Development, begins together.
Banner alanı
IFM Sensor

🚀 AI Support for Autonomous Operations from Yokogawa: CENTUM R7.02 Arrives! 🤖

Erkan Teskancan

Corporate
  • OLM MUH
  • art_961_4a21f4c4b6ca331db0ddad4913cccb89.jpg

    Yokogawa's Next-Generation Integrated Production Control System: CENTUM R7.02​


    Yokogawa Electric Corporation has introduced CENTUM R7.02, a new integrated production control system that enables autonomous operations in industrial processes. This update, part of the OpreX Control and Safety System series, offers artificial intelligence (AI) capabilities as standard and renames the product from CENTUM VP to CENTUM.

    Autonomous Control AI for Challenging Processes​


    Yokogawa's autonomous control AI targets processes that are difficult to automate with traditional methods and require manual intervention from operators. This AI is also effective in control tasks that require balancing multiple conflicting objectives. The system can directly determine and implement appropriate control actions even in disturbances that cause large process fluctuations.

    • Success Story: In 2022, it autonomously controlled a chemical plant for 35 days. The plant has been operating stably for over four years with energy savings and a lower environmental impact.
    • Development: The core reinforcement learning algorithm, Factorial Kernel Dynamic Policy Programming (FKDPP), was jointly developed by Yokogawa and the Nara Institute of Science and Technology (NAIST).

    AI Control Models on the DCS Platform​


    Thanks to the AI Control feature, control models generated by the autonomous control AI operate as a standard function within the CENTUM system environment. These models are downloaded and deployed via the CENTUM engineering environment. Operators can monitor operating conditions using graphics, trends, alarms, and faceplates in the familiar CENTUM operation and monitoring environment.

    Before model deployment, the AI undergoes repeated learning cycles in a plant simulator that reproduces process behavior to obtain an optimal control model. After the customer evaluates the reliability and validity of the model, it is applied to plant control along with safety-providing functions.

    AI Soft Sensors for Quality-Oriented Process Values​


    The AI Prediction function offers AI soft sensor capabilities that estimate values such as component concentrations from process data like temperature, flow rate, and pressure. While these values are important for evaluating product quality and process conditions, they are often difficult to measure directly and continuously in real-time, and some require laboratory analysis.

    Machine learning models predict these values and show how much each process variable contributes to the result. Operators can view the estimated values along with other operational information in the CENTUM operation and monitoring environment.

    Target Markets​


    The target markets for this innovative system include the refinery and petrochemical, chemicals, power, gas, pulp and paper, pharmaceutical, food, iron and steel, metals, water and wastewater, and cement sectors.
     
    Back
    Top