Title Image

Machine Learning: The Truth Behind the Hype

Over the past few years, we have all waded through the sea of articles on machine learning and artificial intelligence. But when it comes to asset performance management, it is tough to understand the truth behind all the hype.

 

What is the Difference Between Machine Learning and Artificial Intelligence?

First, let us start by establishing the difference between machine learning and artificial intelligence. Artificial intelligence is the simulation of human intelligence processes by machines, especially computer systems. Machine learning (ML) is a type of artificial intelligence (AI) that allows software applications to become more accurate at predicting outcomes without being explicitly programmed to do so. Machine learning algorithms use historical data as input to predict new output values.

 

How Does Machine Learning Fit with Asset Performance Management?

In the context of asset performance management technology, it is easy to see where machine learning fits into the software puzzle. But, take a step back. Think about meeting customer needs while simultaneously driving recognizable business value. Then you can see the gaps. When we started Itus Digital, our first step was to understand the market challenges completely. We wanted to base our platform on a practical approach. First, let’s exclude Original Equipment Manufacturers as they are motivated by large parts and services agreements. Now, we can see clearly that machine learning has limited industrial use cases at scale with proven benefits.

For example, we have successfully applied machine learning in certain use cases such as similarity-based modeling, asset tag mapping, and long text mining. However, there is still a significant challenge. To be successful with machine learning, you need to have a clean, golden data set to train the models. Or, you need a large population of similar equipment in the same operating context to produce the data set to train the models. The bottom line is that it’s difficult to build and implement these data sets and models with accuracy.  So, we are very supportive of the technology, but we believe the current hype makes promises that the technology cannot deliver.

 

 

Focus on the Reality and Ignore the Hype

Our point for you is don’t get distracted by the hype around the technology or mathematical approach. Proven engineering approaches are available that mitigate industrial equipment risk through analytics. Also, technology is only one dimension of a solution. For it to create recognizable value, people and processes need to do the driving. Bain & Company wrote this brief, and it is a great reminder to stay focused on the problem you seek to solve. We encourage you to be practical, tailor to the reality of your plant, engage the resources that know the equipment, and retain your independence!

Read Full Bain & Company Briefing

Tags: