Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

192 results about "Probit model" patented technology

In statistics, a probit model is a type of regression where the dependent variable can take only two values, for example married or not married. The word is a portmanteau, coming from probability + unit. The purpose of the model is to estimate the probability that an observation with particular characteristics will fall into a specific one of the categories; moreover, classifying observations based on their predicted probabilities is a type of binary classification model.

Multi-source data fusion method and system for dynamic system scenario behavior deduction and reliability prediction analysis

The present invention discloses a multi-source data fusion method and system for dynamic system scenario behavior deduction and reliability prediction analysis, a computer device, and a storage medium. Based on a Markov / CCMT dynamic reliability prediction analysis method and combined with a multi-source data fusion and assimilation method, the method simulates and statistically analyzes complex dynamic behavior characteristics of digital process control with strong interactive coupling, nonlinearity and high uncertainty by Monte Carlo probability model random sampling, and then achieves forward deduction analysis and reliability prediction of a system operation state through dynamic search analysis of a system state transition probability matrix model.
Owner:SOUTH CHINA UNIV OF TECH

Incompressible turbulent flow field prediction method based on potential diffusion model

The invention belongs to the technical field of turbulent flow field prediction and deep learning, and discloses an incompressible turbulent flow field prediction method based on a potential diffusion model. The method comprises the following steps: acquiring original turbulence data; processing the turbulence data; constructing a turbulence prediction model; model training; and evaluating the model and the like. The model of the technical scheme of the invention specifically comprises the following steps: designing a multi-scale Fourier auto-encoder for extracting multi-scale space and frequency domain features in a turbulence field and obtaining a global structure and a local scale structure of turbulence; a novel accelerated sampling method is proposed and introduced in the diffusion process, namely a diffusion probability model solver greatly shortens the reasoning time in a potential space and keeps high fidelity in long-time-sequence prediction; a physical constraint loss item based on a partial differential equation is introduced, and a Navier-Stokes equation (N-S) is explicitly introduced into a training process, so that the physical consistency of results is effectively improved, and errors are remarkably reduced.
Owner:QINGDAO UNIV OF TECH

Method and system for generating ocean island typhoon scene driven by physical information neural network

The invention discloses a physical information neural network-driven ocean island typhoon scene generation method and system. The method comprises the steps of collecting multi-source heterogeneous meteorological data and performing space-time alignment preprocessing; constructing a coarse-scale space-time probability prediction model, capturing space correlation of meteorological elements by using a graph topology learning network, efficiently processing long-time-sequence dependence of typhoon evolution by integrating a state space model with linear complexity, and generating a probabilistic typhoon scene with coarse resolution through a multivariable joint distribution probability model; further constructing a physical downscaling model, taking a coarse-scale prediction result as condition input, and performing physical consistency downscaling on a coarse-scale scene by embedding an atmospheric fluid mechanics equation in a loss function as a physical hard constraint; and finally, outputting a high-resolution typhoon scene with probability reliability and physical authenticity.
Owner:NANJING NORMAL UNIVERSITY

Sea wave probability prediction method and system

The invention belongs to the cross technical field of artificial intelligence and marine meteorological prediction, and discloses a sea wave probability prediction method and system, and the method comprises the steps: obtaining historical wind field data and sea wave spectrum data of a target sea area, carrying out the preprocessing and organization of the data, and constructing a training data set; constructing a hybrid expert probability model, wherein the model comprises a gating network and a plurality of expert networks; the training data set is used for training the hybrid expert probability model, the trained model receives input wind field data, and hybrid probability distribution is output through the synergistic effect of the gating network and the expert network; and sampling is carried out from the mixed probability distribution to obtain a predicted sea wave spectrum set, and sea wave risk probability prediction is realized. Complete distribution information can be obtained through one-time forward calculation, a numerical mode set is not needed, the computing power and energy consumption expenditure are remarkably reduced, and high-frequency updating and quasi-real-time business application can be conveniently achieved in resource-limited environments such as shipborne, buoys and offshore stations.
Owner:QINGDAO INNOVATION & DEV CENT OF HARBIN ENG UNIV +2

