Document Processing
Bayernwerk's transformer-station commissioning process relied on paper forms, manual image uploads, and back-office re-entry into SAP, creating weeks-long delays, human error, and difficulty keeping computer-vision models reliable as hardware variants and user volume grew.
Reported impact
Bayernwerk standardized and simplified transformer-station documentation, made the computer-vision solution scalable and more reliable, reduced manual model-update work, improved image-recognition accuracy, and cut annual operating costs.
Bayernwerk digitized transformer-station commissioning with NEXT.SwitchON, a tablet application that captures field data and photos during onsite work. The app uses machine-learning computer vision to identify installed hardware and wiring from tablet images and pre-fill digital documentation. The resulting records are transferred into Bayernwerk's end system, SAP, instead of being re-entered from paper. To make the AI reliable in production, Bayernwerk ran the solution on Socrates, an Azure-based integration platform implemented by DXC, and added DXC MLOps Quickstart for Microsoft Azure. DXC then converted the initial ML approach into scalable, reusable pipelines that automate image augmentation, model training, evaluation, CI/CD-based deployment, continuous monitoring, event-driven retraining, model orchestration, and publishing the newest models back into NEXT.SwitchON.
Technicians use NEXT.SwitchON on tablets to capture installation data and take photos of transformer-station work. Computer vision models identify hardware and wiring from the images and pre-fill digital documentation. Through the Socrates platform on Azure, the records are transferred into SAP, while the DXC MLOps Quickstart pipelines augment images, train and evaluate models, monitor them in production, and publish new model versions back to NEXT.SwitchON.
"250,000 euros annually savings"
"75% faster station installation documentations"
"99% machine learning image recognition accuracy"
"NEXT.SwitchON uses advanced machine learning (computer vision) to identify installed hardware and wiring automatically on images taken with the tablet’s camera."
"Socrates was enhanced with cutting-edge MLOps capabilities by DXC using the DXC MLOps Quickstart for Microsoft Azure."
"Socrates, an Azure-based integration platform that was developed and implemented by DXC Technology."
"The problem for Bayernwerk was that documentation was done with paper and pen. Back-office staff then had to manually enter the documentation data into a central SAP system, a lengthy process prone to human error and time delays; it could take weeks"
"This allows continuous automatic image augmentation, as well as model training and evaluation. It also automates the process of publishing the latest model versions directly to NEXT.SwitchON."
"This information is then automatically used to pre-fill parts of the digitalized documentation, which gets transferred to the end system."
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
Microsoft Sample Aug 12, 2025 Repsol Repsol wanted to measure whether generative AI could reduce time spent on routine knowledge work such as finding information, summarizing documents, drawing conclusions, comparing supplier proposals, and preparing… 121 minutes a week Copilot Chat · Excel · Microsoft 365 Copilot Microsoft Sample Mar 13, 2025 Repsol Repsol found that everyday knowledge-work tasks such as summarizing content, pulling key information, and managing emails were consuming time that employees could otherwise spend on higher-value strategic work, so it… 121 minutes per week saved per average employee Microsoft 365 Copilot · PowerPoint · Word Microsoft Sample Sep 25, 2024 National Grid National Grid is helping the UK achieve its net zero ambitions. Azure · Microsoft Copilot 