The Daikin Kashima plant produces a wide range of fluorochemical products used in air conditioning equipment, automobiles, semiconductor production, and other applications. Advanced digital technologies have been applied at this site as part of a digital transformation (DX) initiative. The team has implemented HART-enabled instrumentation, and associated digital diagnostic tools and predictive analytics, all combined with artificial intelligence (AI), so the facility can transition from traditional time-based maintenance to more effective condition-based maintenance.
By first learning normal plant behavior from historized big data, the AI system can then perform nonlinear regression analysis on live data using a neural network, enabling the anomaly detection and prediction needed to address potential problems and avoid unexpected shutdowns.
Many valve positioners, pressure transmitters, and Coriolis flowmeters were already HART-enabled, and the team used Fast Ethernet-based HART converters to access other equipment, along with various DCS/PLC systems. Daikin officials point out that success of AI depends on the accuracy of available data, and HART devices made a difference in this regard.
“The HART signals of each device are wonderful data packed with the know-how of each device manufacturer. By having AI learn this along with various process data in the plant, it's more likely to be able to learn various signs of equipment anomalies,” said Masumi Yoshida of the Daikin Industries engineering department.
Condition-based maintenance at this plant over the past three years has reduced maintenance costs by an estimated US $400,000, and the team is looking to expand the technology to many more production sites around the world.
* A complete list of recipients and their success stories are available here.
No comments:
Post a Comment