Concept shift detection and correction using probabilistic models and learned feature representations

Techniques for concept shift detection and correction using probabilistic models and learned feature representations are described. A gaussian process model is trained using representations generated by a primary machine learning (ML) model for existing training data elements in a training memory. For a new batch of data elements, representations again generated by the primary ML model can be used as input for the gaussian process model to generate predictive distributions. When the true targets for the new data elements are not sufficiently likely according to the corresponding predictive distributions, concept shift is likely and the training memory can be purged of the existing data elements before further retraining of the primary ML model.
Owner:AMAZON TECH INC

Multi-group time sequence student cognitive diagnosis method based on joint probability model

The invention discloses a multi-group time sequence student cognitive diagnosis method based on a joint probability model, which belongs to the field of education and comprises the following steps: acquiring student answer data, group classification labels and covariable data of at least two continuous time points; according to the student answer data, the group classification label and the covariable data, a joint probability model is constructed, and the joint probability model comprises a structure model and a measurement model; the structure model is used for describing a dynamic change process of a potential knowledge mastering state of the student, and the measurement model is used for establishing an association relationship between answer data of the student at each time point and the potential knowledge mastering state; and performing analysis based on the joint probability model to obtain the potential knowledge mastering state of the student. According to the method, the potential knowledge mastering state and response mode difference can be compared among multiple groups, and an important basis is provided for evaluating educational fairness and optimizing teaching strategies.
Owner:JINAN UNIVERSITY

High-dimensional time series data classification method and device based on multi-scale diffusion denoising

PendingCN120277526AProbit modelAlgorithm
The invention discloses a high-dimensional time series data classification method and device based on multi-scale diffusion denoising. According to the method, a multi-scale condition guidance strategy is introduced to guide the denoising process of time sequence labels, and condition priori of different scales is used in the diffusion process to adjust each step. The method comprises the following steps of: encoding time sequence data from two angles of variable and time, extracting features, obtaining multi-scale feature representation of a time sequence, mining a dependency relationship of the sequence on a time dimension and a variable dimension by using a double attention mechanism, and generating condition priori on different scales; a standard denoising diffusion probability model is used for training a process, a fusion vector in a potential space is obtained by using a multi-scale encoder, then the fusion vector and a time step are embedded, and a full connection layer is used for predicting noise. According to the method, the result accuracy of the high-dimensional multivariable time series in the classification task and the robustness of processing irregular time series data containing missing values are improved.
Owner:NANJING UNIV

DEMATEL-BWM fusion assembly sequence evaluation method based on Bayesian probability model

The invention relates to a DEMATEL-BWM fusion assembly sequence evaluation method based on a Bayesian probability model. Assembly sequence evaluation is carried out on a complex mechanical object. Collecting data, establishing a direct influence matrix, normalizing the direct influence matrix into a standard influence matrix, performing Bayesian updating, and performing exponential transformation processing on an output posteriori mean value to obtain a preference matrix; determining optimal and worst elements, performing pairwise comparison to obtain optimal and worst vectors, modeling the optimal and worst vectors as polynomial distribution, and modeling the output weight vectors as Dirichlet distribution; processing input of multiple decision groups through a Bayesian hierarchical model, establishing a joint probability model, and performing decomposition through conditional independence and probability chain rules; the prior distribution and observation data are used, posterior distribution is obtained through Bayesian updating, and a confidence level is used to generate a weighted directed graph; and outputting the aggregation weight, and evaluating the assembly sequence. The problem that an assembly sequence evaluation method is low in efficiency is solved, the inconsistency of subjective judgment is reduced, and the method is more fault-tolerant, concise and efficient for deviation.
Owner:DONGHUA UNIV

Regional debris flow risk dynamic assessment method based on space-time probability

