AI in manufacturing: How to run longer, run better and keep relevant

Imagine if you could anticipate equipment service needs in advance, accurately, and spend time only servicing the equipment that needs it when it needs it. Imagine, too, if you could make smarter production design decisions that optimize the overall manufacturing process.

You can, with data you already have, by leveraging it using artificial intelligence (AI).

Why AI?

You may have heard the terms analytics, advanced analytics, machine learning and AI. Let’s clarify:

  • Analytics is the ability to record and playback information. If you attach a sensor to equipment, you can record uptime and calculate availability.
  • Analytics becomes advanced analytics when you write algorithms to search for hidden patterns. What equipment characteristics are correlated with high availability?
  • Machine learning is when the algorithm gets better with experience. The algorithm learns, from examples, to predict equipment availability.
  • AI is when a machine performs a task that human beings find interesting, useful and difficult to do. Your system is artificially intelligent if, for example, machine-learning algorithms predict equipment failure and adjust production in anticipation.

If you’re in manufacturing, here’s how to make sense of the terms analytics, advanced analytics, machine learning and AI. Click image to expand.

AI is often built from machine-learning algorithms, which owe their effectiveness to training data. The more high-quality data available for training, the smarter the machine will be. The amount of data available for training intelligent machines has exploded. According to an article on Forbes.com, by 2020 every human being on the planet will create about 1.7 megabytes of new information every second. According to IDC, information in enterprise data centers will grow 14-fold between 2012 and 2020.

And we are far from putting all this data to good use. Research by McKinsey’s Global Institute suggests that, as of 2016, manufacturers typically capture only 20 to 30 percent of the value of their data. AI is how you capture that remaining 70 to 80 percent. Here’s what it looks like when you use AI and put your data to better use.

Here’s what it looks like when you apply industrialized AI in manufacturing. Click image to expand.

You keep running

According to a study by the McKinsey Global Institute, about 60 percent of wasted expenses in manufacturing come from unnecessary operation and maintenance. Scheduled maintenance wastes time fixing machines that may not be broken. You service equipment on a regular basis, whether it’s needed or not.

AI can learn to predict equipment failure. With predictive maintenance, you anticipate failure and spend time only on equipment that needs service. You waste less on unnecessary maintenance and your plant stays running longer.

You keep commitments

If you are going to run longer, why not also run better? Hidden inside the records of equipment performance, production yield and safety incidences are patterns of insight. AI can predict overall equipment effectiveness, production quality and even safety risk. This intelligence makes it easier to spot ways to improve production. The McKinsey Global Institute found that, with applied AI, manufacturers have the potential to increase delivery reliability by 20 to 30 percent. Your production runs smoother and, as a result, you do a much better job of keeping your customer commitments.

You keep lean

Making good manufacturing design decisions keeps you lean. The McKinsey Global Institute found that 80 percent of manufacturing costs are affected by decisions made in the design phase. AI can augment production design decisions by narrowing your choices to only those options that will optimize your staff allocation, supply chain performance and production plans. You cut costs by eliminating wasteful practices from consideration.

You keep relevant

Competition can come from anywhere, but good industrial design sets you apart. A study by the National Endowment for the Arts found that design-led manufacturers enjoy a nine percent higher job growth rate than their peers. Design innovation comes down to agility — the ability to spot opportunities and act on them quickly. Manufacturing simulation automates the search for new designs. Real-time production and supply chain planning lets you react quickly. The McKinsey Global Institute found that applied AI has the potential to decrease the time it takes manufacturers to discover and act on innovation by 50 percent. You stay relevant by finding good industrial design ideas and acting on them quickly.

Applied AI is a differentiator

If you see AI as technology, it makes sense to build solutions according to standard systems engineering practices: Build an enterprise data infrastructure; ingest, clean, and integrate all available data; implement basic analytics; build advanced analytics and AI solutions. This approach takes a while to get to ROI.

But AI can mean competitive advantage. When AI is seen as a differentiator, the attitude toward AI changes: Run if you can, walk if you must, crawl if you have to. Find an area of the business that you can make as smart as possible as quickly as possible. Identify the data stories (like predictive maintenance or design simulation) that you think might make a real difference. Test your ideas using utilities and small experiments. Learn and adjust as you go.

It helps immensely to have a strong Analytics IQ — a sense for how to put smart machine technology to good public use. We’ve built a short assessment designed to show where you are and practical steps for improving. If you’re interested in applying AI to manufacturing and are looking for a place to start, take the Analytics IQ assessment.

See more of Jerry Overton’s thoughts in Wired Magazine: Welcome to the Age of AI-Based Super Assistants.


Jerry Overton is a data scientist and senior principal in DXC Technology’s Analytics group. He leads the strategy and development for DXCs Advanced Analytics, Artificial Intelligence and Internet of Things offerings.

Jerry is the author of the O’Reilly Media ebook, Going Pro in Data Science: What It Takes to Succeed as a Professional Data Scientist. He teaches the Safari Live Online training course “Data Science at Enterprise Scale.” @JerryAOverton

RELATED LINKS

How to get started with machine learning in manufacturing

Raising your Analytics IQ

Thriving on Enterprise Data and Analytics

 

 

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: