Accelerate Your Journey to Industrial Autonomy with IA2IA
With IA2IA, Yokogawa offers a path forward and a clear vision for the transition from industrial automation to industrial autonomy—enabling sustainable value creation and addressing global challenges in an increasingly interconnected world.
Yokogawa sees IA2IA as a journey with different levels and has therefore developed a maturity model to establish customers’ current state and the next stage of IA2IA.
How We Power Autonomous Operations
Reinforcement Learning AI Enables Breakthrough in Industrial Autonomy
Jointly developed by Yokogawa and the Nara Institute of Science and Technology (NAIST), Factorial Kernel Dynamic Policy Programming (FKDPP) is an autonomous control AI protocol that makes use of reinforcement learning technology. It can control and autonomize areas of plant operations that have been beyond the capabilities of existing control methods and have up to now necessitated manual operation. Yokogawa put FKDPP into practical use by utilizing the company’s know-how regarding plant operation and control, and successfully autonomized manual operations of a distillation column at a chemical plant.
Robotics Improves Safety and Efficiency in Plant Operations
OpreX Robot Management Core is a key product in the Yokogawa robot operations solution. By integrating the management of various types of robots that perform plant maintenance tasks conventionally carried out by humans, this software will help customers maintain their facilities in a safer and more efficient manner. In addition, when connected to a plant’s control and safety systems, it enables the utilization of manufacturing site data that has been acquired by robots, and the issuing of procedural instructions to robots, thus enabling the first step to be taken toward autonomous plant operations.
Control of Work Enables Safe Industrial Autonomy
Even as industrial autonomy advances, ensuring human safety and managing risks remain essential. Control of Work (CoW) provides strict oversight of who performs which tasks and how they are executed, thereby ensuring the safety of hazardous operations. This oversight ensures that, even in autonomous systems and work environments, appropriate qualifications and procedures are consistently followed, helping to prevent accidents and incidents. As such, CoW serves as a foundational element for maintaining safety in the implementation of industrial autonomy.
Case Studies
Stable Operations & Energy Efficiency with Reinforcement Learning AI
As the world’s first proven application of reinforcement learning AI directly controlling real-world plant operations, ENEOS Materials Corporation used FKDPP autonomous control AI to handle complex operations, ensuring consistent product quality & optimizing waste heat utilization.
Improved Asset Monitoring with AI-Powered Multi-Robot Collaboration
Shell Global Solutions International B.V. and Yokogawa have partnered to develop AI- and robot-based inspection solutions. The collaboration aims to enhance safety and efficiency in plant operations by integrating Shell’s visual analytics tool with Yokogawa’s robot management platform.
Accelerating Transformation with an Industry 4.0 Roadmap
Using the Smart Industry Readiness Index (S.I.R.I.), Yokogawa helped Mewah assess its digital maturity. Yokogawa identified and prioritized areas where transformation could deliver the greatest operational and financial impact, and aligned them with the Mewah Group’s Industry 4.0 roadmap.
Improved Efficiency & Reliability with Machine Learning Enabled Alarm Management
For BASF SE, Yokogawa implemented Alarm Behavior Analysis to analyze the cause-and-effect relationship between alarms and operations, and used e-SOP solution to analyze all the actions taken by operators after alarms were generated.
Shifting Operators to High-value-added Data Analysis Work
For DIC Corporation, Yokogawa realized a Data Utilization Platform to dramatically reduce the enormous amount of time required for data analysis preparation and have enabled operators to focus on data analysis, as it should be. In addition to improving the quality of data analysis, this motivates operators to take on higher-level tasks.
Erőforrások
További információkat szeretne a munkatársainkról, technológiánkról és megoldásainkról?
Kapcsolatfelvétel