304 results about "Probit" patented technology

The invention discloses a laboratory detection data processing method and system based on a machine learning technology, and relates to the technical field of data processing. According to the method, the signal is decomposed through discrete wavelet transform, the noise standard deviation is calculated based on the median of the highest frequency coefficient, the high signal-to-noise ratio data is reconstructed through the dynamic threshold and the soft threshold function, and the signal quality is improved; a sliding window is used for extracting time sequence signal statistics and FFT frequency domain features, spatial features are extracted in combination with an SIFT algorithm, high-correlation features are reserved through mutual information screening, and redundancy is reduced; constructing a graph convolutional network anomaly detection model and an XGBoost-LightGBM weighted regression model, and eliminating pollution data through an anomaly probability threshold to obtain a normal regression predicted value; predicting a compensation amount according to the environmental parameters by using an LSTM network, and obtaining calibration laboratory data according to the normal regression predicted value and the predicted compensation amount; according to the method, the problems of noise sensitivity, feature splitting, model isolation and environment drifting of multi-source data are solved, and the laboratory analysis precision and robustness are remarkably improved.

The invention discloses an open set hyperspectral image instance graph construction method based on a distillation diffusion model, and the method comprises the following steps: extracting the spatial and spectral features of a target domain HSI through a spatial encoder and a spectral encoder, executing forward diffusion in a diffusion classifier by taking a real label as a starting point, and carrying out the condition reverse denoising, and finally, closed set category prediction is obtained. A single sample prediction set is generated through Monte Carlo sampling, a prediction variance is calculated, uncertainty distribution is constructed, an unknown class probability is calculated by using a cumulative distribution function, and finally, a known class probability and an unknown class probability are fused to generate teacher open set prediction through a mapping module. A K neighbor graph structure of a sample is constructed in a feature space, teacher open set prediction and student open set prediction are respectively used as nodes to construct a teacher / student instance graph, a Wasserstein distance of prediction probability distribution of the teacher / student instance graph and the student open set prediction is minimized through a graph isomorphic knowledge distillation module, and knowledge distillation based on prediction manifold alignment is realized.

It aims to more reliably manage abnormal communication. 【Solution means】 The abnormality management device 1 is configured such that a first learning unit 12 treats each observed value of a normal presence time series as discrete values independent of each other, and estimates probability parameters of a probability model representing the normal presence time after quantization based on the appearance frequency of each observed value; and a second learning unit 13 configured to fix the generator parameters of a generator 131 that generates pseudo-normal data sufficiently deviated from the distribution of true normal data, with each observed value of the normal presence time series being true normal data, and update only the discriminator parameters of a discriminator 132 that discriminates between true normal data and pseudo-normal data in a direction to maximize the discrimination accuracy, based on the probability parameters of the normal presence time estimated by the first learning unit 12.

The purpose is to easily manage abnormal program operation. [Solution] The abnormality management device 1 includes a first learning unit 11 that uses normal data indicating processing resource usage data in which the processing resource usage corresponding to each process ID is normal as training data from among a plurality of processing resource usage data each including the usage of processing resources used in executing a process corresponding to each process ID, and learns parameters of a probability model that outputs a posterior probability that the processing resource usage corresponding to each process ID is normal by maximum likelihood estimation, and a derivation unit 12 that derives a probability distribution of abnormal data indicating processing resource usage data including abnormal processing resource usage based on the posterior probability estimated by the learned probability model, the probability distribution of the normal data, and the prior probability of normality.

