A method designs nuclear reactors using design variables and metric variables. A user specifies ranges for the design variables and threshold values for the metric variables and selects design parameter samples. For each sample, the method runs three processes, which compute metric variables for thermal-hydraulics, neutronics, and stress. The method applies a cost function to compute an aggregate residual of the metric variables compared to the threshold values. The method deploys optimization methods, either training a machine learning model using the samples and computed aggregate residuals, or using genetic algorithms, simulated annealing, or differential evolution. When using Bayesian optimization, the method shrinks the range for each design variable according to correlation between the respective design variable and estimated residuals using the machine learning model. These steps are repeated until a sample having a smallest residual is unchanged for multiple iterations. The final model assesses relative importance of each design variable.

The present invention discloses an optimization design method for structural parameters of biomass boiler economizers and belongs to the field of big data learning models. In the present invention, a sample database is established by utilizing historical operating big data of biomass boiler economizers, a heat exchanger residual self-attention convolution model is established based on a CNN and a self-attention mechanism, a plurality of target parameters to be optimized are quickly predicted through machine learning, and multi-target optimization of structural parameters to be optimized in the economizers can be performed in combination with an iterative optimization algorithm. Compared with traditional optimization for all variables of a biomass boiler economizer, the self-attention mechanism can automatically focus on features with high importance, to better optimize variables with high importance, making the subsequent optimization and adjustment convenient and quick, and greatly reducing the optimization cost.

The present invention discloses an optimization design method for structural parameters of biomass boiler economizers and belongs to the field of big data learning models. In the present invention, a sample database is established by utilizing historical operating big data of biomass boiler economizers, a heat exchanger residual self-attention convolution model is established based on a CNN and a self-attention mechanism, a plurality of target parameters to be optimized are quickly predicted through machine learning, and multi-target optimization of structural parameters to be optimized in the economizers can be performed in combination with an iterative optimization algorithm. Compared with traditional optimization for all variables of a biomass boiler economizer, the self-attention mechanism can automatically focus on features with high importance, to better optimize variables with high importance, making the subsequent optimization and adjustment convenient and quick, and greatly reducing the optimization cost.

A method for predicting a specific energy of a cutter head of a tunnel boring machine includes obtaining a parameter of the tunnel boring machine to be measured configured to influence the specific energy of the cutter head to be measured, and inputting the obtained parameter of the tunnel boring machine to be measured into a model for predicting the specific energy of an apparatus to obtain a total predicted specific energy value of the cutter head and a proportion of each component of the total predicted specific energy value. The method comprehensively considers various influence factors, and outputs a proportion and a change of each component in the specific energy of the cutter head along with the construction process, thereby providing a foundation for optimal allocation of the specific energy of the cutter head of the tunnel boring machine.

A computer-implemented method of machine-learning is described that includes obtaining a dataset of virtual scenes. The dataset of virtual scenes belongs to a first domain. The method further includes obtaining a test dataset of real scenes. The test dataset belongs to a second domain. The method further includes determining a third domain. The third domain is closer to the second domain than the first domain in terms of data distributions. The method further includes learning a domain-adaptive neural network based on the third domain. The domain-adaptive neural network is a neural network configured for inference of spatially reconfigurable objects in a real scene. Such a method constitutes an improved method of machine learning with a dataset of scenes including spatially reconfigurable objects.

A computer-implemented method of machine-learning is described that includes obtaining a dataset of virtual scenes. The dataset of virtual scenes belongs to a first domain. The method further includes obtaining a test dataset of real scenes. The test dataset belongs to a second domain. The method further includes determining a third domain. The third domain is closer to the second domain than the first domain in terms of data distributions. The method further includes learning a domain-adaptive neural network based on the third domain. The domain-adaptive neural network is a neural network configured for inference of spatially reconfigurable objects in a real scene. Such a method constitutes an improved method of machine learning with a dataset of scenes including spatially reconfigurable objects.

A method, apparatus, and system provide the ability to design a convective cooling channel in a computer. Input data is acquired and includes a geometry of an object to be cooled, a design objective, and boundary conditions. Channel designs corresponding to the input data are generated using an iterative topology optimization. One of the channel designs is selected and output.

A method, apparatus, and system provide the ability to design a convective cooling channel in a computer. Input data is acquired and includes a geometry of an object to be cooled, a design objective, and boundary conditions. Channel designs corresponding to the input data are generated using an iterative topology optimization. One of the channel designs is selected and output.

An assembling method for a multi-core cable having a plurality of electrical insulated wires is designed to connect one-end-portions of the electrical insulated wires to electrode patterns, respectively, of one circuit board, correspondingly connect other-end-portions of the electrical insulated wires to electrode patterns, respectively, of the other circuit board, compute intersection coefficients on one end side and the other of the cable, and iterate interchanging connecting destinations for the one-end-portions of the electrical insulated wires, correspondingly interchanging connecting destinations for the other-end-portions of the electrical insulated wires, and computing the intersection coefficients on the one end side and the other of the cable. The connecting destinations for the electrical insulated wires to the electrode patterns are determined in such a manner that a maximum intersection coefficient denoting either larger one of the respective intersection coefficients of the one end side and the other of the cable is made small.

In an aspect an apparatus for analyzing machinability of a part for manufacture, wherein the apparatus comprises a processor. The processor is configured to receive a representative part model of a part for manufacture. The processor may also be configured to extract a semantic datum from the print of the part for manufacture. A machinability datum is determined as a function of the semantic datum. A manufacturing quote is generated as a function of the machinability datum.