Evaluation of Practical Applications of Artificial Intelligence in Industrial Design
Main Article Content
Abstract
Industrial product design is an involved procedure that demands optimising several variables to achieve the desired performance and quality standards. How well the model works could depend on how complicated and unpredictable the industrial design problem is. The effectiveness of optimising industrial product design processes is demonstrated in this study by introducing a novel model called Firefly Algorithm Fine-Tuned Random Forest (FA-FRF). Several industrial product design criteria, including capacity, material composition, production techniques, and market segmentation, are included in the vast dataset that the research uses. One of the data pre-processing steps used to normalise the features within a given range is min-max normalisation. Feature extraction makes use of Independent Component Analysis (ICA), which seeks to identify and extract the most relevant attributes from the data. The investigation is conducted using the Python software and measures performance using RMSE (0.0490), MAE (0.0320), MSE (0.0020), MAPE (3.4137), and SMAPE (3.9871), following the technique recommended. The FA-FRF model provides improved quality and performance, allowing designers and technicians to optimise industrial decision-making and design outputs.