Guest Editorial
Predictive Maintenance
How will machine learning impact industrial manufacturing?

he technological advancements of the past couple of decades make it easy to overlook just how reliable weather forecasting has become. I can remember my father laughing at the local weatherman’s predictions on the 5 o’clock news because he was often just flat wrong. Over time, however, weather forecasting has become so precise that a severe storm’s arrival can be predicted almost down to the minute, allowing whole communities to better prepare. If my father were alive, I think he’d say it is pretty spiffy just how accurate weather forecasting is nowadays. What is driving this incredible progress? Machine learning.

Machine learning has become a massive part of our lives, from recommending clothing that suits our personal preferences, to the magic of autonomous vehicles for public transportation. We can argue how useful some of these algorithms are and whether they make our lives better, but they are here to stay and will become more ubiquitous.

Machine learning can be particularly beneficial for manufacturing operations. Simple examples are taking inputs from upcoming orders and staging the necessary materials before each process. Complex examples include analyzing thousands of data points from sensors built into systems to predict how and, even more importantly, when the breakdown of critical components might occur, to identify a problem before it actually arises.

Machine learning also offers enormous advantages to the overall equipment efficiency (OEE), having the potential to save manufacturers thousands and, potentially, hundreds of thousands of dollars in expenditure due to unplanned downtime.

Machine learning is making revolutionary improvements.
Cirrus, an analytics platform from nLIGHT, is explicitly targeted at the crucial pain point of unplanned downtime. nLIGHT uses the hundreds of sensors designed into its fiber laser systems and runs machine learning algorithms on this data set to identify systems needing maintenance before reaching a failure state.
Right Time To Replace
Today’s maintenance model for fiber lasers is driven by the fact that the equipment is much more reliable than the systems they are replacing. CO2 lasers require multiple adjustments and tweaks to ensure smooth daily operations and long-term performance. However, even though fiber lasers have an outstanding maintenance record, parts of the system will degrade over time and require maintenance to keep running. Preventive maintenance is not ideal because parts often are replaced too early, costing more money over the long term. Waiting too long between PM intervals results in unplanned downtime. Unplanned downtime is costly not only because the tool is not producing the parts the business depends on but also because the downstream processing steps become out of sync and require shifting of priorities for the production floor.

The best solution is predictive maintenance. In this model, the operating condition of the laser is continuously monitored by comparing its performance against an entire population of similar lasers operating in the field. Early indicators of declining performance can be identified in advance of a fault or failure so a service event can be scheduled at a time that works best for the shop. This model is the goal of Cirrus. The platform is designed to assess the performance condition of a laser by leveraging the powerful statistics of thousands of other fielded lasers, with operating hours on each of them that can also be in the several thousands. Contemporary machine learning algorithms are perfectly suited to operate on data sets like this, teasing out subtle and reliable indicators of component performance variances.

In this predictive maintenance model, maintenance downtime is mitigated, and maintenance can be performed when convenient for the shop or factory, increasing OEE. In the reactive model, customers may have to wait days for repair teams to arrive and then analyze what went wrong. With the predictive model, that repair time can be cut down to a few hours, a truly revolutionary change to fiber laser maintenance.

Endless Possibilities
Predictive maintenance is only the beginning of machine learning for industrial manufacturing. Cirrus provides a digital platform for all types of data analysis, accommodating sensor data streams from fiber laser cutting, welding and additive manufacturing machine tools. This additional data can provide a view into operating efficiencies of the shop floor or factory and give updated recipes from existing libraries for different material combinations. Additionally, this technology opens new business models, allowing increased capabilities or even decreasing functions as needed.

Improvements occur over time with all new technologies, especially with machine learning. Weather forecasting did not get better overnight. It took many iterations and incremental gains, as with any system. However, data analytics and machine learning are poised to make revolutionary improvements to the industrial markets.

Michael Hepp is the product marketing development manager for cutting at nLIGHT.
Vancouver, Washington, 360/566-4460,