The thermal design of telescopes involves iterative optimization of a large number of parameter combinations, which currently relies on engineers' design experience and repeated attempts, the process that is very time-consuming and difficult to find the global optimal solution. 

The use of reasonable methods to quickly achieve optimal design of telescope thermal design parameters has become a very important issue, and therefore, parameter optimization techniques have received much attention from scholars at home and abroad in recent years.

In a study published in Applied Sciences, a research group led by GUO Liang from the Changchun Institute of Optics, Fine Mechanics and Physics (CIOMP) of the Chinese Academy of Sciences (CAS) proposed a design method (called SMPO) based on an improved back-propagation neural network (called GAALBP) that builds a surrogate model and uses a genetic algorithm to optimize the model parameters.

The surrogate model of atmospheric density measurement device (called DQM) is established using GAALBP and compared with the surrogate model established by traditional back-propagation neural network and RBF neural network, etc. 

The results show that the regression rate of the surrogate model based on GAALBP reaches 99.99% and the mean square error (MSE) error is less than 2*10^-6, and the maximum absolute error is less than 4*10^-3. The thermal design parameters of the surrogate model are optimized by genetic algorithm, and the optimization results are verified by finite element simulation. Compared with the design results of manual thermal design parameters, the maximum temperature of complementary metal-oxide-semiconductor (CMOS) is reduced by 5.33°C, the minimum temperature is increased by 0.39°C, the temperature fluctuation is reduced by 4 times, and the calculation time for parameter optimization is reduced by nearly ten times.

The optimization of space telescope thermal design parameters is mainly done through parameters traversal and iterative attempts, which has problems such as heavy reliance on engineers' experience, large computational workload, time consuming and difficulty in reaching the global optimum. 

Optimization design methods such as those similar to SMPO that can quickly realize multi-parameter intelligence and automation is of particular importance. Moreover, SMPO is an optimization framework and an optimization idea. The rapid optimization process can be transplanted into other models to achieve rapid thermal design and batch implementation. The SMPO is not only applicable to the optimization of thermal design parameters of space telescopes, but also applicable to post-processing and design optimization in other fields, which has good application value.