<track id="ddb4w"><span id="ddb4w"></span></track>

<tbody id="ddb4w"></tbody>
  • <track id="ddb4w"></track>

    <track id="ddb4w"><nobr id="ddb4w"></nobr></track>
    <track id="ddb4w"><nobr id="ddb4w"><address id="ddb4w"></address></nobr></track>

  • Digital

    A bumper harvest of data

    In the fields of agriculture, maintenance, and mechanical engineering, the combination of data and its analysis is making processes faster and more profitable. With its Uptime project, K?rber Digital is a leader in the sector of machine learning.
    Expert in information analysis: Sven Warnke, Data Scientist at K?rber Digital.

    Berta’s udder is still neither reddened nor swollen. The cow is eating normally, producing as much milk as ever, and isn’t exhibiting any strange behavior. As a result, any farmer would think Berta is completely healthy. However, this milk cow is actually ill. In just a few days, the cow’s mastitis will become acute. Katharina Kober, a Data Scientist at K?rber Digital, already knows that. The conductivity, temperature, and amount of Berta’s milk, which have been recorded by a fully automatic milking system, have revealed this to Kober’s expert eye. “Sensor measurements and machine learning algorithms enable us to detect diseases of the udder before they become visible,” Kober says. “If such diseases remain undetected, the situation will worsen and the quality of the milk will deteriorate.” Using smart data analysis to make early diagnoses saves a lot of money. Experts estimate that a sick cow costs its owner more than €600 in productivity losses.

    lOur concept of Data Science: using data to directly generate real added value for our customers.r

    Sven Warnke, Data Scientist at K?rber Digital.

    Data Science has big economic potential

    Turning big data into smart data produces concrete economic benefits. “The project in the field of agriculture that we’ve already completed testifies to our concept of Data Science: using data to directly generate real added value for our customers,” says Sven Warnke, a Data Scientist at K?rber Digital, where he works on projects for the Industrial Internet of Things (IIoT).

    "With sensor measurements and machine-learning-algorithms we can recognise udder infections before they can be noticed visually": Katarina Kober, Data Scientist at K?rber Digital.

    Efficient data analysis can also be applied in many other areas of production that involve complex technical systems. In fact, it can be used wherever sensors supply suitable data. Digitization leads to a big increase in the number of installed sensors, and Internet of Things applications are also being used to a growing extent. “That’s why Data Science with a focus on machine learning has extremely high economic potential,” says Warnke.

    This applies to mechanical engineering in particular, because a machine that unexpectedly stops working generates unnecessary costs. However, the machines also supply huge amounts of information about why they stop working. How can this data be used to shorten maintenance times and make production more efficient?

    This question is the focus of the current development of Uptime by the Data Science specialists at K?rber Digital. Answers to this question are provided by the “classification” of the data using artificial intelligence (AI) technology. This system also forms the basis for cow diagnoses, because it analyses whether the values for milk temperature and milk amounts indicate that a cow is ill. The AI aims to detect patterns in a manner similar to how a spam filter determines whether an e-mail from an unknown sender is spam or not on the basis of the words it contains. With regard to machine downtimes, this means that if there is sufficient data that has been analyzed by AI, it can recognize the fault on the basis of the data scenario and identify the cause of the problem as early as the moment when the machine shuts down.

    Process optimizer: Felix Raab, Product Owner of Uptime project.

    The system continually keeps on learning

    One of Uptime’s customers is a specialist for assembly and testing systems used in industrial series production. Among other things, this customer manufactures and operates testing lines for kitchen appliances, i.e. white goods such as electric ovens. The experts at K?rber Digital have created a database for this customer that provides a more exact description of every fault that is detected by sensors along the testing line. Ideally, the fault has already occurred before. For faults that have not yet been described in detail, the database contains information about similar disruptions as well as product data concerning the affected components. In the future, the customer’s systems will be able to use AI to describe a checked component’s faults in greater detail. The user will then receive precise instructions about the replacement parts and tools that are needed and how the fault can be corrected.

    lIt will improve overall productivity by as much as 20 percent in sectors that have complex processes and frequent downtimes.r

    Felix Raab, Product Owner in the Uptime project.

    Uptime’s economic potential is huge. “We expect that this approach will enable many users to reduce their maintenance processes by around 60 percent. This will improve overall productivity by as much as 20 percent in sectors that have complex processes and frequent downtimes,” says Felix Raab, a Product Owner in the Uptime project.

    It’s clear that this kind of artificial intelligence pays off. Moreover, the system learns something more from every new fault that occurs. As a result, the AI continually improves with time, because the user or maintenance employee enters a confirmation of “correct” statements and corrects any false ones. The solution that is currently undergoing practical testing is very likely to be a success. There are tens of thousands of possible uses for a wide variety of products in Europe alone. “Office chairs, gardening tools, children’s seats for bicycles and cars — we can probably be a big help wherever large numbers of items are produced and the product is so valuable that reworking is worthwhile,” says Raab.

    Every project brings with it valuable knowledge for our clients: the data science team of K?rber Digital in Karlsruhe discuss ideas and new solutions and approaches.

    Machine learning is becoming a basic component of mechanical engineering

    But it’s not just the machines and analytical tools that are becoming smarter with every data set. The experts at K?rber Digital in particular are gaining valuable knowledge from every project, which they can then use for other customers and new solutions. Uptime is also benefiting from the insight gained during the “cow project,” for example — and it will, in turn, supply valuable know-how for future Data Science approaches. K.Edge Solutions, which K?rber Digital implemented in cooperation with the Business Area Tissue, also aims to precisely identify faults so that they can be quickly corrected.

    In this way, comprehensive Data Science is becoming a basic component of mechanical engineering in the 21st century. But the focus is always on people. K?rber Digital ensures that all of its solutions are easy to use and accepted in daily production operations, thus increasing their economic benefit. According to Felix Raab, “We want to have everyone on board on our journey towards Industry 4.0.”

    koerber.digital

    Related News

    Back to top
    Back to top
    狠狠爱狠狠谢狠狠