11 results about "Probability representation" patented technology

The invention belongs to the technical field of uncertainty probability characterization analysis, and discloses a thermoplastic composite material leading edge structure design allowable value probability characterization method and system under a small sample condition, and the method comprises the steps: defining a plurality of candidate probability distribution models; fitting each model based on the original sample data and calculating an AIC value and a BIC value; a dynamic weight factor alpha is calculated according to the sample size n, and then a hybrid information criterion HIC value is calculated; generating a plurality of sample sets through Bootstrap self-service sampling, recalculating the HIC value on each sample set, and counting the selected optimal frequency of each model; and determining an optimal probability distribution model according to the frequency, wherein the optimal probability distribution model is used for representing a design allowable value. According to the method, the dynamic weight factor alpha is introduced, AIC and BIC criteria are effectively unified, optimal balance between prediction precision and model complexity is achieved under the condition of small samples, and engineering practicability and robustness are remarkably improved.

The invention relates to the technical field of yaw control, in particular to a wind power plant robust yaw control method considering wind direction uncertainty. The method comprises the following steps: acquiring historical and real-time wind direction data of each fan in a wind power plant, and preprocessing the wind direction data; extracting wind direction statistical characteristics based on the preprocessed wind direction data, constructing a wind direction uncertainty representation model based on the wind direction statistical characteristics, and representing wind direction uncertainty in a probability form; and establishing a robust wake flow prediction model based on a wind direction uncertainty representation result in combination with terrain and fan layout information so as to predict a change trend of a fan wake flow superimposed effect under a wind direction uncertainty condition. According to the method, the wind direction uncertainty probability representation model based on the circle statistics theory is constructed, the wind direction distribution parameters are updated online in combination with a sliding time window mechanism, and random fluctuation, rapid change and space inconsistency of the wind direction can be accurately described.

The application discloses an automatic penetration testing method and system based on a cognitive decision model, relates to the technical field of information security and data processing, and realizes deep cognitive modeling of a penetration environment by constructing a multilayer state space composed of an explicit state layer, a structural state layer and a potential cognitive state layer, directly records observable attributes through the explicit state layer, infers network topology and component correlation through graph analysis through the structural state layer, and speculates unknown factors based on a probability model through the potential cognitive state layer to form conditional probability representation, so that the modeling mode enables the system to construct complete environmental cognition from fragmented information, maintains decision stability through probabilistic reasoning when the information is incomplete, meanwhile, penetration experience trajectories are parsed into unified state-action sequences through a semantic mapping function from natural language penetration records, so that the trajectories ensure that expert reasoning logic is reflected, and a test system with environmental cognition and experience internalization is formed.

The application provides a cross-condition multivariate time series anomaly detection method based on phase-aware transfer diffusion, comprising: obtaining historical monitoring multivariate time series data, preprocessing and cutting to obtain a source domain training sample set, a target domain adaptation sample set and a to-be-detected sample set; performing time local standardization on each sample set, combining BallTree to construct a dynamic graph structure, performing spatial neighborhood weighted standardization, using a time convolution network and a graph attention network to extract spatio-temporal joint features; training a graph variational autoencoder and a phase encoder to obtain a phase probability representation; using a phase conditional diffusion model to train a source domain pre-training model, constructing a phased normal prototype library and a source domain prior threshold; performing cross-condition transfer adaptation through phase-aware statistical alignment, prototype-driven constraint and parameter efficient fine-tuning to obtain a final detection model and output a detection result. The method realizes stable cross-condition anomaly detection under a few sample conditions, and improves the accuracy and robustness of detection.

This invention relates to a method and system for predicting photovoltaic power uncertainty. The method includes acquiring weather forecast data for the time to be predicted; inputting the weather forecast data into a preset weather forecast data uncertainty measurement model to obtain corresponding probability representations; and sampling based on these probability representations to obtain weather forecast data samples. It also involves acquiring historical sequence operation data up to the time to be predicted within a preset time period, inputting the weather forecast data samples and the historical sequence operation data into a preset deep probability prediction model to obtain the probability distribution of each predicted power generation value; and performing a consistent fusion of the probability distributions at the distribution level to obtain the final probability distribution of the predicted power generation value. This invention improves the accuracy of photovoltaic power prediction.

