Modelling and analysis of artificial intelligence for commercial vehicle assembly process in VUCA world: a case study

Real-time monitoring, is now the integral component in smart manufacturing with the rapid application of Artificial Intelligence (AI) in manufacturing. Machine Learning (ML) algorithms and Internet of things (IoT) make the volatility, uncertainty, complexity, and ambiguity world (VUCA) more reliable and resilient with the stable industrial environment. In this study, two machine learning algorithms such as K-mean clustering and support vector, are used in combination with IoT-enabled embedded devices to design, deploy and test the effectiveness of the vehicle assembly process in the VUCA context. To accomplish this, the design includes both real-time data and training vector data, which were collected from IoT-enabled devices and evaluated using ML algorithms leading to the novel element called Smart Safe Factor (SSF), a critical threshold indicator that helps in limiting different units in assembly line-ups from excess wastages and energy losses in real-time. Test results highlight the impact of AI in enhancing the productivity and efficiency. Using SSF, 21.84% of energy is saved during the entire assembly process and 8% of excess stocks in storage have been curtailed for monetary benefits. This study deliberates the applications of AI and ML algorithms in a Vehicle Assembly (VA) model, connecting critical parameters such as cost, performance, energy, and productivity.

Automated summary

Real-time monitoring using machine learning algorithms and IoT devices in vehicle assembly processes has proven to enhance productivity and efficiency with the introduction of the Smart Safe Factor to limit wastage and energy loss. The study showcases a 21.84% energy savings and 8% reduction in excess stock storage through the application of AI and ML algorithms.