Keynote: The Tech Revolution: Transformational Changes and Challenges for the Automotive Industry

9:00–9:30 a.m.

The automobile is going through a major change in technology. And it's not just electric. The major changes include: software-defined vehicles, digital twins, zonal and centralized computing, ethernet in-car connectivity, adapting to the use of AI, and many more. New entrants are redefining how cars are made. Legacy OEMs have to find new ways to succeed in the face of rising global competition and high battery material costs. While new entrants have the advantage of a clean slate start, legacy OEMs have robust processes that have evolved over decades. But, one thing is clear, everyone has to adapt to this major disruption to be successful.

Keynote: Enabling MATLAB and Simulink for Use in the Cloud

9:30–10:00 a.m.

As automotive platforms advance, the use of cloud and other technologies is becoming central to enabling you to remain competitive. Learn about the 15-year journey of bringing MATLAB^® and Simulink^® to the cloud and the discoveries made along the way. See a high-level overview of the product capabilities and roadmap so that you can feel confident that these tools are ready for you when you start your cloud journey.

Advancing Energy Analysis at GM with the New VERDE Toolchain

10:30–11:00 a.m.

General Motors has a long partnership with MathWorks, utilizing MATLAB^® and Simulink^® to develop proprietary tools for vehicle efficiency and longitudinal performance analysis. Ever-increasing reliance on virtual methods in all phases of product development required improvements to simulation tool efficiency, speed, and fidelity. We also acknowledged the benefits of increased collaboration through modular tool design, democratization, and co-simulation. Recognition of these needs drove a complete redesign of core tool structure and interfaces. The newly introduced VERDE (Vehicle Energy and Range Development Environment) toolchain builds on MATLAB and Simulink with App Designer and Simscape™ to address these needs. In this presentation, hear about VERDE core capabilities, new interface, unique features, and integrated pre- and post-processing that enable General Motors to develop conventional, BEV, and hybrid architectures for leading-edge fuel economy, range, performance, and global CO2/GHG strategy.

Optimizing Calibration Values of Electrified Powertrains with Machine Learning

11:00–11:30 a.m.

The automotive industry is increasingly turning to computer-aided engineering (CAE) tools to streamline product development and reduce time and cost. However, the recent advancements in electric and hybrid electric vehicles have introduced complexities to the product development process. Electrified powertrains incorporate intricate electro-mechanical systems such as internal combustion engines, motors, and batteries, leading to a multitude of operating combinations that are controlled by a set of predetermined calibration variables. The calibration variables can be adjusted to optimize various attributes of the vehicles, including fuel economy and performance. With a vast calibration set available, it is impractical to manually determine the global optimum calibration based on empirical knowledge and experience. This project aims to address the challenge by reframing the calibration development as a mathematical optimization problem to identify the global optimum calibration for a defined objective function. Using Simulink^®, we have developed high-fidelity system-level vehicle models for Ford’s xEVs and utilized them to optimize powertrain calibrations. Leveraging genetic algorithms, a subset of evolutionary machine learning algorithms, we have optimized the calibration to meet specific objectives. Given the high dimensionality of the problem, many simulations (10,000+) must be executed. This necessitates the use of a computing cluster with 512 parallel simulations to complete the studies in a feasible time frame. The project utilized MATLAB^®, Simulink, Parallel Computing Toolbox™, and MDCS licenses, which facilitated the scalability of the problem, enabling us to complete the simulations in 100+ hours (which would otherwise take 30,000+ hours). Upon completion of the study, data analytics techniques are employed to analyze the large data set, and the best calibrations are provided to calibration engineers for further analysis and implementation in vehicles.

Best Practices for Building Large Models from Components to Complex Systems

11:30 a.m.–12:00 p.m.

Model-Based Design processes are well established and have been in use for over two decades. With increased complexity of components, systems, and their interaction with other systems and infrastructure, model sizes are increasing, and implementation challenges are growing. In this talk, get an overview of best practices for dealing with these challenges:

• MATLAB Projects: Automate routine tasks, mistake-proof parts of your work, and integrate source control into MATLAB^® and Simulink^®.
• Components: Optimize Simulink componentization for simulation performance, testability, parallel development, and code generation.
• Interfaces: Define interfaces between components to speed up development and improve performance and code generation.
• Data Types and Parameters: Manage storage for private and shared data types, parameters, and configuration sets.
• Variants: Control design alternatives for data, components, and products via variants.
• Performance: Improve initialization and simulation performance with built-in tools in Simulink.

Women in Tech: Driving Your Career and Navigating the Technology Revolution in Automotive

1:15–2:05 p.m.

