Tokyo, April 8, 2013 - NEC Corporation (NEC; TSE: 6701) developed a “Failure Sign Monitoring System for Large-scale Plants” that analyzes failure signs from large-scale facilities, such as factories and electric power plants, in order to prevent equipment failures prior to an incident.
NEC’s is driving the adoption of these systems featuring the company’s independently developed big data analysis technologies that automatically detect when sensors, for example, indicate that operations are “different from normal” using internally developed invariant analysis technologies (*), which are used without specialized training or complicated settings.
This new system analyzes information gathered from sensors distributed throughout a facility
using invariant analysis technologies. These technologies automatically determine how a facility operates under normal conditions by collecting and analyzing massive amounts of sensor data. This enables the system to compare information under a wide range of conditions, which allows it to quickly detect and understand when abnormal conditions or “failure signs” arise, prior to an actual failure.
As a result, plants can carry out preventative maintenance, thereby improving overall safety and operational effectiveness.
During its development, this system was successfully implemented in field trials by the Chugoku Electric Power Co., Inc. at the Shimane Nuclear Power Station. Initially, the system analyzed sensor information from August 2011 through November 2012, learning how to detect abnormalities based on past examples of defects.
In October 2012, the system was deployed on a test basis at the Shimane Nuclear Power Station’s technology training facility. During these tests, the system successfully detected signs of a variety of artificial equipment failures.
Going forward, NEC aims to continue driving the development of failure sign monitoring systems that utilize invariant analysis technologies to help maintain large-scale facilities throughout the world.
***
Notes:
(*) Invariant Analysis Technologies:
These technologies automatically extract and model universal relationships that represent the characteristics of a system (invariant) based on massive quantities of sensor data, without relying on domain knowledge of the plant system. As a result, the technologies are able to detect “silent failures” that do not match with the system’s model behavior.
About NEC Corporation
NEC Corporation is a leader in the integration of IT and network technologies that benefit businesses and people around the world. By providing a combination of products and solutions that cross utilize the company's experience and global resources, NEC's advanced technologies meet the complex and ever-changing needs of its customers. NEC brings more than 100 years of expertise in technological innovation to empower people, businesses and society. For more information, visit NEC at http://www.nec.com.
NEC Press Contacts (Japan):
Takehiko Kato
NEC Corporation
+81-3-3798-6511
E-Mail:t-kato@cj.jp.nec.com
Joseph Jasper
NEC Corporation
+81-3-3798-6511
E-Mail:j-jasper@ax.jp.nec.com