AI-assisted Service Engineering





Patterns in the machine data are only assigned to possible defects based on simple rules, without deriving precise recommendations
for action for the service employee.





Development of an AI solution based on existing machine and service data.




Added Value

Support of the service staff with further information, which enables service cases to be processed more efficiently.

Diebold Nixdorf is a leading provider of IT solutions and services for retail banks and retailers. The product portfolio ranges from ATMs to software and services. Within the framework of the AI Marketplace, AI procedures will now be developed and trained in the field of cash automation, based on historical machine data as well as information about so-called service calls.

KI-gestütztes Service-Engineering

ATMs are highly complex mechatronic systems whose behaviour is monitored by a multitude of actuator and sensor data. This data is supplemented with information on a service platform, which provides a complete picture of the vending machine. Until now, patterns in the machine data have only been mapped to possible defects by simple rules, without giving differentiated repair instructions to the service technician and without verifying the service instructions by results of the technician’s work. They do not use elaborate AI algorithms either.

Therefore, Diebold Nixdorf is now researching use cases together with Fraunhofer IOSB-INA to develop a suitable AI solution based on existing machine and service data. The aim is to support the company’s service staff with further information on repairs during service calls. Currently, this information is obtained from data pools such as service calls, service contracts or machine data. The product portfolio is now to be rounded off with new services.

With this project, Diebold Nixdorf is aiming for a significant reduction in the processing time of service cases during technician deployments. This makes it possible, for example, to localise the cause of a fault during servicing before the technician arrives at the unit. In addition, the process can help to bring about a reduction in the service call rate. In addition, interfaces to the AI Marketplace platform will be developed, taking into account the validity and meaningfulness of the database and the design of AI applications for product creation.



Michael Friedrich
Diebold Nixdorf, +49 (0) 5251 693 7507, michael.friedrich@dieboldnixdorf.com
Daniel Peters
Industrial Automation branch INA of Fraunhofer IOSB, daniel.peters@iosb-ina.fraunhofer.de


AI-assisted Diagnosis

At present, vehicle diagnosis in a workshop requires comprehensive automotive knowledge and involves a great deal of work. Hella Gutmann’s aim is therefore to develop an AI application for AI-supported diagnosis and identification of potentially defective vehicle components on the basis of historical vehicle data (e.g. fault codes or sensor readings) and to integrate a further variety of data sources (e.g. invoice data, repair information etc.).

Learn more

AI-assisted Production Planning

The project of Westaflex in cooperation with the Fraunhofer IEM focuses on an AI application that helps to optimize the sequence planning of production orders. For this purpose, real-time data from production control as well as from machines are to be evaluated in order to extract hints for optimal machine allocations.

Learn more
Claas Logo

Integration of AI in Computer Aided Design (CAx)

Artificial Intelligence has the potential to fundamentally change the way we work and operate. CLAAS GmbH & Co. KGaA, an internationally active manufacturer of agricultural machinery, has recognised this potential and is testing a special use case for the integration of AI in Computer Aided Design (CAx) in the AI marketplace together with the Fraunhofer Institutes IEM and IPK.

Learn more

AI-assisted Producibility Analysis

A set-up process in an automated manufacturing process that is optimized with the help of AI and replaces the previously manual “teaching” – this is the core of a project by düspohl Maschinenbau GmbH and the Fraunhofer IEM. In addition, the probable producibility of new product specifications is to be assessed automatically.

Learn more

Intelligent Product Monitoring

The goal of Ubermetrics’ project is an AI application that extracts relevant information from unstructured or semi-structured texts (e.g. online ratings, complaint emails, service reports, complaint reports), analyzes it and makes it systematically available to a developer. The application can be used, for example, in the context of targeted optimization of system components.

Learn more