The invention discloses a spatial-temporal probability-based regional debris flow risk dynamic assessment method, and belongs to the technical field of geological disaster prediction.The spatial-temporal probability-based regional debris flow risk dynamic assessment method comprises the steps of establishing a dynamic probability model of a time dimension and a distributed probability model of a spatial dimension by integrating data such as meteorological data and historical disaster records; in particular, the method can solve the problem of result deviation caused by neglecting time dynamic characteristics in a traditional method, achieves the accurate prediction of the debris flow risk, breaks through the limitation of the traditional method in the aspect of data utilization, and improves the accuracy of debris flow risk prediction. Through fusion of multi-source information, the precision and applicability of the model are improved, and the assessment and decision support capability for complex natural disasters is significantly enhanced.
Owner:INST OF MOUNTAIN HAZARDS & ENVIRONMENT CHINESE ACADEMY OF SCI

Ship complex HRRP estimation method and system matched with sea clutter non-Gaussian characteristics

The invention discloses a ship complex HRRP estimation method and a ship complex HRRP estimation system matched with non-Gaussian characteristics of sea clutters. The method comprises the following steps: acquiring original radar echo data; a threshold detection method is adopted for the original radar echo data to obtain a distance interval where the ship multiple HRRP is located; representing the radar echo signals in the distance interval as a vector matrix model; adopting a K-S minimum distance criterion to select a composite Gaussian model matched with the statistical characteristics of the interference vector in the vector matrix model; and estimating the ship complex HRRP by adopting a sparse optimization method corresponding to the composite Gaussian model. According to the method, a single-parameter probability model is adopted to constrain the sparsity of the ship multiple HRRP, a K-S minimum distance criterion is adopted to determine which composite Gaussian model is adopted to constrain the statistical characteristics of sea clutters, and A-D test is adopted to determine the sparse parameter q of the ship multiple HRRP; and the performance loss of ship multi-HRRP estimation caused by clutter model mismatch is obviously reduced.
Owner:DONGHAI LAB +1

Random fracture parameter setting method in DFN model

The invention discloses a random fracture parameter setting method in a DFN model, and relates to the technical field of random fracture parameter setting methods. Comprising the following steps: data collection: collecting geological data of a target area; parameter definition: defining the range and distribution characteristics of fracture parameters according to the collected data; probability model establishment: establishing a probability distribution model of each fracture parameter based on the principle of statistics; random parameter generation: using Monte Carlo simulation or other random sampling methods to generate a group of random fracture parameters according to the probability distribution model; and parameter verification and adjustment: carrying out comparison verification on the generated random parameters and actual fracture data. According to the method, the natural characteristics of the fracture system can be reflected more truly, so that the prediction precision of the DFN model is improved; intelligent algorithms such as machine learning, deep learning and a genetic algorithm are introduced, fracture parameters are automatically optimized, and the parameter tuning efficiency and the performance of the model are remarkably improved.
Owner:GUANGDONG PROVINCE DABAOSHAN MINING CO LTD

Park integrated energy system stochastic planning method and system based on multiple uncertainties

The invention belongs to the technical field of energy system planning, and particularly relates to a park integrated energy system stochastic planning method and system based on multiple uncertainties, and the planning method comprises the steps: building a probability model of a multi-energy load growth rate based on park industrial planning and historical data; utilizing Monte Carlo simulation and K-means clustering to generate a representative load scene tree; establishing an upper and lower boundary prediction model of the energy price and the equipment cost by adopting a quantile regression forest method; constructing a multi-stage collaborative optimization model taking the minimum comprehensive cost expectation as a target, and considering constraint conditions such as power flow, operation, time sequence and space; and carrying out reverse recursion solution by utilizing a dynamic programming algorithm, and outputting an optimal equipment configuration and construction scheme of each stage. According to the method, the problems of load increase unpredictability and energy market price fluctuation risk in different development stages of the park energy system are solved by combining scene analysis, data-driven modeling and a dynamic optimization mechanism.
Owner:NINGBO INST OF DALIAN UNIV OF TECH

Urban activity prediction method and system based on Transform architecture and denoising diffusion probability model

