Return to Blog


Maintenance Con 2019


May 6, 2019

Predictronics had a productive experience at MaintenanceCon 2019 in Chicago, IL, hosted by uMaintenance.

At the conference, CTO Dr. David Siegel delivered his talk, Reducing Downtime Using Advanced Analytics and Predictive Monitoring Technology, to leaders within the maintenance and reliability community.

Dr. Siegel discussed the steps for deploying a predictive monitoring solution, as well as the many benefits, including decreased machine downtime, improved availability, increased productivity, and reduced scrap waste.

Also highlighted was our joint case study with Maxion Wheels, a worldwide leader in wheel manufacturing. Dr. Siegel showcased the details of the configuration of our predictive monitoring software, PDX, at the Maxion Wheels manufacturing facilities, a project that just recently won the 2019 Manufacturing Leadership Award for Artificial Intelligence and Analytics.

PDX is an end-to-end predictive analytics and industrial AI solution, which collects, analyzes, monitors, and visualizes data to pinpoint potential failures and allow for planned downtime and maintenance.

Beyond delivering his talk, Dr. Siegel participated in this event in order to gain a greater understanding of maintenance and reliability practices and the current challenges businesses face in these areas across numerous industrial applications.

The overarching theme of the conference focused on the importance of these practices, as well as the need for well-developed preventative maintenance programs in order to effectively digitize a production environment and incorporate IoT and machine learning technologies.

Below are Dr. Siegel’s top four takeaways from the event:

1. Failure Modes and Understanding the Root Cause of Failures

One highlighted theme at the conference was establishing a better understanding of the root cause of component failures within an asset. Root cause determination is the key to accurate and timely decision-making, not only in maintenance, but also in process design. Identifying the root cause requires knowledge of the possible failure modes and the parameters exhibited during those failures. A failure mode consists of the location of the problem, i.e. the component, a description of the problem, and the cause of the problem. Recording this information through failure codes and maintenance management systems does not necessarily provide all three types of information. The proper labeling of failure mode information is important for performing subsequent criticality analysis, deciding which sensors or parameters would be the most suitable for predictive monitoring solutions, and determining the root cause of the failure. Ultimately, implementing countermeasures that reduce the risk of the failure and/or prevent it from occurring altogether would be the most ideal solution.

2. Criticality Analysis and Selecting the Key Assets

Criticality analysis was a widely discussed subject during the conference, with topics ranging from ranking and prioritizing one’s assets to determining which assets provide the most value if reliability and maintenance are improved. Criticality analysis is typically done on a greater asset level first and then, as degradation emerges, this analysis is performed at the component level for specific assets to diagnose and prevent failures. Common approaches include considering the age of the equipment, the frequency of failures, the cost or downtime associated with the failure, and the cost of the asset. Once the list of critical assets has been determined the appropriate strategies to address failure for each asset are performed.

3. Computerized Maintenance Management Systems and Areas for Improvement

Most companies surveyed during this event have already obtained computerized maintenance management systems (CMMS). However, many revealed that their ultimately successful CMMS installations were not without their challenges. The right CMMS system for your organization relies on many different factors and selecting one can be a daunting process. Despite their popularity, CMMS systems need to be improved as we move into the future. CMMS providers should work to ensure their systems are intuitive, easy to use, and able to quickly generate reports.

4. Incorporating Domain Experience into Predictive Monitoring Solutions

With various industry experts presenting their knowledge of maintenance, reliability, and hardware equipment at the conference, it is apparent that the marriage of domain expertise with analytics provides the most accurate monitoring solution. Determining the important failure modes, choosing sensors to include in an IOT system, and deciding which production challenges to address are all areas of expertise for data specialists and solutions providers. With the help of their knowledge and experience, you can feed these inputs into a predictive monitoring or predictive quality algorithm. It is also imperative that those creating predictive solutions should have some general industry and engineering background, so they can speak the same language as industry experts. The combination of these two talents is needed to deploy accurate solutions that improve and optimize business operations, saving companies time, money and resources.

For more information and weekly updates, follow Predictronics:

Know What Happens Next with PDX!