146 results about "Bayesian framework" patented technology

The invention discloses a battery degradation model construction method based on a Bayesian physical information neural network, and the method comprises the following steps: constructing a pseudo-two-dimensional battery data generation module based on a battery aging mechanism; designing a feature extraction network to extract IC feature parameters; constructing an aging parameter mapping network to describe the relationship between the IC characteristic parameters and the battery aging parameters; and constructing a Bayesian battery health state inference network in a parameter randomization mode. By adopting the battery degradation model construction method based on the Bayesian physical information neural network, while explicit mapping of IC features and aging parameters is realized, physical residual constraints are constructed by using an electrochemical equation in the battery, so that the battery degradation model has relatively high physical interpretability, and the risk of a black box model is avoided; through a Bayesian framework based on random parameter distribution modeling, uncertainty in a model modeling process is quantified, so that confidence quantification of model prediction is realized, and a risk sensitive decision is supported.

The invention provides a deep sea energy system life prediction method, and relates to the technical field of life prediction, and the method specifically comprises the steps: collecting the electrical characteristics of a battery and deep sea environment stress, and carrying out the standardization processing; constructing a deep sea environment degradation model, and constraining the physical characteristics based on the deep sea environment model; inputting the data into a physical branch network to extract consistency constraint features and physical initial priori; the standardized data, the physical enhancement features and the consistency constraint features are input into a lightweight data branch network, and deep residual information formed after the lightweight data branch network is pre-trained is transmitted to a physical branch network; and the RUL priori estimation output by the physical branch network and the data correction item output by the data branch form a final prediction, the final prediction is input into a Bayesian framework to derive posteriori distribution, and uncertainty quantization is carried out. According to the technical scheme, the problems of low service life prediction accuracy and relatively high computing resources of the deep sea energy system in the prior art are solved.

The invention discloses a sparse Bayesian parameter estimation method based on a Markov chain Monte Carlo (MCMC). The sparse Bayesian parameter estimation method is suitable for super-resolution target number detection and high-precision target parameter estimation in a communication perception integration (ISAC) scene. The method comprises the following steps: a base station transmits an orthogonal frequency division multiplexing (OFDM) signal and receives a target reflection echo; performing frequency domain transformation on the echo signal and constructing a high-dimensional observation vector; target parameters are modeled as random variables including path complex gain, time delay, Doppler frequency shift and angle, and a learnable parameterized sensing matrix is constructed; the sparse Bayesian framework is combined with MCMC sampling, the parameters are iteratively updated through random small-batch gradient optimization and the Metropolis-Hastings criterion, and finally the estimation result of the target parameters is output. According to the method, the precision limitation of a traditional gridding method is broken through, super-resolution parameter estimation is achieved, meanwhile, the calculation complexity and the storage overhead are remarkably reduced, and the method is suitable for the high-precision sensing requirement in a 6G communication system.

The invention discloses an intelligent fishing point dynamic prediction method and system based on multi-source marine environment data fusion. The method comprises the following steps: step 1, access, space-time alignment and pre-screening of multi-source heterogeneous marine environment data; step 2, priori knowledge base construction and suitability modeling based on target fish ecological habits; 3, constructing a fishing point prediction model fusing the multi-time-sequence environmental characteristics and deep learning; step 4, fusing two-channel prediction results under the Bayesian framework and quantifying uncertainty; 5, generating a dynamic mask of a real-time sea condition safety threshold value and fishery regulation space constraint; 6.1, constructing a comprehensive scoring function of the risk perception function. According to the method, multi-source heterogeneous data is constructed, a target fish ecological suitability model and a depth time sequence prediction model are combined, the fishing point posterior probability is generated through a Bayesian fusion mechanism, the prediction uncertainty is quantified, and dynamic fishing point recommendation with risk perception and compliance safety is realized.

