In the age of Industry 4.0, process and machine data are increasingly seen as an integral part of a company‘s value creation. The digitization efforts of recent years allow extensive automated data collection, which poses great challenges for many companies. On the one hand, real-time information for the reaction to short-term changes in production should be analyzed and processed; on the other hand, future events should be derived from the collected data pools and predicted as accurately as possible. The aim is to link large data streams and events from sensor networks (Big Data) together with data sources from order, configuration and tool data from the production machines in order to gain an improved understanding of the machine park.


Production machines deliver a lot of data, which are usually not connected to each other. Often there is no connection between the processes, the machine configuration, the ERP data world (such as order data, parts lists, etc.) and the data streams (for example, sensor data). If at all, then these streams are stored in different systems. Therefore it is often not possible to derive valuable information from the existing data. By linking these data streams with each other and with the different data sources from customer and system data of production machines, tools or configurations with the processes, an improved understanding and a holistic view of the machines can be gained. In addition to the timely import of incoming data streams from production and logistics systems using standard protocols, the efficient link to the system data is also guaranteed. OPC UA, an industrial communication protocol of the OPC Foundation, has established itself as the industry standard. In addition to existing data sources, the model knowledge of experts plays an important role. This is represented by the mapping in the form of ontologies, thus expanding the data pool.


ANNA is primarily used to support local experts. It allows all the knowledge about one or more machines to be combined into a common knowledge base and to gain a better understanding of this through data analytics. With the newly-generated knowledge, cause-effect correlations can be identified by the anomalies and patterns of the machine state. The probability of failure of individual components can be reduced and quality improvements in the production machines can be achieved. In addition, maintenance intervals and cycles are optimized and, as a result, quality improvements in production and product are achieved.


Using modern methods from the field of data and visual analytics, as well as techniques from machine learning, valuable information is derived from these data. In this way, relationships, correlations and patterns can be identified which can be used for error and cause analysis as well as for continuous quality monitoring and improvement. With smart technologies, new knowledge can be gained from Big Data.


The use of ANNA guarantees a better understanding of your machine park by recognizing connections between cause and eff ect. Through the interaction of diverse data sets of sensor networks, production, confi guration and tool data with the domain knowledge of your engineers about the underlying machine model, an increase in the quality of your machines can be achieved.

RISC Software GmbH meets the current requirements of modern data management and off ers with ANNA an individually customizable virtual production assistant for knowledge generation of your machines.

Get the current Anna folder from the Downloads page.