July 11, 2024. What was previously based more on intuition and experience is now objectively verifiable: the OpenZfP AI portal uses AI to evaluate noises from machines, systems and processes and thus detects anomalies that can lead to malfunctions or failures.
Categories
Tags
Contact info
Silicon Saxony
Marketing, Kommunikation und Ă–ffentlichkeitsarbeit
Manfred-von-Ardenne-Ring 20 F
Fax: +49 351 8925 889
Contact person:
If there are deviations from the normal state, so-called anomalies, this often manifests itself in unusual noises. Acoustic diagnosis methods have been used for quality assurance, maintenance and servicing for some time now. However, the evaluation of audio data is often difficult, as human perception is subjective and there are no objective criteria for classification.
From now on, the OpenZfP AI portal from Fraunhofer IKTS makes it possible to examine audio data from machines and systems for anomalies and have it evaluated using artificial intelligence (AI). This makes testing automated and traceable. The probability of error detection depends on the respective application and is up to 100 percent.
The OpenZfP AI portal analyzes noises from machines, systems or processes and outputs the results as a spectrogram. Deviations from the normal state are highlighted in red. This allows potentially faulty areas and components to be identified.
Audio recordings of the process are uploaded to the OpenZfP AI portal for analysis. The data can be recorded using a smartphone or from microphones already installed in process monitoring systems.
A specially trained algorithm then carries out the anomaly detection and outputs the results as a spectrogram. Markings in the graph allow even inexperienced users to identify the area in which deviations occur and thus narrow down the troubleshooting process.
The OpenZfP AI portal is a service provided by the “Cognitive Material Diagnostics” working group at Fraunhofer IKTS, which is available free of charge.
This service is intended to reduce fear of contact with AI and identify potential applications. If further classification of the data is required, the “Cognitive Material Diagnostics” research group provides support with AI-based data evaluation, the development and training of adapted algorithms and the integration of appropriate audio technology (microphones) and AI monitoring for automatic and continuous anomaly detection.
– – – – – –
👉 www.ikts.fraunhofer.de
👉 https://ki-zfp.ikts.fraunhofer.de
👉 Project group: Cognitive material diagnostics
Photo: Fraunhofer IKTS