The invention belongs to the technical field of communication, and particularly relates to an AFDM system channel estimation method based on sparse Bayesian learning. On an AFDM system, a sparse Bayesian framework is utilized, and a two-layer channel estimation method of coarse estimation and fine estimation is provided. The coarse estimation uses a uniform grid and a relatively large stop condition to quickly end iteration; in the fine estimation, a sensing matrix is updated by using the time delay and Doppler output in the previous step, a sensing grid is changed into a non-uniform grid, and the energy of a channel coefficient is concentrated on the grid, so that the estimation error is effectively reduced and the convergence speed is increased. The method has the advantages of a Bayesian learning framework and a compressed sensing algorithm for recovering sparse signals, so that the algorithm has inhibition on noise, and the number of propagation paths does not need to be known; peak value searching and zero setting are assisted, the convergence speed is increased, and overfitting is prevented; finally, high-precision channel estimation can be realized under the positive signal-to-noise ratio.

The invention provides a mobile platform foresight super-resolution imaging method combining a structured sparse and Bayesian framework, and relates to the technical field of remote sensing, and the method comprises the steps: building a high-dynamic platform foresight imaging signal processing model; receiving an echo signal, and obtaining a preprocessed signal of the echo signal in a two-dimensional time domain according to the echo signal and the high-dynamic platform forward-looking imaging signal processing model; and constructing a phase compensation factor, and obtaining a multi-domain joint phase correction signal according to the phase compensation factor and the preprocessed signal of the two-dimensional time domain. Expressing the multi-domain joint phase correction signal as a form of an over-complete dictionary and signal scattering coefficient convolution, and determining variable estimation results of the preprocessed signal of the two-dimensional time domain in all range gates; and generating a super-resolution foresight image of the two-dimensional scene according to variable estimation results under all range gates. The high-order motion of the maneuvering platform and the target structure with the block sparse characteristic are considered, and foresight super-resolution imaging of the maneuvering platform on the surface target scene with the structured sparse characteristic is achieved.

The invention belongs to the field of artificial intelligence, particularly relates to an agent strategy generation and online optimization method based on dynamic scene perception, and aims to solve the problems that in a dynamic environment, strategy response is slow, optimization is difficult under sparse rewards, and online learning is unstable. The method comprises the following steps: constructing a multi-modal fused dynamic scene semantic perception module, and generating a high-dimensional scene representation; historical behaviors and environment contexts are fused through an attention mechanism, and an initial probabilistic strategy is output; executing an action and collecting real-time feedback to form an experience tuple; performing incremental strategy updating by adopting a non-parametric Bayesian framework and combining with a multi-peak exploration operator; a Lyapunov stability criterion and a strategy distillation mechanism are embedded to guarantee convergence robustness. According to the scheme, strategy generation within 50 milliseconds is achieved, the convergence speed of sparse reward tasks is increased by three times, strategy fluctuation is controlled within 8%, the system availability reaches 99.5%, and the real-time decision-making capacity and group cooperation efficiency of an intelligent agent in a complex dynamic scene are remarkably improved.

The invention discloses an underwater target tracking method based on multivariable deflection Laplace distribution modeling, and the method comprises the steps: collecting the motion state data of an underwater target through a sonar sensor, and obtaining the target position measurement information through a coordinate system conversion mode; the method comprises the following steps: establishing a motion model of an underwater target, determining a state-space equation of the underwater target, analyzing mathematical characteristics of underwater noise, and establishing a measurement model of the target under non-Gaussian noise; the method comprises the following steps: modeling non-Gaussian noise on the basis of multivariable skew lapace distribution, solving a mixed parameter, a shape parameter and a scale matrix of the noise under a variational Bayesian framework, iteratively updating a target state and a noise covariance matrix, iteratively updating an estimated target motion state by using Kalman filtering, and after the number of iterations is reached, calculating the target motion state according to the estimated target motion state. And outputting the estimated values of the underwater target position and speed and the estimated value of the covariance matrix. The method has better robustness and estimation precision, does not need to select a degree-of-freedom parameter, and can be better applied to target tracking.