The invention discloses an urban activity prediction method and system based on a Transform framework and a denoising diffusion probability model, and the method can achieve the prediction of the urban activity of any building in any future time under the condition that the urban activity of any historical time is known through the trained model based on the Transform framework and the denoising diffusion probability model. The construction of the model specifically comprises the following steps: carrying out fine-grained division on spatio-temporal data according to a building and room units in the building, executing Z-Score standardization, inputting a spatio-temporal causal convolution module, adjusting a data structure to adapt to a Transform structure, carrying out mask processing, and enhancing the time sequence prediction capability by adopting a noise diffusion probability model framework. According to the method, high prediction precision can be realized under the condition of relatively short input time, high-precision prediction of urban activities can be realized on the aspects of large scale and small fine granularity, arbitrary multi-step prediction of urban activities under any time step is realized by using artificial intelligence for the first time, and the blank of artificial intelligence in urban activity prediction is filled.
Owner:HANGZHOU QIUNIVERSE ARTIFICIAL INTELLIGENCE CO LTD

Electric power information network security risk assessment method and system

The invention discloses an electric power information network security risk assessment method and system, and relates to the technical field, and the system comprises the following components: S100, data acquisition, S200, artificial intelligence algorithm analysis, S300, fusion model, S400, risk assessment and S500, prediction model. According to the method, future security threats are predicted through the Markov chain Monte Carlo method and the fusion neural network algorithm, the security state of the power information network is comprehensively defined as the state space of the MCMC, and the transition probability model between the states is constructed, so that the conversion condition and probability between different states can be finely analyzed, and the security threats of the power information network can be predicted. And dynamic and accurate prediction of future security threats is realized.
Owner:GUANGDONG CONSTR VOCATIONAL TECH INST +2

HRRP sample generation method and system based on category guidance DDPM

The invention discloses an HRRP sample generation method and system based on category guidance DDPM, and the method comprises the steps: carrying out the normalization and centroid alignment preprocessing of HRRP original data, and generating a small sample data set; a one-dimensional conditional convolutional network is constructed, the input of the one-dimensional conditional convolutional network is a to-be-denoised sample, the output of the one-dimensional conditional convolutional network is predicted noise of which the dimension is consistent with that of the input, and the one-dimensional conditional convolutional network comprises a down-sampling module and an up-sampling module integrated with a time step and an angular domain; training the one-dimensional conditional convolutional network by using the small sample data set to obtain a trained category guidance denoising diffusion probability model; and utilizing the trained category to guide the de-noising diffusion probability model to generate an expanded sample data set. The problems that in the field of HRRP sample generation, previous model training is unstable, the quality of generated samples is poor under the small sample condition, the angular domain of the generated samples of a conventional diffusion model is uncontrollable, and distribution outside samples are easily generated are solved.
Owner:XIDIAN UNIV

Multi-source data fusion method, system and equipment of active power distribution network and medium

A multi-source data fusion method, system, device and medium for an active power distribution network, the method comprising: using a target training denoising diffusion implicit model of a denoising diffusion probability model, generating a conditional denoising diffusion implicit model by modifying a sampling method of a back diffusion process of the denoising diffusion probability model; and then realizing self-supervised training of the conditional denoising diffusion implicit model introducing conditional information by using a minimization loss function, and finally deploying the trained conditional denoising diffusion implicit model into an actual active power distribution network to perform real-time processing and fusion of multi-source data of the active power distribution network. According to the method, a conditional information denoising mechanism is introduced, a conditional denoising diffusion implicit model is deployed in an actual active power distribution network, and high-quality active power distribution network measurement sample data is generated in fewer steps, so that the generation efficiency and quality of the data are improved, the intelligent level of a data fusion system is improved, and the data fusion efficiency is improved. And efficient and accurate fusion of the multi-source heterogeneous data of the power distribution network is realized.
Owner:ECONOMIC & TECH RES INST OF HUBEI ELECTRIC POWER COMPANY SGCC +1

Conditional diffusion probability model-based lithofacies intelligent mode classification method