The invention discloses a power equipment health evaluation method and system based on time sequence analysis and probability modeling, equipment and a medium, and relates to the technical field of power equipment state monitoring and fault prediction, and the method comprises the steps: obtaining and preprocessing multi-source operation data of power equipment, outputting a predicted value and a confidence interval of a future parameter through a time sequence prediction model, calculating a residual sequence of an actual observation value and a predicted value, fitting distribution through a probability distribution model, establishing a statistical characteristic model of a normal operation state of the equipment, performing anomaly judgment, calculating a health degree index of the equipment based on a deviation degree and a dynamic weight of a monitoring parameter and weighted accumulation, and dividing equipment state grades according to the index. Quantitative evaluation of the health state of the equipment is realized. According to the method, accurate quantification and early abnormity identification of the health state of the power equipment are realized, a reliable basis is provided for predictive maintenance, and the intelligent level and the safety guarantee capability of power grid operation and maintenance are remarkably improved.

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.

The invention relates to the technical field of power system operation and control, and particularly discloses a time-sharing electric quantity prediction method based on a logarithmic load density growth curve, which comprises the following steps of: firstly, performing causal detection and dynamic time-delay optimization on historical load and multivariate external data through convergence cross mapping and mutual information technologies, and constructing a causal time-delay feature set; and the problems of multi-element coupling and time-delay effect quantization are solved. Secondly, fitting a load trend by using time-frequency decomposition in cooperation with a segmented logistic model, extracting dynamic parameters representing a growth rate and a saturation capacity, and endowing the model with a sensing ability for a load evolution stage; then, causal features, growth parameters and load components are deeply fused through cross-domain modulation and a gating mechanism, the nonlinear modulation effect of an external environment on a load mode is explicitly modeled, and finally, a probability interval is generated in combination with quantile regression and residual error correction. According to the scheme, accurate and probabilistic prediction of the time-sharing electric quantity in a complex scene is realized, and the scientificity of an agent electricity purchase decision is improved.

The embodiment of the invention provides a large language model training method and device and a question and answer processing method and device, and the method comprises the steps: obtaining a plurality of samples, enabling each sample to comprise a sample question, a first answer corresponding to the sample question, and a second answer corresponding to the sample question, and according to the similarity between the lexical element of each answer in each sample and the lexical element of another answer, obtaining the lexical element of each answer; determining the weight of lexical elements in each answer, inputting the sample question into a large language model for each sample to obtain first probability distribution and second probability distribution, weighting the probability of each first lexical element in the first probability distribution according to the weight of each lexical element of the first answer, and weighting the probability of each second lexical element in the second probability distribution according to the weight of each lexical element of the second answer; and weighting the probability of each second lexical element in the second probability distribution, and adjusting model parameters in the large language model according to the difference between the weighted first probability distribution and the weighted second probability distribution corresponding to each sample. Based on the method, the quality of model output answers is effectively improved.

The invention provides a privacy protection multi-energy load day-ahead probability prediction method based on a diffusion model, and belongs to the field of multi-energy load prediction of an integrated energy system. Comprising the following steps: S1, acquiring respective energy consumption load data by a local main body, and preprocessing and normalizing the data; s2, dividing the energy consumption data into historical loads and labels, and respectively training two groups of self-encoders-self-decoders; s3, the local main body uploads the latent variables obtained after coding to the cloud; s4, grouping and integrating latent variables by the diffusion model of the cloud, and constructing a joint probability prediction model; and S5, during model reasoning, after a latent variable generated by the cloud is downloaded locally, a final predicted value is obtained through decoding by a self-decoder. According to the method, a prediction framework based on longitudinal federated learning is designed for a multi-energy load probability prediction scene related to a cross-energy form in an integrated energy system, and a diffusion model capable of predicting multi-energy load joint probability distribution is constructed by considering a coupling relationship among multi-energy loads.

