Design and analysis of an advanced thermal management system for the solar close observations and proximity experiments spacecraft

In this paper,the mission and the thermal environment of the Solar Close Observations and Proximity Experiments(SCOPE)spacecraft are analyzed,and an advanced thermal management system(ATMS)is designed for it.The relationship and functions of the integrated database,the intelligent thermal control system and the efficient liquid cooling system in the ATMS are elaborated upon.For the complex thermal field regulation system and extreme space thermal environment,a modular simulation and thermal field planning method are proposed,and the feasibility of the planning algorithm is verified by numerical simulation.A solar array liquid cooling system is developed,and the system simulation results indicate that the temperatures of the solar arrays meet the requirements as the spacecraft flies by perihelion and aphelion.The advanced thermal management study supports the development of the SCOPE program and provides a reference for the thermal management in other deep-space exploration programs.

Model free optimization of building cooling water systems with refined action space

Deep Q Network(DQN)is an efficient model-free optimization method,and has the potential to be used in building cooling water systems.However,due to the high dimension of actions,this method requires a complex neural network.Therefore,both the required number of training samples and the length of convergence period are barriers for real application.Furthermore,penalty function based exploration may lead to unsafe actions,causing the application of this optimization method even more difficult.To solve these problems,an approach to limit the action space within a safe area is proposed in this paper.First of all,the action space for cooling towers and pumps are separated into two sub-regions.Secondly,for each type of equipment,the action space is further divided into safe and unsafe regions.As a result,the convergence speed is significantly improved.Compared with the traditional DQN method in a simulation environment validated by real data,the proposed method is able to save the convergence time by 1 episode(one cooling season).The results in this paper suggest that,the proposed DQN method can achieve a much quicker learning speed without any undesired consequences,and therefore is more suitable to be used in projects without pre-learning stage.