The invention relates to a lithofacies intelligent pattern classification method based on a conditional diffusion probability model, and belongs to the technical field of deep learning, pattern recognition and big data processing. Comprising the following steps: step (1), collecting and preprocessing big data; step (2), constructing a conditional diffusion probability model; step (3), model training and parameter optimization; step (4), generating a category balance sample; (5) enhancing data quality evaluation; and (6) training and verifying the pattern classification model. According to the method, shale lithofacies data enhancement and intelligent mode classification based on the conditional diffusion probability model and the deep learning technology are realized, the lithofacies identification problem under the condition of training set category imbalance is effectively solved, and the minority class lithofacies identification precision and the overall classification performance of the model are remarkably improved; and a reliable technical method is provided for marine shale oil and gas reservoir evaluation and sweet spot prediction.
Owner:SANYA MARINE OIL & GAS RESEARCH INSTITUTE NORTHEAST PETROLEUM UNIVERSITY

Probability model quantification method for flexibility potential of building air conditioner

The invention discloses a probability model quantification method for flexibility potential of a building air conditioner, which comprises the following steps of: extracting an upper and lower bound cumulative distribution function by adopting a probability box method, and describing a flexibility fluctuation range of an air conditioning system in an interval probability form; a Wasserstein distance index is introduced, the difference of load probability distribution before and after regulation is quantified, and a flexible potential expected value is represented according to the difference. According to the method, the adjustable load range of the building can be accurately described under the multi-source disturbance condition, and reliable support is provided for flexible resource scheduling and response strategy making.
Owner:TIANJIN UNIV

Confidentiality-preserving collaborative model for deriving information on a production system

A method is presented for using a distributed network to derive information characterising a production system described by variables. The network comprises two probabilistic models implementing a graph comprising nodes associated with a corresponding one of the variables, and directed edges connecting respective pairs of the nodes. Each graph comprises an interface node for which the corresponding associated variable is common and normal nodes to which edge(s) are directed that are associated with a respective conditional probability table (CPT) specifying a probability of the variable being in a set of states based on the variables associated with the corresponding one or more nodes from which the one or more edges are directed. The interface node is associated with a partial CPT of the common variable. The method comprises generating, using the at least two models, conditioned data specifying a probability distribution of the state of the common variable.
Owner:ASML NETHERLANDS BV

Denoising diffusion probability model-based coal-fired unit digital twin modeling method and device and storage medium

The invention provides a coal-fired unit digital twin modeling method and device based on a denoising diffusion probability model and a storage medium, and belongs to the field of digital twin modeling. The problems that an existing method is large in modeling difficulty and high in model complexity, and mechanism simplification and data quality dependence cannot be avoided are solved. Comprising the following steps: data preprocessing: selecting equipment parameters highly related to operation of a coal-fired unit as diffusion characteristics, selecting diffusion indexes according to the diffusion characteristics, and carrying out normalization processing on the diffusion characteristics and the diffusion indexes; on the basis of the probability denoising diffusion model, a lightweight MobileNet is adopted to replace a residual block in a UNet network, and a lighter and faster industrial digital twinning denoising diffusion probability model DT-DDPM is obtained; guiding a sampling process by adopting diffusion characteristics; carrying out high-fidelity digital twinborn modeling on the coal-fired unit by adopting an industrial digital twinborn denoising diffusion probability model and historical data of operation of the coal-fired unit; the method is applied to coal-fired unit digital twin modeling.
Owner:TAIYUAN UNIVERSITY OF SCIENCE AND TECHNOLOGY

Multi-layer circuit board quality inspection method and system based on machine learning

