a trend term prediction result to generate a complete prediction result.

A method includes receiving a query to determine anomalies in a set of multivariate time series data values including an endogenous variable and an exogenous variable. The method includes determining an impact of the exogenous variable on the endogenous variable. The method includes determining a set of univariate time series data values and training one or more models using the univariate time series data values. The method includes determining an expected data value for a respective time series data value and determining a difference between the expected data value and the respective time series data value. The method includes determining that the difference between the expected data value for a particular time series data value and the particular time series data value satisfies a threshold. In response, the method includes determining that the particular time series data value is anomalous and reporting the anomalous value to a user.

The invention discloses a quasi-linear time complexity coding and unique decoding algorithm for any-order Reed-Muller codes, which comprises the following steps of: defining a q-element RMq (r, m) RM code, defining information and converting the information into a unitary information polynomial; coding is carried out by using an RS code coder, so that MPE acceleration of an m-element polynomial on # imgabs0 # is realized, and the coding complexity reaches a quasi-linear level; and inputting the received code word into a unique decoder of the RS code, calculating to obtain a correct message polynomial, solving an m-element information polynomial through a mapping relation, and taking a coefficient as a unique decoding result. According to the method, on the basis of the thought of transformation between a multivariate polynomial ring on # imgabs1 # and a univariate polynomial ring on an extended finite field # imgabs2 #, a quasi-linear time algorithm for unique decoding of any r-order RM codes is realized, coding and decoding of the RM codes are accelerated, and the applicability of the coding scheme is enhanced.

The invention provides an equipment rule anomaly detection and prediction method in digital twinning. The method comprises the following steps: modeling based on a simulation environment of mechanism and data coupling; defining an action space, a state space and a state transfer function; preprocessing the original data; setting abnormal rule judgment, and constructing a univariate time series data prediction model and a multivariate time series data prediction model according to the abnormal rule judgment; performing model evaluation on each model; packaging the models into an algorithm library; integrating the trained models into a digital twin platform algorithm library to carry out iterative deployment work on the models; and calling the model in a digital twin platform algorithm library, and timely and accurately positioning a key problem sending and processing scheme through real-time abnormal monitoring and prediction of the model on equipment. The real-time monitoring system is established based on digital twinning, data streams from all devices and all point positions of the continuous casting machine can be integrated, the device state can be tracked in real time, potential problems can be detected, and all aspects of the production process can be monitored.

The invention provides a plateau rainfall prediction method, system and device based on intelligent similarity correction, and relates to the technical field of short-term climate prediction.The method comprises the steps that mode rainfall data of a month to be predicted, multivariable historical factor data corresponding to the mode rainfall data and global historical annual rainfall error data are obtained, determining standard grid point data of the wind field, the height field and the air temperature and effective historical annual rainfall error data; inputting the standard grid point data and the effective historical annual rainfall error data into a pre-trained error prediction model to obtain a prediction error field output by the error prediction model; and based on the prediction error field, correcting the mode precipitation data to obtain the final predicted precipitation. According to the method, multivariable information is integrated, the nonlinear synergistic effect relationship is mined more deeply, the description capability of the rainfall anomaly driving mechanism of the to-be-predicted region is enhanced, and compared with a traditional single-variable or linear scheme, the accuracy of similar selection and rainfall season prediction is effectively improved.

The invention relates to the technical field of multi-source data fusion, and discloses a multi-source information unified measurement method and system for complex equipment, and the method comprises the steps: calculating a sample overall variance of a data sample set of the complex equipment as a parameter of a Gaussian kernel function, and obtaining an uncertainty model; by utilizing uncertainty modeling, calculating the contribution degree of each data sample to each preset focal element to obtain a contribution degree set, and performing evidence modeling of uncertain parameters to obtain a univariate evidence structure; calculating an evidence distance sequence among the evidence bodies in the test information and the expert information, constructing a credibility index sequence according to the evidence distance sequence, and further obtaining a weighted multi-source data set through weight configuration; fusing the weighted multi-source data set to obtain multi-source uncertainty fused data; and constructing a multi-source information unified measurement model by using the univariate evidence structure and the multi-source uncertainty fusion data. Unified measurement of incomplete, multi-source and related uncertain parameters of a complex system can be realized.