The invention provides a method and system for evaluating fatigue crack life of a welding structure under a random load, and relates to the technical field of rail transit, and the method comprises the steps: recognizing a load peak value and a load valley value through a point-by-point extreme value extraction method, and generating an equivalent variable-amplitude load data set; initial crack propagation rate parameters C and m and stress intensity factor distribution are calculated, and then a deterministic crack propagation increment result is output; a hierarchical Bayesian framework is combined with an MCMC sampling method, and global parameter distribution considering material heterogeneity and observation noise is generated through a posterior distribution formula; predicting crack depth evolution curves under different confidence coefficients, and outputting fatigue life probability distribution and confidence intervals; and finally generating a fatigue life reliability evaluation report of the welding structure under the random load. The method has the beneficial effects that the problem of fatigue crack propagation of the railway vehicle welding structure under the action of the complex random load can be better solved, and more accurate and reasonable technical support is provided for reliability evaluation of the welding structure.

The invention relates to the technical field of air-ground target tracking, in particular to an air-ground target tracking performance evaluation method based on visual saliency. Comprising the following steps: calculating a center positioning error between a target labeling frame and a prediction frame center point; calculating an adaptive center positioning error threshold based on the width and height of the target labeling box; calculating a precision index by using the threshold value; obtaining a saliency map of the target annotation box through a Bayesian framework, and calculating the weight of the target annotation box in combination with pixel saliency; the overlapping ratio under background suppression is calculated based on the overlapping region by using the significance weight, and pixel weight distribution of a real positive example, a false negative example and a false positive example is comprehensively considered in the overlapping ratio; and finally, drawing a success rate curve by setting different overlapping rate thresholds, and calculating an area under the curve as a model performance evaluation index. According to the method, the visual saliency and the adaptive threshold are combined, so that the accuracy and reliability of target tracking performance evaluation are effectively improved.

The invention discloses a single cell activity evaluation method based on cell nucleus geometric parameters and a Bayesian framework, which comprises the following steps: establishing a HeLa cell activity gradient model through adriamycin induction, carrying out cell nucleus segmentation by adopting Cell pose 3.0 and extracting 26 geometric features, screening a high-confidence sample in combination with a Bayesian deep learning framework, and evaluating the activity of a single cell according to the high-confidence sample. And constructing a multi-modal feature fusion model to integrate geometric features and deep semantic features, and finally realizing unmarked and high-precision single cell activity evaluation. The method overcomes the limitation that a traditional technology depends on biochemical markers, has the advantages of being easy and convenient to operate, high in flux and high in interpretability, and provides an innovative technical means for tumor liquid biopsy and precise medical treatment.

The invention discloses an installation error calibration method based on Student's T distribution and variational Bayes, which comprises the following steps: firstly, constructing an installation error calibration geometric model of an SINS / USBL system, defining coordinate systems, establishing an attitude transfer matrix between the coordinate systems, and designing a state equation and a measurement equation by taking installation error angles in three directions as state variables; time updating and measurement updating are carried out based on a Kalman filtering framework; the method comprises the following steps of: embedding Student's T distribution into a variational Bayesian filtering framework, alternately updating distribution parameters of a state variable, a noise covariance and an auxiliary variable through a variational iterative optimization process, maximizing a variational lower bound until convergence, and outputting an optimized installation error angle estimated value. According to the method, acoustic measurement noise is modeled by using the heavy tail characteristic of the SINS / USBL combined system, the interference of outliers on installation error angle estimation is remarkably inhibited, the positioning accuracy of the SINS / USBL combined system in a complex underwater environment can be effectively improved, and the calibration robustness is enhanced.

