NARA Institute of Science and Technology
Canvas Category Consultancy : Research : Academic
Nara Institute of Science and Technology (NAIST) is a Japanese national university located in Kansai Science City, a border region between Nara, Osaka, and Kyoto. Founded in 1991, NAIST consisted of graduate schools in three integrated areas: information science, biological sciences, and materials science. In 2018, NAIST underwent an organizational transformation to continue research in these areas while promoting interdisciplinary research and education across traditional fields. With this new single graduate school organization, NAIST strives forward with the objectives of conducting cutting-edge research in frontier areas and training students to become tomorrow’s leaders in science and technology.
Assembly Line
Bayesian optimization of radical polymerization reactions in a flow synthesis system
Proportions of monomers in a copolymer will greatly affect the properties of materials. However, due to a phenomenon known as composition drift, the proportions of monomers in a copolymer can deviate from the value expected from the raw monomer ratio because of differences in monomer reactivity. It is therefore necessary to optimize the polymerization process to account for such composition drift. In the present study, styrene-methyl methacrylate copolymers were generated using a flow synthesis system and the processing variables were tuned employing Bayesian optimization (BO) to obtain a target composition. First trials of BO with generation of four candidate points per cycle, completed the optimization within five cycles. Subsequent Bayesian Optimization (BO) trial, using 40 points per cycle, identified several sets of processing conditions that could achieve the desired copolymer composition, accompanied by variations in other physical properties. To optimize the monomer composition ratio in the polymer, it was discovered from a data science perspective that the solvent-to-monomer ratio was as crucial as the styrene proportions. The role of each variable in the radical polymerization reaction was elucidated by assessing the extensive array of processing conditions while evaluating several broad trends. The proposed model confirms that specific monomer proportions can be produced in a copolymer using machine learning while investigating the reaction mechanism. In the future, the use of multi-objective BO to fine-tune the processing conditions is expected to allow optimization of the copolymer composition together with adjustment of physical properties.
Yokogawa and DOCOMO Successfully Conduct Test of Remote Control Technology Using 5G, Cloud, and AI
Yokogawa Electric Corporation and NTT DOCOMO, INC. 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 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.
In a World First, Yokogawa and JSR Use AI to Autonomously Control a Chemical Plant for 35 Consecutive Days
Yokogawa Electric Corporation (TOKYO: 6841) and JSR Corporation (JSR, TOKYO: 4185) announce the successful conclusion of a field test in which AI was used to autonomously run a chemical plant for 35 days, a world first. This test confirmed that reinforcement learning AI can be safely applied in an actual plant, and demonstrated that this technology can control operations that have been beyond the capabilities of existing control methods (PID control/APC) and have up to now necessitated the manual operation of control valves based on the judgements of plant personnel. The initiative described here was selected for the 2020 Projects for the Promotion of Advanced Industrial Safety subsidy program of the Japanese Ministry of Economy, Trade and Industry.
The AI used in this control experiment, the Factorial Kernel Dynamic Policy Programming (FKDPP) protocol, was jointly developed by Yokogawa and the Nara Institute of Science and Technology (NAIST) in 2018, and was recognized at an IEEE International Conference on Automation Science and Engineering as being the first reinforcement learning-based AI in the world that can be utilized in plant management.
Given the numerous complex physical and chemical phenomena that impact operations in actual plants, there are still many situations where veteran operators must step in and exercise control. Even when operations are automated using PID control and APC, highly-experienced operators have to halt automated control and change configuration and output values when, for example, a sudden change occurs in atmospheric temperature due to rainfall or some other weather event. This is a common issue at many companies’ plants. Regarding the transition to industrial autonomy, a very significant challenge has been instituting autonomous control in situations where until now manual intervention has been essential, and doing so with as little effort as possible while also ensuring a high level of safety. The results of this test suggest that this collaboration between Yokogawa and JSR has opened a path forward in resolving this longstanding issue.
Scalable reinforcement learning for plant-wide control of vinyl acetate monomer process
This paper explores a reinforcement learning (RL) approach that designs automatic control strategies in a large-scale chemical process control scenario as the first step for leveraging an RL method to intelligently control real-world chemical plants. The huge number of units for chemical reactions as well as feeding and recycling the materials of a typical chemical process induces a vast amount of samples and subsequent prohibitive computation complexity in RL for deriving a suitable control policy due to high-dimensional state and action spaces. To tackle this problem, a novel RL algorithm: Factorial Fast-food Dynamic Policy Programming (FFDPP) is proposed. By introducing a factorial framework that efficiently factorizes the action space, Fast-food kernel approximation that alleviates the curse of dimensionality caused by the high dimensionality of state space, into Dynamic Policy Programming (DPP) that achieves stable learning even with insufficient samples. FFDPP is evaluated in a commercial chemical plant simulator for a Vinyl Acetate Monomer (VAM) process. Experimental results demonstrate that without any knowledge of the model, the proposed method successfully learned a stable policy with reasonable computation resources to produce a larger amount of VAM product with comparative performance to a state-of-the-art model-based control.