Please use another Browser
It looks like you are using a browser that is not fully supported. Please note that there might be constraints on site display and usability. For the best experience we suggest that you download the newest version of a supported browser:Continue with the current browser
The Future of Manufacturing
Tomorrow’s production centers won’t just produce parts and products; they will produce – and benefit from – inexhaustible streams of information. Essentially artificial intelligence-driven self-organizing Internets-of-Things, they will operate holistically and flexibly, allowing their human workers, robot assistants and additive and subtractive manufacturing systems to optimize flows of materials and energy.
Thanks to advances in algorithms and simulation technologies, most products are already created in the virtual world as so-called “digital twins” of their real-world counterparts. But as this process evolves, much more than just an object’s geometric characteristics is being created this way. Its functional characteristics, such as expansion and contraction coefficients, and heat resistance, not to mention its security optimization, are already being tested and refined in the virtual world as well. What’s more, entire manufacturing processes are also on track to being developed, tested, and optimized this way.
What’s really amazing is that the story doesn’t end there. Once an object – anything from a gas turbine blade to an entire production facility – has been optimized in the virtual world and its physical counterpart has been built, tested and operated in the real world, a new dimension in the virtual world is opened: Data from the physical world can flow into, refine, and augment the accuracy of the original digital twin across a product’s entire life cycle. “The concept of the digital twin completes the knowledge loop from design and testing to production and operation, and from data acquisition and analytics to improved service, and then back again,” says Dr. Norbert Gaus, Head of Research in Digitalization and Automation at Siemens Corporate Technology.
Along this continuum, multiple modalities will draw from and contribute to manufacturing’s evolving digital ecosystem. For instance, in the near future, once a product has been created in the virtual world, its data will be seamlessly transferred to production facilities where humans, assisted by semi-autonomous robots, will use additive as well as traditional subtractive manufacturing methods to automatically translate that data into physical objects. Furthermore, as these production steps take place, they will be simulated in real time, thus allowing models of behavior to be compared with actual performance with a view to continuously improving quality and predictive maintenance.
The concept of the digital twin completes the knowledge loop from design and testing to production and operation, and from data acquisition and analytics to improved service, and then back again.
Such production facilities will be cyber-physical, meaning that all of their robots, machines and processes will function as an artificial intelligence-driven self-organizing Internet-of-Things that will constantly optimize the flows of materials and energy within – and between – production facilities.
An example of the degree to which artificial intelligence (AI) and neural networks can optimize complex system is provided by its application to a Siemens gas turbine. “Even after experts had done their best to optimize the turbine’s nitrous oxide emissions,” says Gaus, “our AI system was able to reduce emissions by an additional ten to fifteen percent.” This new world of manufacturing will open the door to production of affordable, individually-produced parts and products tailored to customers’ unique demands and scheduling requirements, as well as to the use of composite materials designed to increase the performance-to-weight ratio of parts and products.
Although this vision remains to be fully realized, Siemens already provides many parts of this new industrial ecosystem. Furthermore, through its laboratories around the world, the company is rapidly generating prototype manufacturing solutions that are nothing short of amazing. A leader in simulation and factory automation technologies, Siemens is actively merging its vast domain know-how with Big Data from the virtual and physical worlds in MindSphere, its open, cloud-based IoT operating system. Whether it’s digital planning methods (virtual reality), additive manufacturing, software for robotic systems, or new technologies for Industrie 4.0 environments, Siemens is leading the way.
Inside Siemens‘ Labs
Data from machines and industrial plants is collected and processed in MindSphere. This IoT operating system from Siemens offers users a simple way to take advantage of the possibilities of digitalization for their own operations. Now Siemens has connected its Ruggedcom communication technology for rugged conditions – extreme temperatures, humidity, etc. In addition, RFID transponders and thus the products themselves are also provided with direct access to MindSphere.
Infographic: On the Road to Digital Manufacturing
As manufacturing becomes increasingly digital, products will be produced with a growing level of customization, while boosting accuracy, quality and speed.
Interview with S. Shankar Sastry
How can advanced technology make manufacturing companies more competitive? As pressure builds to provide increasingly customized products, companies will need to invest in simulation, additive manufacturing, autonomous robots, and the data analytics needed to capture and make sense of the information these systems generate.
