Tokyo, Japan - May 30, 2022
Yokogawa Electric Corporation
NTT DOCOMO INC.
Yokogawa Electric Corporation (TOKYO: 6841) and NTT DOCOMO, INC. (DOCOMO) announced today that they have conducted a proof-of-concept test (PoC) of a remote control technology for industrial processing. The PoC test involved the use in a cloud environment of an autonomous control AI, the Factorial Kernel Dynamic Policy Programming (FKDPP) algorithm*1 developed by Yokogawa and the Nara Institute of Science and Technology, and a fifth-generation (5G) mobile communications network provided by DOCOMO. The test, which successfully controlled a simulated plant processing operation, demonstrated that 5G is suitable for the remote control of actual plant processes.
The trend to locate production facilities in remote and/or hazardous areas in recent years is fueling a growing demand for remote industrial operations and transforming how people work. Meanwhile, equipment used in plants to purify and refine resources and materials for essential products can deteriorate after many years of use, so remote, autonomous regulation and control would be hugely beneficial. One possible solution is to install edge devices equipped for high-speed wireless communications at plants and employ cloud-based autonomous control AI to control the equipment dynamically. Yokogawa has already proven that its FKDPP algorithm is a feasible autonomous control AI solution. In a field test at a chemical plant*2 this past February, for 35 days FKDPP successfully controlled processes known to be difficult to automate using existing PID*3 and APC*4 control technologies, and which therefore had been performed manually. The combination of FKDPP and the cloud with 5G, which offers low latency and the capability to connect a large number of devices, promises to be a core technology for achieving industrial autonomy.
Following an agreement between Yokogawa and DOCOMO announced on April 14, 2021, the demonstration test was conducted to verify whether a three tank level control system*5 could be controlled using FKDPP in the cloud via a 5G network. A target water level was set, tests with low- to high-speed control cycles were conducted, and the effects of mobile-communications latency on FKDPP control were confirmed. Compared to 4G, the test demonstrated that especially with high-speed control 5G delivers 1) lower latency, 2) less overshoot relative to the target water level, and 3) is capable of handling a control cycle as short as 0.2 seconds, thereby achieving better control for more stable quality and higher energy efficiency.
Envisioned future application of 5G, cloud, and AI for industrial autonomy
Yokogawa, which has been advocating the concept of industrial automation to industrial autonomy (IA2IA) since 2019, aims to apply 5G technology for remote plant control. In collaboration with DOCOMO and customers, it will continue carrying out advanced initiatives aimed at facilitating a shift toward industrial autonomy.
DOCOMO is continuing to enhance and evolve its network technologies, create advanced networks tailored to the needs of specific customers, and develop 5G solutions for diverse public and private purposes.
Both Yokogawa and DOCOMO, as members of the 5G Alliance for Connected Industries and Automation (5G-ACIA), which is pursuing industrial applications for 5G, will continue to evaluate the use of 5G for remote, autonomous plant operations. By carrying out demonstrations in a wide range of customers' plants and examining communications reliability and latency-related issues during long-term use, the companies will strive to achieve 5G and AI-enabled autonomous control. The 5G-ACIA will present the results of this demonstration test at Hannover Messe 2022*6, between May 30 and June 2.
Comments from the Companies
Kenji Hasegawa, Vice President and Head of the Yokogawa Products Headquarters at Yokogawa Electric Corporation:
“Our autonomous control AI can be used not only in the process industry, but also for certain processes in factory automation, such as heating processes. It can be used in areas where existing control technologies cannot be applied, can achieve shorter settling times compared to existing technologies, and prevent overshoot. In general, the tangible benefits included improved productivity and contribution to a more sustainable society. By linking information on production, inventory, demand, and other matters with the cloud-based autonomous control AI, it will be possible to align management directives with the actual control of operations on the plant floor. Although wireless communications have been used in plants, this innovation uses 5G for cloud-based autonomous control AI. By carrying out this cutting-edge initiative in collaboration with DOCOMO and our customers, we will lead the shift to industrial autonomy.”
Hisakazu Tsuboya, Senior Vice President and General Manager of the 5G & IoT Business Department at NTT DOCOMO:
“DOCOMO is helping to transform the industrial sector with cutting-edge technologies and diverse mobile solutions. The demonstration has shown that low-latency 5G communications helps to improve the accuracy of remote-control operations in plants, which is expected to contribute significantly to sustainable productivity for processing and other types of manufacturing. DOCOMO, together with Yokogawa and partners, will continue to develop 5G and other mobile communications environments for diverse worksites in processing industries in order to overcome challenges and create new value.”
*1 The FKDPP AI algorithm, which uses reinforcement learning technology, can be applied to all kinds of control applications, including those that cannot be automated with existing control methods such as PID control or APC, to achieve conventionally challenging simultaneous goals, such as high quality and energy efficiency (see attachment for details).
*2 See press release (In a World First, Yokogawa and JSR Use AI to Autonomously Control a Chemical Plant for 35 Consecutive Days: https://www.yokogawa.com/news/press-releases/2022/2022-03-22/)
*3 Proportional-Integral-Derivative control, first proposed by Nicolas Minorsky in 1922, is an infrastructure-control technology for processing industries that is used to control items such as quantity, temperature, level, pressure, and ingredients. It implements control aimed at target values based on P, I and D calculations according to deviations between current and set values. In some cases, due to the characteristics of the mathematical expression, a value might exceed (overshoot) the set value or take time to settle to avoid overshoot.