The invention provides a debris flow risk assessment method and system based on debris flow parameter probability inversion calibration, and relates to the technical field of geological disaster risk assessment. According to the technical scheme provided by the embodiment of the invention, an effective means is provided for scientifically identifying debris flow parameters, and the method is particularly suitable for setting single gullies which are limited in detailed observation and cannot directly measure the parameters. A traditional method depends on statistical parameters or deterministic back analysis, the former introduces errors due to poor regional adaptability, and the latter has the problem of non-uniqueness of parameters; according to the scheme, the parameter posteriori distribution is updated by combining the Bayesian framework with historical observation data (debris flow influence areas), so that the standard deviation of key parameters is generally reduced. In the embodiment of the invention, the influence area is taken as core observation information, the practical limitation that the flow depth and the flow velocity are difficult to observe in real time in the debris flow event is avoided, the observation information can be obtained through post-event field investigation or satellite images, and the scheme is high in practicability.

The invention relates to the technical field of unconventional oil-gas exploration, in particular to a well-seismic integrated geological model intelligent construction and reservoir gas-bearing prediction system, which is characterized in that a data acquisition and preprocessing module generates multi-dimensional feature mapping through wavelet transform denoising and principal component analysis; the well-seismic integrated modeling module adopts a Transform and BiGRU hybrid model to fuse well-seismic data, and constructs a three-dimensional geologic model adaptive to a fracture network; the dynamic gas-bearing prediction module is used for predicting an adsorbed gas / free gas ratio and gas saturation based on a Monte Carlo-Bayesian framework; the real-time iteration module corrects model parameters through online optimization and multi-source data feedback; and the output and visualization module generates a dynamic distribution diagram and an uncertainty interval, and through efficient multi-source data processing, construction of a high-precision three-dimensional geologic model, dynamic prediction of gas content and quantification of uncertainty, prediction precision, timeliness and decision reliability of exploration are improved in combination with real-time iterative optimization of the model and visualization output.

The invention discloses a hybrid antenna array direction of arrival estimation method based on noise marginalization SBL. The method comprises the following steps: initializing system parameters and a sampling grid set; establishing a hybrid antenna array receiving signal model, and initializing a hybrid beam forming matrix into a block diagonal matrix meeting constant modulus constraint; constructing a hierarchical probability model under a Bayesian framework, and introducing a noise precision parameter into signal prior; integral operation is carried out on the noise precision parameter, so that the signal posterior distribution is converted into student t distribution; an objective function is constructed, an expectation maximization algorithm is adopted to iteratively update a signal energy spectrum, and the process does not involve noise parameter estimation; an alternating iteration strategy is adopted, the signal energy is fixedly updated through inner circulation, and optimization is performed through a gradient descent method after outer circulation is fixed; after convergence, constructing a target function of off-grid estimation by reconstructing a covariance matrix; and searching the off-grid direction of the maximized objective function near a spectrum peak to obtain a final DOA estimation value.

A pre-stack wide-azimuth seismic fracture prediction method based on maximum likelihood attribute constraint belongs to the technical field of pre-stack fracture prediction, and comprises the following steps: firstly, using post-stack maximum likelihood attributes to construct a fracture probability distribution model containing anisotropy information of an underground medium, the model being used for simulating large-scale underground fractures and faults; then, the post-stack maximum likelihood attribute is used as a fracture development prior information constraint to be added into a target function, so that the reliability and the stability of pre-stack fracture prediction are improved; and finally, adding Gaussian distribution and a smooth background model into a target function by using wide-azimuth seismic data by adopting a pre-stack anisotropy inversion method under a Bayesian framework so as to improve the rationality and stability of inversion. Compared with crack prediction carried out by directly utilizing wide-azimuth seismic data, the crack prediction technical effect in the invention has the advantages that multiple solution lines of pre-stack crack prediction are greatly reduced, and the accuracy of a crack prediction result is improved.

