The software Audi has developed recognises and marks the finest cracks in sheet metal parts automatically, reliably and in a matter of seconds. With this project, Audi is promoting artificial intelligence at the company and revolutionising the testing process in production.
Due to the increasingly sophisticated design of its cars and the high quality standards at Audi, the company inspects all components directly after production in the press shop. In addition to visual inspection by employees, several small cameras are installed directly in the presses. They evaluate the captured images with the help of image-recognition software.
This process will soon be replaced by an ML procedure. Software based on a complex artificial neural network operates in the background of this innovative procedure. The software detects the finest cracks in sheet metal with the utmost precision and reliably marks the spot.
"We are currently testing our automated component inspections for series production at our Ingolstadt press shop. This method supports our employees and is another important step for Audi in the transformation of its production plants into modern smart factories," stated Jörg Spindler, Head of the Competence Center for Equipment and Forming Technology.
The solution is based on deep learning, a special form of machine learning that can operate with very unstructured and high-dimensional amounts of data such as with images. The team spent months training the artificial neural network with several million test images.
The biggest challenges were on the one hand, the creation of a sufficiently large database, and on the other hand, the so-called labeling of the images. The team marked cracks in the sample images with pixel precision – the highest degree of accuracy was required. The effort was worth it because the neural network now learns independently from the examples and detects cracks even in new, previously unknown images. The database consists of several terabytes of test images from seven presses at Audi's Ingolstadt plant and from several Volkswagen plants.
"Artificial intelligence and machine learning are key technologies for the future at Audi. With their help, we will continue to sustainably drive the digital transformation of the company," emphasised Frank Loydl, Chief Information Officer (CIO) at Audi AG. "In this cross-divisional project, we are jointly developing a production-ready solution that Audi will use exclusively in the company and which is unique in the market." The software was mainly developed in-house, from the idea to the finished prototype. Since mid-2016, the innovation department of Audi IT has been working hand in hand with the Production Technology division of the Equipment and Metal Forming Technology Competence Centre."
In the future, quality inspection using ML will replace the current optical crack detection with smart cameras. This involves a great deal of manual effort. Whether doors, engine hoods or fenders – the camera currently has to be reconfigured for every new component produced in the press shop.
In addition, false detections regularly occur, since the simple algorithms of the image-processing program are highly dependent on ambient factors such as lighting conditions and surface properties.
In the future, it will be possible to apply the ML approach also for other visual quality inspections. If a sufficiently large number of labelled datasets are available, the system can also support paint shops or assembly shops, for example.
Data from radar sensors helps drivers to assess the traffic situation when turning left, entering a roundabout or at right-before-left intersections. Machine-learning has played a key role in the three-and-a-half-year research project. Algorithms create an always up-to-date driver profile based on a range of vehicle data, allowing them to adapt the driving maneuver recommendations given by the City Assistant System in line with the driving style.
Acting like a good passenger, an advanced driver assistance system must analyse the driver's style of driving and, in turn, their subjective sense of safety or risk so that, in complex traffic situations, it can give the driver recommendations that are also met with a high degree of acceptance. The driving profile is created quickly and accurately on the basis of a machine-learning process. For this, a range of data recorded during journeys is evaluated. Acceleration, yaw rates, braking and lateral acceleration in particular give the algorithm an idea of what type of driver is behind the wheel.
Extensive test drives with testers showed that the algorithms used in the City Assistant System allow conclusions to be drawn about the current driving style within three to five driving maneuvers. The system can therefore assign the driver to one or more clusters of driving profiles, meaning that the City Assistant System can then offer highly personalised driving recommendations.
Machine-learned algorithms are becoming increasingly common in vehicle systems. While the number of vehicle system units utilising artificial intelligence stood at 7 million in 2015, this figure is expected to increase to 225 million by 2025.
"The driver has to develop confidence in the City Assistant System and its recommendations. Trust is the basis for the acceptance of advanced driver assistance systems, which in turn are an essential component of accident-free driving," said Ralph Lauxmann, Head of Systems & Technology at Continental's Chassis & Safety division.
Based on the driving profile, the system monitors the time windows for driving recommendations – for example, with the left-turn assistant. This determines how big the gaps in the oncoming traffic are for a left turn based on data about the vehicle's own position as well as the speed of and distance between oncoming vehicles. The task of object detection is carried out by ready-for-production long- and short-range radars installed on the sides of a vehicle. These are already in use in many assistance systems today, such as Adaptive Cruise Control or Blind Spot Detection.
