JGC and NEC Collaborate for Efficient Plant Operations Using AI and IoT
Joint provision of abnormality sign detection via analysis of operating data
TOKYO, Feb 2, 2017 – (JCN Newswire) – JGC Corporation and NEC Corporation today announced their cooperation in the provision of data analysis services for plant operations using AI (Artificial Intelligence) and IoT (Internet of Things) technologies.
The cooperation, which the two companies agreed to in a memorandum concluded in November 2016, involves joint development of systems that detect signs of abnormalities in plant operations and provide related services for plants serving the oil refinement, chemical, LNG (liquefied natural gas) and gas, power, resource development, and other fields.
Energy and chemicals industries in Japan and other developed countries are currently seeking to lower overall operating costs, including maintenance costs, while sustaining plant stability and safe operations as plant life lengthens and plant operators become older. At the same time, emerging countries are seeking to maintain stable and safe operations and ensure plant efficiency amid difficulties securing skilled plant operators. In this environment, significant expectations have emerged for utilization of AI and IoT in plant operations.
In January 2016, JGC launched a specialty organization to provide services that analyze plant operating data utilizing its broad, advanced engineering know-how accumulated through the implementation of many construction projects for energy and chemical plants. Since its establishment, the organization has analyzed data from customers and supplied services that include the identification of abnormality signs for a series of plants, including an LNG plant and five refineries, both inside and outside of Japan. Additional requests for these services include five plants in the chemical, resource development and power fields.
NEC provides systems for plant abnormality sign monitoring, energy demand forecasts, quality analysis, and other services utilizing “System Invariant Analysis Technology” that detects abnormal signs from data correlations(1), “Heterogeneous Mixture Learning Technology” that analyzes a wide range of data(2), and “NEC the Wise”, a suite of proprietary cutting-edge AI technologies(3), to customers operating power, oil, and chemical plants.
The data analysis services for plant operations provided jointly by JGC and NEC analyze a broader scope of operating data, covering entire plants (enhanced data coverage), and shorten the analysis time for abnormal signs (faster analysis speed) when compared to the services supplied individually by the two companies. Additionally, the service identifies cause-effect relationships in abnormal signs based on operating data for the entire plant and contributes substantially to trouble avoidance and mechanization and automation of early prevention.
The two companies have received an order for the plant operation data analysis service and are providing this service as a first step in their collaboration. They also intend to strengthen joint efforts with the goal of providing services to 30 plants in Japan and other countries within the next two years.
(1)”System Invariant Analysis Technology”
This technology automatically extracts and creates invariant relationships that represent the characteristics of facilities or systems based on massive quantities of sensor data. By comparing the values predicted by the invariant model with real-time data, “not usual” behaviors can be detected.
(2)”Heterogeneous Mixture Learning Technology”
Heterogeneous Mixture Learning Technology learns multiple relationships hidden in big data, discovers useful patterns and regularities, and selects the appropriate one depending on the situation. This enables higher-precision prediction in dynamically changing environments than existing machine learning technologies, which often take just a single pattern into account.
(3)July 19, 2016 NEC announces new AI technology brand, “NEC the WISE”
NEC’s AI (Artificial Intelligence) Research