Indoor personnel positioning method based on feature extraction adaptive neural network and CO2

Abstract

The invention discloses an indoor personnel positioning method based on a feature extraction adaptive neural network and CO2, and belongs to the technical field of environment monitoring and electronic information. The method comprises the following steps: 1, collecting original environment parameter data; 2, processing the acquired data by adopting a least square method; 3, performing feature extraction on the data by adopting a sliding window; 4, training a neural network model in combination with a neural network evaluation module; 5, positioning the indoor personnel through the trained neural network model; and 6, controlling an air conditioner ventilation system. According to the method, building ventilation, air conditioning and other systems can be accurately and intelligently controlled, the comfort degree of life and work of people is improved, and energy consumption is reduced.

Description

technical field [0001] The invention relates to a feature extraction based adaptive neural network and CO 2 The indoor personnel positioning method of the present invention belongs to the field of environmental monitoring and electronic information technology. Background technique [0002] Nowadays, people live and work indoors for a long time, and a healthy and comfortable indoor environment is an important guarantee for people's life and work. However, to achieve a healthy and comfortable indoor environment requires a large amount of energy consumption. Usually, heating, ventilation and air conditioning systems account for about 40% of the total energy consumption of buildings, because ordinary heating, ventilation and air-conditioning systems are usually fixedly operated according to the schedule preset by people, which will cause a certain amount of energy waste. Studies have shown that in large indoor environments, precise control of HVAC systems based on occupant info...

AI Technical Summary

Problems solved by technology

[0004] In order to solve the problems of large energy consumption, imprecise and flexible control, and high cost of obtaining indoor personnel locations in traditional building heating, ventilation and air conditioning systems, this invention proposes a feature extraction based adaptive neural network and CO 2 The indoor personnel positioning method improves the comfort of people's life and work and saves energy consumption

Images