The invention relates to the technical field of smart agriculture, and discloses a smart agricultural crop demand-driven multi-source linkage method and a water and fertilizer intelligent allocation system, the smart agricultural crop demand-driven multi-source linkage method comprises the following steps: constructing an adaptive sparse sensor network and planning a mobile inspection path; based on a Bayesian framework, a data credibility weight mechanism is introduced, and spatial-temporal resolution unification is realized by using a variational Kriging interpolation method; variety-adaptive crop stress state recognition is realized through the health state correction factor and a multi-state classifier; generating a crop water and fertilizer demand prediction scheme considering the yield loss risk in combination with the value-at-risk model and future weather prediction; generating an optimal water and fertilizer blending strategy; multi-source linkage closed-loop feedback control is realized, and self-adaptive evolution is realized by continuously optimizing system parameters through an online learning mechanism; through the adaptive sparse sensor network construction technology, the number of sensor nodes is reduced on the premise of ensuring the monitoring coverage rate.

The invention belongs to the technical field of battery residual life prediction, and particularly relates to a lithium ion battery residual life prediction method considering dynamic temperature influence, and the method specifically comprises the steps: building a lithium ion battery capacity degradation model, and obtaining a state space model under the dynamic temperature influence; a filtering method based on a Bayesian framework is used for predicting the capacity degradation state estimation value and the residual life of the lithium ion battery, a time-varying fading factor is introduced in the importance sampling process, and adaptive kernel density estimation is used in the resampling process. According to the method, a Wiener process is adopted to model a battery capacity degradation process in a nonlinear and time-varying temperature environment, and meanwhile, a time-varying fading factor and adaptive kernel density estimation are introduced to construct an importance density function and a resampling process of a filtering algorithm based on a Bayesian framework, so that the capacity degradation state change tracking capability of the filtering is improved, and the filtering efficiency is improved. And the battery residual life prediction error under the influence of the external environment is reduced.

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 relates to a photometric high-resolution terrain navigation landmark construction method only constrained by a single image. The method comprises the following steps: acquiring a single high-resolution image and low-resolution initial terrain data of a target asteroid surface; under a Bayesian framework, a terrain and albedo inversion problem is modeled into a posterior probability maximization problem, a Bayesian model is constructed, a likelihood item in the model is used for describing a relationship among luminosity information of an image, the terrain and the albedo, an inversion result is ensured to be consistent with an observation image, and the accuracy of the inversion result is improved. A local terrain smoothness constraint and a local albedo consistency hypothesis are introduced into a priori item so as to solve the ill-conditioned problem under the constraint of a single image; converting the Bayesian model into an optimization problem under a variational framework, and iteratively optimizing the terrain and albedo by adopting an alternating direction multiplier method; and constructing a terrain navigation landmark based on the high-resolution terrain and albedo data obtained by inversion. Compared with the prior art, the method has the advantages of being capable of achieving fine three-dimensional terrain and albedo inversion and the like.

The invention discloses a travel destination prediction method and system based on a Logit model, and belongs to the technical field of travel destination prediction.The travel destination prediction method comprises the steps that a spatial-temporal characteristic matrix containing a POI type, a traffic state and a user portrait is constructed based on multi-modal data, a nested mixed Logit model is introduced, travel destination options are divided into a plurality of logic groups through a nested structure, and the POI type, the traffic state and the user portrait are predicted; relevance of options in a group is quantified through a containing value and an elastic coefficient, so that a real selection behavior is reflected more accurately, the fitting ability of the model to a complex decision path is further enhanced through an upper and lower layer probability separation design, and meanwhile individual preference differences are captured through random parameters, so that the algorithm is more accurate. Parameters of the mixed Logit model are dynamically updated through Bayesian maximum likelihood estimation, and a Bayesian framework corrects fixed effect parameters and random parameters in combination with new observation data in each iteration by introducing a parameter prior distribution and posteriori updating mechanism.

