13 results about "Stochastic variation" patented technology

The invention discloses a Bayesian deep learning-based fan power prediction method and system. The method comprises the steps of screening mixed sample features related to fan power prediction under the condition of considering icing according to a physical model; taking the mixed sample features as input, and constructing an adaptive wind power prediction model based on a Bayesian multilayer neural network; generating a fan power output expert experience sample database according to the physical model, taking the fan power output expert experience sample database as a self-adaptive wind power prediction model constructed by priori pre-training, and collecting historical operation data of a wind power plant as posteriori; based on a random variational derivation method, regularly retraining the adaptive wind power prediction model to obtain a fan power prediction model; and inputting the fan operation real-time data into the fan power prediction model, and outputting to obtain a fan power prediction result. And expert knowledge and historical operation data are comprehensively utilized to greatly improve the accuracy of wind power prediction under the fan icing condition.

The invention belongs to the technical field of environmental monitoring and ecological risk assessment, and particularly relates to a Yangtze River Delta basin water ecological risk prediction method and system based on a Bayesian network model. The method comprises the following steps: firstly, constructing a water ecology risk assessment system, and preprocessing sample data; sub-basins are divided based on DEM data, and the sub-basins which are adjacent in space and similar in data feature are aggregated into non-overlapping data blocks; constructing a dynamic Bayesian network model by adopting a random variational inference method, and inputting meteorological prediction data to obtain probability distribution of risk levels of each sub-basin; constructing a risk space correlation model according to sub-basin division, and simulating conduction and superposition processes of risks in a basin network; and finally, evaluating the comprehensive risk state of each sub-basin in combination with a network topology index. By constructing the dynamic Bayesian network model and the risk space correlation network, the spatial-temporal dynamic assessment of the watershed water ecological risk is realized, and the propagation path and the cumulative effect of the risk in the watershed can be predicted.

The invention relates to a dynamic evolution interpolation method for safety monitoring data of a fully mechanized coal mining face of a coal mine, and belongs to the field of fully mechanized coal mining face monitoring data interpolation. The method comprises the steps that firstly, an original time sequence is disassembled into a trend part, a seasonal part and a residual error part through a mixed decomposition method, the trend and the seasonal part are extracted through static Loess STL, and the residual error is dynamically adjusted through a Kalman filter; thirdly, modeling trend and seasonal components by using a Gaussian process GPs, and introducing a Shenchang differential equation NODEs to simulate a change rule of a potential state; and finally, constructing a stochastic differential equation (SDE) model, integrating results of the NODEs and the GPs, adding a diffusion term to reflect a random change, solving the SDE to obtain a potential state, and mapping the potential state back to an observation space to generate a predicted value. According to the method, different characteristics in the data are comprehensively considered, and the data with changing time dynamics can be better captured and processed.

A mask pattern for a semiconductor device can be used as an input to determine a photoresist thickness probability distribution using a machine learning module. For example, the machine learning module can determine a probability map of Z-height. This can be used to determine stochastic variation in photoresist thickness for a semiconductor device. The Z-height may be calculated at a coordinate in the X-direction and Y-direction.

A method includes grouping, in a first layout, pattern regions which have duplicate layout patterns including weak regions as a group, calculating defect probabilities of the pattern regions, respectively, calculating a defect frequency and a defect rate of the group based on the defect probabilities of the pattern regions, predicting a degree of defects of a second layout of the pattern regions, based on the defect frequency and the defect rate, and performing an extreme ultraviolet (EUV) lithography process on a substrate, based on the second layout. The defect probabilities are calculated by performing an optical proximity correction (OPC) simulation on the pattern region, calculating a stochastic variation of a linewidth of a simulation pattern in the weak region as a Gaussian distribution, and defining a threshold linewidth, which is used as a reference of the random defect, in the Gaussian distribution.

A method of determining a relationship between a stochastic variation of a characteristic of an aerial image or a resist image and one or more design variables, the method including: measuring values of the characteristic from a plurality of aerial images and / or resist images for each of a plurality of sets of values of the design variables; determining a value of the stochastic variation, for each of the plurality of sets of values of the design variables, from a distribution of the values of the characteristic for that set of values of the design variables; and determining the relationship by fitting one or more parameters from the values of the stochastic variation and the plurality of sets of values of the design variables.

