Mercedes-Benz (Germany)

ABSTRACT The necessity of corrosion protection significantly influences the development of automotive body‐in‐white assemblies. This paper presents a digital hybrid framework that enables early‐stage prediction of corrosion behavior in complex automotive geometries by combining physics‐based simulations with data‐driven artificial intelligence (AI) models. Validation on real vehicle components demonstrates high predictive accuracy, with correlation coefficients up to and the majority of results within a 30% deviation from experimental measurements. The approach thus provides a scalable and physically interpretable method for virtual corrosion evaluation, enabling data‐driven optimization of corrosion protection concepts in automotive design.

ABSTRACT Increasing the usage of recycled aluminum (Al) is an efficient way to maintain a low‐carbon supply‐chain for modern automobile companies, where the major challenge is the mitigation of the negative effect of tramp element, such as Fe. This paper aims at the application scenario of recycled Al in automobile profiles, presenting a thorough investigation on the morphology, size, and fraction of Fe‐contained intermetallic compounds (IMCs) in Al‐Mg‐Si alloys with excess Fe contents. Comprehensive understandings were established across the entire process chain, leading to a two‐pronged adjustment strategy. First, the Mn/Fe ratio and Mn content were found to govern the morphology and fraction of IMCs, while the solidification cooling rate dictates their size and distribution. Notably, we revealed that the solidification cooling rate exerts a decisive, penetrative influence that persists through homogenization and deformation processes. This combined effect yields fine, short‐rod IMCs in the as‐cast microstructure, which subsequently undergo spheroidization and fragmentation during homogenization and deformation, minimizing the harmful impact of Fe‐contained IMCs. Second, the Mg/Si ratio and aging parameters enable direct control over Mg 2 Si precipitation, optimizing the strength‐ductility balance. Further, plant‐scale trials successfully produced Al–Mg–Si extrusions from recycled Al, which fully meet the mechanical property requirements for automotive structural components.

In recent decades, abiotic stress factors, including drought, salinity, heat, and nutrient deficiencies, have emerged as major challenges in global agriculture, significantly reducing crop yields and threatening food security. The advent of deep learning (DL) technologies presents a transformative opportunity for improving the detection, prediction, and management of these stresses. This chapter explores the application of DL in abiotic stress management, focusing on various architectures, such as convolutional neural networks and recurrent neural networks, for stress detection in crops using high-dimensional data from sensors, imagery, and environmental inputs. This chapter reviews case studies and real-world implementations where DL has been successfully applied to identify early stress indicators, optimize resource use, and support precision agriculture practices. Furthermore, future directions in DL, including the integration of multimodal data, edge artificial intelligence (AI) for real-time processing, climate-adaptive models, and explainable AI, are discussed. By enhancing early detection and enabling targeted interventions, DL has the potential to revolutionize how we manage abiotic stress and build climate-resilient, sustainable agricultural systems.

<div class="section abstract"><div class="htmlview paragraph">Addressing climate issues is a key aspect of good global governance today. A key aspect of managing the threats caused to the environment around is to ensure a sustainable transportation system so that humans exist in peace with nature. According to sources, in 2020 alone, cars accounted for approximately 23% of global CO<sub>2</sub> emissions. In addition, they also emit dangerous pollutants thus damaging the ecosystem.</div><div class="htmlview paragraph">To keep pollutants in check there are emission level testing strategies in place in each country. However, we can do better for a sustainable future. On one hand, the huge volume of vehicles around the world makes it an excellent choice and source for a vast emission level dataset comprising of input features as well as the target variable representing the emission band of the vehicle.</div><div class="htmlview paragraph">In addition to the big data available as mentioned above, major advancements in the machine learning algorithms are done today. The advent of algorithms such as Artificial Neural Networks (ANN) has made it possible to develop models with very high accuracy.</div><div class="htmlview paragraph">In this paper, the authors therefore propose the application of Extreme Learning Machines (a type of feedforward neural networks) to solve the pressing challenge of classifying the emission band of a vehicle which can be used by agencies to ensure that healthy vehicles operate on road at large. Extreme Learning Machines (ELM), by definition, is an excellent choice for emission band prediction task as it offers a significant reduction in training time and thereby is scalable such as to the task confronted with in this paper. Results from the metric, namely classification accuracy, are discussed at length. The highly accurate trained model, thus developed, can be used by agencies to then predict the emission band for any given vehicle scenario thus complementing the strategies already in place today for a greener earth.</div></div>

<div class="section abstract"><div class="htmlview paragraph">The rapid development of science and technology has impacted on the human lifestyle. The automotive industry plays a crucial role as travel is an integral part of human lifestyle. This indeed has increased the need and demand for automotive domain to step ahead with technology and innovations. Especially, related to ADAS features and AI/ML based algorithms to provide comfort, safety, and many other factors for the consumers. The busy life of human beings has shown an increased rate of many health-related issues like stress, anxiety, heart attacks, blood pressure and so on. The existing system in vehicles detects health emergency and triggers SOS to the emergency service center. However, several catastrophic events occur due to delayed information, thus there is a need for a proactive solution that combines technology and human safety.</div><div class="htmlview paragraph">In this work, we have investigated the different methods which detect the health issues of occupants in a vehicle by monitoring their stress level, heart rate, blood pressure and so on. We propose a solution which helps to navigate to the nearest health center or ambulance meeting point in emergency cases, overcoming technical glitches and delays by driving cars to the emergency center or meeting point, thus saving time for occupants. The prerequisite is that the vehicle has an advanced driver assistance system, detects health emergency of the occupants, V2X communication and SOS are triggered with the basic details of the situation. The system selects the nearest relevant hospital to drive to or requests the SOS center for the geo-coordinates of the ambulance meeting point using V2X communication. As soon as the system receives information related to meeting point from SOS center, autonomous driving mode is initiated, acknowledgment is sent to SOS center, and live location is shared for better communication and coordination. Additionally, the system triggers a siren and emergency lights to indicate an emergency drive, ensuring safety and a clear path. This proactive solution increases the probability of rescuing occupants by taking necessary action, rather than just monitoring, reporting, and waiting for measures.</div></div>

<div class="section abstract"><div class="htmlview paragraph">In automotive safety systems, Time to Collide (TTC) is traditionally used to trigger warnings in auto-emergency braking systems. However, TTC can lead to premature or inaccurate warnings as it is calculated based on the relative speed and distance between the ego and an obstacle. TTC does not consider the vehicle’s braking dynamics, such as brake prefill lag which varies across different vehicles, maximum deceleration, and the effectiveness of braking systems and assumes constant speed which may not always be realistic. We propose Time to Brake (TTB) as a more effective parameter for driver warnings. TTB directly relates to the action a driver needs to take—braking. It provides a clear indication of when braking should begin to avoid a collision, whereas TTC only tells us about the possibility of a collision. To calculate TTB we utilize the brake profile, which incorporates both deceleration and system jerk for improved accuracy. The proposed warning time is the sum of variable brake prefill lag, average driver reaction time, and TTB. TTB is calculated for two distinct scenarios due to differing constraints using Newtonian equations of motion. The comoving and oncoming scenario involve both ego and object colliding at the same location, but in the former, the relative velocity is zero, and in the latter the ego’s velocity is zero at the point of collision. This approach enhances driver response and safety by providing timely and relevant warnings. Tailored for specific braking dynamics, TTB improves the effectiveness of automotive safety systems.</div></div>