Multi-functional Lighting Control System using Artificial Intelligence

Abstract

Several scenarios required for landscape lighting were constructed, and the operation was confirmed by designing and implementing a large-capacity general-purpose multifunction controller to operate the scenario. The control system's hardware consists of an AVR control unit, a CLCD output unit, an LED control unit, a scenario selection switch unit, and an operating speed display unit, and is produced as a 13-channel. ATmega128 was used as the CPU, and FET was used to control the current signal. In order to operate the CPU, DC 12V was converted to DC 5V using a regulator 7805. The LED lighting control system was designed to represent the color of fuzzy rule according to the input values of illumination and distance, and computer simulations were conducted with crisp control and fuzzy control, respectively. The fuzzy control was controlled more flexibly and effectively than crisp control, looking at the processes where output power colors appear according to the input/output power.And three input variables and three output variables were used in the structure of the multi-layer neural network, and the number of neurons consists of three input layer neurons, 10 hidden layer neurons, and three output layer neurons, and is designed with i=3, j=10, and k=3. Computer simulations were conducted by designing to output desired R, G, and B values according to input values of illuminance, temperature, and humidity, and R, G, and B values of the output are combined to express LED colors. Also, using the fuzzy control system and the neuro control system, the control system was designed to represent the most appropriate colors according to various input values and computer simulation was carried out. As a result, unlike the existing crisp logic, fuzzy control and neuro control do not need to store a lot of data input values and are simply controlled to desired values by learning data. Due to these characteristics, it was confirmed that LED lighting control through artificial intelligence becomes a more organic and efficient system than general LED lighting control.