Systems and methods for optical proximity correction (OPC) model calibration in a stitching region, including obtaining an aerial image profile of a black-border region and an absorber region of a mask; and calibrating a model characterizing a transition region between the black-border region and the absorber region of a mask using the aerial image profile. Systems and methods may include obtaining stochastic variation data across a transition region between a black-border region and an absorber region of a mask from a measured aerial image; and modeling variability in a critical dimension across the black-border region of the mask.

The invention discloses a wind power time sequence stochastic simulation method considering a high-temperature heat wave event, and the method comprises the following steps: 1), defining a weather state type, and obtaining a historical typical weather state sequence; 2) based on the weather state type, establishing an upper-layer day-by-day weather state sequence; 3) establishing joint distribution for meteorological factors in each weather state in the historical typical weather state sequence by adopting an R-vine copula function, and constructing a meteorological factor joint probability density function; and 4) integrating the upper-layer day-by-day weather state sequence and the meteorological factor joint probability density function to generate a weather scene sequence, and inputting the weather scene sequence into the wind power generation physical model to generate a wind power time sequence. The wind power generated by the method can effectively capture the random change characteristics of weather and the duration of the heat wave event, and accurately reflect the heat wave events of different time scales.

A method can include generating a plurality of synthetic objects and associated labels using a trained first machine learning system that is trained to generate a synthetic object based at least in part on a feature of a labeled object, an assigned label that represents the feature, and stochastic variation input; training a second machine learning model to predict labels for features of objects based at least in part on the plurality of synthetic objects and associated labels; and predicting a label for an unlabeled feature of an object using the second machine learning model.

A method and system for 3D modeling of stochastic variation of a lithographic process. The lithographic process is subject to random stochastic phenomena, with the resulting stochastic randomness potentially becoming a major challenge. The stochastic phenomena are modeled using a stochastic model, such as a random field model, that models stochastic randomness. To extend the application of the stochastic model to predict 3D aspects and increase the accuracy of modeling, the stochastic randomness for each level of a plurality of levels discrete from one another in a resist thickness direction may be modeled and analyzed across the plurality of level to generate a 3-dimentional distribution of the stochastic randomness. In turn, indications of 3-dimentional distribution of the stochastic randomness may be used to modify one or both of the light exposure and resist parameters in order to reduce the effect of stochastic randomness on the lithographic process.

Provided is a process including: obtaining, with a computer system, with a stochastic layer of a multi-layer neural network, inputs to the stochastic layer from, wherein the multi-layer neural network comprises both deterministic layers and the stochastic layer, and the stochastic layer comprises a plurality of parameters that vary stochastically according to respective probability distributions; determining values of the plurality of parameters by randomly sampling from the statistical distributions; determining an output of the stochastic layer based on both the determined values of the plurality of parameters and the inputs to the stochastic layer; and providing the output of the stochastic layer to a downstream layer of the multi-layer neural network or as an output of the multi-layer neural network.

The application discloses a transformer adaptive fault failure threshold differentiation online life prediction method considering missing degradation information, belongs to the field of power equipment degradation evaluation and operation and maintenance, and comprises the following steps: a prediction framework including degradation data analysis, comprehensive degradation data composition, intelligent smoothing fitting, degradation model construction and adaptive dynamic prediction is constructed. Through a fuzzy logic and TIME-LLM hybrid model, multi-index weighted fusion is realized, intelligent adaptive smoothing fitting is adopted to process comprehensive degradation data with different noise characteristics, a TFD-Hformer model is used to capture time-frequency domain nonlinear coupling characteristics, and a variational Bayesian neural network is used to generate a differentiated fault threshold correction factor by combining stochastic variation inference. The application can realize reliable prediction in the historical data missing scene, adaptively adapt to the individual differences of different transformers, and support efficient prediction of large-scale clusters.

A method for predicting post-etch stochastic variation in transferring a target layout onto a substrate using a lithographic apparatus. The method includes predicting a stochastic variation in transferring a target layout onto a substrate by predicting a stochastic etch bias and combining the stochastic etch bias with post-lithographic process stochastic variation to predict the stochastic variation in an etch process. The method includes determining a performance in transferring the target layout to the substrate based on the stochastic variation.