The invention discloses a multi-period non-stationary multi-hydrological variable spatial valuation method, and relates to the technical field of hydrogeology. Comprising the steps of obtaining a univariate time sequence; combining the univariate time sequences of all observation stations in the drainage basin to obtain a multivariate random time sequence; calculating a long-term average level of each observation station through a space-time random function to obtain a long-term trend; subtracting the multivariable random time sequence of each observation station from the corresponding long-term trend to obtain a random residual error; according to the random residual error, determining a covariance function and a variation function between any two observation stations in the drainage basin; and on the basis, a multi-period non-stationary multivariable space valuation model is constructed by combining a multivariable Kriging model theory, and multi-hydrological variable valuation is performed on the drainage basin to be measured. According to the invention, internal correlation between variables can be revealed, and the prediction precision and reliability can be effectively improved.

Some embodiments of the present disclosure provide a manner for an automatic theorem solver to answer a query. Ahead of time, data that supports columns is received. The data is converted to a data structure. Sets of univariate and multivariate morphisms are then determined and the numbers of morphisms in the sets may be reduced in accordance with various metrics. Additionally, the morphisms may be used to generate chains of morphisms. A plurality of equations may be selected for a category. Upon receiving the morphisms, chains of morphisms and selected equations, the automatic theorem solver may be ready to receive a query. The automatic theorem solver may then determine an answer to the query and present the answer.

The invention discloses a reliability analysis method for static irregularity of rail tracks on a road-rail dual-use bridge based on a high-order moment method, including establishing a finite element model of a real bridge structure; constructing a structural function function; generating fitting values ​​of random variables in the structural function function according to measured data; converting the fitting values ​​of random variables to the same standard normal space by Rosenblatt inverse transformation, and obtaining the estimated point values ​​and weight values ​​of the fitting values ​​of random variables by Gauss-Hermite quadrature formula; substituting the estimated point values ​​and weight values ​​of the fitting values ​​of each random variable into the finite element model of the real bridge structure, and taking the mean of other random variables to obtain the univariate structural function function corresponding to each random variable; solving the first four moments according to the fourth-order moment theory, and calculating the structural failure probability and reliability through all the first four moments. The scheme of the invention realizes the quantitative analysis of the reliability of static irregularity of rail tracks on road-rail dual-use bridges based on the high-order moment method.

The disclosed embodiments are directed toward cryptographic methods and variants thereof based on homomorphic encryption enabling the evaluation of real-valued functions on encrypted data, in order to allow carrying out homomorphic processing on encrypted data more broadly and efficiently.

This disclosure relates to method and system for training of deep learning based time-series models based on self-supervised learning. The problem of missing data is taken care of by introducing missing-ness masks. The deep learning model for univariate and multivariate time series data is trained with the distorted input data using the self-supervised learning to reconstruct the masked input data. Herein, the one or more distortion techniques include quantization, insertion, deletion, and combination of the one or more such distortion techniques with random subsequence shuffling. Different distortion techniques in the form of reconstruction of masked input data are provided to solve. The deep learning model performs these different distortion techniques, which force the deep learning model to learn better features. It is to be noted that the system uses a lot of unlabeled data available cheaply as compared to the label or annotated data which is very hard to get.

The present invention discloses an electric load forecasting method and system based on the GLA-UNet model structure, which relates to the technical field of electric load forecasting. The key points of the technical solution are: projecting single variable or multivariate data to a high-dimensional feature space through a linear mapping layer to generate an embedded vector sequence; performing multi-level downsampling on the embedded vector, each level including an average pooling layer and a GLA attention unit, outputting coding features of different time granularities; upsampling the deepest coding features step by step, each level fuses the coding features of the corresponding level and optimizes through the GLA attention unit, and outputs a reconstructed sequence with the same resolution as the input; adjusting the time length and feature dimension of the reconstructed sequence respectively through two linear layers to generate a power load forecast value. The present invention can effectively capture the multi-level features in time series data, and achieves a balance between accuracy, robustness and practicality in sparse daily-level power load forecasting, especially periodic and seasonal patterns.