The invention discloses a machining parameter self-adaptive tuning method and system, and relates to the technical field of numerical control machining. According to the method, by obtaining initial cutting parameters and cutter parameters of a process planning system and combining machining signals collected by a machine tool in real time, dynamic sensing of the machining process is achieved. A working condition result is output through prediction of a fusion physical model and a data driving model, meanwhile, a real-time signal is processed through a machine learning model to generate a working condition index, the two are combined and then input into an optimization method based on probability modeling, and candidate parameter combinations meeting constraint conditions are obtained and screened. Dynamic threshold monitoring is introduced in the processing execution stage, and parameters can be corrected or retreated in real time when abnormity is detected. And an execution result and processing data are fed back to the process planning system. According to the method, parameter self-adaptive adjustment and optimization can be achieved, prediction precision and machining stability are improved, the service life of the tool is prolonged, risks are reduced, and the method has the continuous optimization capacity and is suitable for intelligent manufacturing under complex working conditions.

The invention discloses a post-earthquake railway structure state evaluation method and system based on multi-source data fusion. The method comprises the steps that a finite element model is constructed according to the structure of a regional railway network, a simulation data set is generated, a physical information neural network model is trained, and a proxy model library is formed; acquiring multi-source observation data, and performing inversion according to the Bayesian theory, the structural damage parameters of the physical information neural network agent model and the multi-source observation data to obtain complete posterior probability distribution of the damage parameters; according to the method, statistical characteristics of damage parameters are extracted from posterior probability distribution, probability grading is carried out on the damage degree of the structure, driving constraint suggestions are generated according to the combination of damage probability grading and specifications, and Bayesian inversion time is reduced from several days to several hours through a physical information neural network agent model, so that the evaluation efficiency is improved; the output of the Bayesian method is probability distribution, the uncertainty range of the evaluation result is clearly displayed, and the uncertainty is quantified.

The invention discloses a non-parametric probabilistic load flow calculation method considering complex uncertainty for a power system. The method comprises the following steps: firstly, constructing source-load nonparametric probability distribution based on a multivariate Gaussian mixture model; then, constructing an alternating current power flow model under a polar coordinate system in the power system, and performing linear expansion on the alternating current power flow model under the polar coordinate system in the power system at a mean point of source-load non-parametric probability distribution by adopting a first-order Taylor series approximation method to obtain a system operation simplified model based on alternating current power flow linearization of the power system; and finally, according to the linear transformation property of the Gaussian distribution, obtaining the probability distribution of the power flow distribution of the power system under each Gaussian component, and in combination with the total probability law, carrying out weighted summation on the probability distribution under each Gaussian component according to the weight to obtain the non-parametric probabilistic power flow probability distribution of the power system. The method provided by the invention has stronger generalization ability and accuracy, and has important reference significance for operation uncertainty quantification of the power system under complex uncertainty.

The invention discloses a multi-dimensional distribution offset adaptive threshold detection method and system, and the method comprises the steps: obtaining real-time data, extracting a multi-dimensional statistical feature, and obtaining a feature vector; based on historical normal data, using an expectation maximization algorithm to train a Gaussian mixture model, and determining parameters to obtain a normal distribution model; inputting the feature vector into the model, and calculating a probability value of the feature vector belonging to normal distribution as a first offset judgment index; based on the real-time data distribution of a plurality of detection objects in the same group, the distribution difference of any two objects is calculated by using a Wasserstein distance, and the similarity between the objects is obtained; and constructing a similarity network and calculating connectivity as a second offset judgment index. Setting a fixed-length sliding window, dynamically updating two indexes in the window, and obtaining a first self-adaptive threshold value and a second self-adaptive threshold value; and when any index is lower than a corresponding threshold value, determining distribution offset and giving an alarm, and updating model parameters in real time by using an incremental expectation maximization algorithm. According to the invention, accurate detection and intelligent analysis of data distribution offset are realized.

Provided are techniques for the calibration of distillation learning from a teacher model to a student model. Specifically, the present disclosure proposes systems and methods that provide convergence with both high quality and speed. That is, example proposed systems both enable the distillation loss to be minimized at the probability mean value in the probability domain of the teacher's predictions distributions while also providing a loss that is nicely (e.g., symmetrically and / or strongly) convex around an optimum in the logit and / or probability domains (e.g., including far from the minimum) to encourage fast convergence of gradient based methods (e.g., irrespective of distance from the minimum).

