Before plant managers implement an AI-driven approach, they must take a number of steps starting with meeting the infrastructure needs of AI.
Artificial intelligence promises to go a long way in automating and enhancing the monitoring capabilities of sensors and process controls that power today’s process industrial plants. However, a recent analysis out of McKinsey finds the advancement of AI is still very much a work in progress for these sites. So, the AI-driven factory is still on the horizon.
At this point, only 10% of these plants, ones that employ process manufacturing to produce chemicals, fuels, and other ingredients, use AI to “describe, predict, and inform process decisions,” the McKinsey team finds. They foresee, however, more plants moving toward building “data-driven advanced models to drive performance in complex systems.”
For starters, there is advance work that needs to pave the way for an AI-driven factory. “Sensor and process control upgrades are often necessary to enable the deployment of AI,” the report’s team of authors, led by Nathan Flesher, find.
See also: Lights-Out Factories? Not Quite Ready for Prime Time
A quantitative assessment of readiness is an important first step, but greater alignment is needed. In terms of sensors and instrumentation, “75% of plants have instrumentation in place that controls critical process variables — density, mill power, etc. — and only 70% of these instruments are properly calibrated and catalogued,” they conclude.
Process plants employ a tiered system of control systems, topped off by advanced process controls (APCs), which oversee base-layer controllers, such as programable logic controllers, proportional integrative derivatives, or distributed control systems. “In this way, APCs facilitate the optimization of these systems, providing standalone strategies and helping to connect advisory systems at the top with the systems and subsystems below,’ the McKinsey team states.
The challenges are the value of adding additional sensors or APCs may be hard to cost-justify, and, often, “data or process automation teams want to install sensors indiscriminately, without a plan to link to value creation.”
At this point, only 34% of plants have installed APC systems for crucial unit operations, and use of those APCs is only 63%; more plants would benefit from installing APCs and using them for better process control. To complicate matters further, only 18% of plants have dedicated IT teams that support deploying and scaling AI solutions.
Before plant managers implement an AI-driven approach, it’s important to take the following steps:
- Focus on developing “a full-time dedicated team within the IT department to drive the deployment of AI solutions.”
- “Increase sensor coverage, and focus on calibrating and cataloging installed instruments.”
- “Improve use of installed APCs, and increase coverage of APCs for crucial unit operations.”
- “Use advisory models to describe, predict, and inform process decisions.”
- “Build dedicated IT and operational technology teams for AI deployment and upskilling on agile, digital, and analytical skills.”
- “Incorporate a change management strategy to embed AI solutions, and invest in capability building and talent development.”
