Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.
Title
Siemens Electronics Factory Erlangen Reduces Machine Learning Deployment Time by 80% with AWS and Siemens Industrial AI on Industrial Edge
Siemens Electronics Factory Erlangen Reduces Machine Learning Deployment Time by 80% with AWS and Siemens Industrial AI on Industrial Edge | Siemens Electronics Factory Erlangen & Siemens Case Study | AWS Skip to main…
Description
Siemens Electronics Factory Erlangen, which manufactures PCBs and controllers such as SINAMICS converters and SINUMERIK CNC controllers, used computer vision models to spot anomalies in PCB assembly, but training and retraining ML models on premises was time-intensive and constrained by GPU bottlenecks. The factory adopted AWS services together with Siemens Industrial Edge and Siemens Industrial AI, sending shopfloor images via Edge applications to Amazon S3 before training via Amazon SageMaker or AWS Lambda; training results and edge prediction results are monitored through AI Model Monitor, with AI Model Manager providing central management of models on the shopfloor. This reduced time spent on model training and retraining by 80 percent (from about 30 minutes to roughly 5 minutes for retraining and deployment), cut costs by more than 90 percent compared to on-premises data storage systems, and reduced the false call rate by over 50 percent, while continuously preventing around 4 percent of PCB assembly errors compared to around 60 percent at peaks in the past.
…ining and deployment through Siemens Industrial Edge and Siemens Industrial AI. Images from the shopfloor are sent via Edge applications to Amazon Simple Storage Service (Amazon S3) for storage, before going through Amazon SageMaker or AWS Lambda for model training. The training results from Amazon SageMaker, as well as the prediction results f…
Company
Siemens Electronics Factory Erlangen
…se call rate 50% cost savings compared to on-premises storage Over 90% Overview Siemens Electronics Factory Erlangen makes electronic components, such as printed circuit boards (PCBs), as well as supply systems and solutions for drive technology and controllers f…
Industry
Manufacturing
…se call rate 50% cost savings compared to on-premises storage Over 90% Overview Siemens Electronics Factory Erlangen makes electronic components, such as printed circuit boards (PCBs), as well as supply systems and solutions for drive technology and controllers for machine tools. To improve error detection in electronic assembly, the factory created machine…
Problem
The factory's engineering team uses images as training data to create ML models to inspect and spot anomalies in PCBs during production. In the early days, engineers trained models locally on computers running on premises, but computing limitations with GPUs and a lack of elasticity became challenging, so the team needed a more flexible and faster way to train and retrain its ML models.
…ers trained models locally on computers running on premises. But after a while, computing limitations with Graphics Processing Units (GPUs) and a lack of elasticity became challenging. The team needed a more flexible and faster way to train and retrain their ML m…
Solution
The factory adopted AWS services together with Siemens Industrial Edge and Siemens Industrial AI to cover the complete AI lifecycle from cloud training to shopfloor deployment: images from the shopfloor are sent via Edge applications to Amazon S3 before going through Amazon SageMaker or AWS Lambda for model training; training results from SageMaker and prediction results from the AI Inference Server on each Industrial Edge Device are sent to AI Model Monitor for observability; and AI Model Manager provides central management of models on the shopfloor.
…torage, before going through Amazon SageMaker or AWS Lambda for model training. The training results from Amazon SageMaker, as well as the prediction results from AI Inference Server from each Industrial Edge Device, are sent to AI Model Monitor for observability measures. Additionally, all the models are visible within AI Model Manager, which is a co…
Business value
The factory reduced time spent on model training and retraining by 80 percent — from about 30 minutes to roughly 5 minutes up to deployment — achieved cost savings of more than 90 percent compared to on-premises data storage systems, reduced its false call rate by more than 50 percent, and is continuously preventing around 4 percent of PCB assembly errors, down from around 60 percent at peaks in the past.
…apid improvement in the automation of our ML pipeline.” Herchenbach added, “And our cost savings are more than 90 percent by using AWS lifecycle management and getting rid of using on-premises data storage. It’s truly a seamless integration from cloud to edge.” Not only did AWS and Sie…
Technology
Amazon S3, Amazon SageMaker, AWS Lambda, Siemens Industrial Edge, Siemens Industrial AI, AI Model Monitor, AI Model Manager, AI Inference Server
…ining and deployment through Siemens Industrial Edge and Siemens Industrial AI. Images from the shopfloor are sent via Edge applications to Amazon Simple Storage Service (Amazon S3) for storage, before going through Amazon SageMaker or AWS Lambda for model training. The training results from Amazon SageMaker, as well as the prediction results f…
AI capabilities
Computer Vision, Fraud & Anomaly Detection
…of industries, from intralogistics, to aerospace, to automotive, and many more. The factory has been using computer vision (CV) for more than 20 of its 50 years in operation. It relies on those images to ensure its PCBs have all their components in the r…
Deployment options
cloud, hybrid
…our cost savings are more than 90 percent by using AWS lifecycle management and getting rid of using on-premises data storage. It’s truly a seamless integration from cloud to edge.” Not only did AWS and Si…