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 provides a lossless compression and decompression method and system based on a probability model, and belongs to the technical field of data compression. The method comprises the processes of segmentation of input data, probability model training, probabilistic reasoning, entropy coding compression / decompression of an asymmetric digital system and bisection reconstruction input. The system comprises a software module and a hardware module, the software module comprises probabilistic model training, probabilistic reasoning and asymmetric digital system entropy coding compression / decompression, and the hardware module comprises a probabilistic model operation module and a compression / decompression module. According to the method, lossless, high-speed and high-compression-ratio lossless compression can be carried out, and input sequences of different sizes and different types can be compressed through segmentation and parameterization on the input sequences, such as pictures, audios and videos; lossless compression with a high compression ratio is realized through a joint function of probability model reasoning and asymmetric digital system entropy coding; through independent selection or design of hardware modules, high-speed lossless compression is realized.

The invention discloses a power system probabilistic power flow method and system based on polynomial proxy and graph parallelism, and belongs to the technical field of power system planning and operation optimization. The method comprises the following steps: establishing a probability distribution model of a bus load prediction error to obtain sample distribution of predicted power; representing the output response quantity of the system as an input polynomial function, and establishing an initial polynomial agent model; determining an optimal configuration point set; mapping all the selected configuration points to an input sample space to obtain a small number of sample points of an input variable; performing deterministic load flow calculation on the sample points to obtain a sample vector of output response; calculating an undetermined coefficient in the proxy model according to the configuration point matrix and the sample vector; and solving the statistical characteristic quantity of the power flow response to obtain the probability distribution of the response. According to the calculation method provided by the invention, the probability distribution of the power flow response can be accurately and efficiently estimated, and convenience is provided for probabilistic power flow calculation of a novel power system under the access of a distributed power supply.

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.

The present invention discloses a method for predicting and modeling the vertical straightness and angular error of a linear axis of a machine tool. First, through probability statistics and the "3σ" product qualification inspection criterion, a sine function with manufacturing error as the amplitude is used to characterize the surface curve of the guide rail during manufacturing. Based on finite element analysis, the pre-tightening force distribution law of the guide rail group bolts under specific assembly processes is revealed, and a deformation model of the guide rail assembly with statically indeterminate analysis is proposed. Finally, considering the superposition effect of manufacturing and assembly, the spatial profile curve equation of the guide rail is established. Furthermore, according to the geometric transformation relationship, the vertical straightness and angular error of the linear axis of the machine tool are calculated. By carrying out uncertainty analysis on the relevant design parameters in the manufacturing and assembly processes of the guide rail, the spatial profile curve of the guide rail obtained by the present invention is more accurate than the regular and periodic sine function assumption in traditional research, which lays a theoretical foundation for the optimization of the original design scheme of the machine tool and the improvement of geometric accuracy.

The invention discloses a probabilistic optimal power flow calculation method based on a second-order cone and unscented transformation, belongs to the field of power system optimization, and efficiently processes the uncertainty of new energy output and load by coupling the probabilistic sampling capability of unscented transformation (UT) and a convex optimization framework of second-order cone programming (SOCP). According to the method, unscented transformation efficient sampling is utilized, a covariance matrix is directly embedded to simplify correlation processing, and accurate probability distribution of network loss, voltage and line power can be output. Test results show that the calculation efficiency is improved by dozens of times compared with Monte Carlo simulation, the error is lower than 3%, and the method is suitable for risk assessment and operation optimization of the power system.

