“Domain expertise is the secret sauce that separates industrial AI from more generic AI approaches. Industrial AI will guide innovation and improved efficiency in capital-intensive industries for years to come, ”said Willie K Chan, CTO of AspenTech. Chan was one of the original members of the MIT ASPEN research program which later became AspenTech in 1981, now celebrating 40 years of innovation.
The integration of this domain expertise gives industrial AI applications an integrated understanding of the context, inner workings and interdependencies of highly complex industrial processes and assets, and takes into account design features, capacity limitations. and the crucial safety and regulatory guidelines for reality. global industrial operations.
More generic AI approaches can result in specious correlations between industrial processes and equipment, generating inaccurate information. Generic AI models are trained on large volumes of factory data that typically does not cover the full range of potential operations. This is because the plant can operate in a very narrow and limited range of conditions for safety or design reasons. Therefore, these generic AI models cannot be extrapolated to respond to market changes or business opportunities. This further exacerbates the production barriers around AI initiatives in the industrial sector.
In contrast, industrial AI relies on domain expertise specific to industrial processes and real-world engineering based on first principles that take into account the laws of physics and chemistry (e.g. balance sheet energy balance) as a safeguard to mitigate risk and comply with all necessary requirements. safety, operating and environmental regulations. This enables a safe, sustainable and holistic decision-making process, producing comprehensive results and long-term reliable information.
Digitization in industrial facilities is essential to achieve new levels of safety, sustainability and profitability, and industrial AI is a key driver of this transformation.
Industrial AI in action
Talking about industrial AI as a revolutionary paradigm is one thing; actually seeing what it can do in real industrial environments is another. Below are a few examples that show how capital-intensive industries can leverage industrial AI to overcome barriers to digitalization and increase the productivity, efficiency and reliability of their operations.
A processing plant can deploy an advanced class of industrial AI enabled Hybrid models, relying on deeper collaboration between domain experts and data scientists, machine learning and first principles for more complete, precise and efficient models. These hybrid models can be used to optimally design, operate and maintain plant assets throughout their lifecycle. Because they are reliably relevant for a longer period of time, they also provide a better representation of the plant.
A chemical plant could leverage industrial AI to gain real-time insights from industrial data integrated from the edge to the cloud, using the Artificial Intelligence of Objects (AIoT) to enable agile decision making across the organization. Through richer and more dynamic workflows, supply chain and operations technologies are seamlessly linked to detect changes in market conditions and automatically adjust the operating plan and schedule accordingly.
A refinery can use industrial AI to simultaneously assess thousands of oil production scenarios, across a diverse set of data sources, to quickly identify optimal crude oil slates for processing. Combined with AI-rich capabilities, company-wide insights, and integrated workflows to improve executive decision-making, this approach empowers workers to dedicate their time and effort to more strategic and value-creating tasks.
A next-generation industrial facility could use industrial AI as a factory “virtual assistant” to validate the quality and efficiency of a production plan, in real time. AI-based cognitive orientation ultimately helps reduce reliance on individual domain experts for complex decision-making, and instead institutionalizes historical decisions and best practices to remove barriers to business. expertise.
These use cases are by no means exhaustive, but are just a few examples of how industrial AI capabilities can be ubiquitous, innovative, and widely applicable for industry and for laying the groundwork for the factory. digital future.
The digital factory of the future
Industry organizations need to accelerate digital transformation to remain relevant, competitive and able to cope with market disruptors. The self-optimized factory represents the ultimate vision of this journey.
Industrial AI integrates domain-specific know-how alongside the latest AI and machine learning capabilities, in AI-enabled applications. This enables and accelerates the autonomous and semi-autonomous processes that perform these operations, thus realizing the vision of the self-optimized factory.
A Self-Optimized Factory is a collection of self-adapting, self-learning, and self-sustaining industrial software technologies that work together to anticipate future conditions and act upon them, adjusting operations within the digital enterprise. A combination of real-time data access and integrated industrial AI applications enables the self-optimization factory to constantly improve, leveraging domain knowledge to optimize industrial processes, make easy-to-execute recommendations and automate critical workflows.
This will have many positive impacts on the business, including:
Reduce carbon emissions caused by process disruptions and unplanned shutdowns or starts, helping to meet corporate environmental, social and governance goals. This reduces both production waste and carbon footprint, ushering in a new era of industrial sustainability.
Strengthening overall safety by dramatically reducing unsafe site conditions and reassigning operations and production floor personnel to more secure roles.
Unlock new production efficiencies by tapping into new areas of margin optimization and production stability, even in times of downturn, for increased profitability.
The self-optimized factory is the ultimate goal of not only industrial AI, but also the digital transformation journey of the industrial sector. By democratizing the application of industrial intelligence, the digital factory of the future generates higher levels of safety, sustainability and profitability and enables the next generation of digital workforce to sustain the business in volatile and complex market conditions. This is the real potential of industrial AI.
To learn more about how industrial AI enables the digital workforce of the future and lays the foundation for the self-optimization factory, visit
www.aspentech.com/accelerate, and www.aspentech.com/aiot.
This article was written by AspenTech. It was not produced by the MIT Technology Review editorial team.