Today, most parts, products and their associated production processes are born in the virtual world – that is, through simulation. How is simulation itself evolving?
Sastry: Simulation has always been a very important part of conceptualizing designs to see how they look; and the associated tools and level of computation have gotten better and better. In addition, augmented reality and virtual reality have made it possible to conceptualize reality in ways that are far more detailed than in the past. In fact, the idea of integrating augmented reality and virtual reality displays early in the prototyping process is really where simulation is heading.
Another major way in which simulation is evolving is that it is no longer limited to a product’s geometric characteristics. Today, it increasingly includes physics-based functions such as the strength of the materials a product will be made of and the product’s electromechanical interfaces. All of this adds up to saving a lot of prototyping time.
Siemens talks a lot about digital twins. How close are we to creating objects in the virtual world that are the twin of their real-world counterparts?
Sastry: Whenever you simulate and visualize something, there is always the question of how close to reality the simulation is. But I believe that we are pretty close to being able to develop designs that integrate a product’s geometric and functional characteristics in a way that is meaningful enough for designers to be able to make accurate decisions. That is particularly true for Siemens, with its PLM NX product.
In the future you could develop a basic device and several variants of it, each of which could be individualized by customers. I think this would take the guess work out of whether a new product would be marketable.
How is the role of robots in manufacturing changing?
Sastry: The role of robots is changing tremendously. Until now we have used them to do jobs that are too dull, dirty or dangerous for human beings. But today, we are starting to see them as being able to aid or enhance human work with a degree of autonomy. Take factory workers. They may, for instance, need a robot assistant to perform tasks that are too delicate for human hands. So the notion of a robot as a human helper could become a new paradigm.
What will be the role of additive manufacturing in the future?
Sastry: Additive manufacturing – 3D printing – is certainly a technology of the future. The concerns about it until now have been that it has been applied to materials that are not production grade. But we are seeing the creation of parts made out of composite materials and even metals. And this has grown to the point of producing finished products with this technology.
Simulation, robotics, additive manufacturing, data analytics – in what ways are product development and production likely to change in the near future?
Sastry: In the world of mass production, it is a tremendous gamble whenever a company launches a new product. But we are moving toward the concept of Iot size one. And here, I think customization tools ranging from advanced simulation to autonomous robots will really change the picture and give companies a chance to address the customer pool much more directly than ever before. For instance, you could develop a basic device and several variants of it, each of which could be individualized by customers. I think this would take the guess work out of whether a new product would be marketable.
Interview conducted by Arthur F. Pease
S. Shankar Sastry is Dean and Roy W. Carlson Professor of Engineering, Director of the Blum Center for Developing Economies; Professor of Electrical Engineering & Computer Sciences, Bioengineering and Mechanical Engineering at the University of California, Berkeley.
Research in Manufacturing-Related Technologies – a look at Siemens’ Activities
Siemens scientists in India develop a simulation-based algorithm.
This enables accurate quantification of model parameters.
With reduced uncertainties in their estimates.
PLM software is transforming the way products and production lines are created
The key to this is the concept of the “digital twin”
That opens the door to the possibility of autonomous reconfiguration of production processes
Modeling the entire gas turbine production process
Increasing machine tool utilization by ten percent
A framework that interlinks 2D and 3D models
How semantic technology can reduce engineering time in the automobile industry
Documentation files automatically generated from semantic models
Data analytic solutions developed by Siemens Corporate Technology
The age of intelligent machines is about to dawn
How Siemens is using artificial intelligence to transform industry
From Roland Busch, CTO Siemens AG
How the cloud could supercharge robot learning
Cooperation between UC Berkeley and Siemens
Focusing on grasping and deep reinforcement learning
Allows suppliers’ systems to automatically derive production plans
Based on embedded semantic descriptions of available resources
A voice-activated service for industry
Specific to Siemens domains
A system technicians can talk with interactively as if it were a human expert
Generates virtual representations of environments
Analyzes how robots respond to unforeseen circumstances
Designed to make Siemens products more robust