Indoor comfort comprehensive evaluation system and method based on artificial neural network model

Abstract

The invention particularly relates to an indoor comfort comprehensive evaluation system and method based on an artificial neural network model. The system comprises a data acquisition unit, a data transmission unit and a remote server. The data acquisition unit is used to collect indoor temperature, relative humidity, average radiant temperature, light intensity, wind speed, noise and CO2 content,and transmit the collected data to a remote server through the data transmission unit. The remote server substitutes the received data into the neural network model for calculation to acquire the indoor environment comfort. The neural network model is trained through a cuckoo search algorithm. The noise and CO2 content are acquired, which can further improve the accuracy of indoor environment comfort evaluation. The cuckoo search algorithm is used to optimize the neural network model, which can prevent the neural network from falling into the local optimal solution. The accuracy of the modelcan be effectively improved. The operating rate is accelerated. System errors are reduced.

Description

technical field [0001] The invention belongs to the technical field of indoor environment regulation, and in particular relates to an indoor comfort comprehensive evaluation system and method based on an artificial neural network model. Background technique [0002] The quality of the indoor environment has a direct impact on the physical and mental health, comfort and work efficiency of the human body. With the continuous improvement of people's living standards, people's requirements for the comfort of the indoor environment are also getting higher and higher. At present, artificial intelligence algorithms are widely used in the evaluation of indoor environment comfort, such as the evaluation model based on fuzzy theory, which uses the maximum membership function and fuzzy evaluation matrix to complete the comprehensive evaluation, but fuzzy theory has its fatal flaw, that is, it is composed of various The weights of each indicator determined by experts are subjective to a...

AI Technical Summary

Problems solved by technology

At present, artificial intelligence algorithms are widely used in the evaluation of indoor environment comfort, such as the evaluation model based on fuzzy theory, which uses the maximum membership function and fuzzy evaluation matrix to complete the comprehensive evaluation, but fuzzy theory has its fatal flaw, that is, it is composed of various The weights of each indicator determined by experts are subjective to a certain extent and do not conform to scientific principles, and in some cases, the determination of membership functions has certain difficulties

In addition, the comprehensive evaluation model based on neural network is widely used. This model has the characteristics of adaptability and strong learning ability, but there are also problems such as difficulty in network structure selection, over-learning, and difficulty in ensuring global optimality, which is not conducive to identification. Model building and generalization

Images