The invention discloses a multi-layer circuit board quality inspection method and system based on machine learning, and the method comprises the steps: carrying out the time-space registration of collected multi-source data through an adaptive weighted fusion algorithm, and generating a multi-mode quality inspection data set containing a line topological structure and material characteristics; outputting a fused circuit board defect sensitive feature vector set by using a pre-trained nested attention deep learning model based on the multi-modal quality inspection data set; inputting the defect sensitive feature vector set into a twin network architecture, positioning a potential defect area through a dynamic anchor frame generation mechanism, carrying out multi-label classification on defect types in combination with a Bayesian probability model, and synchronously introducing a defect severity evaluation module to quantify the influence degree of defects on circuit performance, and outputting a detection result containing the defect position type and severity. According to the embodiment of the invention, the collaborative judgment of the type, position and severity of the defect can be realized, and the detection precision and generalization capability of the defect of the multilayer circuit board are improved.
Owner:JIANGXI KUNYU ELECTRONICS CO LTD

Carbonate rock fault control fracture-cavity type high-quality reservoir prediction method and system and electronic equipment

The invention discloses a carbonate rock fault control fracture-vug type high-quality reservoir prediction method and system and electronic equipment, and belongs to the technical field of fracture-vug type carbonate rock oil and gas reservoir development. The method comprises the following steps: obtaining the number of finished drilling wells, the number of wells with mud leakage or drilling tool emptying, the number of wells without mud leakage or drilling tool emptying, corresponding amplitude values and maximum likelihood attribute values in a seismic data work area, and introducing a binary Logistic regression model according to obtained original data, and establishing a relation model of whether emptying leakage occurs, an amplitude value and a maximum likelihood attribute value. On the basis of the model, the probability of emptying leakage at any position in the same set of seismic data work area can be judged, and prediction of a high-quality reservoir is achieved. According to the method, a mathematical probability model is introduced, and quantitative characterization and prediction of the fault control fracture-cavity type high-quality reservoir are realized through combination of a geophysical prospecting technology and mathematical analysis; the process is simple and rapid, and accurate prediction of the cave type fracture-vug type high-quality reservoir is achieved for the first time.
Owner:PETROCHINA CO LTD

Systems and methods for automated probabilistic based forecasts of component demand and cost incorporating data up-sampling

ActiveUS12165103B1CommerceProbit modelProbability of survival
Disclosed is generating an acquisition request of a component, using a probabilistic model based on current and planned life consumption, to maintain a usable component inventory, by: determining planned consumption of the component; retrieving historical lifetime data associated with the component; determining the associated normalized current life consumed for historical specimens at failure based on a power law equivalency model; determining a probability of survival distribution associated with the component; determine a probability of future failure of each component in inventory given planned consumption of the component; determine a projected number of component failures prior to completion of the job associated with the component; generate the at least one acquisition request to acquire a quantity of new components at least equal to the projected number of specific component failures prior to completion of the job; wherein the usable inventory of the component includes at least the quantity of new components.
Owner:HALLIBURTON ENERGY SERVICES INC

Copula-based bridge response and load joint probability modeling method

The invention relates to the technical field of bridge monitoring, and provides a Copula-based bridge response and load joint probability modeling method, which comprises the following steps: S1, acquiring a structure response index and a load parameter through a structure health monitoring system, and carrying out probability density modeling on the structure response index and the load parameter through a Gaussian mixture model to obtain a probability density model; screening and fitting an optimal probability distribution model of each structure response index and load parameter through a Bayesian information criterion; s2, analyzing the correlation between variable pairs formed by the structure response indexes and the load parameters by adopting a Pearson correlation coefficient, and determining the strength and direction of the correlation; s3, constructing a joint probability density function between variables through a Copula probability density modeling method in combination with the fitted variable probability distribution marginal model; and S4, verifying the constructed joint probability density function by adopting a Monte Carlo sampling method. According to the method, the multivariable joint probability model between the key load and the response is generated, and the uncertainty is quantified.
Owner:SHANGHAI RESEARCH INSTITUTE OF BUILDING SCIENCES CO LTD

Soil moisture sensor data quality inspection and interpolation method

The invention provides a soil moisture sensor data quality inspection and interpolation method, which comprises the following steps: screening multivariable soil moisture time sequence data based on a preset core physical feature list, carrying out abnormal value detection through physical rule constraint and an isolation forest algorithm, and carrying out data labeling by creating a complete time axis; generating a training sample from the preprocessed data through sliding window sampling, and performing deep feature learning by using a denoising network based on a space-time diffusion probability model; performing interpolation on missing values in the original data by using the trained space-time diffusion probability model, generating a noisy data sample through a forward noise adding process, and performing conditional data interpolation based on a known observation value and a mask matrix in a reverse denoising process to generate a preliminary interpolation result; and performing post-processing correction on the preliminary interpolation result, wherein the post-processing correction comprises clamping correction based on a monthly historical range and correction based on interlayer physical logic.
Owner:FARMLAND IRRIGATION RES INST CHINESE ACAD OF AGRI SCI

Business income prediction method and device, electronic equipment and storage medium

The embodiment of the invention provides a business revenue prediction method and device, electronic equipment and a storage medium, and relates to the technical field of computers, the method comprises the following steps: obtaining a decision tree model and training data for a target business, the training data comprising historical business revenue data and expansion data, obtaining a probability model and a segment loss function aiming at the decision tree model, adjusting and optimizing hyper-parameters of the decision tree model according to the training data, the probability model and the segment loss function to obtain a business income prediction model, and performing weight prediction on the business income prediction model according to the training data and the segment loss function to obtain a business income prediction model; according to the method, the weight coefficients corresponding to the business income prediction models are obtained, then the business income prediction models are fused based on the weight coefficients, and the target fusion model for the target business is obtained, so that the accuracy of model prediction is effectively improved.
Owner:CHINA TELECOM CORP LTD

A Carbon Dioxide Concentration Prediction Method Based on Semi-Supervised Deep Probability Model

ActiveCN119538205BBiological modelsGas analyser construction detailsProbit modelPrincipal component regression
The present invention discloses a carbon dioxide concentration prediction method based on a semi-supervised deep probability model for on-line detection of the carbon dioxide content in a carbon dioxide absorption tower. Based on the conventional probabilistic principal component regression model, the present invention simultaneously introduces the ideas of semi-supervised learning and deep learning, expands the basic probabilistic principal component regression model into the structure of a semi-supervised deep learning model, that is, proposes a new soft sensing method based on a semi-supervised deep probabilistic principal component regression model for on-line detection of the carbon dioxide concentration in a carbon dioxide absorption tower. Compared with the conventional principal component regression model, the method of the present invention can not only effectively utilize a large amount of cheap unlabeled sample information, but also deeply extract the information hidden in the process data, thereby improving the actual prediction effect of the carbon dioxide concentration.
Owner:SOUTHEAST UNIV

Cable fault probability prediction method and device considering joint interface stress, and medium

The invention relates to a cable fault probability prediction method and device considering joint interface stress and a medium, and the method comprises the following steps: obtaining and preprocessing historical data of a cable, and recognizing abnormal data and fault data; analyzing the preprocessed historical data of the cable, and determining factors causing a cable fault; establishing a cable fault probability model based on Weibull distribution or Poisson regression analysis for each factor; and determining the overall cable fault probability based on the cable fault probability model of each factor. Compared with the prior art, the method has the advantages of accurate prediction and the like.
Owner:STATE GRID SHANGHAI MUNICIPAL ELECTRIC POWER CO

Abnormality management device and abnormality management method

The purpose is to appropriately manage abnormal communications with a simpler configuration. [Solution] The abnormality management device 1 includes a second learning unit 12 that updates only the classifier parameters of a classifier 122 that distinguishes between true normal data and pseudo-normal data, based on the probability parameters of a probabilistic model representing the number of normal received packets estimated by the first learning unit 11, in a direction that maximizes the classification accuracy, while keeping fixed the generator parameters of a generator 121 that generates pseudo-normal data that deviates sufficiently from the distribution of true normal data, taking each observed value of the series of number of normal received packets as true normal data, and an abnormal received packet number database 13 that stores the pseudo-normal data output by the generator 121 after the second learning unit 12 updates the classifier parameters of the classifier 122 as information indicating the number of abnormal received packets that deviates from the range considered to be the number of normal received packets.
Owner:INTERNET INITIATIVE JAPAN INC