How to Get the Most Out of Your Maintenance Data

By Alexander Rose, Manager and Chris Barnes, Senior Manager, Data Science, Kalypso: A Rockwell Automation Business

For many organizations. maintenance is still predominantly a reactive endeavor. As simple predictive solutions become more commonplace, leading enterprises are looking beyond predictive capabilities to prescriptive insights to advise maintenance functions on what assets and tasks to prioritize.

Organizations now have access to vast amounts of data, and ideas for using that data continue to proliferate. The real challenge has become prioritizing which opportunities to pursue.

To advise maintenance functions, organizations are using advanced analytics and predictive maintenance. Predictive maintenance (PdM) uses statistical, machine learning (ML) and artificial intelligence (AI) techniques to predict asset health issues before they arise.

When successful, these predictive technologies provide a prescriptive approach that balances the potential severity of a particular failure mode with an estimate of how likely that failure is to occur. This measure, commonly called criticality, empowers teams to focus their time and resources on the assets, systems and subsystems most critical to business outcomes.

The effective use of PdM strategies can help manufacturers reduce mean time to repair (MTTR) and improve first-time fix rates (FTFR), which may further decrease the non-value-added “windshield time” associated with field service requests.

For leaders at organizations who want to improve their maintenance operations and routines by using data from connected assets, the question remains: “How do we start?”

“Value-First” Prioritization Strategy

It may be tempting to begin collecting and storing every data point available to an organization. However, undirected data collection can result in high levels of activity with few measurable results. To protect against this common pitfall, we offer a framework for “value-first” prioritization.

An iterative approach assesses the criticality of an application in its business context. This assessment can rank opportunities by their value. High-value targets should then be assessed for feasibility to make sure resources are dedicated to use cases that have a high probability of success. More specifically, organizations should

1. Identify high-value opportunities based on the criticality of the failure mode.
2. Frame use cases in terms of value-driven business goals and an analytical objective.
3. Use that analytical objective to assess the feasibility of the asset.
4. Select an analytical method and modeling approach that supports the target objective.

Measuring for “Criticality”

Unsuitable applications can consume valuable time and resources. Organizations should work backward from ideal business outcomes to identify high-value opportunities for improvement.

When thinking of predictive maintenance, it’s important to articulate the business value associated with predicting — and subsequently preventing — a particular failure mode and determine if the effort/cost of predicting this failure mode is economically attractive.

Collecting several assets and then ranking them by criticality can help teams prioritize opportunities most likely to result in a meaningful organizational impact. While there are many ways to think of criticality, we have converged on the simplified measure outlined in Figure 1.

Teams should focus on finding an approachable and repeatable way to assign some indication of criticality to each of their applications so opportunities can be ranked and prioritized.

Retaining information about elements that make up this criticality measure may allow teams to further refine their maintenance strategy even when a PdM approach isn’t warranted.

Plotting each use case by the Frequency of Failure vs. the Total Cost of Failure allows teams to consider how a variety of maintenance strategies may be leveraged. An example of such a plot is shown in Figure 2.

Dividing this plot into quadrants highlights the following:

• Quadrant 1: Frequently occurring, high-cost failure modes. These are prime targets for PdM strategies coupled with contingency planning.
• Quadrant 2: Failure modes that occur frequently but are low cost. These are likely strong candidates for preventative maintenance strategies.
• Quadrant 3: Both low cost and low frequency — may warrant only corrective maintenance interventions (run to failure).
• Quadrant 4: High-cost failure modes that occur relatively infrequently. The cost associated with such a failure may warrant predictive or preventative maintenance strategies.

Investing enough time to assess criticality and to determine if a given asset is a strong candidate for predictive maintenance up front can help teams verify the right toolset before incurring the cost of that toolset.

Framing use cases in terms of business value can make it easier to assess the criticality of a given failure mode. This also helps teams assess feasibility.

Assessing Use Cases for Feasibility

Determining the feasibility of an asset is an iterative process. Once a business problem is well understood and its criticality assessed, we recommend tracing the logic of the business goal all the way through method selection and data and infrastructure feasibility. Figure 3 offers a visual representation of this process.

At each step, teams may uncover information that will require them to re-evaluate previous steps. For example, they may discover they lack sufficient data to leverage a classification algorithm model. In such a situation, the team may opt to restate its analytical objective to better suit the data available.

Reframing the opportunity in this way doesn’t represent a failure, but rather serves to guide teams toward the analytical methods and modeling approaches that best fit the system’s current level of maturity.

Reframing challenges/opportunities also allows teams to localize their analytical objective to the appropriate level of granularity. Objectives may deal with defining outcomes at the system, sub-system, or component level.

Understanding how these levels interact with one another will facilitate the kind of analytical thinking necessary to deliver the value of a particular asset. A vital component to an organization’s success is selecting the right use case(s) relative to their position on the path to a “right-sized” maintenance practice.

Advanced Analytics for PdM

Establishing a predictive maintenance (PdM) practice may appear daunting. Organizations that wish to take advantage of the promise of advanced analytics would do well to focus on high-value use cases as proofs of concept that allow their teams to build skill and familiarity in the space.

To accomplish this, prioritizing use cases based on criticality and then assessing use case feasibility can help teams select the most promising use cases for their own PdM pilots.

Kalypso: A Rockwell Automation business, helps companies bring digital solutions to product problems. Whether it’s weaving a digital thread from product ideation all the way through manufacturing and service, or advancing operations from automation to autonomy, Kalypso specializes in improving what’s being made and how it’s made. Kalypso serves the largest names in the discrete, hybrid and process industries, around the world.

Like this article? Sign up for the digital magazine (4X/year) and e-newsletter from The Journal From Rockwell Automation and Our PartnerNetwork.

^{The Journal From Rockwell Automation and Our PartnerNetwork™ is published by Endeavor Business Media.}