How Industrial Automation and AI Deliver Beyond Human Limits

This year marks the fiftieth birthday for a Japanese technology which has transformed industrial plants operations. CENTUM^TM, the world’s first distributed control system (DCS) created by Yokogawa Electric, was released in 1975. 

In 2012, its first-generation system was registered, alongside other paradigm-shifting innovations such as the Walkman and LCD-equipped digital camera, as “an essential historical material for science and technology” by the Japanese National Museum of Nature and Science for its significant impact.^[1]

Though the compact audio player and digital camera have essentially been replaced by smartphones, CENTUM remains current and vital. Now into its 10^th generation, some 30,000 CENTUM systems have been deployed in more than 100 countries around the world, making it a market leader for DCSs. Such systems are generally used in the oil and gas, petrochemicals, chemicals, steel, pulp and paper, electric power, and water treatment industries.^[2]

Countless plants continue to depend on Yokogawa’s “reliability, stability and continuity” in control as embodied by the CENTUM.

Today’s industry, however, faces different challenges from when CENTUM was born.

Half a century ago, there was little notion of climate change, green transition or a circular economy. Though computers had begun to be used in plants (CENTUM was among the first to adopt microprocessors), it was a world without internet, digital mobile and wireless technology, cloud, AI or machine learning. Workforces, at least in the West and Japan, were younger and larger. Supply chains were mostly shorter and less complex, less vulnerable to global-level disruption as they are today.

Under these contexts, companies are expected to deliver ever higher productivity and resilient production in the face of greater globalized competition. Resource use and carbon emissions must be tracked and minimized across the production chain.^[3]  Cybersecurity challenges must be met, even as digital transformation needs to be accelerated.^[4] 

There are also concerns about how industries can pass on the know-how of seasoned plant operators and veteran workers in the face of a “great crew change,” i.e. challenges of a shrinking skilled workforce due to retirement and lack of new workers.^[5]  Increasingly complex, round-the-clock plant operations also threaten to overburden existing workers.^[6]

In other words, manufacturers need to “optimize for increased productivity, improved sustainability, greater resilience and a stronger workforce,” according to a survey by the World Economic Forum and Boston Consulting Group.^[7] 

Their white paper – “Industries in the Intelligent Age” – argues that AI and automation in industry will help meet these challenges, greatly lifting productivity and competitiveness, while freeing personnel to focus on creativity, oversight and decision-making.^[8] In the report’s survey, 89% of companies see AI as highly relevant to industrial operations and plan to adopt it into their production networks. In fact, AI is already boosting production efficiency, with early adopters reporting an average 14% savings on manufacturing costs, according to the report.

CENTUM is at the heart of these developments of capturing the benefits of automation and AI for industry. The latest 10^th-generation of CENTUM features expanded scope of control and monitoring, predictive monitoring and ability to reduce operator workload. It also has greater cybersecurity features and can deliver AI-driven plant operations which leverage the knowhow of plant operators.^[9]

“In this era of greater volatility, uncertainty, complexity and ambiguity, the conditions required for manufacturing sites and management are becoming ever more complex,” says Mitsuhiro Yamamoto, Vice President of Yokogawa Electric. “By realizing stable operations and expanding the scope of autonomy, CENTUM VP Release 7 will help our customers achieve a more sustainable society and sustainable business growth.”^[10]

Yokogawa has already demonstrated in different domains how industrial Al can deliver.

In 2022, together with the former elastomers business unit of JSR Corporation (now part of ENEOS Materials Corporation), Yokogawa deployed the reinforcement learning-based Al algorithm called Factorial Kernel Dynamic Policy Programming (FKDPP), which 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. In JSR's chemical plant, Yokogawa achieved a world's first by integrating the AI with CENTUM to autonomously and safely control a plant for 35 days, stabilizing quality, achieving high yields, and saving energy.^[11]

Yokogawa's Al solution continued to control the operations at the industrial facility to produce a raw material used in synthetic rubber, and after a year-long trial this reinforcement-learning-based Al was officially adopted, another world’s first. FKDPP is used to automate valve operations and has brought about decreased operator workload, eliminated the production of off-spec products, and reduced steam usage and CO2 emissions by 40%, thereby saving energy and reducing costs.^[12] The AI solution has ensured stable operations for almost three years since its deployment.

Building on this success, in 2025 Yokogawa deployed multiple, coordinated autonomous control AI agents of FKDPP at the Fadhili Gas Plant operate by Aramco, one of the world’s leading integrated energy and chemicals companies. The AI solution directly and autonomously controls and optimizes acid gas removal (AGR) operations at the plant to reduce energy and chemical usage.^[13]

These use-cases are further steps towards Yokogawa’s vision of “autonomous operations”, a world where control systems autonomously perform operations and free operators from repetitive or burdensome tasks so they can focus on creating new value, by merging human experiential knowledge with AI technology.

Fifty years since the first distributed control system was introduced, a future of plant operations performing beyond human limits while further unlocking human potential is now unfolding.

Sources

[1] Yokogawa  [2] Yokogawa  [3] World Economic Forum  [4] World Economic Forum  [5] S&P Global  [6] Yokogawa  [7] BCG  [8] World Economic Forum  [9] Yokogawa  [10] Yokogawa  [11] Yokogawa  [12] Yokogawa  [13] Yokogawa