The embodiment of the invention provides a tool determination method and device, equipment, a medium and a product, and relates to the field of data processing. According to the method, the input risk intention is automatically judged by carrying out multi-dimensional compliance detection on the statement input by the user and combining a probability calculation model, and the input safety does not need to be verified by manually contrasting static rules; meanwhile, the credibility and the risk value of the tool are automatically calculated according to the state data of the target tool, and the reliable and low-risk first tool is screened out, so that the complexity of manually sorting tool rules and intervening in complex scene correction is avoided; in the subsequent process, a final adaptive tool can be determined by automatically calculating the deviation degree between user input and the first tool behavior sequence, automatic processing of all links in the whole tool determination process is achieved, and process delay caused by manual intervention is reduced; the problem that in the prior art, tool determination depends on static rules, the process is tedious, and the efficiency is low due to manual intervention is solved, and the tool determination efficiency is improved.

Here is postprocessing calibration of class probabilities inferred by a machine learning (ML) model, and this calibration is improved by generation of novel initial points that accelerate a genetic algorithm that optimizes fairness and accuracy of the ML model. Tri-objective optimization for multiplier tuning is enhanced by adding a “warm start” mechanism. Innovative designed points are high performance as follows. An identity point has all group multipliers set to 1.0, corresponding to the original model. By definition, this solution will have high accuracy scores and no outcome regression. A parity point has multipliers that have near-perfect disparity and outcome regression. This entails finding multipliers that provide every subgroup approximately the outcome rate of the subgroup with the highest outcome rate. An opportunity point has multipliers that give an approximation of the outcome rate given by an Equality of Opportunity algorithm. This solution provides near-optimal values for accuracy and disparity.

The invention discloses a two-stage space-time diagram network and multi-source information fusion time sequence probability prediction method and device, and relates to the technical field of artificial intelligence and big data analysis. The method comprises the following steps: acquiring historical wind speed sequence data and corresponding target variable sequence data; preprocessing the data, and constructing a training sample according to a preset time sliding window; constructing a time sequence probability prediction framework of the two-stage space-time diagram network and multi-source information fusion; based on the fluctuation correlation of the historical sequence data, constructing an adjacent matrix between nodes; inputting the training sample and the adjacent matrix between the nodes into a wind speed prediction model, training the model through a designed threshold perception loss function of a wind speed-power nonlinear relationship, and outputting a multi-node wind speed prediction probability of a first stage; and inputting the multi-node wind speed prediction probability and the multi-source environmental factor data into the gradient boosting tree model for second-stage prediction, and outputting a multi-node wind power prediction result. According to the invention, prediction errors can be reduced.

The purpose is to appropriately manage abnormal communications with a simpler configuration. [Solution] The abnormality management device 1 includes a learning unit 12 that uses the characteristic directions of normal data as training data to learn, by maximum likelihood estimation, parameters of a probability model that outputs the posterior probability that the number of packets received in each time period corresponding to each of the characteristic directions of the normal data is normal; a derivation unit 13 that derives a probability distribution for the characteristic directions of abnormal data that indicates the number of abnormal packets received in each time period that deviates from the range of normal packet numbers, based on the posterior probability estimated by the probability model learned by the learning unit 12, the probability distribution for the characteristic directions of the normal data, and the prior probability of normality; and a calculation unit 14 that calculates a first index value that indicates the degree of spatial agreement formed by the probability distribution for the characteristic directions of the abnormal data derived by the derivation unit 13 and the probability distribution for the characteristic directions of the normal data.

The object is to manage signal abnormalities even when there is little measurement data of the abnormal signal. [Solution] The abnormality management device 1 includes a learning unit 12 that uses the characteristic directions of normal data as training data to learn, by maximum likelihood estimation, parameters of a probability model that outputs the posterior probability that the intensity of each frequency component corresponding to each of the characteristic directions of the normal data is normal; a derivation unit 13 that derives a probability distribution for the characteristic directions of abnormal data that shows abnormal intensities of frequency components that deviate from a normal intensity range, based on the posterior probability estimated by the probability model learned by the learning unit 12, the probability distribution for the characteristic directions of the normal data, and the prior probability of normality; and a calculation unit 14 that calculates a first index value that indicates the degree of spatial agreement formed by the probability distribution for the characteristic directions of the abnormal data derived by the derivation unit 13 and the probability distribution for the characteristic directions of the normal data.

