News: company & solutions
Predictive Analytics in industrial manufacturing
In an ambitious research project, MES manufacturer Industrie Informatik worked intensively with customers, researchers and educational institutions on the topic of predictive analytics. The result is an out-of-the-box solution that enables a quick and efficient look into the future.
Transparency is the elementary component of an efficient manufacturing environment. It illuminates past and current processes, identifies potential, and thus helps industrial companies to optimize their value creation process. So far, so good. However, the wave of digitalization that is sweeping over us unchecked is also increasing the demands on efficient processing of the almost unlimited quantities of data that we obtain from it – and ideally in real time. Combined with new insights into the trendy topics of artificial intelligence and machine learning, now we can take the much-cited look into the crystal ball and expect reliable results.
Of course, Industrie Informatik co-founder and Head of Strategic Product Management Thomas Krainz knows that predictive analytics is not a new topic. However, he sees the approach as crucial: “Our goal was to develop an out-of-the-box solution that lets our users achieve results quickly, easily and, of course, affordably. The aim is to enable medium-sized companies in particular to handle large volumes of data and thus gain access to comprehensive digitalization measures. This is not something that can be taken for granted in the area of predictive topics.”
The road to a marketable product involved a research project that lasted several years and in which a number of different bodies played a key role. The theoretical, scientific approach was provided by the Vienna University of Economics and Business Administration. RISC Software GmbH, an established and internationally recognized research company, was also involved. The jointly acquired knowledge was then elaborated in case studies with selected customers. The focus was on the development of possible fields of application on the basis of existing data, as well as the elaboration, development, testing and evaluation of algorithms, procedures and technologies for forecasting purposes.
“The research project produced an out-of-the-box technology stack that can be used both in the cloud and on premises. Furthermore, we developed a data preprocessing model that helps the user to cleanse and prepare data from cronetwork MES in the first step before AI conducts the ongoing evaluation and interpretation of the information obtained from it,” says Thomas Krainz. The fact that all these processes are based on the standard data model of cronetwork MES ensures great efficiency advantages for our users, as reflected in the rapid implementability of predictive analytics methods. In addition, the Random Forest Model is used as a learning algorithm; it is known for fast turnaround times and very good interpretability of results. Thomas Krainz continues: “In the end, the decisive factor for success is the adaptation of all these technologies and functions to the respective data situation and, above all, the expectations of our customers. Artificial intelligence and predictive analytics are not miracle cures. They are neither better nor smarter at their tasks than a human. Their advantage lies in the replication of human know-how — and at high speed and moreover around the clock! Many possibilities derive from this.” Specifically, this means predictions of relative scrap and workstation disruptions in subsequent shifts, as well as quality status values per manufacturing step. “With this information alone, you can uncover hidden savings potential and massively optimize efficiency on the shop floor,” concludes Krainz.
“Our goal was to develop an out-of-the-box solution that lets our users achieve results quickly, easily and, of course, affordably.”
Member of the Board
Head of Strategic Product Management