*4 Advanced Process Control uses a mathematical model to predict process responses and supply set values to the PID control loop in real time in order to improve productivity, quality, and controllability. It is easily applied for control to increase production, reduce labor time, and save energy. APC results in smaller deviations in data, making it possible to more closely approach the limits of operating performance (i.e., optimal performance), but it is not adept at responding to the rapid vaporization of fluids, similar chemical reactions, major changes in material composition, and changes in machinery.
*5 A three tank level control system that is used for training and experiments involving the regulation of water flow from one level to the next with the aim of controlling the water level at the lowest tank.
*6 One of the world's largest international manufacturing exhibitions, which attracted some 6,500 companies and 220,000 people in 2019. https://www.hannovermesse.de/en/
Yokogawa provides advanced solutions in the areas of measurement, control, and information to customers across a broad range of industries, including energy, chemicals, materials, pharmaceuticals, and food. Yokogawa addresses customer issues regarding the optimization of production, assets, and the supply chain with the effective application of digital technologies, enabling the transition to autonomous operations.
Founded in Tokyo in 1915, Yokogawa continues to work toward a sustainable society through its 17,500 employees in a global network of 119 companies spanning 61 countries.
For more information, visit www.yokogawa.com
About NTT DOCOMO
NTT DOCOMO, Japan's leading mobile operator with over 83 million subscriptions, is one of the world's foremost contributors to 3G, 4G and 5G mobile network technologies. Beyond core communications services, DOCOMO is challenging new frontiers in collaboration with a growing number of entities ("+d" partners), creating exciting and convenient value-added services that change the way people live and work. Under a medium-term plan toward 2020 and beyond, DOCOMO is pioneering a leading-edge 5G network to facilitate innovative services that will amaze and inspire customers beyond their expectations. https://www.docomo.ne.jp/english/
The names of corporations, organizations, products, services and logos herein are either registered trademarks or trademarks of Yokogawa Electric Corporation, NTT DOCOMO Inc., or their respective holders.
Overview of PoC
1. Purpose of PoC test
The test confirmed the range of operations that can be controlled with a cloud-based autonomous control AI via a 5G mobile network. Control performance using separate 4G and 5G communications was compared in terms of latency and throughput (amount of data sent and received in a fixed period).
|Control target||Water level in a three tank level control system|
|AI||Autonomous control AI (FKDPP algorithm)|
|Period of PoC test||April 14, 2021 to April 26, 2022|
3. Roles of each company
It was confirmed that, compared to 4G, 5G offers (1) lower latency and (2) enables control operations to be performed with less overshoot, especially when using high-speed control. It was also confirmed that (3) operation is possible within a control cycle as short as 0.2 seconds. Overall, 5G can achieve better control and contribute to more stable quality and higher energy efficiency.
5. About the autonomous control AI (FKDPP algorithm)
The AI used in this demonstration test was the Factorial Kernel Dynamic Policy Programming (FKDPP) algorithm, which was jointly developed by Yokogawa Electric Corporation and the Nara Institute of Science and Technology (NAIST) in 2018. It was recognized by the IEEE as being the first reinforcement learning-based AI in the world that can be utilized in plant management*1.
FKDPP provides the following key benefits:
- Can be used for all kinds of control, including applications that cannot be automated with existing control methods (PID control or APC), enabling engineers to achieve complicated goals that conventionally have been difficult to achieve simultaneously, such as high quality and energy efficiency.
- Improves productivity in terms of higher quality, better energy efficiency, higher yield, and shorter settling time.
- Simple, because it requires less learning and does not require load-labeled data.
- Is relatively easy to explain how the AI works.
- Achieves the same level of safety as conventional systems (very robust and can be integrated with existing production control systems).
In April 2020, Yokogawa used a simulation model*2 to confirm that its autonomous control AI has the potential to control an entire plant. In the same year, in an exhibit at Measurement Exhibition 2020 OSAKA (hosted by the Japan Electric Measuring Instruments Manufacturers' Association), the company demonstrated how this AI can autonomously control a three tank level control system. Although the system can be controlled with conventional PID control technology, it was shown that FKDPP can reduce the settling time by 30% to 50% while also preventing overshoot. In February 2022, Yokogawa successfully used the technology to control an actual chemical plant for 35 consecutive days, a world's first.
*1 Factorial Kernel Dynamic Policy Programming for Vinyl Acetate Monomer Plant Model Control (August 2018) https://ieeexplore.ieee.org/document/8560593/ The Institute of Electrical and Electronics Engineers (IEEE) is an academic research group and technology standardization institution for electric engineering, headquartered in the United States with more than 400,000 members in more than 160 countries.
*2 Scalable Reinforcement Learning for Plant-wide Control of Vinyl Acetate Monomer Process, Control Engineering Practice, Volume 97 (April 2020) https://www.sciencedirect.com/science/article/pii/S0967066120300186
We have been solving customers’ issues in many industries using our AI. Utilizing our analysis experience and elemental technologies, we can offer a lineup of easy-to-use AI products. AI functions such as predictive detection and future prediction can be easily applied, and operation efficiency is improved.