Salt field crystallization calculation method, system and equipment based on SSA-D3QN and medium

Abstract

The invention discloses an SSA-D3QN-based salt field crystallization calculation method, system and device and a medium. The method comprises the following steps: initializing an SSA population and D3QN network parameters; updating the SSA population position, and screening out an individual with the optimal concentration; judging whether the screened individuals meet the precision requirement or not until the screened individuals meet the precision requirement; the individual with the optimal concentration is used as an agent to be trained, and experience is stored in a prioritized experience return visit pool Priority Replay Buffer; the method comprises the following steps of: extracting a sample from a Priority Replay Buffer (Priority Replay Buffer) to train a D3QN network; testing the whole model for a plurality of times to obtain a minimum value and an average value in the plurality of times of testing; and judging whether the obtained minimum value and average value meet the error requirement or not until the error requirement is met. According to the method, the sparrow search algorithm SSA and the deep reinforcement learning algorithm D3QN are used for cooperatively solving the reverse calculation problem of the salt field crystallization model, the precision of the crystallization model can be met, the calculation time is shortened, and the calculation efficiency is improved.

Description

technical field [0001] The invention belongs to the technical field of electronic information, and relates to a salt field crystallization calculation method, system, equipment and medium based on SSA-D3QN. Background technique [0002] The production of sun-dried salt in the salt field is a process of concentrating the brine to the saturated concentration step by step and precipitating the sea salt by using the method of sun-tanning in the salt field. This process mainly uses the action of solar radiation and wind to evaporate water. Therefore, the construction of photovoltaic projects in the salt field of the salt field will inevitably affect the salt production of the salt field. The "Salt-Light Integration" project must consider providing economic compensation for the loss of the salt field. The amount of compensation will directly affect the economics of the project. Therefore, it is essential to quantitatively evaluate the impact of photovoltaic projects on the output ...

AI Technical Summary

Problems solved by technology

In the actual implementation process, it is found that the existing genetic algorithm will take a long time, occupy a large space, have large errors, and even fail to converge to the required accuracy. However, the accuracy of the sparrow search algorithm (SSA) can meet the requirements, but the time complexity is too high, there is an urgent need for a method that can meet the accuracy of the reverse calculation of the crystallization model and takes a short time

Images