Thermal generator set combustion control optimization method and device and readable storage medium

Abstract

The invention provides a thermal generator set combustion control optimization method and device and a readable storage medium. The method comprises steps of obtaining a real feature data set of a power generation system; training a preset to-be-trained thermal power combustion simulator according to the real feature data set to obtain a trained thermal power combustion simulator; training a strategy network, a value network and a constraint network in a preset framework based on deep reinforcement learning through the real feature data set and a simulated feature data set generated by the trained thermal power combustion simulator according to the real feature data set to obtain a trained strategy network; and optimizing a power generation system through the trained strategy network. Themethod is advantaged in that the real feature data set is used for training, so reliability of describing operation state change of the power generation system can be improved, and optimization efficiency can be improved.

Description

Technical field [0001] The invention relates to the field of thermal power generation, and in particular to a method, device and readable storage medium for optimizing combustion control of a thermal power generating set. Background technique [0002] With the expansion of my country's economy and industrial scale, industrial and economic power consumption is increasing. Behind the process of industrialization that has continued for many years is a large amount of energy dependence. Due to the status quo of “rich coal, poor oil, and low gas”, my country’s current energy consumption pattern is still dominated by non-renewable fossil energy such as coal, of which coal resources account for about 70% of the total fossil fuels, and power generation consumes raw coal in the country. About 50% of coal consumption. Since the 21st century, China’s power industry has developed rapidly. The total installed power capacity and power generation have increased rapidly. Thermal power generatio...

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a combustion control optimization method, device and readable storage medium for a thermal power generating set, which are used to solve the problem that the existing thermal power generating set boiler combustion optimization method lacks full utilization of operating data and cannot carry out system-level precise construction of a thermal generating set. model, and can only be optimized at a single point, resulting in limited effects of the optimization scheme and the inability to achieve long-term comprehensive optimality

Images