Skip to main content
+49 721 9654-724

Product

IoT Data Hub

An open and scalable data platform for businesses that want to make machine data readily available and later expand its use in a controlled manner for analytics, applications, and AI.

Book a demo

Typical triggers

When companies need the IoT Data Hub

The IoT Data Hub is useful when machine data needs to be made available quickly without having to set up multiple separate data silos for dashboards, analytics, applications, and AI.

Common drivers include scattered machine data, the significant effort required to integrate OT and IT systems, or the desire to quickly gain initial visibility using just a few data sources.

To this end, the platform provides a common foundation for MDE, dashboards, analytics, custom applications, and integrated AI capabilities.

Connectivity

Record and connect machine data

The platform connects controllers, sensors, gateways and store floor systems via specific industrial protocols and reusable integration patterns.

  • Concrete protocols such as Siemens S7, OPC UA, MQTT, Modbus
  • Connection of PLCs, sensors, historian systems and specialist sources
  • Reusable templates for machine, line and location rollouts
Further information
Connecting machine data

Data management

Model, manage and provide data

Raw data is converted into a consistent data model and structured using asset management and semantic descriptions for dashboards, analyses, and AI.

  • Asset management for locations, areas, labels and machine types
  • Consistent structuring and provision of industrial data via a common data model
  • Semantic metadata model for data streams, measured values, measurement units, data types and semantics
Data management

Flexible self-service analytics powered by AI

Flexibly analyze live data streams and historical data using natural language. The AI translates business requirements into executable logic and actionable insights.

AI Pipelines for Real-Time Data Analysis

Live data analysis

Analyze live data using natural language and feed it directly into operational logic

Technical requirements for real-time machine data can be expressed in natural language. The AI translates these specifications into executable logic, enabling analyses, monitoring, and responses to be put to productive use immediately.

  • Define live analyses using natural language and deploy them as executable pipelines
  • Make current metrics, statuses, and events directly available to the shop floor and control center
  • Flexibly implement alerts, triggers, and operational responses
View AI Pipelines
AI Notebooks for Historical Data Analysis

Historical data analysis

Convert historical data into clear and understandable reports using natural language

History, trends, and domain-specific contexts can be analyzed using natural language. The AI generates clear analytical logic and readable code from this data, which can be reviewed, adapted, and reused.

  • Analyzing time series, historical data, and contextual data together
  • Use AI notebooks for flexible analysis of stored data
  • Reuse results as code, visualizations, and further analyses
View AI Notebooks

Application layer

Build your own applications and modules

Using the platform, custom analytical applications or proprietary user interfaces can be deployed with minimal development effort.

  • APIs and SDKs for company-specific applications
  • Roles, rights and governance for productive environments
  • Client libraries for numerous programming languages
Further information

Architectural building blocks

The platform integrates data connectivity, data modeling, the application layer, and operational aspects into a unified architecture.

Data connection

Siemens S7, OPC UA, MQTT, REST, BeckhoffProven industry protocols and standard interfaces for controllers, gateways, historian systems, and other data sources.
Connector templatesReusable configurations for machine types, lines and cross-location rollouts.
Edge component in the OT networkData collection and preprocessing close to the plant, with controlled communication to the central or cloud instance.

Processing and persistence

Streaming and event processingLive data for rules, monitoring, pipelines, and further processing.
Time series and history managementBasis for trends, comparisons, dashboards and historical analyses.
Pipelines and pre-processingTransformation, enrichment and transfer of data for operational and analytical workflows.

Data model and use

Asset management and data structureLocations, departments, labels, machine types, and signals organized in a consistent structure to provide production data that can be used for technical purposes.
Semantic metadata modelDescribe and manage data streams, measured values, units, data types, and their technical significance in a clear and understandable manner.
APIs, dashboards and data explorationProvision for engineering, production, quality and own applications on the same platform basis.

Operation and expansion

On-prem, cloud and hybridAdaptable to existing infrastructure requirements and distributed operating models.
Roles, rights, governanceManagement of productive use across teams, locations, clients, and responsibilities.
Open source basis and expandabilityCan be expanded with custom modules, services, dashboards, analytics features, and AI components.

Operating models and deployment

The IoT Data Hub can be operated as an integrated solution for a quick start or as a distributed architecture with governance and security requirements.

Edge

Data acquisition and pre-processing directly in the OT network

An edge component can be operated close to machines, controllers, or cells, collect data locally, and synchronize it with a central or cloud-based instance in a controlled manner.

  • Suitable for networks with limited connectivity or segmentation
  • Pre-processing, buffering and secure transfer to central instances
  • Clean separation between OT-related operations and central governance
SMES

Integrated MDE and analysis platform for a quick start

For small and medium-sized businesses, the IoT Data Hub can be used as an integrated solution for machine data collection, dashboards, and basic analytics.

  • Less integration effort thanks to a common platform
  • Quick start with connectivity, charts and dashboards
  • Gradual expansion in the direction of analysis and AI possible
Enterprise

Governance, security and distributed deployment for large organizations

For larger companies, the platform supports cross-site architectures with roles, responsibilities, distributed instances and controlled provision of data and applications.

  • Governance across locations, divisions and teams
  • Security and operating models for centralized, hybrid and distributed scenarios
  • Common technical basis for local and central data rooms

Quick start, later expansion if required

The IoT Data Hub can be started with just a few data sources. Additional locations, applications or AI functions can be added later on the same basis.

01Home

Connect initial data sources quickly

At the beginning, the relevant machines, control systems or sensor sources are connected so that the first live data can be displayed without a long lead time.

02Visibility

Structuring data and creating initial views

Assets, signals and specialist contexts are then structured and initial dashboards, charts or analytical views are provided on the same database.

03Benefit

Use initial analyses and applications productively

The first analyses, rules or application-specific modules can be used productively and evaluated in operation after just a short time.

04Expansion

Expand step by step if required

If additional lines, locations, specialist applications or AI modules are added, the platform can be expanded in a controlled manner on the same basis.

Demo

Experience Bytefabrik live

Arrange a demo to get to know the platform, analysis and AI functions based on your questions.

Book a demo