Tools


Siemens Worldwide

Pictures of the Future

Contact

Contact

sts.components.contact.mr.placeholder Sebastian Webel
Mr. Sebastian Webel

Editor-in-Chief

Tel: +49 (89) 636-32221

Fax: +49 89 636-35292

Werner-von-Siemens-Straße 1
80333 Munich


sts.components.contact.mr.placeholder Arthur F. Pease
Mr. Arthur F. Pease

Executive Editor English Edition

Tel: +49 (89) 636-48824

Fax: +49 89 636-35292

Otto-Hahn-Ring 6
81739 Munich
Germany

Pictures of the Future
The Magazine for Research and Innovation
 

The Future of Manufacturing

Artificial Intelligence:                                Optimizing Industrial Operations

In cooperation with Deutsche Bahn, Siemens is running a pilot project for the predictive maintenance and repair of high-speed trains. Impending faults and malfunctions as well as the sources of these problems will be identified at an early stage by means of data analysis; recommendations for vehicle maintenance will then be derived from this data.

The age of intelligent machines is about to dawn. Siemens AG Chief Technology Officer and Member of the Managing Board Roland Busch explains how Siemens is using artificial intelligence to transform industry.

Whether it’s for autonomous optimization of gas turbines, improved monitoring of smart grids or predictive maintenance of industrial facilities, artificial intelligence harbors great potential for Siemens — and we are consistently making use of it. We are the leaders when it comes to the industrial application of artificial intelligence and we can offer new services that enable our customers to boost their productivity and efficiency.

Artificial intelligence is one of the leading technology topics at our company. We have been conducting in-depth research in this area for more than 30 years. Neural networks were already being installed in steel mills back in the 1990s. Today, the company has about 200 experts working on data analytics and neural networks. The current focus is on areas such as reinforcement learning and deep learning. But what does that mean? A neural network has connections between its nodes akin to the links between the neurons in the brains of living organisms. These links enable the network to learn how to interpret data and make decisions. Our deep learning techniques use thousands of simulated neurons and millions of connections between them.

Roland Busch, Siemens AG Chief Technology Officer and Member of the Managing Board

Intelligent Data Analyses

But whereas people often talk about how spectacularly successful artificial intelligence is in strategy games such as Go and poker, we at Siemens are using AI to optimize industrial facilities and are employing it for a wide variety of other applications in areas such as energy distribution, electric motors, and rail technology. For example, we are using it to improve the operation of gas turbines for one of our customers. By learning from operating conditions and other data, the system can significantly reduce the emission of toxic nitrogen oxides without affecting the performance of the turbine or shortening its service life. We are also using the technology to improve the operation of wind turbines. It does this by autonomously adjusting the position of the rotors to the changing direction of the wind in order to increase the wind farm’s yield.

Our industrial operating system MindSphere also benefits from intelligent data analyses — with regard to predictive maintenance, for example, as well as through its ability to optimize the operation of systems and facilities. The software’s ability to analyze operating data and sensor measurements, allows it to spot anomalies in facilities and automation systems.

Siemens' flagship H Class gas turbine. Artificial intelligence can significantly reduce the turbine's emission of toxic nitrogen oxides without affecting its performance.

Artificial Intelligence for Industry, Power Grids and Rail Systems

We install smart boxes to bring older motors and transmissions into the digital age. These boxes contain sensors and a communications interface for data transfer. By analyzing the data, our artificial intelligence systems can draw conclusions regarding a machine’s condition and detect irregularities in order to make predictive maintenance possible.

We use artificial intelligence not only in industrial settings, but also to improve the reliability of power grids by making them smarter and providing the devices that control and monitor electrical networks with artificial intelligence. This enables the devices to classify and localize disruptions in the grid. A special feature of this system is that the associated calculations are not performed centrally at a data center, but decentrally between the interlinked protection devices.

Equipped with neural network-based artificial intelligence, which allows systems to optimize their operations based on what they learn, wind parks can make the best possible use of changing wind currents.

In cooperation with Deutsche Bahn, we are currently running a pilot project for the predictive maintenance and repair of high-speed trains. Our data analysts and software recognize patterns and trends from the vehicles’ operating data. Moreover, artificial intelligence helps us build optimized control centers for switch towers. From the billions of possible hardware configurations for a switch tower, the software selects those options that fulfill all of the requirements, including those regarding reliable operation.

Dr. Roland Busch