Open to all attendees, this session aims to inspire and equip professionals with the insights and strategies needed to thrive in leadership roles amidst the fast-evolving automotive technology landscape. Women leaders from the automotive industry will share their journeys of navigating careers, embracing change, overcoming challenges, and seizing opportunities in the technology-driven automotive sector. Gain valuable knowledge, foster connections, and empower yourself to shape the future of the automotive industry with confidence and vision.

Software-Defined Vehicle Realization with Model-Based Design and FEV’s Gateway

2:05–2:30 p.m.

Emerging technologies such as artificial intelligence (AI), connected and autonomous vehicles (CAV), and electrification motivate the need for a new EE architecture that can handle the complexity of these systems. SDVs are key enablers for these technologies in the automotive industry. However, SDVs come with challenges including legacy software adaptation and high-performance computer (HPC) testing. FEV can help with overcoming these two specific challenges by utilizing MathWorks Model-Based Design tools and FEV’s Gateway. Hear about two use cases that highlight the effectiveness of FEV’s approach towards a rapid realization of SDV software development and testing. The first use case illustrates migrating a traditional legacy E-drive torque path function to a service-oriented architecture (SOA) for SDVs. The second use case demonstrates the integration of an SDV HPC with an existing EE architecture using FEV’s Gateway for rapid integration and testing.

Using Bus Element Ports and MATLAB Functions in Simulink for Algorithm Development

2:30–2:55 p.m.

Simulink^® algorithm designs are traditionally constructed using a top- down approach of subsystems to provide hierarchy, with bottom-level block diagrams consisting of basic blocks to calculate the outputs of subsystems from inputs. In this presentation, see the advantages of using this same top-down approach, but using MATLAB^® Function blocks to calculate the outputs of subsystems from inputs. Discover the ease and advantages of using bus element ports over traditional bus hierarchy designs. And last, explore the use of scripts to help the user provide a Simulink IDE for rapid algorithm development. Together, these three development techniques allow for clean and simple differencing and merging, compact representations of complex logic, consistent modeling standards across large models, and streamlined management of model data.

SIL for E-Drive Systems for Virtual Calibration and Development

2:30–2:55 p.m.

In the push to reduce/eliminate physical testing and to perform virtual calibration, it is increasingly important to have accurate and high-fidelity models that replicate the performance of hardware and software for the electric drive system (including the motor and inverter). Fast execution speed of these models is critical if they are to be widely used to replace physical testing and to perform rapid prototyping of controls development in a continuous integration/development manner. Historically, these two requirements have been in conflict with each other in the electric drive modeling space; where high frequency inverter switching and electrical simulations require small model time steps. Utilizing a flexible modeling approach in conjunction with Simscape™, electric drive hardware models can be simulated alongside full software and calibrations, running as a virtual ECU (VECU) to create a true “virtual dyno” achieving close to real time simulations on a standard laptop computer. These models have been validated using physical data, ensuring their accuracy and reliability. By utilizing these models, it is possible to deliver a calibrated electric drive system prior to physical characterization.

Migration of a Monolithic Algorithm to Service-Oriented Architecture (SOA)

3:50–4:15 p.m.

Service-oriented architectures have been around for a while. In this presentation, see how to break apart a monolithic algorithm into services that can be reused. Follow an explanation of guiding principles and examples of breaking apart a large algorithm into service-based components using System Composer™ as a method to be refactored, and then see how to reuse the test from the large component to the newly refactored composition of SOA components. Finally, learn to generate C++ code (via Adaptive AUTOSAR^®) across the new composition of SOA-based components.

How Cloud-Based Virtual Vehicles Can Help You Build Your Next-Gen Software

4:15–4:40 p.m.

Can you optimize new software algorithms without on-vehicle testing time? How much can we minimize the need for HIL benches and vehicle tests to release new software components? With the rapid rise in the number of software components, introduction of complex E/E architectures, and deployment using over-the-air updates, the future of automotive innovation will be highly software-defined. This future of evergreen software releases demands processes that can decouple software from hardware to ensure we are not constrained by the need for vehicle time and HIL bench tests during development. Virtual vehicle simulations play a key part in helping us "shift-left" away from such hardware dependencies; and when deploying effectively on the cloud, can help you scale up your analysis and testing very quickly. In this talk, see how cloud-based simulations can help you build a new "sport plus" mode for your EV, with faster 0 to 60 mph (100 kph) times. Increasing the power consumption will have effects on the thermal system, and on the EV range—both of which need to be quantified. Using a virtual vehicle model, see how to:

• Quickly change parameters (such as battery current discharge) and quantify the effects of these changes at the component and system level (battery temperature, EV range)
• Scale up your simulation runs by deploying Simulink^® on the cloud
• Combine your fleet data together with virtual models to gain insights such as expected EV range change
• Extract vehicle and environment data to test your production intent software stacks on virtual ECUs and HIL benches
• Combine virtual vehicles with virtual ECU emulators (the future of virtual validation)

Development of a Real-Time Thermal System Model for Electric Class 8 Trucks

2:05–2:30 p.m.

