This study presents an innovative framework that integrates artificial intelligence (AI) into automotive product life cycle management (PLM) and Stage Gate decisions within the Product Development Process (PDP). Our goal is to revolutionize the automotive industry by enhancing the efficiency and effectiveness of PLM through the application of AI technologies. We identify the unique challenges faced in automotive PLM, such as complex supply chains, rapidly changing customer demands, and the need for cross-functional collaboration. Additionally, we detail how our specialized AI framework addresses these challenges by providing solutions that improve manufacturing, maintenance, product design, testing, and quality control processes. Our findings demonstrate that AI-driven solutions can significantly optimize various stages of the product life cycle, leading to streamlined development processes. The study also outlines actionable recommendations derived from our research to refine the AI framework, along with suggested avenues for future research. This groundbreaking approach has the potential to transform PLM practices in the automotive sector, enabling companies to better respond to evolving market demands, and ultimately enhancing overall industry performance. By embracing Artificial Intelligence and Deep Learning Models, companies can position themselves for greater success in a competitive landscape.

This study introduces an innovative method to regulate the target price of a new automotive product by amalgamating deep learning, game theory, and control theory. Through this interdisciplinary approach, we aim to enhance pricing strategies to align with market demands and optimize profitability. Specifically, we leverage Artificial Intelligence, employing Convolutional Neural Networks (CNNs) to extract and analyze cost features from design data, such as Product Lifecycle Management Software. Subsequently, a Generative Adversarial Network (GAN) facilitates effective management of design choices. By integrating Learning-based control, utilizing a reinforcement learning model, the game dynamics converge to the Nash equilibrium, thereby achieving optimal cost values aligned with the target cost.