A Machine Learning Agorithm Walks into a Bar…

A Machine Learning Algorithm Walks into a Bar…

Have you heard the joke about the machine learning algorithm that walks into the bar?

The bartender asks, “What’ll you have?”

The algorithm says, “What’s everyone else having?”

Machine-Learning in Asset Performance Management

This joke is not genuinely characteristic of machine-learning in asset performance management (APM) applications. But it does highlight the role of data modeling and analytics in improving equipment performance. Machine-learning algorithms use statistics to find patterns in massive amounts of data. How are we defining data? It is many things—numbers, words, images, clicks; if you can digitally store it, you can feed it into a machine-learning algorithm. Further, as a branch of artificial intelligence, machine learning algorithms build a model based on sample data, known as “training data,” to make predictions or decisions.

Industrial assets have widely varied designs, functional expectations, and operating contexts. So, making a broad application of any given algorithm is difficult.  If you are not careful in your analytic design, you may run the risk of getting “what everyone else is having” for all your equipment.

The Role of Asset Strategy

For a machine-learning or deterministic algorithm to succeed, it must be underpinned by an asset strategy. Otherwise, it is only detecting a data anomaly which is just one aspect of accurately predicting asset performance. Asset strategies define how equipment can potentially fail, what to monitor/maintain to prevent failure, and determine what action to take when a failure risk is detected.  The asset strategy is a critical success factor for any software algorithm to be effective. It brings the core business, engineering, and operational context to whatever mathematical approach you use to automate and scale equipment failure management efforts.

To learn more about how Itus Digital has approached Asset Performance Management, take a look at the recent ARC view by Paula Hollywood, Senior Analyst at ARC Advisory group @  ARC Advisory Group – Itus Digital –  ARC View