Our Sites

Industry 4.0 arrives in Düsseldorf and in the manufacturing sector

Data collection, network connection, input detection work together to refine manufacturing

Editor’s note: This is the first of two articles to preview TUBE®, the international trade fair for the tube industry, April 4-8, Düsseldorf, Germany. This article, provided by the tradeshow organizer, discusses the growing role of modern digital technology, specifically Industry 4.0, in the manufacturing environment.

The term Industry 4.0 has been a frequently used buzzword for several years now. This doesn’t mean that it’s just a buzzword—it’s a synonym for the fourth industrial revolution, which is a merging of the real and virtual worlds. Much more than a process of connecting computers, it’s a process of connecting machinery, controllers, and other systems and subsystems that formerly were stand-alone units. The other term for Industry 4.0 sums it up: The Internet of Things.

Industry 4.0 isn’t isolated, but should be seen against the background of changes in industrial production, with an increasing individualization of products and highly flexible manufacturing processes. According to the German federal ministry of education and research, it has led to a “far-reaching integration of customers and business partners into value-added and business processes, while the link between production and high-quality services has led to so-called hybrid products.”

The term Industry 4.0 shows up particularly in the increased automation of the various processes within an industrial company. A prerequisite is the development of intelligent, autonomous monitoring and decision-making processes, so that the relevant routines can be controlled and optimized in real time. Two concepts that are associated closely with Industry 4.0 are the terms smart factory and smart production. The focus of a smart factory is on developing intelligent production systems and processes and using distributed and networked production sites. Smart production includes cross-company production logistics and human-machine interaction.

Implementing Industry 4.0 requires large volumes of data. Although big data sets are available in many companies, they still tend to be rather isolated and disconnected. To set up genuinely efficient routines within a business, it is important to analyze, process, and connect all data.

“Unless large collections of data are analyzed, they can degenerate into data cemeteries,” said Prof. Katharina Morik, PhD, of the Department of Artificial Intelligence at Technical University Dortmund, Germany.

Artificial intelligence (AI) tools enable machines to learn. To dig for knowledge among the available data, a process known as data mining, the company RapidMiner has developed a tool of the same name that is now widely used and requires no programming.

Big data and cyber-physical systems are areas studied by SFB 876, a unit within the IT department of TU Dortmund. One of its projects is the development of data stream algorithms that analyze incoming data streams in real time. The special research unit has developed a tool called Streams for the convenient configuration, parallel arrangement, and distributed execution of online processes.

Big Data, Big Steel, Big Pipe

The theoretical foundation that was created by SFB 876 has been implemented by SMS Siemag AG (Düsseldorf, Germany) and a working group of Dillinger Hütte (Dillingen, Germany) under a real-time forecasting project at a steel mill. This innovative system is adaptive, meaning it learns and therefore fine-tunes a production process based on the data it receives from the manufacturing process, enabling it to improve the process.

According to Dr. Dominik Schöne, Dillinger Hüttenwerke is “Europe’s leading heavy plate manufacturer,” with an annual output around 1.8 million tons, some of which is used to produce large-diameter pipes. The central furnace at the smelting plant in Dillingen is a basic oxygen furnace (BOF), which is fed pig iron, scrap steel, and slag-forming agents such as lime. A thermal lance blows oxygen into the molten mass at supersonic speed, burning up any undesirable elements such as carbon, phosphorus, and sulfur, ensuring their disposal in the form of slag and waste gas. The result is a heat of steel with specific properties at the blowing end-point. The target variables are the tapping temperature and the percentage of carbon and phosphorus in the iron and the iron content of the slag.

The data-driven forecasting model for the BOF converter was developed with the aim of improving predictability of the four target variables at the blowing end-point. To record the process data, the system uses a computer to gather 90 static process variables. To increase its predictive accuracy, it collects 36 dynamic process variables and relies on additional sensors that collect visual, audio, and vibration inputs. In all, the data-driven forecasting model can deal with 126 process variables.

In addition to learning independently, the forecasting model can make real-time predictions and control the blowing process by suggesting corrections in real time. A comparison with the forecast target values of a conventional metallurgical model shows that the data-driven model is far more accurate in predicting the temperature at the blowing end-point. Additionally, unlike the conventional method, the new model can predict all of the other target variables.

The data-driven forecasting model has a number of economic benefits: While it increases steel production by reducing the after-blowing and over-blowing rates, it also reduces process costs and raw material costs. The refined process also subjects the fireproof lining of the converter to less wear and tear and the company has lower personnel expenses. An anticipated improvement in tapping temperature accuracy, about 40 degrees F (5 degrees C), is expected to lower fuel consumption, saving more than $500,000 per year.

