Application of hybrid learning algorithm for optimization of LED lens design

In this study was performed optimization procedure of LED lens design by adaptive neuro fuzzy inference system (ANFIS). There are two objective functions in the optimization procedure: viewing angle and luminance uniformity. Optical design software was used for experimental procedure in order to extract training data for the ANFIS optimization procedure. In the first step of the optimization procedure the viewing angle was used as the optimization objective function. Afterwards the initial optimization of the lens shape was found. In the next step the luminance uniformity was used as the second optimization objective function. ANFIS model was used to find the optimal parameters for the LED lens design. The optimal parameters were found based on minimization of the ANFIS prediction accuracy of the viewing angle and luminance uniformity. The selected optimal parameters could be used further for improvement of the LED lens design.