The invention provides a wind speed simulation method based on a time-varying autoregression model and a maximum entropy method. The wind speed simulation method based on the time-varying autoregression model and the maximum entropy method comprises the following steps: S1, determining a non-stationary characteristic of a target wind speed through a specified evolution power spectral density, namely an EPSD function, calculating a pulse matrix of a time-varying autoregression, namely a TVAR model, and considering a single-variable non-Gaussian non-stationary wind speed process x (t); the mean value and the standard deviation of the time change are respectively expressed as mu x (t) and sigma x (t), and t represents time. By adopting the wind speed simulation method combining the time-varying autoregression model and the maximum entropy method, the coexistence problem of non-Gaussian property and non-stationarity of special wind speeds such as typhoon and thunderstorm is effectively solved, and the non-stationarity characteristic in the wind speed process is captured through the time-varying autoregression model, so that the simulation is more accurate.

The invention provides a multi-scale time sequence feature extraction method based on a local linear layer. The method comprises the following steps: S1, carrying out standardization processing on an input univariate or multivariate time sequence; s2, setting a plurality of time windows with different sizes, wherein the size of each window corresponds to one scale; s3, under a single scale, retaining a local connection structure in a time dimension by adopting a mask mechanism, and independently extracting local features of time steps in each window in the scale through linear transformation; s4, under a single scale, sharing a linear weight in a channel dimension, and carrying out special extraction on all variables by adopting the same linear weight matrix; and S5, stacking the initial sequence and the feature sequence extracted under each scale along the dimension of the scale to form a multi-scale feature sequence of each variable, and outputting the multi-scale feature sequence to be used by a subsequent model. The invention provides a novel neural network layer named as a local linear layer, local modeling and multi-scale feature extraction can be realized, parameter efficiency and modeling capability can be improved, and the method is suitable for time sequence modeling tasks.

The invention provides a hybrid uncertainty analysis method and device, equipment and a storage medium, and particularly relates to the technical field of hybrid uncertainty analysis. The method comprises the steps that a processor obtains the second-order Taylor series of a univariate function of the (k + 1) th round according to a first parameter vector of a harmonic reducer of the (k + 1) th round and a second parameter vector of a harmonic reducer of the kth round; processing the second-order Taylor series of the univariate function of the (k + 1) th round to obtain the minimum value of the limit state function in the interval; according to the interval minimum value corresponding to the minimum value of the limit state function in the interval, calculating to obtain a second parameter vector of the harmonic reducer of the (k + 1) th round; and determining the reliability index of the (k + 1) th round as the maximum failure probability. The method improves the efficiency of iterating the first parameter vector of the harmonic reducer and the second parameter vector of the harmonic reducer.

The invention provides a building energy consumption time sequence missing data interpolation method, equipment and a program product, and relates to the technical field of computers. According to the building energy consumption time sequence missing data interpolation method disclosed by the invention, the target input sequence is constructed based on the univariate energy consumption time sequence data of the target building, and the subsequent model training is carried out, so that the target data interpolation model obtained after training is used for carrying out missing data interpolation; the method does not need to depend on multivariable information such as external meteorological data or building attributes, and the applicability in an actual engineering scene is expanded. Moreover, the statistical constraint term is embedded in the total loss function of the adversarial learning joint training, so that the internal structure characteristics and the global mode of the building energy consumption data are effectively maintained, and the interpolation stability under the condition of high missing rate or long missing interval is remarkably improved. Moreover, the calculation of multiple times of tensor expansion and singular value decomposition does not need to be carried out, and the calculation cost of missing data interpolation is reduced.

The invention belongs to the technical field of traffic flow prediction, and discloses a traffic flow probability prediction model construction method and application based on dynamic time domain coding, and the method comprises the steps: training a traffic flow probability prediction model through employing a data set; wherein samples in the data set comprise traffic flow data of T historical time steps and alternating current flow data of tau predicted time steps; the traffic flow probability prediction model comprises a dynamic time domain coding network, a splicing network and a probability prediction network; according to the invention, dynamic time domain coding (DTE) is deeply fused into a univariate traffic flow prediction method. In the prediction process, self-adaptive triangular position coding, learnable position coding and the like are carried out on original traffic flow data, so that the position symmetry of a traffic flow time sequence is broken, and relative position information is increased; the defect that the traffic flow is difficult to accurately predict due to lack of time sequence information in a traditional univariate traffic flow prediction model is overcome.