The invention relates to a fusion characterization method for output probability distribution of a distributed photovoltaic power station, and the method comprises the steps: collecting photovoltaic output historical data, carrying out the preprocessing, and carrying out the statistics of the number of effective hourly data of a modeling set; dividing the data into a data sufficient scene, a middle data volume scene and a data insufficient scene, and performing model construction for different scenes; and verifying the photovoltaic output probability representation model, and outputting a photovoltaic output probability distribution model which is verified to be qualified. According to the method, three scenes of data sufficiency, intermediate data volume and data insufficiency are clearly divided for the first time, the time-varying correlation depiction advantage of K-L expansion is directly played when the data is sufficiency, PCE enhancement is selectively performed when the intermediate data volume is used to correct a short plate, samples are fully supplemented through PCE when the data is insufficient, and the time-varying correlation depiction advantage of K-L expansion is directly played when the data is sufficiency. Full engineering scenes such as newly-built power stations, remote power stations and operation power station data accumulation transition periods are covered, and the adaptability is far better than that of the prior art; the probability characterization result is ensured to accord with the distributed photovoltaic operation physical law, and the reliability is high.

The invention discloses an active learning training method and system for a three-dimensional point cloud segmentation model, and a storage medium. The method comprises the following steps: providing a basic segmentation model, a basic probability model and a training data set; performing supervised pre-training to obtain a pre-training model; extracting embedded features for fitting training to obtain a joint probability model; calculating prototype characteristics; interpolation fusion is carried out to obtain fusion features, and joint probability representation is generated; calculating a stability score of the unlabeled data based on the fluctuation degree; performing redundancy removal and stability screening on the unlabeled data to obtain to-be-labeled data; receiving a marking operation on the to-be-marked data to form new marked data; performing semi-supervised training on the pre-training model by using the updated training data set to obtain an updated segmentation model; and iteration training is completed. According to the method, high-value samples are screened for labeling by constructing a joint probability modeling mechanism, and the discrimination capability and generalization performance of the model can be efficiently improved under limited labeling budget.

The invention discloses an automatic penetration testing method and system based on a cognitive decision model, and relates to the technical field of information security and data processing. Deep cognitive modeling of a penetration environment is realized by constructing a multi-layer state space composed of an explicit state layer, a structural state layer and a potential cognitive state layer; the explicit state layer directly records observable attributes, the structure state layer deduces network topology and component association through graph analysis, the potential cognitive state layer deduces unknown factors based on a probability model and forms conditional probability representation, and the modeling mode enables the system to construct complete environment cognition from fragmented information and to obtain a complete environment cognition result when the information is incomplete. Decision stability is kept through probabilistic reasoning, meanwhile, natural language permeation records are analyzed into a unified state-action sequence through a semantic mapping function according to the permeation experience track, it is ensured that the track reflects expert reasoning logic, and a test system of environmental cognition and experience internalization is formed.

A probabilistic representation method for underwater explosion shock wave load based on Bayesian reasoning is disclosed, relating to the field of underwater explosion load calculation. The method is based on Bayesian probability models of underwater shock wave loads, and performing probability representations of underwater explosion shock wave loads. The method is used to effectively represent uncertainty of underwater explosion shock wave loads, and to provide random inputs for modeling load variability for the design of explosion-proof underwater structures.

The invention provides a cross-working-condition multivariable time sequence anomaly detection method based on stage perception migration diffusion, and the method comprises the steps: obtaining historical monitoring multivariable time sequence data, and carrying out the preprocessing and segmentation, and obtaining a source domain training sample set, a target domain adaptive sample set, and a to-be-detected sample set; performing time local standardization on each sample set, constructing a dynamic graph structure in combination with BallTree, performing spatial neighborhood weighted standardization, and extracting spatio-temporal joint features by using a time convolutional network and a graph attention network; training a graph variational auto-encoder and a stage encoder to obtain a stage probability representation; training by using a stage condition diffusion model to obtain a source domain pre-training model, and constructing a staged normal prototype library and a source domain prior threshold; and cross-working-condition migration adaptation is carried out through stage perception statistical alignment, prototype driving constraint and efficient parameter fine adjustment, a final detection model is obtained, and a detection result is output. Stable cross-working-condition anomaly detection under the condition of few samples is achieved, and the accuracy and robustness of detection are improved.

The invention relates to a photovoltaic power uncertainty prediction method and system, and the method comprises the steps: obtaining weather forecast data at a to-be-predicted moment, inputting the weather forecast data into a preset weather forecast data uncertainty measurement model, obtaining a corresponding probability representation, and carrying out the sampling according to the probability representation, thereby obtaining a weather forecast data sample; according to a preset time period, historical sequence operation data ending to the to-be-predicted moment is obtained, the weather forecast data sample and the historical sequence operation data are input into a preset depth probability prediction model, and probability distribution of all predicted power generation power values is obtained; and performing unification fusion on each probability distribution on a distribution level to obtain final probability distribution of the predicted power generation power value. The method has the effect of improving the accuracy of photovoltaic power prediction.