Light environment intelligent control method based on neural network

Abstract

The invention provides a light environment intelligent control method based on a neural network. The method comprises following steps of step 1: acquisition of original sample data; step 2: sample preprocessing including 2.1, data conversion and 2.2, data cleaning; step 3: design of a BP neural network: designing an initial structure model of the BP neural network, and training and testing the neural network model by use of sample data obtained in the step 2; and step 4: optimization of the light environment: after obtaining an evaluation function according to the neural network model, establishing an optimization model, solving values to which indexes should reach in the current environment in order to achieve a best light environment, establishing a following optimization model target function: max F = alpha1 P1 + alpha2 P2 + ... + alphan Pn, establishing corresponding constraint conditions for different index requirements according to different environments so as to obtain an optimal solution, substituting data of each index under the obtained optimal value into a system, thereby achieving adaptive control and optimization of the light environment. According to the invention, effects imposed by active facts are avoided and adaptive adjustment is achieved.

Description

technical field [0001] The invention relates to the field of intelligent control of light environment, and is a light environment measurement and control method based on a deep learning neural network. Background technique [0002] The light environment refers to the physiological and psychological environment related to the shape of the room established indoors by light and color. It includes and is not limited to illuminance, color temperature, and lighting form. People know the world through hearing, sight, smell, taste and touch, and 80% of the information they get comes from vision caused by light. Therefore, creating a comfortable light environment and improving visual performance has great research value. [0003] Various indicators of the light environment, such as illuminance, color temperature, stroboscopic and glare index, etc., can be directly or indirectly measured by sensors. In different places and in different light environments, these index data are diffe...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the shortcomings of the existing light environment optimization methods that cannot adaptively adjust the indoor light environment, and the current light environment regulation is mainly affected by subjective factors, in order to solve this problem, the present invention proposes a method that effectively avoids subjective factors Neural network-based intelligent control method for light environment

Images