Another benefit is flexibility. This sort of model can be transferred to other applications, such as other converters and other furnaces, with relatively few adjustments.

Implementing Industry 4.0

The new automation options of Industry 4.0 offer even more benefits to system manufacturers in metallurgical and rolling mill engineering. Such systems, which are large, complex, and technologically advanced, cover the entire portfolio of the power supply and of electrical and automation engineering. The systems, which are consistently tailor-made, mostly consist of fully customized technical processes with relevant automation characteristics.

“This is why, prior to the actual commissioning, we conduct comprehensive tests on the relevant software of all our systems, so that we can ensure the highest quality standards and so that the commissioning periods are as short as possible,” said Hubertus Schauerte of SMS Siemag AG.

Compared with the world of models described in Industry 4.0, engineers go one step further, replacing the real physical world with a virtual physical world in their system tests. To test a customer’s software engineering, this involves the use of real-time simulation of the relevant system. To do so, they build models of the processes, the dynamic behavior of the control systems, and all the functional connections. These are implemented in server clusters in which simulations can be executed in real time. Because it is heterogeneous in structure, it comes very close to an Internet of Things.

Simulating such a complex process often requires processing more than 10,000 signals, a process assisted with the help of generic processes. Such real-time simulations are used by SMS Siemag and pipe system manufacturer SMS Meer (Mönchengladbach, Germany).

The next stage in process and production simulations, according to Schauerte, will be a debut in the 3-D world. This means that the 3-D designs required for manufacturing undergo automated simplification and are integrated directly into the relevant simulation models. This relies on developments from a different industry, computer and online gaming, in which virtual worlds and simulations have reached a high level of sophistication over the last few years.

“This is an area where complex scenes, routines, and elementary physical relationships have been developed that can be embedded directly into our systems for the purpose of real-time system simulations,” he said.

For further information, contact Anne Meerboth-Maltz, senior director, corporate communications and public relations, Messe Düsseldorf North America, 150 N. Michigan Ave., Suite 2920, Chicago, IL 60601, 312-781-5180, info@mdna.com, www.mdna.com.

  • Europipe, jointly owned by Dillinger Hüttenwerke and Salzgitter AG, will exhibit in hall 4, booth H42 at TUBE®, the international tube and pipe trade expo, Düsseldorf, Germany, April 4-8, 2016.
  • RapidMiner Inc., 10 Fawcett St., 5th Floor, Cambridge, MA 02138
  • SMS Meer will exhibit in hall 7a, booth B15/B16 at TUBE.
  • Technische Universität Dortmund, Fachbereich Informatik, Lehrstuhl für Künstliche Intelligenz, LS VIII, D-44221 Dortmund, Germany, katharina.morik@cs.uni-dortmund.de

Industry 1.0, 2.0, and 3.0

The history of mankind is marked by occasional breakthroughs or developments that cause severe disruptions, leading to widespread social, economic, and technological upheaval. Among the most drastic was the Agricultural Revolution, which put an end to hunting and gathering, replacing these activities with animal husbandry and farming. It also allowed formerly nomadic societies to settle in fixed locations. As far as technology, the discovery of bronze swept aside the use of stone tools, and later the mastery of iron led to the many ferrous alloys we use today.

The Industrial Revolution is another step in the advancement of technology, and it has been broken down into four distinct phases.

  • The first industrial revolution took place from about 1760 to 1830. Chief characteristics were the use of steam-powered machines rather than manual tools and the development of the factory system. This era also gave rise to chemical processing and large-scale iron production.
  • The second industrial revolution, which started around 1870, picked up where the first left off, and was characterized by the increased use of various systems: long-distance communication and transportation, specifically telegraph and railroad; water and gas distribution; and sewage collection.
    The communication and transportation systems of the day allowed unprecedented movement of people and ideas, which culminated in a new wave of globalization.
    Industry 2.0 drew to a close around the time World War I started. The use of the telephone was on the rise, and steam power gave way to electricity in factories, some of which were converting to the production line concept.
  • The Digital Revolution, known as the third industrial revolution, is the change from analog and mechanical technologies to electronic (digital) technologies. The key development was the transistor, invented in 1947, which replaced the vacuum tube. It led to the rise of digital computers and digital recordkeeping. Related to this is the Information Age, a product of the affordability of personal computers and cellular phones, as well as the network that allows the fast, easy spread of information: the Internet.
About the Author
FMA Communications Inc.

Eric Lundin

2135 Point Blvd

Elgin, IL 60123

815-227-8262

Eric Lundin worked on The Tube & Pipe Journal from 2000 to 2022.