The invention discloses an inverse synthetic aperture radar imaging and motion compensation method based on OFDM signals. Interference between distance units is effectively suppressed in a distance compression process by utilizing OFDM signals with enough long cyclic prefixes, and estimation errors are reduced. In order to solve the problem of over-resolution unit migration occurring under high-resolution or long-coherent processing, a vectorization observation model containing low-order and high-order phase error terms of target motion is constructed, and a target image and rotation parameters are jointly estimated through two layers of prior models under a sparse Bayesian framework. In order to enhance the calculation robustness of matrix inversion, joint optimization is carried out by adopting an alternating direction multiplier method, and target rotation parameters are accurately estimated by utilizing a maximum image contrast criterion, so that joint imaging and motion compensation are realized. A simulation result shows that the method has remarkable advantages in the aspects of reducing sidelobe interference, improving resolution and realizing real-time imaging, and is suitable for high-resolution inverse synthetic aperture radar imaging of a non-cooperative target.

The invention relates to the technical field of seismic exploration, and relates to an oil and gas seismic impedance inversion method, in particular to a space-time correlation adaptive MCMC wave impedance inversion method. According to the method, the problems of instability, low calculation efficiency, high multiplicity of solutions and insufficient uncertainty quantization of a traditional random inversion method in the prior art are solved. The method comprises the following steps: constructing a space-time correlation covariance matrix; constructing a target function of the fitting degree; performing iterative inversion; and post-processing an inversion result. According to the method, an inversion strategy based on a Bayesian framework is adopted, space-time correlation covariance is constructed as a prior constraint, spatial correlation and stratum vertical continuity describing impedance parameters are displayed, a physical model is combined to ensure that a prediction result meets the matching performance of observed seismic data, meanwhile, deep fusion with a delay rejection self-adaptive MCMC algorithm is carried out, and the prediction accuracy is improved. And collaborative innovation of physical model constraint and statistical optimization in seismic wave impedance inversion is realized. And the requirement of high-precision seismic inversion is met.

The application discloses a scanning radar two-dimensional super-resolution imaging method based on Bayesian sparse learning, first constructs a bearing-pitch two-dimensional scanning radar signal model, then, according to a maximum posteriori criterion under a Bayesian framework, establishes a sparse optimization target function about target scattering and environmental noise, finally, utilizes a conjugate gradient algorithm and Kronecker product properties to accelerate iterative estimation of target scattering and noise power, realizes adaptive sparse two-dimensional super-resolution imaging of the scanning radar. The method solves the problems of high complexity and poor noise robustness of prior art means, compared with prior art two-dimensional super-resolution methods, has lower calculation complexity, is more robust, has excellent noise adaptive capacity, and can realize two-dimensional scanning radar super-resolution imaging under a low signal-to-noise ratio condition.

This invention provides a germline mutation detection method and system with a low false positive rate. The system is computer-executed and includes: first, performing a PCR repeat cluster consistency test on sequence alignment files generated from high-throughput sequencing reads, down-regulating the base count weights of inconsistent sites within the cluster; then, based on the sample-specific background error baseline, calculating the variation confidence index of each genomic site using an empirical Bayesian framework to obtain candidate single nucleotide variants (SNPs); obtaining candidate insertion / deletion variants through read clustering and physical verification of insertion fragment lengths; subsequently, performing a dual-engine cross-feedback iteration on the two candidate types until convergence, integrating and filtering, and outputting a structured mutation detection report. This invention significantly reduces the false positive rate of both SNPs and insertion / deletion variants while maintaining sensitivity, and improves the detection capability of complex insertion / deletion variants.

The application discloses a kind of ground and satellite-borne measurement precipitation data fusion algorithm under bayesian framework, comprising the following steps: selecting time and space matching satellite-borne measurement precipitation and ground radar measurement precipitation data, when matching, set certain space window and time window, time window is within ±6min with the time difference that ground radar starts once body scanning time that satellite-borne measurement sweeps matching space window, space window is the region that with ground radar as center, the circular region of r radius and the region that satellite-borne radar survey strip is intersected, the ground and satellite-borne measurement precipitation data fusion algorithm under bayesian framework of the application, based on hierarchical bayesian method, the fusion of ground radar and satellite-borne measurement precipitation data, improve satellite-borne measurement instantaneous precipitation precision, obtain the high-precision, high-resolution precipitation estimation result of comprehensive multi-source precipitation observation, and can quantitatively give the uncertainty size that fusion result contains, to better be applied to hydrological model.