The invention discloses an automatic driving acceleration test method compatible with variable correlation, which comprises the following steps of: taking vehicle driving data as variables, quantifying the correlation among the variables to select variables needing to be concerned, and fitting a probability density function of the variables by adopting a kernel density estimation method; converting the probability density function into cumulative distribution of the same space; solving Copula parameters by utilizing a Copula model so as to obtain a joint probability density function of the variables; introducing an evaluation index of the scene risk degree, constructing an indicator function, and counting the occurrence probability of the dangerous scene based on the indicator function; adjusting the joint probability density function by using an importance sampling method, establishing a target function based on the number of test times, and solving an optimal sample sampling weight by using a Bayesian optimization method; obtaining the optimal importance joint probability density based on the optimal sample sampling weight, and carrying out random sampling to obtain new observation data of the variable; and constructing a test scene by using the new observation data to perform simulation test on automatic driving.

The invention provides a composite beam reliability optimization method based on a failure probability function. The method comprises the following steps: 1) defining a random input variable, a design variable, a target function and a performance function; 2) calculating a failure sample and an extended failure probability based on an autonomous learning Kriging agent model and a Monte Carlo method according to the Bayesian theory; the method comprises the steps of (1) calculating a design parameter failure sample, (2) calculating a joint probability density implicit function on the basis of an adaptive K-nearest neighbor method and autonomous learning Kriging according to the calculated design parameter failure sample, and (3) calculating a failure probability implicit function on the basis of the Bayesian theorem.By means of the method, the problem that in the reliability optimization process, the calculation cost is difficult to bear due to reliability analysis is solved.

The invention discloses a foundation pit horizontal displacement probability prediction method and system based on a sparse Bayesian extreme learning machine, and belongs to the technical field of civil engineering monitoring and artificial intelligence crossing. According to the method, a probability model containing input and output noise is constructed, feature selection and uncertainty quantification are automatically carried out by using a sparse Bayesian framework, and probability prediction of horizontal displacement at the position where a sensor is not arranged is realized. The method can output the prediction mean value and the confidence interval, effectively solves the problems of data sparsity and noise, and improves the prediction reliability and the engineering decision support capability. The method has the advantages of being high in automation degree, high in anti-interference capacity, suitable for actual engineering monitoring and the like.

The invention discloses a machine abnormal sound detection method based on enhanced self-coding reconstruction and probability modeling, and aims to solve the problem that in an existing unsupervised machine abnormal sound detection method based on a generative adversarial network, the time-frequency feature reconstruction result of machine operation sound is too smooth, so that the machine abnormal sound detection capability is insufficient. According to the method, time-frequency feature extraction is carried out on collected machine operation sound signals, modeling is carried out on machine operation sound time-frequency feature distribution under a normal working condition in combination with a probability statistical model, and the time-frequency features of the machine operation sound under the normal working condition are reconstructed and learned by using an auto-encoder of a structure enhancement mechanism. The method realizes unsupervised machine abnormal working condition determination by combining the reconstruction error and the probability determination result, can improve the determination stability and robustness of abnormal sound detection, reduces the model complexity, and is suitable for application scenarios such as industrial equipment operation state monitoring and fault early warning.

Some embodiments provide a method for training a machine-trained (MT) network. The method receives a network comprising a plurality of parameters. The method trains the network by iteratively (i) propagating inputs through the network to generate outputs and adjusting the parameters based on differences between the generated outputs and expected outputs to minimize a loss function with respect to the parameters, (ii) probabilistically projecting the parameters to minimize the loss function with respect to a set of constraints on the weight values, the probabilistic projection treating the parameters as probability distributions, and updating a set of variables of the loss function based on the probability distributions.