Manuel Terranova, CEO Peaxy, recently spoke on a panel for the Naval Surface Warfare Center, Carderock Division in West Bethesda, Maryland. With a focus on digital twins, model-based systems engineering, live-virtual-constructive approaches and autonomy/unmanned systems, the two-day event featured a wide array of guest lecturers and panelists.
Here are some highlights from the discussion:
Predictive maintenance at low confidence levels is relatively easy to accomplish. Predicting equipment failure with a high level of confidence is much more difficult, and requires substantive historical failure data down to the serial number. Data analytics are a key part of a predictive maintenance program, and “ground-truthing” is essential to avoid false alarms. This generally takes time and more specialized skill sets.
Here are four types of equipment maintenance routines:
- Reactive – “deal with it when it breaks and keep lots of spares.” This is the most simple approach, and not surprisingly has been used since the birth of the industrial revolution with varying degrees of success. The downsides are high inventory levels, and significant logistical load to ensure spares are available. Of course, this is the most unpredictable routine, and requires highly trained personnel to be available on the spot to deal with equipment failures.
- Interval-based – “follow the OEM recommended practices and keep lots of spares.” This is the most prevailing model with the most acceptance, and requires low data and connectivity requirements. Maintenance is treated as a planned event, based on the usage of the equipment. This mode of maintenance is commonly used in the aviation industry with a high degree of success. It doesn’t, however, remedy the unplanned outage event, depending on the frequency and comprehensiveness of the maintenance regime.
- Condition-based – “dynamically adjust the maintenance, interval-based equipment condition (order spares when you need them).” Condition-based monitoring requires that you understand in detail the operating profile of the equipment, including ambient profiling under different operating conditions. Data requirements can be 10x versus interval-based monitoring. This method is ideal for newer equipment which can already have the necessary sensors to capture data; it’s a challenge to retrofit older equipment. This is the first area where digital twins can start to provide value by running various what-if scenarios.
- Predictive-based or “CBM+” – True predictive maintenance programs are serial number specific, and thus data requirements can be up to 10x the condition-based approach. Connectivity is key, with high fidelity and real-time monitoring. Data captured at the “edge” can be processed to understand transient states and avoid false positives. Data context is essential, since the system must make recommendations on what to do next. Digital twins are the most powerful tool in this scenario, and can drive what-if scenarios and degradation modeling.
What solutions does Peaxy offer?
Peaxy built one of the first combined physics and economic digital twins in 2016 for a Fortune 10 company. That effort delivered a digital twin of a complex system, including gas turbines, steam turbines, steam generation and power generation equipment all faithfully modeled and validated. While that first effort spanned over 200 days, we can now create twins in as little as 65 days, at a fraction of the cost.
Peaxy offers predictive asset management for industrial equipment that turns operational data into insights that optimize productivity and increase revenue. Our Peaxy Lifecycle Intelligence (PLI) product is a modular, scalable, cloud-based asset management solution aligned with the needs of the value-driven enterprise. By rapidly turning operating data into financial insights, PLI lets operators minimize O&M costs and optimize performance, improving the lifetime value of industrial assets. PLI serves a wide range of use cases involving precision-engineered equipment, grid-scale battery installations, aviation components, gas turbines, steam turbines, wind turbines, compressors and propulsion systems.