Application of Artificial Intelligence in Industrial Design: An Exploration from Concept to Practice

Abstract

Designing industrial products is a complicated process that requires maximizing a number of factors to get the required level of quality and performance.  The model's effectiveness may differ on the intricacy and unpredictability of the industrial design challenge. This study introduces a novel Firefly Algorithm Fine-Tuned Random Forest (FA-FRF) model to demonstrate the efficacy of optimizing industrial product design processes. The research makes use of an extensive dataset that includes several industrial product design criteria, such as capacity, material composition, production procedures, and market segmentation. Min-max normalization is one of the data pre-processing stages applied to normalize the characteristics in a given range. The process of feature extraction uses Independent Component Analysis (ICA), which attempts to locate and extract the most pertinent characteristics from the information. Based on the suggested methodology, this study is carried out using the Python program and performance is examined in terms of RMSE (0.0490), MAE (0.0320), MSE (0.0020), MAPE (3.4137), and SMAPE (3.9871) measures. Designers and technicians may optimize design outputs and decision-making in industrial settings with the help of the FA-FRF model, which delivers the enhanced quality and performance.