In order to create a basis for all digitalization applications and ultimately obtain added value from plant data, the data must be available in a structured, well-organized form. To this end, the SMS DataFactory converts raw data such as relational, process, or time series data or files into information and turns it into added value.
Customer challenges addressed
Depending on the problem that needs to be solved, all data in a steel plant must be available in different formats. The data are typically viewed from a condition, quality, and planning perspective. For the maintenance view, the data are often retrieved using certain events in time. The data must therefore be addressable and selectable via a time range.
- Data from different processes transformed to same position of material.
- Have all relevant product data with good granularity.
- Make data available to customer standardized, on demand.
- Have all processing data of each production route available.
- Analyze the influence of each processing parameter on the final product quality.
- Horizontal bi-directional "value chain" of (hot) data for gaining outcomes in asset utilization, efficiency, stability, product quality, safety or delivery performance and take actions based on recommendations supported by ML/AI (machine learning / artificial intelligence).
Key features
- Seamless data from upstream and downstream lines.
- Standardized connectors for typical OT systems of steel plants.
- Unified API and standardized naming scheme. As steel plants grow over time, a range of new systems is added by multiple manufacturers.
- DataCatalogue that is tailor-made for the metals industry, gives meaning to data, and helps you find relevant information easily.
-
Autonomous plant operation
Generating added value from data
The autonomous plant has one goal: using data to enable production that is as sustainable and resource efficient as possible. The software collects data from a plant, transforms it into information, and finally into added value using artificial intelligence and machine learning. This allows essential findings to be gained for later implementation in practice – thus saving costs and resources. Predictive algorithms help to detect a plant's condition, predict the product quality, redirect production routes, and minimize downtimes. Companies need solutions that process large volumes of data and analyze it in real-time to identify new correlations. In the era of digitalization and Industry 4.0, it is crucial to obtain maximum performance from both plant and processing routes.
![]()
Data factory architecture -
Breaking data silos
Turn data into value and make them universally available
As the basis and tool for implementing the learning steel plant, it collects data from the existing plant automation system and makes it available to other applications.
The system consists of various components that jointly enable the comprehensive preparation and analysis of all plant data.
-
Data catalogue
Turn data into value and make them universally available
Provides metadata on the data and signals stored in the SMS DataFactory. The metadata assist with the interpretation of data, give meaning to the data, describe their characteristics, and define rules for using the data in external applications.
-
Scalability
Turn data into value and make them universally available
The SMS DataFactory is a scalable product and can be used for a specific plant or machine as well as for a complete plant complex or an entire company. This way, a specific plant section can be used for starting small, and the application can be extended later to include other plant components.
-
Full material genealogy
Turn data into value and make them universally available
The SMS DataFactory provides full material genealogy. This allows data consumers to combine and map data from length-based products to any other up- or downstream length-based product, e.g., map the stopper rod position and mold level positions of the continuous casting machine with surface-inspection system data from the continuous galvanizing line for detecting non-metallic inclusions.
![]()
Genealogy schema
