High power light-emitting diodes (HP-LEDs) always are applied for energy-saving to replace the traditional light sources.
HP-LEDs lighting has been regarded in the next generation lighting. In this study, the RGY colors enhance of whit LED
lighting was researched and modulated by artificial neural network (ANN). An ANN model was used to investigate the
correlated color temperature (CCT) and luminous flux (Lux) for the white LED enhanced with different power of single
RYG LEDs. The starting color temperature of the white LED will be set at 7500K (D75 white light standard), then
changed the voltage of the single LED of the red, green or yellow, respectively, to find the best tuning function for the
color temperature and luminous efficiency. These results exhibited that changing the voltage of red LED had the broader
color temperature from 7500 K to 1500 K than the range of green and yellow LEDs from 7500K to 8200K and 7500K to
4700K, respectively. Then, these experimental results were used as input data for the training model. After the learning
model was completed, an analysis was used to obtain the internal representation of the color information by the
responses of the individual chips of the three hidden units in the middle layer. Identification rate of data would be
achieved to 100% by the neural network pattern-recognition tool. Anyway, the correlation coefficient could reach to 99%
by the ANN fitting tool for the color enhancement.