The proposed presentation will delve into the transformative role of artificial intelligence (AI) in the automotive industry, specifically focusing on product development from concept to series support. The presented effort is driven by the need to enhance development efficiency, reduce time to market, improve product quality, and lower production costs. AI was explored as a solution to address challenges such as late availability of hardware components, issues during software integration, and high warranty costs.
The AI applications discussed are primarily in the automotive industry, covering areas such as vehicle concept development, usage space analysis, root cause analysis, battery health monitoring, and failure prediction and health monitoring. The methodologies used include advanced AI methods to shorten the time from customer expectations to target agreements, statistical driving data analysis to understand user behaviour, machine learning (ML) surrogate models to identify key parameters influencing failures, and AI methodologies to predict battery lifetime and identify primary influencing factors associated with failures.
The presentation showcases several case studies and application results. For instance, AI-powered vehicle concept development reduced concept assessment time from over 9 minutes to less than 10 milliseconds, achieving a time-to-market reduction potential of 1-3 months. Unsupervised usage space analysis optimized validation fleet driving routes and confirmed durability target achievement by comparing validation tests to real-world usage. Data-driven root cause analysis ranked influencing factors based on healthy and faulty fleet data, telematics, and diagnostic trouble codes (DTCs), leading to reduced time to fix issues. Battery health monitoring predicted battery lifetime and provided recommendations for first and second life usage, reducing warranty costs. AI failure prediction and health monitoring identified primary influencing factors associated with failures and predicted known issues long before they occurred, enhancing product reliability.
The AI applications discussed in the presentation achieved significant improvements in development efficiency, product quality, and production quality. Key results include a reduction in concept assessment time, time-to-market reduction, optimization of validation fleet driving routes, reduction in time to fix issues, prediction of battery lifetime, and enhanced failure prediction and health monitoring. These advancements position AI as a critical tool for the future of automotive engineering.
In conclusion, the application of AI in automotive development has demonstrated substantial benefits, including reduced development time, improved product quality, and lower production costs. These advancements position AI as a critical tool for the future of automotive engineering.