This paper presents the development and implementation of a digital twin (DT) for the suspension assembly of automotive vehicles—an essential subsystem for assessing vehicle performance, durability, ride comfort, and safety. The digital twin, a high-fidelity virtual replica of the physical suspension system, is constructed using advanced simulation methodologies, including Finite Element Analysis (FEA), and enriched through continuous integration of empirical test data. Leveraging machine learning techniques, particularly Artificial Neural Networks (ANNs), the DT evolves into a dynamic and predictive model capable of accurately simulating the behaviour of the physical system under diverse operational conditions.
The primary aim of this study is to enhance the precision and efficiency of suspension testing by enabling predictive maintenance, real-time system monitoring, and intelligent optimization of test parameters. The digital twin facilitates early detection of potential failures, thereby minimizing downtime and reducing maintenance costs. Furthermore, it enables the exploration of a wide range of test scenarios without the need for extensive physical prototyping, resulting in significant savings in time and resources.
Experimental results validate the digital twin’s capability to replicate the physical suspension assembly with high accuracy, offering actionable insights into system reliability and performance. This study underscores the transformative potential of AI-augmented digital twin technology in modernizing traditional testing frameworks, providing a scalable and cost-effective solution for the design, validation, and lifecycle management of automotive components.