Porsche Shares its New ‘Digital Twin' Concept Using Sensors in the Vehicle and Big Data to Aid in Diagnostics & Predictive Maintenance
【Summary】Automaker Porsche has shared a new concept called a “digital twin” that can be used for predictive driving functions and the status of a vehicle’s components. It involves sensors embedded deep in the vehicle, including in the chassis, that can determine if the vehicle is operating normally, while also identifying mechanical or electrical issues that require attention.
Imagine if two buyers purchased the exact same year and made a vehicle, but one of these cars was on the road for 100,000 miles, while the other driver reached 200,000 miles before mechanical issues and wear prompted them to purchased a new vehicle.
The identical vehicles purchased by the two drivers were in a sense, mechanically and electrically the same, yet one lasted for 100,000 while the other driver was able to double the service life to 200,000 miles.
So what went wrong with the one car? Most likely it was a lack of maintenance and individual driving habits that caused premature wear and tear rather than manufacturing defects that shortened the vehicle's service life. But a new concept from automaker Porsche might help to address these types of service and maintenance issues in the future, including for electric vehicles.
Porsche has shared what it calls a "digital chassis twin" that can be used for predictive driving functions and the status of a vehicle's components.
The concept involves sensors embedded deep in the vehicle, including in the chassis, that can determine if the vehicle is operating normally, while also identifying mechanical or electrical issues that require attention.
Creating a virtual copy of an existing object (in this case a vehicle), allows for data-driven analysis, monitoring and diagnostics without the challenges and constraints of real-world tests, according to Porsche.
The so-called "digital twin" of a vehicle comprises not only the operating data it collects but also any related data, such as information collected during planned maintenance work and unexpected repairs. Porsche says that some elements of this digital twin already exist in ECUs and in the databases maintained at Porsche service centers.
A Centralized Intelligence System for Data
The main advantage of vehicle "digital twins" is that they can be networked and vehicle data combined with a centralized AI-powered intelligence system can determine if a vehicle on the network is operating at its peak, both mechanically and electrically.
For example, an algorithm can compare big data from the centralized systems against sensor data from a specific vehicle's powertrain and chassis to identify a customer's driving style, or diagnose potential problems.
The algorithm can then recommend not only the optimal time for service work on the vehicle but also the required scope of that work based on the data from the embedded sensors.
More importantly, this data makes it possible to customize service intervals based on individual driving styles or servicing specific components based on how the customer uses their Porsche vehicle.
Similar types of sensors are already in vehicles today, although they are not currently networked to a central location. An engine knock sensor for example, is a piezoceramic sensor that picks up vibration from the engine to determine if fuel is being burning properly and "engine knock" not occurring, which can cause damage.
If engine knocking noises are picked up by the knock sensor, it sends a signal to the vehicle's ECU to make small ignition time corrections to eliminate it. These same concepts can be applied to electric vehicles and powertrains to make sure everything is running smoothly by collecting and analyzing sensor data and comparing it to big data from a fleet of vehicles which are operating normally.
Another benefit of this approach is that component wear and even faults can be identified before they are noticeable by the driver, which is a significant advantage from a safety perspective, according to Porsche.
Software engineers at Porsche have been working on the "digital twin" concept for the past three years, primarily focusing on the chassis, known as a "chassis twin". The project is being managed by CARIAD, the standalone automotive software company within the Volkswagen Group.
In addition to data from Porsche vehicles, the project now has access to data from all Volkswagen Group vehicles, which increases the data pool by a factor of 20, Porsche says.
Porsche said it started the project with the focus on the chassis components since they are subjected to the highest loads, particularly when the vehicle is used on racing circuits.
The sensor technology in the vehicle along with the intelligent neural algorithms used for analysis allow the load on the chassis to be detected within the vehicle and conveyed back to the driver.
This intelligent use of this data ultimately makes the vehicle safer, as any specific faults are identified immediately, even before the driver has to visit a repair shop for diagnosis. Just like with people visiting a doctor, vehicle problems are generally not noticed until symptoms occur, such as unusual noises coming from the vehicle. By then, the repair might be more extensive and in many cases it leads to other problems.
The digital chassis is already being used in the Porsche Taycan electric sedan. Its being used to monitor the components of the vehicle's air suspension. For now, the project is primarily for collecting data about body acceleration, which is then evaluated and transferred via Porsche Connect to the central backend system for analysis.
Next year, Porsche plans to launch the first digital twin and only sensor data from mechatronic components will be evaluated. Other functionality will be added in the future, such as functions that allow wear on specific components to be calculated without the need for physical gauges to be used.
