Artificial intelligence in the edge gateway

Mara Hofacker,

Machine learning in the control cabinet

At the Hannover Messe, SSV is showcasing the IGW/941, a compact edge gateway with a pre-installed AI software stack. In addition to numerous mathematical functions, this also offers various machine learning algorithms for classification and regression. This allows applications to be created in which sensor data is analyzed in real time directly on the DIN rail with the help of machine learning, for example to predict required maintenance dates or detect anomalies in the status data of a machine.

At the Hannover Messe, SSV is showcasing the IGW/941, a compact edge gateway with a pre-installed AI software stack. © SSV Software Systems

Data is the raw material of the 21st century. It is constantly being generated in every machine, every system and every process. With the right hardware and software, this valuable treasure trove of data can be extracted and converted into information using machine learning (ML). This enables predictive service and maintenance concepts (predictive maintenance), quality improvements (predictive quality), productivity increases (predictive efficiency) and ML-based anomaly detection.

In the IIoT environment, useful data must first be generated, linked and processed using special sensor technology. Information is then obtained using appropriate ML algorithms. The information is then available for further use both locally (e.g. via OPC UA) and with the help of a cloud.

At the Hannover Messe,SSV will be showcasing the IGW/941, a compact edge gateway with pre-installed ML algorithms and various data science modules for industrial applications. It can be used to create applications that capture sensor data, for example, convert it into information using classification or regression and forward the result via OPC UA or MQTT.

Advertisement

IGW/941 includes preconfigured and ready-to-use development tools for the ML training phase and model building. Furthermore, SSV offers all IGW/941 users a webinar with the following content: 1. basic principles and terminology of machine learning. 2. a complete machine learning process, including sensor data acquisition, data preparation, modeling and model evaluation 3 Determine model accuracy and adjust hyperparameters. 4. connect the output of a machine learning algorithm to other systems.

Hanover Fair, Hall 5, Stand D05

  • Xing Icon
  • LinkedIn Icon
Advertisement
Advertisement

You might also be interested in

Advertisement
Advertisement
Advertisement
Advertisement
Advertisement
Advertisement
Advertisement

IIoT networking

How production can benefit from AI

Together with AI technology, IIoT networking makes it possible to better control machine parameters and optimize quality with predictive quality. Downtimes and set-up times can also be further minimized. Cloud platforms also make these technologies...

read more...
Subscribe to our newsletter
Advertisement
Back to home