11 results about "Uncertainty calculation" patented technology

This invention relates to a method for constructing a machine learning potential energy model based on hierarchical active learning, comprising the following steps: constructing a database of background solvent molecules and lithium salt molecules; initializing a machine learning potential energy model committee; outer active learning automatically exploring the chemical species composition space of the electrolyte, generating electrolyte formulations and initial structures; determining whether a structure needs to be included in the labeling range based on uncertainty calculations; automatically constructing a liquid phase environment based on classical force field simulation methods; performing high-precision simulations based on first-principles calculations and labeling the energy and force values ​​of the structures; inner active learning driving the machine learning potential energy model to explore the configuration space and label the energy and force values ​​of structures with high uncertainty; obtaining a first-principles structure database of the real liquid phase environment through several iterations; and training to obtain the final high-performance machine learning potential energy model. This invention systematically and comprehensively samples the chemical species composition space of the electrolyte and the molecular simulation configuration space based on hierarchical active learning, thereby ensuring the predictive performance and simulation accuracy of the machine learning potential model on unknown and complex electrolyte systems.

The application discloses a kind of based on multi-modal data fusion fermentation environment control method, comprising: collection multi-modal fermentation data and executes pre-processing, forms multivariate time series dataset;Improved MTAD-GAT model is input, calculates prediction error reconstruction error and consistency score, generates dynamic reliable weight;Coupling relationship matrix is constructed across mode, coupling residual is calculated and iterative correction data, reconstructs state vector and uncertainty;Coupling stability index is calculated, and state anchoring is executed, obtains stable reference state parameter;Based on state vector and reference state, construct metabolic feasible region, form control constraint interval;Self-scaling robust controller is constructed, dynamic scaling constraint and rolling optimization calculation, output fermentation control instruction.The application realizes stable identification to fermentation process state and adaptive control to fermentation environment parameter by multi-modal data fusion, coupling relationship analysis and self-scaling robust predictive control.

The present application relates to the technical field of intelligent monitoring of electric power metering equipment, in particular to a mutual inductor full life cycle uncertainty tracking method and system based on physical information neural network. The method realizes real-time tracking of uncertainty through data preprocessing, data noise reduction processing, physical equation definition, physical information neural network construction and uncertainty calculation. The present application is economical and practical. A system framework based on physical information neural network is proposed. Through the combination of the full life cycle monitoring of the data analysis module, the calibration efficiency and result reliability are improved. Not only can the limitations of traditional technology be solved, but also the uncertainty tracking can be optimized through physical constraints, providing more accurate full life cycle management, significantly reducing maintenance costs and improving system stability.

It is evaluated how reliable a determination result by a determination model is. A determination evaluation device that evaluates a determination result for input data based on a determination model includes an uncertainty calculation unit that calculates uncertainty of the determination result, and an analysis evaluation unit that evaluates the determination result on the basis of the uncertainty.

This invention discloses a method, device, storage medium, and program product for monitoring the concentration of galvanized baths. The method includes: acquiring multispectral data collected by an optical fiber probe; calculating a quality assessment index vector and extracting feature vectors; calculating the reliability weights of each spectrum based on current measurement conditions using an adaptive attention module; weighting and fusing the features of each spectrum according to the reliability weights; inputting the fused features into a neural network and adding random perturbations to perform multiple forward propagations to obtain multiple sets of predicted values; statistically calculating the mean as the final predicted value and the standard deviation as the uncertainty; calculating the deviation between the predicted temperature and the measured probe temperature and adjusting the reliability score accordingly; and assigning a reliability level based on the uncertainty and reliability score. This invention avoids contamination by inferior data through adaptive weight adjustment and provides a reliability assessment by combining uncertainty quantification and temperature cross-validation, thereby improving monitoring reliability and accuracy.

This invention discloses an intelligent topographic mapping generation method and system based on artificial intelligence, belonging to the field of artificial intelligence technology. It includes real-time data acquisition through a multi-source network integrating satellites, UAVs, and ground sensors, followed by timestamp alignment and noise filtering preprocessing to output a spatiotemporally synchronized data stream. This invention establishes parameterized prior probability distributions for system errors and random noise based on sensor physical models and historical calibration data, accurately classifying measurement errors, environmental noise, and system biases. It configures a lightweight Bayesian model for each data source type and dynamically adjusts uncertainty calculations through environmental impact factors and environmental sensitivity coefficients, achieving environmentally adaptive uncertainty measurement. It converts posterior uncertainty into probabilistic feature weights, directly reflecting data reliability in feature representation, significantly improving the accuracy and reliability of uncertainty quantification.

The present application relates to the technical field of carbon footprint uncertainty analysis, and particularly relates to a carbon footprint uncertainty calculation method and electronic equipment, the method comprising: automatically generating a plurality of rules from unstructured text comprising carbon footprint historical data; fuzzy weighted synthesis of the plurality of rules in a scenario to generate a credibility distribution; extracting a global range and a scenario range according to a credibility threshold, and truncating the probability density function of the obtained truncated normal distribution on the global range to obtain a background distribution; equally dividing the scenario range into three scenario sub-intervals, and calculating the scenario weights using the background distribution; conditionally truncating sampling for each scenario sub-interval, and independently running Monte Carlo simulation to output the corresponding mean and variance; and weighting and synthesizing the Monte Carlo simulation results of each scenario through the corresponding scenario weights to obtain the uncertainty of the carbon footprint. Compared with the prior art, the present application has the advantages of efficient and accurate analysis of carbon footprint uncertainty, etc.

The application discloses a large model text generation method based on semantic adaptation and dynamic hierarchical comparison, and belongs to the technical field of artificial intelligence and natural language processing, which can at least partially solve the problems of lack of semantic perception ability, fixed hierarchical selection strategy and waste of computing resources in the prior art contrast decoding technology, and introduces a semantic routing module in the decoding process.The method obtains the hidden state of different levels of the model and the final layer output distribution when the model reasons and generates each word element; the semantic routing module is used for semantic attribute determination and uncertainty calculation on the current generation state; according to the determination result, a strategy is dynamically selected from a preset decoding strategy set to calculate the final output value; and the final output value is normalized and combined with a sampling algorithm to generate a word element.The application realizes dynamic balance of factuality and fluency, suppresses hallucinations and reduces reasoning delay.