Acoustic quality assurance with artificial intelligence

Fraunhofer IDMT will show how and where acoustic methods based on air-borne sound analysis and artificial intelligence can monitor the quality of products and processes in industrial manufacturing.

Acoustic methods for quality assurance in industrial applications
(Hall 16)

The innovative procedure for acoustic quality assurance will be demonstrated using an air hockey table. Here, pucks that seem to look the same and sound very similar, are distinguished by reference to the “pling” sound they emit as they hit the border of the table. During the game, these acoustic signals occur so frequently and regularly that they can be used for acoustic analyses based on machine-learning methods in order to make a reliable statement about the material the pucks are made of.

This non-contact method, in which Fraunhofer IDMT combines its many years of expertise in the fields of acoustic measurement technology, signal processing and machine-learning, can be used to detect material or process faults, either for end-of-line quality control or in-line monitoring such as during welding processes. Production processes can be aborted and restarted promptly, if acoustically perceptible errors are detected in real-time within the process. In addition, this acoustic test method is non-destructive and thus prevents tons of expensive test scrap.

In addition to the technical exchange, visitors to the Fraunhofer booth can experience the entertaining air hockey table for a sporty diversion.

Reliable engaging of plug connectors and speech-based documentation in industry (Hall 6)

Division Hearing-, Speech- and Audiotechnology in Oldenburg

Screws were yesterday. Nowadays, production is automated and adhesive or plug connectors are used. In this context, the reliable documentation of work processes and in-line testing are very important.

At the Hanover Fair 2020, the Fraunhofer IDMT from Oldenburg will present an intelligent acoustic sensor system that can be used for process and production monitoring in manufacturing and assembly. It recognizes whether a plug connector has engaged properly and documents the process from start to finish. This aids quality assurance and avoids expensive claims and complaints.  

Simple, secure and reliable documentation of important information – with automated speech recognition even in a noisy environment and with no need for an internet connection! The speech-to-text documentation system developed by the Fraunhofer IDMT in Oldenburg can also save time and money. It allows the contact-free entry of data into existing systems too. For less interruptions in the workflow and minimization of security risks.

We are looking forward to your visit at the Hannover Messe 2020!