Post sponsored by NewzEngine.com

MIL OSI Translation. Region: Germany / Deutschland –

Source: BMW GroupGießen is a process several thousand years old, which today at the BMW Group is increasingly determined by high-tech: The light metal foundry in the Lower Bavarian plant in Landshut has recently been monitoring its highly complex production using business intelligence, predictive analytics and artificial intelligence (AI ) – and analyzes all casting processes in real time with the help of big data. The Landshut foundry specialists can not only generate full data transparency and data visualizations at the click of a mouse, they can also make quality predictions. At the same time, profitability increases. Last year, the light metal foundry at the BMW Group’s Landshut plant produced 4.3 million cast components with a total weight of 73,000 tons. The scope of production includes engine components such as cylinder heads and crankcases, components for electric drives or structural components for the vehicle body. Completely new opportunity through artificial intelligence and smart data analysis “Artificial intelligence and smart data analysis offer completely new opportunities that go far beyond our previous analysis options. We can use it to manage our foundry intelligently and evaluate huge amounts of data quickly and reliably, ”says Nelly Apfel, consultant for data science at the BMW Group light metal foundry in Landshut. “This not only ensures the premium quality of our cast parts, but also ensures greater efficiency in the entire value-added process. And at the same time it offers an important decision-making aid for process improvements. “Thousands of parameters per casting process The basis for this is data from various systems in which thousands of material, condition and process parameters are stored for each casting process and each individual component – starting with the factors influencing the shaping sand cores through the parameters of the individual casting systems to the systems for the subsequent processing of the cast raw parts. For the sand cores alone, this is a wide range of data, for example the composition of the sand, the room temperature and the room humidity, the storage time of the sand cores or the length of time spent in the temperature-controlled high-bay warehouse. In addition, there are all parameters related to the actual casting process, such as the temperature curves of dozens of built-in thermal sensors, pressure curves, vacuum values, cycle times, the data of the respective casting system (such as target parameter specifications), data of the casting tool used (such as the age of the tool or the Number of maintenance performed) – or the data of the heating and cooling circuits. During the casting process, these control the solidification of the liquid aluminum, which is up to 750 degrees Celsius. In order to be able to carry out root cause analyzes at all, a clean database is required. For this purpose, the machine and process data are linked with quality data and processed automatically so that they can be evaluated in real time. The quality data include, for example, the three-dimensional measurement data of cast parts from the computer tomograph. The 3D measurements are used to determine any defect patterns in the cast parts – from porosity to bubbles to so-called cold runs when the metal solidifies. Quality data from the vehicle and engine plants of the BMW Group, which process components from the Landshut light metal foundry, are also used. Detection of causal relationships using intelligent algorithms All these linked data are then analyzed using intelligent algorithms and are immediately available to the foundry experts in a visualized form . “Data transparency helps us to recognize causal relationships. This is important for the component quality. And our casting technologists can put together an optimal set of parameters for the individual casting systems, ”explains Nelly Apfel. Parameter value monitoring is used to ensure stable and constant production. It continuously checks the approved parameters, automatically triggers an alarm in the event of any deviations – and automatically stops casting processes if necessary. In addition, using machine learning, recurring patterns or abnormalities in the casting processes can be recognized and quality predictions can be made with great accuracy based on possible error images (predictive quality) . Real errors in the production process are thus reduced to a minimum. “We score the probability of rejects based on the parameters with which our components are manufactured,” explains Nelly Apfel. In addition, the data specialist sees further advantages: “The visualization of crucial process parameters such as flow rates, temperatures or thermal images not only helps those responsible for production, but also enables early intervention by maintenance. ”Two examples: Anomalies in the temperature profiles can indicate defects, low flow values ​​to deposits in the cooling circuits. “That increases the output of our systems and thus the cost-effectiveness.” No distinctive IT skills requiredSpecial IT skills are not required to operate the intelligent data solution: it can be easily used via the web app on the tablet or smartphone. “In the past, such comprehensive data analyzes were only possible with complex manual evaluations and test runs,” says Nelly Apfel. She and her team are currently working on a new AI application in the area of ​​deep learning. Images of cast parts are evaluated and quality statements are made via a neural network. From this, it is automatically derived whether and to what extent a casting needs to be processed further. The aim is to automatically identify any necessary reworking steps for cast parts. If you have any questions, please contact: Saskia EßbauerBMW Group Corporate Communication and Political Communication LandshutTelephone: +49 871 702 3232, Mobile: +49 151 6040 3232, E-Mail: Saskia.Essbauer @ bmw.de Internet: www.press.bmwgroup.com E-mail: presse@bmw.de The BMW Group Plant Landshut At the BMW Group Plant Landshut, around 4,000 employees produce engine, chassis and body structure components made of light metal castings, plastic components for the vehicle exterior and body components Carbon, cockpit and equipment, electric drive systems, special motors and cardan shafts. These components are supplied to all vehicle and engine plants in the BMW Group worldwide. In every BMW, MINI and Rolls-Royce there is a piece of Landshut’s innovative strength. As a competence center for the future technologies of lightweight construction and electromobility, the Landshut plant is not only involved in the development processes of new vehicles at an early stage. At the components location in Lower Bavaria, items are also created for the pioneering BMW i models and the BMW brand’s flagship, the BMW 7 Series. The BMW Group’s Lightweight Construction and Technology Center (LuTZ) is also based in Landshut. Specialists from a wide range of disciplines are jointly researching innovative high-tech materials as well as tailor-made mixed construction concepts and production processes for the mobility of tomorrow. Www.bmw-werk-landshut.de

MIL OSI

EDITOR’S NOTE: This article is a translation. Apologies should the grammar and / or sentence structure not be perfect.

MIL Translation OSI