Air-conditioner control method based on neural network

Abstract

The invention relates to an air-conditioner control method based on a neural network. A neural network control method is combined with a conventional control method. As observed quantity of an air-conditioner system is detected automatically, controlled quantity generated acts on the air-conditioner system to achieve automatic control, and refrigerating capacity or heating capacity or energy consumption of the air-conditioner system is kept at a value of expectation. The conventional control method includes a fuzzy control method or a PID control method. To achieve the same control target, themethod has the advantages of enabling the air-conditioner system to achieve higher refrigerating capacity or heating capacity and lower energy consumption.

Description

technical field [0001] The invention relates to an air conditioner control method, in particular to an air conditioner control method based on a neural network. Background technique [0002] Air conditioning refers to keeping the environmental state parameters in indoor spaces (such as building buildings, trains, airplanes, etc.) at the desired value at all times under the condition of changing outdoor climate conditions and indoor loads. Automatic control of air conditioning is to automatically adjust the control parameters (control quantity) of air conditioning equipment through automatic detection of air state parameters (observation quantities), so as to keep the air conditioning system in the optimal working state, so that the cooling capacity of the air conditioning system, or Heat, or energy consumption, is always at the desired value. [0003] Among them, the main air state parameters (observations) include: indoor and outdoor ambient temperature, indoor and outdoor...

AI Technical Summary

Problems solved by technology

[0007] However, the two traditional control methods mentioned above all have the following problems: 1. Due to the limitation of the ability of the processor (mainly single-chip microcomputer), the algorithm design of the fuzzy control method and the PID control method is relatively simplified; 2. Both the control method and the PID control method are based on limited data samples and rely on artificially optimized control parameters, so they cannot be optimally applied to all work scenarios; 3. When it comes to high-dimensional problems, it is generated based on more than one observation For problems with more than one control quantity, the parameter tuning optimization of fuzzy control method and PID control method becomes extremely complicated

It is precisely because of the above-mentioned problems in the traditional control method that the air-conditioning system has the limitation of low energy efficiency in cooling or heating.

Images