Cloud-to-Edge Deployment
Assembly Line
☁️🧠 Automated Cloud-to-Edge Deployment of Industrial AI Models with Siemens Industrial Edge
Due to the sensitive nature of OT systems, a cloud-to-edge deployment can become a challenge. Specialized hardware devices are required, strict network protection is applied, and security policies are in place. Data can only be pulled by an intermediate factory IT system from where it can be deployed to the OT systems through highly controlled processes.
The following solution describes the “pull” deployment mechanism by using AWS services and Siemens Industrial AI software portfolio. The deployment process is enabled by three main components, the first of which is the Siemens AI Software Development Kit (AI SDK). After a model is created by a data scientist on Amazon SageMaker and stored in the SageMaker model registry, this SDK allows users to package a model in a format suitable for edge deployment using Siemens Industrial Edge. The second component, and the central connection between cloud and edge, is the Siemens AI Model Manager (AI MM). The third component is the Siemens AI Inference Server (AIIS), a specialized and hardened AI runtime environment running as a container on Siemens IEDs deployed on the shopfloor. The AIIS receives the packaged model from AI MM and is responsible to load, execute, and monitor ML models close to the production lines.
Bringing Scalable AI to the Edge with Databricks and Azure DevOps
The ML-optimized runtime in Databricks contains popular ML frameworks such as PyTorch, TensorFlow, and scikit-learn. In this solution accelerator, we will build a basic Random Forest ML model in Databricks that will later be deployed to edge devices to execute inferences directly on the manufacturing shop floor. The focus will essentially be the deployment of ML Model built on Databricks to edge devices.
How Corning Built End-to-end ML on Databricks Lakehouse Platform
Specifically for quality inspection, we take high-resolution images to look for irregularities in the cells, which can be predictive of leaks and defective parts. The challenge, however, is the prevalence of false positives due to the debris in the manufacturing environment showing up in pictures.
To address this, we manually brush and blow the filters before imaging. We discovered that by notifying operators of which specific parts to clean, we could significantly reduce the total time required for the process, and machine learning came in handy. We used ML to predict whether a filter is clean or dirty based on low-resolution images taken while the operator is setting up the filter inside the imaging device. Based on the prediction, the operator would get the signal to clean the part or not, thus reducing false positives on the final high-res images, helping us move faster through the production process and providing high-quality filters.