“Domain expertise is the secret sauce that separates AI from more general AI methods. AI will drive innovation and efficiency improvements in capital-intensive industries for years to come,” said Willie K Chan, AspenTech’s chief technology officer. “AI will drive innovation and efficiency improvements in capital-intensive industries for years to come.” Chan was one of the members The originals were in the MIT ASPEN research program that later became AspenTech in 1981, and is now celebrating 40 years of innovation.
Incorporating this domain expertise gives industrial AI applications an internal understanding of the context, inner workings, and interdependence of highly complex industrial processes and assets, and takes into account design characteristics, capacity limits, and critical safety and regulatory guidelines in real-world industrial operations.
More general AI approaches may find deceptive associations between industrial processes and equipment, generating inaccurate insights. General AI models are trained on large amounts of factory data that typically do not cover the full range of potential operations. This is because the plant may operate within a very narrow and limited range of conditions for safety or design reasons. Thus, these general AI models cannot be extrapolated to respond to market changes or business opportunities. This exacerbates production hurdles around AI initiatives in the industrial sector.
In contrast, AI makes use of domain expertise of real-world industrial processes and engineering based on first principles that observe the laws of physics and chemistry (eg, mass balance and energy balance) as a buffer to mitigate risks and comply with all necessary requirements. Safety, operational and environmental systems. This makes the decision-making process safe, sustainable and inclusive, leading to comprehensive outcomes and reliable long-term insights.
Digitization in industrial facilities is critical to achieving new levels of safety, sustainability and profitability – and artificial artificial intelligence is a key enabler of this transformation.
Artificial intelligence at work
Talking about artificial intelligence as a revolutionary model is one thing; In fact, seeing what you can do in real-world industrial environments is another thing. Here are some examples that show how capital-intensive industries can take advantage of artificial intelligence to overcome the barriers of digitization and increase productivity, efficiency and reliability in their operations.
Processing plant may deploy advanced class of artificial intelligence Hybrid models, drawing on deeper collaboration between domain experts and data scientists, machine learning, and first principles for more comprehensive, accurate, and performing models. These hybrid models can be used to optimally design, operate and maintain plant assets across their life cycles. Since they are relevant for a longer period of time, they also provide a better representation of the plant.
A chemical plant can leverage artificial AI to produce real-time insights from integrated industrial data from the edge to the cloud, using Artificial Intelligence of Things (AIoT) To enable rapid decision making throughout the organisation. Richer and more dynamic workflow, supply chain, and operations technologies are seamlessly linked together to detect changes in market conditions and automatically adjust operating plan and schedule in response.
A refinery can use AI to simultaneously assess thousands of oil production scenarios, across a variety of data sources, to quickly identify optimal crude oil slabs for processing. Combined with the rich capabilities of AI, enterprise-wide insights, and integrated workflows to improve executive decision-making, this approach enables workers to allocate their time and efforts to more strategic and valuable tasks.
The next generation industrial facility can apply artificial intelligence as the “virtual assistant” of the plant to check the quality and efficiency of the production plan, in real time. AI-powered cognitive guidance ultimately helps reduce reliance on individual domain experts to make complex decisions, and instead institutionalizes historical decisions and best practices to remove expertise barriers.
These use cases are by no means exhaustive, but are just a few examples of how widespread, innovative and applicable AI capabilities are in the industry and to lay the foundation for the digital factory of the future.
The digital factory of the future
Industry organizations need to accelerate digital transformation to stay relevant, competitive and able to tackle market disruptions. The Self Improvement Station represents the ultimate vision of that journey.
Artificial AI integrates domain-specific know-how along with the latest capabilities of AI and machine learning, into fit-for-purpose applications that support AI. This enables and accelerates the autonomous and semi-autonomous processes that manage those processes – achieving the vision of a self-improvement plant.
A self-improvement factory is a set of self-adapting, self-learning, and self-sustaining industrial software technologies that work together to anticipate future conditions and act accordingly, modifying processes within a digital enterprise. A combination of real-time data access and embedded industrial AI applications enable the self-improvement plant to continually improve itself — drawing on industry knowledge to improve industrial processes, make easy-to-implement recommendations, and automate critical workflows.
This will have many positive effects on the business, including the following:
Reducing carbon emissions from operational disruptions, unplanned shutdowns or start-ups, helping to achieve the company’s environmental, social and governance goals. This reduces production waste and carbon footprint, leading to a new era of industrial sustainability.
Enhance public safety by significantly reducing hazardous site conditions and redeploying personnel in operations and production departments to safer roles.
Unleashing new production efficiencies by leveraging new areas of margin improvement and production stability, even during downturns, for greater profitability.
Self-improvement factory is the ultimate goal of not only AI, but the journey of digital transformation of the industrial sector. By democratizing the application of artificial intelligence, the Digital Factory of the Future drives higher levels of security, sustainability, and profitability and empowers the next generation of the digital workforce – proving business to the future in volatile and complex market conditions. This is the real potential of artificial intelligence.
To learn more about how AI will enable the digital workforce of the future and create the foundation for a self-improvement factory, visit
www.aspentech.com/accelerate, And the www.aspentech.com/aiot.
This article was written by AspenTech. It was not produced by the editorial staff of the MIT Technology Review.