[ad_1]
Demand is high, but Zapf says it supports artificial intelligence (AI) technology by capturing the right data and guiding engineers into product design and development
Not surprisingly, the November 2020 McKinsey survey reveals that more than half of organizations have accepted AI in at least one function, and 22% of respondents report at least 5% of the company’s profits attributed to AI. And in manufacturing, 71% of respondents have increased revenue by 5% or more with the adoption of AI.
But that wasn’t always the case. Once “rarely used in product development,” Zapf says AI has evolved in recent years. Today, technology giants known for their innovations in AI, such as Google, IBM, and Amazon, have “set new standards for the use of AI in other processes,” such as engineering.
“AI is a promising and exploratory field that can significantly enhance the user experience for engineering design, as well as gather relevant data in the application development process for specific applications,” says Katrien Wyckaert, Director of Industrial Solutions at Siemens Industry Software.
The result is a growing appreciation of technology that promises to simplify complex systems, make products more marketable, and drive product innovation.
Simplify complex systems
A perfect example of AI’s ability to review product development is Renault. In response to growing consumer demand, the French automaker is supplying more and more new vehicle models with manual transmission (AMT), which acts as an automatic transmission but allows drivers to change gears electronically via the push button control.
AMTs are popular among consumers, but designing them can pose daunting challenges. The performance of the AMT depends on the operation of three different subsystems: an electromechanical actuator that changes gears, electronic sensors that monitor the state of the vehicle, and software embedded in the transmission control unit that controls the engine. Because of this complexity, lengthy trials and errors can be made to define the functional requirements of the system, design the actuator mechanics, develop the necessary software, and validate the overall system.
In order to speed up the AMT development process, Renault turned to Siemens Digital Industries Software’s Simcenter Amesim software. Simulation technology is based on artificial neural networks, shaped by AI “learning” systems in the human brain. Engineers simply drag, drop, and connect icons to create a pattern graphically. When displayed as a sketch on the screen, the model shows the relationship between all the elements in an AMT system. Engineers can also predict the behavior and performance of the AMT and make the necessary improvements at the beginning of the development cycle, avoiding problems and delays in the late stage. In fact, while developing hardware using virtual motors and transmissions as a replacement, Renault has managed to reduce the development time of the AMT by almost half.
Without sacrificing speed quality
They are also creating environmental standards that encourage Renault to rely more on AI. To meet carbon dioxide emissions standards, Renault has been designing and developing hybrid vehicles. But the energy to develop hybrid engines is more complex than in vehicles with a single energy source, such as in a conventional car. That is, because hybrid engines require engineers to perform complex feats, such as balancing the power required from multiple energy sources, choosing from a variety of architectures, and studying the impact of transmissions and cooling systems on the vehicle’s energy performance.
“To meet the new environmental standards of a hybrid engine, we need to completely rethink the architecture of gasoline engines,” says Vincent Talon, head of simulation at Renault. The problem he adds is that “carefully examining the dozens of different factors that can affect the final results of fuel consumption and pollutant emissions is a long and complex process that makes rigid terms more difficult.
“Currently, we clearly don’t have the time to carefully evaluate the various hybrid architectures of the train engine,” says Talon. “Instead, we needed to use an advanced methodology to manage this new complexity.”
For more information on AI in industrial applications, visit www.siemens.com/artificialintelligence.
Download full report.
This content was created by Insights, a custom content from the MIT Technology Review. It was not written in the editorial board of the MIT Technology Review.
[ad_2]
Source link