The same principle applies to the second application: entering a roundabout. Here, too, the system uses the vehicle and environment sensors to determine whether a gap in traffic is large enough and whether it makes sense, in view of the driver profile, to recommend that the driver enters the roundabout or waits for a larger gap.
The more accurately the position of one's own vehicle is known; the more reliably advanced driver assistance systems can make decisions in complex traffic situations. One component of PRORETA 4 was therefore a camera-based system for automatically mapping landmarks such as prominent points on buildings or infrastructure. These landmarks will later be recognised by the vehicle camera, allowing for even more accurate localisation of the vehicle than is possible with GPS or navigation data.
Graphene has recently generated the enthusiasm and excitement in the automotive industry for paint, polymer and battery applications.
Dubbed a "miracle material" by some engineers, graphene is 200 times stronger than steel and one of the most conductive materials in the world. It is a great sound barrier and is extremely thin and flexible. Graphene is not economically viable for all applications, but Ford, in collaboration with Eagle Industries and XG Sciences, has found a way to use small amounts in fuel rail covers, pump covers and front engine covers to maximise its benefits.
"The breakthrough here is not in the material, but in how we are using it," said Debbie Mielewski, Ford senior technical leader, sustainability and emerging materials. "We are able to use a very small amount, less than a half percent, to help us achieve significant enhancements in durability, sound resistance and weight reduction applications that others have not focused on."
Graphene was first isolated in 2004, but application breakthroughs are relatively new. The first experiment to isolate graphene was done by using pencil lead, which contains graphite, and a piece of tape, using the tape to pull off layers of graphite to create a material that is a single layer thick – graphene. This experiment won a Nobel Prize in 2010.
In 2014, Ford began working with suppliers to study the material and how to use it in running trials with auto parts such as fuel rail covers, pump covers and front engine covers. Generally, attempting to reduce noise inside vehicle cabins means adding more material and weight, but with graphene, it's the opposite.
"A small amount of graphene goes a long way, and in this case, it has a significant effect on sound absorption qualities," said John Bull, president of Eagle Industries.
The graphene is mixed with foam constituents, and tests done by Ford and suppliers has shown about a 17% reduction in noise, a 20% improvement in mechanical properties and a 30% improvement in heat endurance properties, compared with that of the foam used without graphene.
"We are excited about the performance benefits our products are able to provide to Ford and Eagle Industries," said Philip Rose, XG Sciences' chief executive officer. "Working with early adopters such as Ford Motor Company demonstrates the potential for graphene in multiple applications, and we look forward to extending our collaboration into other materials, and enabling further performance improvements."
Graphene is expected to go into production by year end on over ten under hood components on the Ford F-150 and Mustang and eventually, other Ford vehicles.
The core computer is based on NVIDIA's DRIVE AGX Xavier technology and will allow Volvo Cars to implement an advanced computing platform for its new cars on the forthcoming Scalable Product Architecture 2 (SPA 2) vehicle platform. The first car with the new core computer will appear early next decade.
The agreement will deepen the existing collaboration and partnership between Volvo Cars and NVIDIA. Last year the companies started joint development of advanced systems and software for self-driving cars.
The new computing platform will use NVIDIA's advances in AI as well as its unrivalled computing power, allowing Volvo Cars to take considerable steps forward in implementing advanced driver support systems, energy management technology and in-car personalisation options.
Adding advanced 360-degree perception capabilities and a driver monitoring system, the core computer will help Volvo Cars safely introduce fully autonomous cars.
"A successful launch of autonomous drive will require an enormous amount of computing power as well as constant advances in artificial intelligence," said Håkan Samuelsson, president and chief executive of Volvo Cars. "Our agreement with NVIDIA is an important piece of that puzzle and helps us to safely introduce fully autonomous Volvo cars to our customers."
"As a world-leader in safety technology and innovation, Volvo understands there is a direct connection between safety, comfort, and the computing capability inside the vehicle," said Jensen Huang, founder and CEO of NVIDIA.
The forthcoming SPA 2 vehicle architecture is the next generation of Volvo Cars' award-winning SPA modular vehicle architecture, which forms the basis of all new 90 Series and 60 Series cars launched in recent years. They have been instrumental in the operational and financial turnaround of Volvo Cars since 2010.
SPA 2 takes the existing advantages of the modular SPA architecture and adds next generation technologies in areas such as electrification, connectivity and autonomous drive. The powerful core computer plays a key role in this process and provides a much easier route towards regular over-the-air software updates.
Volvo Cars is developing strategic relationships with third parties to increase the introduction of new technology, embracing the disruption currently underway in the car industry.