For example, if multiple vehicles require the same adjustment to their wheel alignment or have a suspension component issue, the sensors could detect the alignment deviations. The data collected from multiple vehicles can indicate a pattern that needs addressing.
The system continuously compares the data from each vehicle against the fleet data. Algorithms calculate thresholds based on these findings and if any are exceeded, the customer can be notified via the onboard Porsche Communication Management system (PCM) that the chassis in their vehicle may need to be inspected at a Porsche service center.
This approach ensures that wear does not go beyond specified limits and the early repairs also help to prevent further damage.
While electric automaker Tesla does not use a digital twin concept like Porsche, the automaker can diagnose and correct potential problems in its vehicle the same way by collecting data from the entire Tesla fleet. This data includes insights into battery health and range, which can be addressed if needed via OTA software updates pushed out to the entire fleet.
An example of this capability occurred in May 2018, when Consumer Reports (CR) published a report of poor performance from the Model 3s brakes taking too long to stop. CR said the brake performance was a"big flaw" and would no longer recommend the vehicle.
However Tesla was able to push out a software update that improved the braking distance of all of the Model 3s. Shortly afterwards, CR verified that the software update corrected the problem and put the Model 3 back on its recommended vehicle list.
Porsche aims to take this capability a bit further by addressing any potential problems before a driver even becomes aware of it.
Another benefit to the technology is that these "digital records" can be used to show the residual value of a pre-owned vehicle, making the process of buying and selling used vehicles more transparent.
Vehicle manufacturers could consider offering an extended warranty based on the documentation of component status updates that can indicate that a vehicle is problem-free at the time of sale. The individual data can also be used by dealers to set fair market pricing for used models.
For the chassis data collection for the Taycan, customers are prompted via the PCM to provide their consent to data being collected anonymously. Porsche said around half of all Taycan customers have agreed to take part in this pilot project, which the automaker says is an "incredibly positive response" to the application of the digital chassis.
Originally hailing from New Jersey, Eric is a automotive & technology reporter covering the high-tech industry here in Silicon Valley. He has over 15 years of automotive experience and a bachelors degree in computer science. These skills, combined with technical writing and news reporting, allows him to fully understand and identify new and innovative technologies in the auto industry and beyond. He has worked at Uber on self-driving cars and as a technical writer, helping people to understand and work with technology.
A Look at How Waymo’s Self-Driving Test Fleet Safely Traveled 2.7 Million Miles in San Francisco Last Year
Baidu & Geely’s New Smart Electric Vehicle Company JiDU Raises $400 Million in Series A Round
General Motors is Investing $7 Billion to Build EVs in Michigan, the Largest Manufacturing Commitment in the Company’s History
Connected Vehicle Software Platform Developer Sibros Raises $70 Million in Series B Funding Round
Ford’s Bronco Gets a High-Performance Makeover With the Launch of the 400+ HP ‘Raptor’ Edition
Honda Invests in Software Startup Helm.ai to Strengthen its Computer Vision and AI Development
Toyota-backed Startup Pony.ai Builds Autonomous Driving Computing Unit Built on the NVIDIA DRIVE Orin Processor
Mercedes-Benz to Partner With Luminar on LiDAR for Autonomous Driving
- Solar-Electric EV Startup Lightyear Signs Agreement to Supply 5,000 Vehicles to LeasePlan for the World’s First Solar Car Subscription Service
- Here’s Why The Battery Pack of Tesla Model S Plaid is An Electrification Masterpiece
- EV Battery Supplier CATL Starts Production at its Largest Global Battery Plant in China, With 120 GWh Annual Capacity Target
- GM’s BrightDrop Will Supply Electric Delivery Vans to Walmart, Expanding its Existing Supply Deal With FedEx
- Tesla Signs Nickel Supply Deal With Talon Metals, Which Aims to Make the Mining of the Raw Material for EV Batteries ‘Carbon Neutral’
- In a Boost to Electric Truck Maker Rivian, Illinois Governor Signs into Law the ‘Reimagining Electric Vehicles in Illinois Act’
- U.S.-listed EV startup XPeng is Delivering its New P5 to Customers Without Millimeter-Wave Radar Installed Due to Semiconductor Shortages
- GM to Start Deliveries of the Electric Cadillac Lyriq 9 Months Ahead of Schedule
- Mercedes-Benz to Partner With Luminar on LiDAR for Autonomous Driving
- Volvo Plans to Launch its New ‘Ride Pilot’ Autonomous Driving Feature in California, Which Requires No Human Supervision