Search Results

As vehicle warranty claims, recalls, and maintenance costs continue to grow, new methods are needed to predict, detect, and diagnose vehicle health issues. By integrating artificial intelligence (AI) technology into the vehicle’s embedded electronics, automakers and fleet owners can benefit from highly effective and adaptable vehicle health management capabilities that are not available today. This paper describes how embedded AI-based signal integrity monitoring can be used to detect complex anomalous patterns in engines. It introduces a novel end-to-end signal integrity monitoring solution, which is based on a pipeline of machine learning models that are trained in an unsupervised manner. It also describes how unsupervised deep learning technology can simplify the data collection and labeling process that is needed to train the AI-based vehicle health management models.

This paper presents an overview of the evolution & revolution of automotive E/E architectures and how we at Bosch, envision the technology in the future. It provides information on the bottlenecks for current E/E architectures and drivers for their evolution. Functionalities such as automated driving, connectivity and cyber-security have gained increasing importance over the past few years. The importance of these functionalities will continue to grow as these cutting-edge technologies mature and market acceptance increases. Implementation of these functionalities in mainstream vehicles will demand a paradigm shift in E/E architectures with respect to in-vehicle communication networks, power networks, connectivity, safety and security. This paper expounds on these points at a system level.

The development of vehicle communication networks is challenged not only by the increasing demand in data exchange and required data rate but also the need to connect the vehicle to external sources for personal connectivity of driver and car to infrastructure applications. Solutions are required to master complexity of in-vehicle communication networks, e.g. diagnostic access, flashing of Electronic Control Units, the data backbone connecting the vehicle domains and the data transfer of cameras. Safety (data transfer) and security (violation) issues of the communication networks gain more importance especially by introducing interfaces to external sources either via mobile devices or by connecting the vehicle to other external sources, e.g. Internet and Car to Infrastructure applications. The Internet Protocol (IP) appears to be an ideal solution to address these challenges, especially in connection with an Ethernet physical layer for fast data transfer.

The release of ISO 26262 is only about three months after the 2011 World Congress. However, there are still some contentious aspects that can introduce challenges or cause a disproportionate effort. In this paper, we will show how to avoid these problems. ISO 26262 provides a detailed method for classifying the Automotive Safely Integrity Level (ASIL) of in-vehicle electronic systems. However, the ASIL value for a specific function/product can vary significantly across the industry. Applying a lower level than the industry norm can cause substantial liability problems. Applying a higher level can initiate an “arms race” with competitors. This is particularly true if there are no vehicle-related reasons for choosing the higher level or if it doesn't make the product any safer. To encourage international harmonization, this paper will define ASIL classifications for the main automotive components. Most functions/products are currently being developed using parts of existing products.

EPA and NHTSA have harmonized Regulations for Greenhouse Gas (GHG) emissions and Corporate Average Fuel Economy (CAFE) for model year (MY) 2012-16, published on April 1st, 2010. This requirement applies to all passenger cars and light trucks. Therefore the reduction of CO₂ emissions will be a major challenge for the automotive industry in the coming years to achieve the targets (GHG & CAFE) of 250 g/mi CO₂ and 35.5 miles per gallon (mpg) for MY 2016. In addition to combustion engine improvements, vehicle energy management and operating strategies offer a huge potential to reduce CO₂ emissions through innovative electronic systems. The paper will show a possible implementation of a holistic vehicle energy management system including the operating strategy "Free wheeling." Starting from a top-down approach, we have developed operating strategies that offer the possibility to optimize the energy usage of the entire system.

This paper describes a new system for early detection of tripped rollover crashes. The main goal of this system is to improve the protection of restraint devices, such as curtain window bags, in these rollover situations. This is achieved by a new rollover sensing (RoSe) algorithm in the airbag controller which produces a very early and robust deployment decision. Based on the analysis of tripped rollover test data, this paper shows how improved rollover sensing performance can be achieved by considering information about the vehicle's driving state before the rollover occurs. The results of this new approach are discussed in terms of deployment times. Finally a combined active and passive safety system architecture for the realization of the approach is suggested.