Designing Micro-Structure Parameters for Backlight Modules by Using Improved Adaptive Neuro-Fuzzy Inference System

A Taguchi-based genetic algorithm (TBGA) is adopted in an adaptive neuro-fuzzy inference system (ANFIS) to optimize the micro-structure parameters of backlight modules (BLMs) in liquid-crystal displays. The method reduces the number of experiments and accumulates the data that indicate performance quality of the modules. The TBGA selects appropriate membership functions and optimizes the premise and consequent parameters by minimizing the performance criterion of root-mean-squared error. The results indicate that the ANFIS with TBGA is significantly superior to ANFIS with particle swarm optimization, ANFIS with GA, and conventional ANFIS for designing the BLM model. Another role of the TBGA is optimizing micro-structure parameters for the backlight module. The results confirm excellent outcome of the TBGA-based ANFIS approach in terms of prediction accuracy, cost reduction, and luminance uniformity. Far more superior results were obtained when compared with those reported in the literature using conventional trial-and-error design methods and even Taguchi-based design methods. Fuzzy model in nature, our approach is applicable generally to industrial product designs and, thus, offers an effective route to solving problems in various industries.