Integration of Artificial Neural Network (ANN) in Set-Based Concurrent Engineering (SBCE) for Automotive Front Reinforcement Bumper Design

• Published in: Journal of physics. Conference series 2025-01, Vol.2933 (1), p.12015
• Main Authors: Shaharudin, Muhammad Syafiq bin, Maulana, Muhd Ikmal Isyraf bin Mohd, Najib, Abdillah Sani bin Mohd, Kadir, Aini Zuhra binti Abdul, Bakar, Saiful Anuar bin Abu, Saufi, Mohd Syahril Ramadhan bin Mohd
• Format: Article
• Language: English
• Subjects: Alternatives; Artificial neural networks; Concurrent engineering; Critical components; Data analysis; Decision making; Design analysis; Design factors; Design improvements; Design optimization; Machine learning; Pattern analysis; Performance evaluation; Product development; Safety factors
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/2933/1/012015

This research evaluates the effectiveness of the SBCE application, specifically targeting the design and optimization of the front reinforcement bumper of a car. SBCE is an enabler of lean product development process. The front reinforcement bumper is a critical component in automotive safety and performance, and its optimization requires evaluating numerous design alternatives to ensure the best possible solution. The primary goal of this integrated strategy is to enhance the efficiency of product creation, improve product performance, eliminate unnecessary waste, and reduce costs. SBCE, a collaborative methodology, facilitates this by systematically assessing multiple designs before selecting the most optimal solution. Conventional product development methodologies often lead to extended and costly iterations of modifications and inadequate final products. In contrast, SBCE promotes the development of diverse design alternatives systematically. However, manual decision-making and communication present considerable obstacles due to inherent biases and dependence on human implicit knowledge. By utilizing data analysis and pattern discovery, decision-making can be enhanced through integrating SBCE with machine learning (ML) that significantly improves the analysis of complex designs where optimal design solution generated automatically, particularly for the front reinforcement bumper of a car. This methodology results in enhanced design optimization based on customer requirement by reduce 22% part weight with increasing 56% for safety factor of the front reinforcement bumper.