The project involves creating a real-time compatible thermal system model for Navistar electric Class 8 trucks. The model is primarily built using Simscape Fluids™ submodels. The workflow involves creating a variable time step model initially and later converting the model to fixed time step to prepare deployment on real-time platform dSpace^® SCALEXIO. The model involves coolant hydraulics representation for powertrain (motor, inverter, DC/DC converter), brake compressor, battery chiller, and flow routing valves. It also includes separate refrigerant loops for subambient battery cooling and cabin HVAC. Execution of the model on a real-time platform is demonstrated. Correlation of hydraulic model performance and refrigerant model with detailed 1D model used for component designs is discussed. A workflow to bridge the gap between complex models for component design and simplified models for faster solver performance on a real-time platform while maintaining the necessary fidelity is demonstrated.

4 Advantages of Making Esoteric HIL Testing Accessible

2:55–3:20 p.m.

Nikola is a Class 8 truck OEM with battery and hydrogen fuel cell electric trucks in market. These products have multiple Nikola ECUs that communicate with components, supplier ECUs, and among themselves. An elaborate setup was created for efficiently testing each ECU in an HIL setup with the ability to test different calibrations, and compare and test software while maintaining ease of use. We leveraged Speedgoat^®, MATLAB^®, Simulink^® and App Designer to create a UI that makes the HIL bench(es) accessible to any engineer (controls, calibration, testing etc.). The setup can flash software and invoke a real-time application that the user can interact with for their tests. The GUI emulates a truck on their computers where they can test each ECU in isolation or in unison with other models with only a few clicks, thus reducing resources spent on dyno and field tests—they can develop, test, fail fast, and retry. This allows Nikola engineers to test different scenarios without recompiling, rebuilding, and redeploying the model or concocting different test harnesses. Users of this application can override multiple model parameters, signals to the ECU, and component calibrations to not only test a software but compare different software versions. Previous software versions are available to the user via a dropdown. Four ways the setup is helping Nikola stay agile are:

• Reducing the time between software release, model development, and testing
• Reducing resources required for dyno/field tests
• Increasing accessibility of tools company wide
• Comparing multiple software/calibrations efficiently

In this session, discover:

• How MATLAB and Simulink products have helped Nikola build this setup
• The process pipeline after each software release: harness setup, updating models to interact with Speedgoat, etc.
• The model components and other non-hardware ECU models that interact with the real-time output
• How to decrease variable costs by making HIL accessible

A Unified Data Analytics Framework for Time-Series Data

2:55–3:20 p.m.

In the automotive industry today, vehicle data is collected and archived from a large, diverse group of vehicles and test cells for a variety of purposes. This data is usually time-series data with varying sampling rates. Often the teams collecting this data utilize different acquisition methods and file formats and have different reporting requirements. Furthermore, the data identifiers, units, and the sampling rates themselves are often subject to change. For this reason, a need for a unified data analytics platform that provides a common foundation that satisfies the requirements of multiple departments was identified. Dashboard2 is an in-house tool that provides a strict separation between the foundational code that processes the input data and the analysis code that generates interactive reports within MATLAB^®. It also provides interfaces to remote data sources and quick query capabilities that allow engineers to access specific data sets of interest in a generic and efficient manner. MATLAB and Simulink^® products such as Parallel Computing Toolbox™, MATLAB Compiler™, Database Toolbox™, Vehicle Network Toolbox™, as well as MATLAB tables, timetables, and built-in interfaces to Java, were instrumental in the development of Dashboard2. The same platform is designed to support interactive and automated data analysis on both Linux^® and Windows^®. Being able to frequently distribute updates and deliver a compiled, distributable solution allows engineers to work more efficiently and focus on data analysis function development rather than file processing code, with the assurance that there will be no need to rewrite the analysis function even if the data acquisition sources, signal units, or file formats change.

A New Method for Battery Characterization 

3:50–4:15 p.m.

Discover a new way to find battery model parameters from characterization experiments. You can use Model-Based Calibration Toolbox™, a tool traditionally used for conventional engine mapping, to estimate the lookup tables that describe the battery behavior. The simple structure of the battery equivalent circuit allows the toolbox to perform the optimizations using symbolic expressions, resulting in an efficient computational scheme. In addition, vectorization and parallel computing take advantage of the independence among most of the processes involved, enabling a complete fingerprinting of a battery across SOC and temperature in a matter of minutes on a common laptop computer. This talk may be useful to battery engineers and calibration engineers with experience in ICE calibration with an interest in electrification. 

