Smart Factory Platform_PosFrame

PosFrame is a smart platform that can collect structured and unstructured data of production sites in real time providing optimal control using data-based analysis and AI. PosFrame is the world's first and most advanced platform for heavy and continuous processes that can be delivered on a cloud basis.

APP

  • Production

  • Quality

  • Equipment

  • Energy

  • Safety

PosFrame

5. Analysis

Analysis Workbench (AWB)

4. Storage

Big Data Platform (BDP)

3. Alignment

Time amp; Length Alignment (TLA)

2. Processing

Real Time Platform (RTP)

1. Acquisition

Interface Middleware (IFM)

6. Control

PosFame Edge

Devices

Equipment

Sensor

PLC/DCS CMC

Features

  • Supports a real-time data-based decision-making system

    Supports data-based decision making through real-time acquisition, analysis, and control of data generated by various IoT sensors.

  • New smart factory IT technology All-In-One platform

    The real-time, fault-tolerant, integrated smart factory platform based on new technologies such as loT, Big Data, and AI continually applying new future IT technologies.

  • Successful application to continuous processes and expansion to all industries

    In continuous processes, large data generated by unit facilities/processes can be analyzed horizontally and vertically to enable tracking and analysis, and management between processes.
    It can be applied to all industry areas, including production acceleration, quality assurance, facility efficiency improvement, energy optimization, and proactive safety control.

Functions

  1. 1. Data acquisition
    Interface Middleware

    High-speed acquisition of formatted/unformatted data from different types of systems and equipment

    • Interface to multiple types of equipment
    • Acquisition of large-capacity formatted/unformatted data
    • Supporting data standard conversion and acquisition automation
    • Real-time, high-speed acquisition (20ms-1s)
  2. 2. Data processing
    Real Time Platform

    High-speed, parallel processing of data horizontally and vertically for the integrated analysis of standardized data and real-time activation of alert when an abnormality is detected.

    • Alignment of data horizontally and vertically according to the customer's business needs

      • Factory: Interface of upstream and downstream processes and alignment of lengths
      • B&C: Smart home, smart building, and smart city data processing
      • Energy: Equipment efficiency and performance time series; alignment

    • Real-time monitoring and abnormality alert function

  3. 3. Data alignment
    Time & Length based Alignment

    Data connection between Upstream and downstream process specialized in continuous steel making processes.

    • Data connection of operation - quaky -equipment data

    • Assignment of material unit calculation length data

    • Establishment of material-based traceability of work/ quality abnormality

      • ※ Customized development according to the business requirements of each industry domain.
  4. 4. Data storage
    Big Data Platform

    Storage of big data for each type of RTP and TLA alignment data and presentation of query engine for analysis and utilization.

    • Large capacity at petabyte level and high-performance storage of big data
    • 10 times' compress. storage and 2 times' performance improvements compared. to the existing Hadoop storage
    • Low-cost, high-efficiency storage of large-capacity formatted/unformatted data
  5. 5. Analysis
    Analytics Workbench

    Even field staff without analysis expertise can carry out the entire analysis process in one stop to improve the site and systemize the knowledge assets with the Al analysis solution.

  6. 6. Control
    PosFrame Edge

    PosFrame Edge is a solution that can artificially control equipment without speed delay by executing real-time data processing and Al. big data model near the field equipment.

    • Real-time data collection

      • Connection to the related system following data collection from instruments, PLC/DCS, and DAQ and data preprocessing (calculation and filtering).

    • Smart PLC function

      • Equipment sequence and process control using the software PLC function.

    • Real-time model control based on reinforcement learning

      • Supports the model optimization environment through reinforced learning using real-time Al and big data control model execution and control results.
        *Al and big data model development and performance management use the PosFrame platform.

Additional PosFrame features

Smart Factory Portal

The portal includes the app store providing smart apps that the user can download as needed and the 3D factory layout that provides personalized indicators, chart, and dashboard for the user to check the production status at a glance in real time.

  • 3D View

    The function visualizes the diffusion of the smart factory by laying out the data needed for steel mills in three dimensions.
    Drill down on the smart factory by linking indicators and tasks for each factory.

  • Smart App Store

    Download, installation, and deployment of needed smart apps. Personalized categorization using the My Folder function.

  • Dashboard

    Manage your own dashboard by selecting and placing metrics you need (specify batch charts and layouts).

Use Cases

  • Production
    Reduction of production lead time
    • AI-based operation modeling for the prediction of blast furnace output, cokes’ quality, and sintered steel strength.
    • Reproduction of operation troubles and cause analysis (control data + image data synchronization analysis).
    • Intuitive automation of manual operation: automatic equipment control.
    • Improvement of work accuracy through image analysis technology (product number recognition, coil load centering, etc.)
  • Quality
    Securing quality in advance
    • Material length unit quality defect tracking of upstream and downstream processes.
    • Reproduction of quality defect situation and analysis of root cause.
    • Post-processing control/operation guide by predicting the slab surface quality.
    • Quality prediction modeling through the correlation analysis of quality influence factors.
  • Equipment
    Improvement of equipment efficiency
    • Real-time monitoring using smart sensors (torque, ultrasonic, laser, image, etc.).
    • Prediction of equipment maintenance period to maintain the optimal performance (rolling system, control system, electrical system, etc.).
    • Improving equipment control formula model information by AI analysis of facility status + operation + environment data.
  • Energy
    Energy optimization
    • Maximization of energy production by predicting failure of power turbine.
    • Big data-based improvement of energy supply-demand balancing and prediction accuracy.
    • Monitoring of energy usage by equipment and increase of heavy energy-consuming equipment.
    • Production scheduling reflecting the energy cost.
  • Safety
    Proactive safety control
    • Monitoring of in/out of danger zone and management of danger blind area (crane safety management, etc.).
    • Pre-detection and warning of worker unsafe behavior (smart TBM, smart helmet/watch, etc.).
    • Safety training using VR.