Masayoshi Kinoshita
Deputy General Manager
ENEOS Corporation
He is the Deputy General Manager of the Engineering and Capital Planning Dept. He gained experience as a systems engineer at Sony Corp. and Hitachi, Ltd. He joined ENEOS Corp. and contributed to the competitiveness of its refineries as a process engineer. He serves as the project manager for the AI-Based Autonomous Operation of Crude Distillation Unit. He earned BS and MS degrees in Information Engineering, and MBA.
Participates in
TECHNICAL PROGRAMME | Energy Technologies
Smart Infrastructure for the Future Energy Industry: Digitalisation & Innovation
Forum 18 | Digital Poster Plaza 4
27
April
15:30
17:30
UTC+3
In recent years, manufacturing industries in Japan have been facing a serious decline in the working population due to declining birthrate and aging population, as well as rising employee turnover rates. There are concerns about a shortage of experienced personnel in the oil refining and petrochemical industries, and an increase in problems caused by aging equipment in the industries. Prompt actions are required to cope with these concerns.
Digital technologies have been rapidly and continuously evolving in the world, which can offer promising solutions to the concerns.
Currently, plant operations rely on the round-the-clock monitoring and decision making by operators. To cope with the decline in experienced operators, our company has developed AI systems that enable advanced operation of a plant, simultaneously ensuring its stability and safety with prevention of the problems caused by aged equipment. Our goals also include improving production efficiency and reducing energy consumption in the plant beyond what experienced operators can achieve.
We have collaborated with “Preferred Networks”, a leading deep learning company in Japan since 2019. As a result of the collaboration and these endeavors, we have finally succeeded in introducing the AI systems to a Crude Distillation Unit (CDU) and a butadiene extraction unit in our plants. We have achieved continuous usage of them under various operating conditions of the units.
Our AI with deep neural networks learned the intricate relationships between the values of plant sensors and environmental variables, such as ambient temperature and precipitation, enables the prediction of the future values of the sensors and the selection of optimal operations as an alternative to human intervention. Unlike conventional advanced control systems, our AI excels at handling the non-linear dynamics between manipulated and controlled variables, allowing for flexible adaptation to changing operating conditions.
CDU especially requires a high level of skills and experience with operational factors to control and as many as sensors to monitor. The world’s first AI-based continuous autonomous operation of the CDU has been achieved. The AI system for the unit continuously monitors dozens of key operational factors and simultaneously adjusts dozens of valves to stabilize fluctuations resulting from crude oil switching as well as changes in crude oil throughput. The AI system has demonstrated higher stability and efficiency compared with manual operations. Moving forward, we will consider deploying the co-developed AI systems to our other refineries. Moreover, we aim to refine our AI models and investigate their applicability in other industries, expanding our reach beyond our company’s core operations.
Digital technologies have been rapidly and continuously evolving in the world, which can offer promising solutions to the concerns.
Currently, plant operations rely on the round-the-clock monitoring and decision making by operators. To cope with the decline in experienced operators, our company has developed AI systems that enable advanced operation of a plant, simultaneously ensuring its stability and safety with prevention of the problems caused by aged equipment. Our goals also include improving production efficiency and reducing energy consumption in the plant beyond what experienced operators can achieve.
We have collaborated with “Preferred Networks”, a leading deep learning company in Japan since 2019. As a result of the collaboration and these endeavors, we have finally succeeded in introducing the AI systems to a Crude Distillation Unit (CDU) and a butadiene extraction unit in our plants. We have achieved continuous usage of them under various operating conditions of the units.
Our AI with deep neural networks learned the intricate relationships between the values of plant sensors and environmental variables, such as ambient temperature and precipitation, enables the prediction of the future values of the sensors and the selection of optimal operations as an alternative to human intervention. Unlike conventional advanced control systems, our AI excels at handling the non-linear dynamics between manipulated and controlled variables, allowing for flexible adaptation to changing operating conditions.
CDU especially requires a high level of skills and experience with operational factors to control and as many as sensors to monitor. The world’s first AI-based continuous autonomous operation of the CDU has been achieved. The AI system for the unit continuously monitors dozens of key operational factors and simultaneously adjusts dozens of valves to stabilize fluctuations resulting from crude oil switching as well as changes in crude oil throughput. The AI system has demonstrated higher stability and efficiency compared with manual operations. Moving forward, we will consider deploying the co-developed AI systems to our other refineries. Moreover, we aim to refine our AI models and investigate their applicability in other industries, expanding our reach beyond our company’s core operations.