Deep Learning–Based Reduced Order Models for Electric Motors

4:15–4:40 p.m.

Full vehicle system modeling is used in applications such as electric vehicles and energy systems and plays a pivotal role in understanding system behavior, system degradation, and maximizing system utilization. The behavior of these systems is dictated by multi-physics complex interactions that are well suited for finite-element simulations, but modeling system behavior and system response is computationally intensive and requires high-performance computing resources. Additionally, such models cannot be deployed to hardware (HIL/PIL) to predict real-time system response. Another alternative is reduced order modeling using curve fitting and system identification, which makes subsystem models computationally feasible. However, in many critical systems, this approach is not preferred as these surrogate models are less accurate and do not represent the full spectrum of component behavior. With deep learning, we can now rely on data to develop small footprint, detailed models of components without approaching the problem from first principles. In this presentation, walk through the development of a deep learning– based reduced order model (ROM) for a permanent magnet synchronous motor (PMSM), a popular component for electric vehicles and future green transportation.

Developing Simulink Co-Simulation with SUMO and CARLA

2:05–2:30 p.m.

Ford ADAS Toolbox is a user-friendly toolbox developed for Ford by MathWorks Consulting Services. The toolbox is a plug-in for Simulink^® to use CARLA and SUMO (open source software for autonomous driving and traffic simulation). A creative implementation of the plug-in enables the user to launch CARLA/SUMO server, clients, and co-simulation directly from Simulink without the need to write any code. It allows the user to control actors (vehicles, pedestrians, etc.); access traffic, map, and route info; and access modeling sensors (camera, radar, lidar, etc.) using Simulink block diagrams. It supports code generation and can be installed in both Windows^® and Linux^® environments. It also supports MATLAB^® functions, Simulink blocks, and deployment via MATLAB Coder™, Simulink Coder™, and Embedded Coder^®. The toolbox has been applied by major projects, brought significant benefits, and proved to be very effective.

Scene Sync: Bridging Real-World Scenarios with Virtual Environments for ADAS Development

2:30–2:55 p.m.

This presentation delves into the meticulous process of crafting real-world scenarios through the utilization of vehicle test data logs, subsequently employing them to simulate scenarios within a virtual environment. The workflow showcased integrates HD maps and recorded sensor data to generate driving scenarios, structured into key stages including importing HD maps and vehicle trajectories into RoadRunner via MATLAB programmatically, utilizing gRPC APIs for data extraction, and ensuring interoperability with IPG CarMaker through ASAM OpenScenario Export. Aimed at fostering a sophisticated virtual environment, this workflow advances early control algorithm design and testing, particularly concerning Advanced Driver Assistance Systems (ADAS) features. Challenges encountered will be addressed, and potential future applications of the workflow will be explored, emphasizing its pivotal role in accelerating the development of automated driving applications.

Scenario Simulation for Automated Driving with MATLAB, Simulink, and RoadRunner

2:55–3:20 p.m.

Hear an overview of workflows used to develop scenes and scenarios for automated driving applications, including designing scenes and scenarios interoperable with common driving simulations tools, building scenarios from recorded sensor data, and simulating driving applications for early design and test. See how these workflows are applied to a case study featuring a Euro NCAP test suite for an autonomous emergency braking application.

Electric Vehicle Chassis Modeling and Control Applications

3:50–4:15 p.m.

Chassis development is a critical part of the design, functionality, and performance of automobiles. Development of the chassis ranges from the mechanical design of suspension hardpoints all the way to electrical design of control algorithms like electronic stability control and emergency braking. As new technologies such as electric vehicles are introduced, new opportunities like torque vectoring and active suspensions arise to further improve chassis response. In this talk, discover how you can use MATLAB^® and Simulink^® to accelerate chassis development and tackle the challenges that new technologies provide.

Automated Driving in the Urban Environment with RoadRunner Scenario

4:15–4:40 p.m.

Learn how to simulate automated driving in the urban environment with RoadRunner.

• Create a complex urban scene consisting of intersections with traffic lights.
• Generate a V2X Map from the RoadRunner HD map and a V2X SPaT (signal phase and timing) from the RoadRunner traffic signalization.
• Implement a mission planner to search the shortest path for a given start and destination position using an A-star planner.
• Design a behavioral planner to follow traffic lights in the urban intersections using V2X Map and SPaT.