“Domain expertise is the secret sauce that separates Industrial AI from more generic AI approaches. Industrial AI will drive innovation and efficiency in capital-intensive industries for years to come,” he said. said Willie K Chan, CTO of AspenTech. Chan was one of the original members of the MIT ASPEN research program that later became AspenTech in 1981, now celebrating 40 years of innovation.
Incorporating that domain competence gives industrial AI applications an integrated understanding of the context, internal operation, and interdependencies of highly complex industrial processes and assets, and takes into account design features, capability limits. , and safety and regulatory guidelines are crucial to reality. global industrial operations.
More generic AI approaches can come with specific correlations between industrial processes and equipment, generating inaccurate insight. Generic AI models are formed on large volumes of plant data that usually do not cover the full range of potential operations. This is because the plant could work in a very narrow and limited range of conditions for safety or design reasons. Consequently, these generic AI models cannot be extrapolated to respond to market changes or business opportunities. This further aggravates production barriers around AI initiatives in the industrial sector.
In contrast, Industrial AI leverages domain-specific experience for real-world industrial processes and engineering based on early principles that take into account the laws of physics and chemistry (e.g. , mass balance, energy balance) as guardrails to mitigate risks and comply with all necessary safety, operational and environmental regulations. This makes a decision-making process safe, sustainable and holistic, producing complete results and reliable insights in the long run.
Digitization in industrial plants is critical to achieving new levels of security, sustainability and profitability — and Industrial AI is a key factor in this transformation.
Industrial AI in action
Talking about Industrial AI as a revolutionary paradigm is one thing; really seeing what it can do in real life industrial environments is another. Below are a few examples that show how capital-intensive industries can leverage Industrial AI to overcome digitalization barriers and drive greater productivity, efficiency and reliability in their operations.
A process plant can implement an advanced class of industrial AI Hybrid models, using deeper collaboration between domain experts and data scientists, machine learning, and early principles for more complete, accurate, and high-performance models. These hybrid models can be used to conceive, operate and optimally maintain the plant’s assets throughout its life cycles. Because they are reliably relevant for a longer period, they also provide a better representation of the plant.
A chemical plant could exploit Industrial AI to deliver real-time returns from integrated on-board industrial data to the cloud, using the Artificial Intelligence of Things (AIoT) to enable agile decision making throughout the organization. Using richer and more dynamic workflows, the supply chain and operations technologies are perfectly matched to detect changes in market conditions and automatically adapt the operating plan and timing in response.
A refinery can use Industrial AI to evaluate thousands of oil production scenarios simultaneously, across a different set of data sources, to quickly identify the optimal crude oil slates to process. Combined with AI-rich capabilities, insights across the company and integrated workflows to improve executive decision making, this approach enables workers to devote their time and efforts to more strategic and valuable activities.
A next-generation industrial plant could apply Industrial AI as the plant’s “virtual assistant” to validate the quality and efficiency of a production plan, in real time. AI-enabled cognitive guidance helps reduce reliance on individual domain experts for complex decision-making, and instead institutionalizes historical decisions and best practices to eliminate barriers to competence.
These use cases are by no means exhaustive, but only a few examples of how ubiquitous, innovative and widely applicable capabilities of Industrial AI can be for the industry and to lay the foundations for the digital plant of the future. .
The digital plan of the future
Industrial organizations need to accelerate the digital transformation to remain relevant, competitive and able to face market disruptions. The self-optimization system represents the ultimate vision of that journey.
Industrial AI incorporates domain-specific skills alongside the latest AI and machine learning capabilities, in applications tailored to AI. This allows and accelerates the autonomous and semi-autonomous processes that manage those operations – realizing the vision of the Automated Station.
A Self-Optimization Plant is a set of self-adapting, self-learning, and self-sufficient industrial software technologies that work together to anticipate future conditions and act accordingly, adapting operations in the digital enterprise. A combination of real-time data access and integrated industrial AI applications allow the User Optimization Self to constantly improve on themselves – basing their domain knowledge to optimize industrial processes, make recommendations easy to execute and automate mission-critical workflows.
This will have numerous positive impacts on the company, including the following:
Limiting carbon emissions caused by disruption of processes and unplanned processes or startups, helping to meet environmental, social and corporate governance objectives. These reduce both production waste and carbon footprint, leading to a new era of industrial sustainability.
Increasing overall safety by significantly reducing hazardous site conditions and reassigning personnel on operations and production plans to safer roles.
Unlock new production efficiencies by exploiting new areas of margin optimization and production stability, even during recessions, for greater profitability.
The self-optimization system is the ultimate goal not only of Industrial AI, but of the digital transformation journey of the industrial sector. By democratizing the application of industrial intelligence, the digital plant of the future will drive higher levels of security, sustainability and profitability and empower the next generation of the digital workforce – the future test of business in conditions of volatile and complex markets. This is the real-world potential of Industrial AI.
To learn more about how Industrial AI enables the digital workforce of the future and creates the foundation for the Self-Optimizing Plant, visit
www.aspentech.com/accelerate, and www.aspentech.com/aiot.
This article was written by AspenTech. It was not produced by the editorial staff of MIT Technology Review.