7 results about "Parallel dynamics" patented technology

The invention discloses a rice bakanae disease bacterium-carrying seed detection method and device based on a hyperspectral image, and the method comprises the steps: preprocessing the hyperspectral data of rice seeds, and inputting the preprocessed data into a rice bakanae disease bacterium-carrying seed discrimination model; a hierarchical and adaptive feature learning and decision-making system is realized by using a multi-scale spectral feature extraction module, an adaptive spectral attention mechanism module, a deep feature cross fusion network module and a result discrimination module, the self-adaptive spectrum attention mechanism module dynamically analyzes the importance of each wave band, and the judgment result module adopts a parallel dynamic meta-learning classifier module and an uncertainty quantification module, and provides the credibility of a judgment result while outputting the judgment result of the seed health state. According to the method, efficient, accurate and lossless bacteria-carrying seed identification with quantifiable result reliability is realized.

Detection and classification of anomalies for powder bed metal additive manufacturing. Anomalies, such as recoater blade impacts, binder deposition issues, spatter generation, and some porosities, are surface-visible at each layer of the building process. A multi-scaled parallel dynamic segmentation convolutional neural network architecture provides additive manufacturing machine and imaging system agnostic pixel-wise semantic segmentation of layer-wise powder bed image data. Learned knowledge is easily transferrable between different additive manufacturing machines. The anomaly detection can be conducted in real-time and provides accurate and generalizable results.

The application discloses a kind of discrete dynamic event tree and nuclear simulation program efficient parallel dynamic coupling analysis method, this method includes: constructing discrete dynamic event tree DET simulation model, determine nuclear simulation program simulation time and run, according to nuclear simulation program simulation result analysis obtains the time information of all DET simulation object state transition control TRIP variable change, and according to DET simulation model branch rule obtains the restart time and restart number of nuclear simulation program backtracking restart of all DET simulation objects of current accident sequence, judge whether restart time and parent sequence restart time are identical, update the failure restart file as input, copy necessary restart input file in parent sequence to current folder, according to branch number backtracking executes multi-thread parallel simulation to complete the simulation of all DET failure branches.This method makes up the deficiency of traditional safety analysis method in handling the time sequence dynamic response of nuclear power plant accident process, and multi-thread parallel computing mode also improves the calculation efficiency.

The invention provides a river channel evolution model construction method and device, electronic equipment and a readable storage medium, and relates to the technical field of intelligent water conservancy. By constructing normal prior distribution of riverbed roughness parameters and combining a customized likelihood function and a Bayesian inference framework, accurate estimation of posterior distribution of the parameters is realized, the defects that a traditional method only outputs a single optimal solution, is easy to sink into local optimum and cannot quantify uncertainty are overcome, and the parameter calibration precision is remarkably improved. A self-adaptive and multi-chain parallel dynamic simulation algorithm is adopted, parallel sampling is carried out, the step length is dynamically adjusted, and the sampling efficiency and the convergence speed in a complex posterior space are greatly improved. Through deep coupling of a hydrodynamic error model and a likelihood function, the consistency of the model and an actual hydraulic process is enhanced. Parameter uncertainty is propagated to simulation results, mean values, variances and confidence intervals of water level, flow and other prediction results are constructed, and a scientific and reliable uncertainty quantification basis is provided for flood early warning and scheduling decision making.

The invention relates to the technical field of artificial intelligence monitoring, in particular to an epidemic disease early warning method and system fusing a depth probability graph model and Bayesian inference, and the method comprises the steps: inputting multi-source time sequence monitoring data and static attribute features into a depth generation model, mapping the data to an independent potential space, and decoupling and outputting pathology, environment and noise variables. The pathological variables are purified by using the two; obtaining parallel dynamic propagation structure particles based on the purification features, and inputting a continuous time evolution model to generate a plurality of epidemic situation evolution trajectories; and finally, a comprehensive risk value is calculated through a risk sensitivity evaluation function to trigger early warning. Environment drift and random noise are accurately stripped from the mixed signals, and the false alarm rate is remarkably reduced; and meanwhile, by deducing multiple propagation hypotheses in parallel and amplifying a high-risk trajectory weight by using nonlinear aggregation, it is ensured that long-tail disaster risks can be effectively captured in the face of uncertainty.

The application discloses a kind of rice seed detection method and device based on hyperspectral image of seed-borne smut, the hyperspectral data of rice seed is inputted after pretreatment rice seed-borne smut discrimination model, utilize multiscale spectral feature extraction module, adaptive spectral attention mechanism module, deep feature cross fusion network module, discrimination result module, realize hierarchical, adaptive feature learning and decision system, wherein, multiscale spectral feature extraction module realizes the extraction of different scale spectral features, adaptive spectral attention mechanism module dynamically analyzes the importance of each band, discrimination result module uses parallel dynamic meta-learning classifier module and uncertainty quantification module, while providing the credibility of the judgment result, the discrimination result of output seed health state is provided.The application realizes efficient, accurate, non-destructive, quantifiable result reliability of seed-borne smut identification.

Detection and classification of anomalies for powder bed metal additive manufacturing. Anomalies, such as recoater blade impacts, binder deposition issues, spatter generation, and some porosities, are surface-visible at each layer of the building process. A multi-scaled parallel dynamic segmentation convolutional neural network architecture provides additive manufacturing machine and imaging system agnostic pixel-wise semantic segmentation of layer-wise powder bed image data. Learned knowledge is easily transferrable between different additive manufacturing machines. The anomaly detection can be conducted in real-time and provides accurate and generalizable results.