OpenZfP-KI-Portal (Open AI portal for non-destructive testing (NDT))

Service

The Fraunhofer IKTS OpenZfp-KI-Portal (Open AI portal for non-destructive testing (NDT)) now makes it possible to examine audio data from machines and systems for anomalies and have them analyzed using artificial intelligence (AI). Anomalies are deviations from the normal state that provide indications of wear, loose or defective components. These deviations do not necessarily have an impact on the process, but could lead to reduced quality, disruptions in the process or even failure.

Until now, such data has only been checked on a random basis, usually manually, and in many cases is based on the experience of the inspectors. The OpenZfp-KI-Portal is now intended to automate the inspection and make it traceable. The probability of error detection depends on the respective application and is up to 100 percent.

Audio recordings of the process must be uploaded to the OpenZfp-KI-Portal for analysis. 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 recognize the area in which deviations occur and thus narrow down the search for errors.

The portal offers an automatic mode that is preset with standard parameters and is particularly suitable for users who are just starting out with AI. Experienced AI users, on the other hand, can use the professional mode and adjust individual parameters themselves. The experimental nature of the data analysis is intended to reduce the fear of contact with AI.

Registration is required to use the portal. The data will only be used for your own data classification; it will not be passed on or used by third parties. The data is automatically deleted after 30 days. Until then, users have the option of having their own data reclassified and, if necessary, evaluated using other parameters. It is also possible to “donate“ your own data anonymously and thus help the portal to obtain a broader database in order to further train the AI algorithms. 

© Fraunhofer IKTS
Output of the OpenZfP-KI-Portal: The spectrogram of the normal state (without errors) on the left and the spectrogram of the state with errors on the right. The anomalies are marked in red.

 

Who can use the portal?

 

The portal is open to everyone: Plant operators, technicians, employees from research departments, maintenance companies and other interested parties. AI experience is not a prerequisite, as analysis can be carried out in an automatic mode in which the most important parameters are already preset. Users who already have AI experience can adjust individual parameters themselves.

 

 

In which languages is the portal available?

 

When using the portal, you can choose between German and English.

 

What does it cost to use the portal?

 

Use of the portal is free of charge.

 

What applications is anomaly detection suitable for?

 

Anomaly detection is suitable for many applications in industry, such as the diagnosis of general machine noises, pump and valve noises and sorting noises. But everyday noises can also be analyzed: such as those from household appliances, vehicles or natural noises such as twittering of birds or the sound of water. There are almost no limits to the field of application.

 

What are the requirements for the data that is uploaded

 

The data can be recorded with a smartphone or from microphones already installed in existing systems for process monitoring or quality control. It is important that at least five audio files are uploaded, ideally more than half of which should represent the normal state, i.e. without errors.

 

Is my data safe?

 

Your data is secure. The data is only used for our own classification and is deleted from the system after 30 days. The servers on which the data is temporarily stored and processed are Fraunhofer's own servers, so that no data is passed on to third parties or abroad.

If you actively decide to “donate“ your data, you will help the system to obtain a broader database and thus to further develop the algorithms.


 

Why does Fraunhofer IKTS operate the OpenZfp-KI-Portal?

 

With the OpenZfp-KI-Portal, we want to reduce fear of contact with AI and address potential users. If you require a classification of your data that is specifically tailored to your application, our research group “Cognitive Material Diagnostics“ will be happy to support you in the AI-based evaluation of the data, in the development and training of customized algorithms and in the integration of appropriate audio technology (microphones) and AI monitoring for automatic and continuous anomaly detection in your plant.

Video demonstration of the OpenZfp-KI-Portal