The invention discloses a univariate time sequence probability prediction method and device and a storage medium, and belongs to the technical field of industrial large models, and the method comprises the steps: carrying out the sliding window segmentation of a univariate time sequence, and obtaining an original data window sequence; performing physical constraint frequency domain enhancement operation on the original data window sequence to obtain an enhanced window sequence; extracting a time domain feature and a frequency domain feature of the enhanced window sequence and splicing the time domain feature and the frequency domain feature into a joint feature vector; inputting the joint feature vector into a pre-constructed Lags-Lama decoder architecture, outputting a hidden state vector, inputting the hidden state vector into a parameterized generalized extreme value distribution GEV output layer, and generating a probability prediction result of a future time point; according to the method, the problems of poor zero sample generalization ability, insufficient long sequence dependence modeling and data distribution offset in univariate time sequence prediction are solved.

The present invention relates to the field of motor detection technology, and in particular to a method for detecting circular runout faults of servo motors. The present invention adopts the following technical scheme: a laser ranging sensor is used to perform circular runout detection on the rotating shaft of a servo motor in a non-contact manner to collect test data, a univariate variance analysis method and a multivariate covariance matrix analysis method are used to calculate and process the test data to determine whether the servo motor to be tested has a fault, and the specific fault type of the servo motor is determined by calculating the deviation rate of each indicator of the detection data and combining historical test records. The beneficial effects of the present invention are: by using a laser ranging sensor to collect circular runout data, the sampling speed and accuracy can be effectively improved; at the same time, by using a univariate variance analysis method and a multivariate covariance matrix analysis method, the overall distribution characteristics of the data can be fully considered, the assembly quality can be reflected, and the type of servo motor fault can be determined.

Systems and methods of anomaly detection in time-series are disclosed. A time-series dataset is received and a set of segments is iteratively defined from the time-series dataset by identifying a set of changepoints in the time-series dataset based on a changepoint type and a sensitivity parameter, determining whether the set of segments defined by the changepoints satisfy at least one threshold criteria, and modifying the sensitivity parameter when the threshold criteria is not met or outputting the set of segments when the threshold criteria is met. A segment-specific anomaly detection threshold is determined for each segment in the set of segments and a set of anomaly-flagged segments is generated. The set of anomaly flagged segments are generated by an anomaly detection process based on the segment-specific anomaly detection threshold for a corresponding segment. An anomaly-flagged time-series is generated by combining the set of anomaly-flagged segments.

This disclosure relates to a time series segmentation system that efficiently and accurately segments univariate time series data. For example, the time series segmentation system utilizes proxy variable time series to identify distinct segments in a univariate time series. To illustrate, the time series segmentation system generates proxy variables that approximate a univariate time series and combine with the time series to generate a supplemented multivariate time series. The time series segmentation system then divides the supplemented multivariate time series into portions using time-based windows, converts the windowed subsequences into graph objects using a sparse graph recovery model, utilizes a conditional similarity model to determine segmentation timestamps from the graph objects, and generates a segmented univariate time series from the segmentation timestamps.

The invention discloses a sample set determination method and device, electronic equipment and a computer program product. The method comprises the steps that a historical observation data set of the multi-energy microgrid is acquired, and the historical observation data set comprises historical observation values with uncertainty of a plurality of new energy units; determining univariate probability distribution and univariate empirical distribution of each historical observation value according to the historical observation data set; determining correlation probability distribution corresponding to the single-variable probability distribution and correlation empirical distribution corresponding to the single-variable empirical distribution by using a preset joint distribution function; and in the historical observation data set, selecting historical observation values in which a first optimal transmission distance between the univariate probability distribution and the univariate empirical distribution is not greater than a first preset distance threshold and a second optimal transmission distance between the correlation probability distribution and the correlation empirical distribution is not greater than a second preset distance threshold to obtain a sample set. The technical problem that the sample set cannot be accurately selected is solved.

A prediction system for a building including a processing circuit including a processor and memory, the memory having instructions stored thereon that, when executed by the processor, cause the processing circuit to receive data relating to a plurality of components, the data indicating performance of the plurality of components, generate, based on the received data, a univariate prediction model and a multivariate prediction model, generate, using the received data, one or more predicted operational parameters for the plurality of components corresponding to a future time period, and execute at least one of the univariate prediction model or the multivariate prediction model on the one or more predicted operational parameters to predict a fault associated with at least one of the plurality of components to occur during the future time period.