Predictive Maintenance—the First Step Toward Self-Maintenance and AI

By Kenneth Sanford

How to pave the way for artificial intelligence and self-maintenance, by first optimizing your operations with predictive maintenance

  • TAGS
image_pdfimage_print

Predictive maintenance is widely considered to be the obvious next step for any business with high-capital assets looking to harness machine learning to minimize equipment maintenance costs. Predictive maintenance takes data from multiple and varied sources, combines it, and uses machine-learning techniques to anticipate equipment failure before it happens.

Many businesses are already using continuous monitoring technologies—Internet of Things (IoT)-connected devices, for example. This is a good start, but the key lies in not just simply monitoring the output of various data (which is how many companies currently use it), but by taking the next step and employing advanced algorithms and machine learning to take action from real-time insights and anticipate future outcomes.

Going one step further, the most innovative enterprises, no matter what type of high-capital assets they maintain, see the largest cost savings from predictive maintenance—not only by putting a system in place that returns simple predictive outputs, but by rethinking and optimizing their entire maintenance strategy as a whole, from top to bottom. This means:

• Paving the way for artificial intelligence (AI) and self-maintenance by optimizing for (and automating) the immediate next steps once predictive systems point to imminent failure, whether this automatically triggers a work order, notifies a technician or certain team, places an order for a replacement part, etc.

• Considering a combination of maintenance strategies to determine the optimal cost-saving combination of predictive and traditional maintenance, perhaps even on an asset-by-asset basis.

• Identifying how to best execute necessary repairs through second-order or secondary analytics. This means having a process in place for an entire deeper layer of analysis to determine the best time to actually remove the asset from service, as well as which additional repairs, if any, should be conducted simultaneously to minimize the cost of having to remove the asset again for a different failure within a short window of time.

To get started, data science company Dataiku has published a free whitepaper titled “How To: Future-Proof Your Operations with Predictive Maintenance,” which outlines the steps every organization needs to embrace to make predictive maintenance effective within the short term, and to prepare for the long-term changes and benefits it can bring:

1. Understand the Need
The first step in moving toward predictive maintenance is to understand pain points (namely, drivers of costs, waste or inefficiency) and identify the best use case for your business.

2. Get Data
Of course, the proliferation of the IoT plays a large role in predictive maintenance, especially with cheap sensors and data storage combined with more powerful data processing that has made the technology accessible. But there are other data sources out there, which might include data from programmable controllers; manufacturing-execution systems; building-management systems; manual data from human inspection; static data, such as manufacturer service recommendations for each asset; external data from application programming interfaces (APIs), like weather, that could impact equipment conditions or wear; geographical data; equipment usage history data; and parts composition.

3. Explore and Clean Data
After identifying relevant data sets, it’s time to dig in. Ensure you really understand all the data you’re dealing with and that you know what all of the variables mean, what is being measured and where all the data is coming from.

4. Enrich Data
Manipulating data at this stage means adding more features and joining it in meaningful ways so that each data set, or data from multiple sensors, can be taken as a whole instead of in parts.

5. Get Predictive
It is precisely this combination of a variety of sources and data types that allows for the most robust and accurate predictive models. The more sources and types of data available, the better the complete picture of a particular asset in general, and the better the prediction.

6. Visualization
Visualization is an important tool in predictive maintenance as it often closes the feedback loop, allowing maintenance managers and staff members to see the outputs of predictive models and direct their attention accordingly. Robust data science or data team tools allow maintenance managers and personnel on the ground to easily access and digest outputs in a familiar format so that the entire team—from analysts to technicians—receive the same feedback.

7. Iterate, Deploy and Automate
Deploying a predictive maintenance model into production means working with real-time data, but to iterate and deploy means providing visual real-time dashboards for maintenance teams on the ground. For some use cases, feedback can be integrated directly into the predictive maintenance process, requiring no (or little) human interaction.

Secondary Analytics
Once it’s clear that a repair is necessary and initial first steps or processes have been kicked off, that’s where secondary analytics come in. The goal of secondary analytics following predictive maintenance is to determine a plan of action for exactly when the asset should be taken out of service, so as to minimize disruption and loss (both imminent and future) and maximize resources.

Conclusions and Next Steps
The biggest initial win with predictive maintenance initiatives is cost savings. But after implementing a larger, more robust and more mature predictive maintenance strategy, larger opportunities begin to open from a business perspective, and high-value assets can bring in some additional revenue instead of just being costs.

Predictive maintenance also lends itself to the future of artificial intelligence (AI), in which operations will be entirely self-maintenance with very little human interaction whatsoever. AI in the predictive maintenance space would go one step beyond the steps discussed above, which would still require some manual analysis of models and outputs. These systems will watch thousands of variables and apply deep learning to find information that could otherwise be undetected that might lead to failure. Ultimately, predictive maintenance isn’t so far off from AI, and businesses that get started with predictive maintenance programs now will be well-poised as market leaders in the future.

To learn more about implementing predictive maintenance, download the free whitepaper, “How To: Future-Proof Your Operations with Predictive Maintenance.”

Dr. Ken Sanford is the U.S. lead analytics architect at Dataiku. He is a reformed academic economist who likes to empower customers to solve problems with data. In addition, Dr. Sanford teaches courses in applied forecasting, stress testing and big data tools at Economists at Boston College. He has a Ph.D. in economics from the University of Kentucky in Lexington, and his work on price optimization has been published in peer-reviewed journals.