The invention discloses a noise enhancement nonlinear system joint detection and estimation method under a Bayesian framework, and belongs to the field of signal processing. Firstly, independent additive noise is added to a nonlinear system input signal, and noise-corrected nonlinear system output is obtained after the signal passes through a nonlinear system. And secondly, under the Bayesian criterion, judging which hypothesis in the binary hypotheses is established by utilizing the output of a nonlinear system of noise correction, and estimating unknown parameters in the signal of which the judgment result is H1. On the premise that the detection performance is not reduced, a noise enhancement nonlinear system joint detection and estimation model which minimizes the estimation risk is constructed. The additive noise is the optimal solution of the model and is random distribution formed by not more than two constant vectors. According to the method, noise enhancement and nonlinear system joint detection and estimation under the Bayesian framework are combined, and the Bayesian estimation risk is further reduced under the condition that the Bayesian detection cost is not increased.

This invention discloses a method for constructing a battery degradation model based on a Bayesian physical information neural network, comprising the following steps: constructing a pseudo-two-dimensional battery data generation module based on the battery aging mechanism; designing a feature extraction network to extract IC feature parameters; constructing an aging parameter mapping network to characterize the relationship between IC feature parameters and battery aging parameters; and constructing a Bayesian battery health state inference network through parameter randomization. This invention employs the above-mentioned method for constructing a battery degradation model based on a Bayesian physical information neural network. While achieving explicit mapping between IC features and aging parameters, it utilizes the internal electrochemical equations of the battery to construct physical residual constraints, enabling the battery degradation model to possess high physical interpretability and avoiding the risks of black-box models. Through a Bayesian framework based on random parameter distribution modeling, the uncertainty in the model modeling process is quantified, thereby achieving quantified confidence of model predictions and supporting risk-sensitive decision-making.

The invention relates to the technical field of laser-induced breakdown spectroscopy data processing, in particular to an LIBS spectrum processing method and device based on residual skewness estimation and a storage medium. The invention discloses an LIBS (Laser-induced Breakdown Spectroscopy) processing method based on residual skewness estimation. The method comprises the following steps: step S10, acquiring an observation signal of an LIBS; s20, on the basis of morphological analysis of the LIBS spectrum, constructing a spectrum model by using prior distribution of a Bayesian framework; step S30, based on the updated hidden variable observation signal, analyzing the updated hidden variable spectrum model by using variational inference to obtain iteration deviation and posterior analysis data; s40, judging whether the updating hidden variable iteration deviation meets an iteration termination requirement or not; if yes, iteration is stopped, and actual spectrum data is obtained according to the updated hidden variable posteriori analysis data; and if not, executing the step S20. According to the method, the spectrum model is analyzed by utilizing variational inference, the optimal convergence point is judged, effective separation of observation signals is realized, posterior analysis data is obtained, and the spectrum estimation precision and the calculation efficiency are greatly improved.

The present invention pertains to a method for determining DNA sequence variation in a fetus from samples of the fetus and parents using a Bayesian framework. The method comprising the following steps: receiving the samples comprise genomic sequence data covering one or more genomic regions of interest in relation to the fetus and the parents; processing the received samples at least in part based on a reference genome; computing a probability of fetal genotypes based on the samples using the Bayesian framework, where the Bayesian framework computes a posterior probability of whether a DNA sequence variant is present in the samples based on a prior probability and a likelihood function; and determining, based on the posterior probability of fetal genotypes, whether the DNA sequence variant is present in the fetus.