The technological basis for "Industrial Artificial Intelligence"
In the context of Totally Integrated Automation (TIA), scalable solutions can be implemented in projects with the open IoT operating system MindSphere or other cloud-based solutions.
These solutions enable a seamless data transmission from the field level to the controller, then from the edge level all the way to the cloud.
AI Model Deployer provides a service to deploy trained machine learning models to Siemens targeted hardware.
Using industrial-grade hardware ensures an optimal inference environment for AI models and their easy integration into the existing automation. Currently, Siemens supports the following target hardware.
TM NPU
The first important step for integrating AI into the automation environment is the S7-1500 TM NPU (neural processing unit) module. It’s especially appropriate for use on the field level at the machine, and wherever reliable, fast, deterministic decisions are required.
The installed VPU, Intel's new Myriad X VPU chip, is a dedicated hardware accelerator for deep neural network structures. The integrated image processing unit, together with the computing unit for neural networks, facilitates new applications in industrial automation. It speeds up the image processing and local data evaluation by means of the trained models.
Users can connect compatible sensors such as cameras to the integrated interfaces of the S7-1500 TM NPU module. The S7-1500 sends a trigger message to the TM NPU, which captures an image using the camera. The TM NPU then preprocesses the image, runs the inference with the trained neural network and returns the evaluation result back to the PLC.