An industrial maintenance worker in the oil industry communicates with their team from the field

What is Predictive Maintenance Data Analytics?

Data analytics for predictive maintenance refers to the process of analyzing raw data in order to make smart, data-driven decisions. Maintenance data analysis has been around for as long as people have been recording readings from machinery. What’s changing now is the sheer volume of data collected and what is actually doing the analysis: predictive maintenance data analytics software.

Traditionally, data was collected by technicians who would then pass the information to their managers or other experts for analysis. The experts would draw conclusions from the data and determine any actions needed.

Today, data analytics is more important to maintenance than ever before. With the next wave of prescriptive analytics, instead of manually collecting the data, software collects and analyzes it for you — and Artificial Intelligence (AI) and Machine Learning (ML) decides what actions to take and when. While this is still the future and most operations are still running on manual data readings, many manufacturers are already racing to achieve prescriptive analytics as a reality.

A Computerized Maintenance Management System, or CMMS, is a software platform with the ability to gather asset data, analyze it for alarming trends, and automatically trigger work orders when assets are in danger of failure. CMMS software is the perfect tool for maintenance and reliability teams who want to harness the power of data analytics for predictive maintenance.

Below is a timeline of data analytics in maintenance — from reactive, paper-based maintenance to prescriptive maintenance with a CMMS.

Figure 1: Maintenance strategies are progressing toward prescriptive analytics, where software will not only collect and analyze data, but also offer recommendations. Courtesy: Fluke Reliability Solutions

Manual data analytics is incredibly time-consuming: it takes time and legwork to collect and organize the data, pour over spreadsheets, and extract the relevant information and insights needed to make solid decisions. It has become even more challenging thanks to the large volume of data — “Big Data,” as it were — now being generated by IoT devices. In order for this information to be useful, it has to be extracted, analyzed, and put into action. That’s where the true challenge lies.

As Industry 4.0 continues to revolutionize maintenance and repair operations, data analytics will be transformed by the intelligent software capabilities a CMMS provides. While AI data analysis is still in the future for many, current CMMS software are leveraging more and more data to assist maintenance teams and augment easily automated tasks.

Sources of Industrial Data a CMMS Can Access

There are many different sources of industrial data that a CMMS draws from for data analytics.

eMaint CMMS integrates with third-party sensors and tools. Asset data can come from a range of sources: thermographic tools used take readings from multiple assets, vibration sensors conducting continuous condition monitoring, and more.

Plus, data from a technician spot-check using a handheld tool can be sent to the cloud immediately. From there, an integrated software can fuse the data sources into a comprehensive picture and make inferences and recommendations based on that bigger picture.

Leading platforms like eMaint can also tap into siloed data from industrial systems: Supervisory Control and Data Acquisition (SCADA) systems, Programmable Logic Controller (PLC) systems, Building Management Systems (BMS), and more.

Five Key Steps to Implement Data Analytics for Predictive Maintenance

The road to the future of data analytics is not same for every manufacturer. For example, some manufacturers already have a CMMS and reliability-centered maintenance (RCM) ingrained into their operations. Meanwhile, others are just starting their reliability journey. However, everyone can benefit from the following steps regardless of their starting point.

Here are the 5 steps to take with your CMMS to achieve predictive maintenance data analytics:

Step 1: Use your CMMS to conduct an asset criticality analysis

An asset criticality analysis is key to prioritizing asset health and maintenance on a hierarchy of importance. Start by grading each asset by its use within the organization — and the potential business impact in the case of failure. This step helps teams identify which assets are prime candidates for condition monitoring.

Step 2: Identify assets for a pilot program

Best practice for advanced data analytics is to start with a manageable set of assets to glean insights.  Start condition monitoring on the more critical assets identified in the asset criticality analysis.

Step 3: Launch and continuously improve the program

Launch the program, knowing it won’t be a one and done approach. The plan will need to be iteratively refined to make sure it fits your maintenance and operational needs. If a process or automation isn’t working for you, refine and gather more data. But most of all, stick with it! Too many organizations drop a pilot program because it isn’t giving them the desired results right away. Instead, improvise, adapt, and overcome.

Step 4: Review the pilot program’s results

Once you have data in-hand from your pilot program, use that data to as proof of concept to gain consensus and approval from your leadership to expand the program.  Prove to them the program is sound and expandable with data. Your leadership team will also likely have suggestions based on years of business management and process change experience.

Step 5: Scale your data analytics program

Once leadership is on board, return to the asset criticality analysis to determine the best opportunities to strategically expand your condition monitoring program. This expansion could be in the same facility, between facilities in the same region, or even between different countries.

Growing the data analytics program also means testing new sources for industrial data. Sensors, handheld tools, equipment-integrated SCADA and PLC systems and other resources can be fused, improving analytics in the process. While vibration monitoring is a great starting point for new programs, thermal imaging, oil analysis and other condition-based maintenance (CBM) resources also are useful.

Your CMMS Equips You for the Future of Data Analytics in Maintenance

Now is the best time to learn about the best CMMS software so you can prepare the data analytics groundwork for your company in the coming age of Artificial Intelligence and Machine Learning. Companies that achieve their data analytics goals today will have everything they need to integrate emerging technology as soon as it becomes available.