Autonomous technology will touch nearly every part of our lives, changing the products we build and the way we do business. It’s not just in self-driving cars, robots, and drones; it’s in applications like predictive engine maintenance, automated trading, and medical image interpretation. Autonomy—the ability of a system to learn to operate independently—requires three elements:
- Massive amounts of data and computing power
- A diverse set of algorithms, from communications and controls to vision and deep learning
- The flexibility to leverage both cloud and embedded devices to deploy the autonomous technology
In this talk, Michelle shows you how engineers and scientists are combining these elements, using MATLAB® and Simulink®, to build autonomous technology into their products and services today—to build their autonomous anything.
Innovations in Comfort and Energy Efficiency in Buildings: Leveraging System Design Methods and Data Analytics
A significant proportion of today’s global energy consumption is used in buildings. It is the industry’s responsibility to develop and build innovative technology in the HVAC market to provide comfort, safety, and efficiency in buildings.
R&D teams at Belimo have a passion for delivering superior solutions for controlling heating, ventilation, and air-conditioning systems. Actuators, control valves, and sensors make up integrated total solutions for global customers.
Key innovations at play are the motorization of dampers and valves, actuators with fail-safe or electronic emergency control, cutting energy consumption, avoiding energy losses, volumetric flow control, and monitoring energy flows.
Belimo’s engineers are leveraging modern system design methods and data analytics to develop components, subsystems, and integrated solutions including monitoring and management functions that create added value for the customers and the environment.
Engineers and scientists are increasingly using simulation to develop products in today’s market. Gone are the days when software and hardware can be developed and tested directly on the physical prototypes. An environment that can model both the algorithmic and physical components of a system is needed to fully understand and develop the systems of tomorrow.
Key elements of an enterprise simulation platform are:
- Multidomain authoring, modelling, simulation, and analysis capabilities
- Intellectual property integration addressing specific domain needs
- Scalability for small to large organizations
Join this session to discover how you can use Simulink® as your enterprise simulation platform.
Application Track A
Solar Impulse is the only airplane of perpetual endurance that can fly day and night on solar power, without a drop of fuel. It is a fine example of how pioneering spirit, innovation, and clean technologies can change the world.
Bertrand Piccard, André Borschberg, and their team was to attempt the first-ever round-the-world solar flight.
They completed the first phase in 2015, flying from Abu Dhabi to Hawaii—the longest solo flight ever undertaken by a single pilot. The second phase, from Hawaii back to Abu Dhabi, was completed in 2016.
This presentation focuses on flight dynamics and flight operations, and shows how Model-Based Design and code verification processes were instrumental in enabling the Solar Impulse team to meet their ambitious objectives.
Many industrial, automotive, robotic, and aerospace applications are becoming increasingly complex and demand high-bandwidth motor control. This often requires implementation on systems-on-chip. Model-Based Design facilitates close collaboration among the different engineering disciplines needed for these applications.
Manufacturing companies that aim to increase production rates and to reduce costs need a method to virtually test system behavior. Configurable material handling systems make this particularly challenging, given that a myriad of processes may be involved. These processes include, among others, machining, deburring, measuring, and storage. Virtual commissioning requires the ability to integrate simulation models of the mechanical, electronic, and control algorithms.
Reishauer AG, a producer of high-precision gear grinding machines, addresses this challenge by using Simscape™ to unite CAD designs with mechatronic simulations. Multibody simulation models imported from CAD assemblies are connected to models of PMSM motors, elastic belt drives, and cascaded controllers to simulate the entire system within the Simulink® environment. To ensure realistic behavior, these models had to be parameterized by input from data sheets. Subsequently, these models had to be compared with actual measurements to verify how closely they would fit reality. This methodology helped to determine which physical effects were critical for achieving the required accuracy.
This presentation covers how an integrated solution makes it possible to perform virtual commissioning, and how to verify designs early in the development process.
Most system design errors are introduced in the original specification but are not found until the test phase. In this session, you will learn how to apply verification and validation techniques at every stage of the development process to catch design errors before they can derail your project.
The human brain is the most complex organ in the known universe, and understanding its function has become one of the major challenges for modern biology. A better understanding of how the brain works will hopefully lead to more efficient treatments for numerous neurological and psychiatric diseases. Over the last decade, imaging techniques have become critically important in providing neuroscience with empirical data about brain structure and function. Nevertheless, the complexity and amount of imaging data produced by these techniques has posed great challenges for neuroscientists.
This presentation discusses several recent neuroscience applications for which MATLAB® has become a valuable tool for quantification and interpretation of imaging data. Applications include registration and segmentation techniques for image processing, machine learning approaches for the analysis of neuronal network function, and optimization strategies for reconstruction of neuronal activity from noisy imaging data. Finally, the presentation discusses how MATLAB can be combined with recent big data computing frameworks, notably Apache Spark™, to achieve scalable processing of large volumes of imaging data in a cluster environment.
Application Track B
Machine learning is ubiquitous. From deep learning in medical diagnosis, speech, and object recognition to data-driven modeling for engine health monitoring and predictive maintenance, machine learning techniques are used to make critical engineering and business decisions every day. In this session, we discuss both machine learning and deep learning techniques in MATLAB® with emphasis on real-world examples in both predictive maintenance and computer vision applied to object detection and recognition.
Swiss Re is the world's second largest reinsurer, founded in 1863, based in Zurich, and has a long history of using an “internal risk model” to steer the company. The model defines its target capital, sets risk-based business volume limits, allocates capital costs across various lines of business, determines the company's solvency ratio for regulatory purposes (Swiss Solvency Test, Solvency II), and more.
For a decade, Swiss Re has used MATLAB® to implement its internal risk model, ICAM (Internal Capital Adequacy Model). Dynamic and increasingly complex internal and regulatory requirements create a challenging development environment, where MATLAB proved to be the perfect development platform to quickly react to changing requirements. In 2017, Swiss Re concluded a major project to overhaul its internal risk model, the key goals being transparency, flexibility for future developments, speed, and precision of risk measures.
This presentation demonstrates how MATLAB is used for several specific tasks within Swiss Re's internal risk model, including organizing and processing data with the table data structure in MATLAB, running fast algorithms in some cases accelerated by MATLAB Distributed Computing Server™, building graphical user interfaces, and visualizing data.
Culture has spread widely with the emergence of the internet and worldwide communication. Today, we can easily download music and movies to our phones or carry an entire bookshelf in a handheld e-reader. But what about paintings, drawings, and sculpture? While technology allows us to enjoy literature, film, and music with the same quality as older formats, current digitization techniques can’t translate fundamental aspects of artwork.
This presentation explores the origin of ARTMYN, a highly accurate solution for the digitization of visual artwork, and discusses what it takes to faithfully represent art online. Julien Lalande explains the ARTMYN process and workflow from acquisition to rendering and discusses how MATLAB® is used in the process.
MATLAB® is often perceived as good for prototyping and internal organizational use, but not for serious user-facing applications. This talk addresses this misconception by showing a few simple-to-use yet surprisingly little-known tips that could be highly effective for improving MATLAB program run-time performance, usability, and visualization quality. Yair demonstrates how easy it is to spice up a simple-looking program.