Physical prior neural network-based satellite component layout temperature field prediction method

Abstract

The invention discloses a satellite component layout temperature field prediction method based on a physical prior neural network, and the method comprises the steps: building a structural model of the satellite component layout according to the layout characteristics of a satellite component; acquiring a plurality of training data, and preprocessing the training data; according to a heat conduction steady-state equation obeyed by a satellite component layout temperature field, constructing a loss function embedded with physical prior; the weight of each prediction point of the temperature field is determined through online data mining, a loss function is updated according to the weights of the prediction points, a regularization item of the loss function is constructed through regional heat flux conservation, and a final loss function is determined; constructing a deep neural network model, and training the deep neural network model by using the preprocessed training data and the final loss function; and utilizing the trained deep neural network model to predict the temperature field of the satellite component layout. According to the method, stable and rapid training of the deep neural network model can be realized by using the training data without labels, and the prediction precision of the model is ensured.

Description

technical field [0001] The invention relates to the technical field of component layout optimization design, in particular to a method for predicting the temperature field of satellite component layout based on a physical priori neural network. Background technique [0002] In order to achieve different functions and perform various tasks, a large number of components are usually integrated inside the satellite. The components will generate a lot of heat during normal operation. If the components cannot be effectively dissipated, the high ambient temperature will cause the components Reduced reliability or even failure. Since the satellite structure and the heat dissipation method of the satellite components are fixed, at present, effective heat dissipation is mainly achieved by adjusting the layout of the satellite components to reduce the temperature of the temperature field corresponding to the layout of the satellite components. [0003] When optimizing the layout of sa...

AI Technical Summary

Problems solved by technology

[0004] However, since the optimization design of the satellite component layout is an iterative process, using numerical methods to simulate and analyze the satellite component layout to determine the corresponding temperature field requires a lot of computing resources and time, and the calculation time increases with the calculation accuracy. exponential growth

When using the deep learning agent model to predict the temperature field of the satellite component layout, it is necessary to use a large amount of training data including the satellite component layout and its temperature field to train the neural network model. Since the real data of the temperature field corresponding to the satellite component layout is difficult to obtain, each The acquisition of each training data needs to simulate and analyze the layout of satellite components by using numerical methods, which will also consume more computing resources and computing time.

Images