Uncategorized

Optimizing Electric Utility O&M With Predictive Analytics

Issue 3 and Volume 93.

by Mike Reed, Schneider Electric

With ongoing pressure from regulations and consumers, electric utilities are operating with the highest levels of efficiency, reliability and safety as top priorities.

Electricity demand is slowing, capital expenditures are rising and competition is growing with new market entrants. The utility industry is in the midst of a major financial restructuring. The growth of distributed generation and diversification of power sources bring operational system challenges, including loading issues, less switching flexibility and the potential for reverse power flow, among others. In addition, an aging infrastructure and work force also is driving the need for asset renewal prioritization and knowledge capture.

Utilities are continually employing new and old strategies to overcome these industry challenges and remain relevant in the changing energy marketplace. Adapting to new rules, innovating new offerings and investing in cost-saving technologies are just a few avenues for transforming challenges into opportunities. The amount of data available is providing utilities with the information needed to operate more efficiently, effectively and safely, consequently allowing them to overcome some of these disruptive obstacles. Navigant Research estimates that utilities will spend nearly $50 billion on asset management and grid monitoring technology by 2023. Using predictive analytics and asset-monitoring software, utilities can improve equipment reliability and performance while avoiding potential failures. These solutions provide the information needed to prioritize maintenance and reduce operational and maintenance expenditures.

Maintenance Practices

When considering new investments in predictive monitoring software, organizations first should ensure that a solid maintenance foundation exists.

Reactive maintenance is the most basic strategy and involves letting an asset run until failure. It is only appropriate for noncritical assets that have little to no immediate impact on safety or the reliable generation of electricity and have minimal repair or replacement costs so they do not warrant an investment in advanced technology.

Preventative maintenance (PM) approaches are designed in hopes that an asset will not reach failure. The PM strategy prescribes maintenance work to be conducted on a fixed time schedule or based on operational statistics and manufacturer/industry recommendations of good practice.

Condition-based maintenance (CBM) focuses on the physical condition of equipment and how it is operating. CBM is ideal when a measurable parameter is a good indicator of impending problems. The condition must be definable using rule-based logic where the rule does not change depending on loading, ambient or operational conditions.

Figure 1: Maintenance

If a potential asset failure could result in significant damage, safety issues or power outages, the risk is much higher and an even more proactive maintenance approach is required.

Predictive maintenance (PdM) relies on the continuous monitoring of asset performance through sensor data and prediction engines to provide advanced warning of equipment problems and failures. PdM typically requires predictive analytics software for real-time insights of equipment health and performance.

Figure 2: PRiSM Key Benefits

Predictive asset analytics solutions are a key part of a comprehensive maintenance program to ensure that assets are operating optimally and with little risk to the organization. According to the recent report “Proactive Asset Management with IIoT and Analytics” by ARC Advisory Group, only 18 percent of assets have a failure pattern that increases with use or age. This means that preventative maintenance alone is not enough to avoid failure in the other 82 percent of assets, and a more advanced approach is required. Predictive analytics software uses historical operational signatures for each asset and compares it with real-time operating data to detect subtle changes in equipment behavior. The software can identify changes in system behavior well before the deviating variables reach operational alarm levels, creating more time for analysis and corrective action.

All of the aforementioned maintenance approaches create the foundation for reliability-centered maintenance (RCM). RCM is a complex prognostic strategy focused on outcomes and is a process for determining what should be done to ensure that an asset operates the way the user intended. RCM is the capstone of a fully integrated maintenance program and can’t be deployed sufficiently without a repeatable process for the foundational maintenance practices, which includes using a predictive analytics solution in support of predictive maintenance.

Maintenance, Reliability Benefits

Predictive asset analytics software enables operations and maintenance personnel to address equipment issues before they become problems that significantly affect operations. Unscheduled downtime can be reduced because personnel receive early warning of developing issues. These advanced analytics solutions can identify problems days, weeks or months before they occur, creating time for personnel to be proactive. Instead of shutting down the plant immediately, O&M teams can assess situations for more convenient outcomes. Loads could be shifted to reduce asset strain or the necessary maintenance could be scheduled during a planned outage, if possible. Maintenance costs also can be reduced because of better planning; parts can be ordered and shipped without rush and equipment can continue running. In addition, some suggested maintenance windows can be lengthened as determined by equipment condition and performance. Other benefits include increased asset utilization and the ability to identify underperforming assets.

Not only do plants reduce expenses by extending equipment life, lengthening maintenance windows, increasing asset efficiency and increasing availability; other savings are realized when considering the costs that “could have been,” including loss of power, replacement equipment, lost productivity, additional man-hours, etc., when a major failure is avoided. In addition, predictive analytics solutions that transform raw data into easy-to-understand and actionable insights help personnel further improve availability, reliability and decision-making.

With predictive analytics, personnel know and understand the actual and expected performance for an asset’s current ambient, loading and operating conditions. They know where inefficiencies are and their impact on financial performance and can use this information to understand the impact of performance deficiencies on current and future operations. This information also helps utilities assess the risk and potential consequences associated with each monitored asset and can be used to better prioritize capital and operational expenditures.

Predictive analytics solutions also provide the capability for knowledge capture, which is increasingly important as many utilities are facing an aging work force because of an influx of retiring workers. Knowledge capture ensures that maintenance decisions and processes are repeatable, meaning that after more experienced personnel leave the company, the information and decision-making insights remain available for other staff.

Validation

In one case, a large North American power utility was able to save an estimated $8.9 million in avoided costs in one year because of the early warning detection provided by Schneider Electric’s Avantis PRiSM predictive asset analytics software. In one catch, plant engineers were alerted by email notification from the software that an aging steam turbine experienced a vibration step change. The appropriate personnel verified that a proximity probe and casing vibration both had changed. Further analysis indicated a likely loss of mass in the turbine blade path. They immediately suspected shroud material had been lost, based on the unit’s history. It was determined that the unit could continue to run at a reduced output under increased observation until a more convenient and strategic time to bring it offline. Once it was brought offline, a borescope inspection verified missing shroud material and several other segments that were close to liberating. Had this issue not been identified with predictive analytics software, it could have caused immediate unplanned downtime, loss of generation, possible catastrophic failure and danger to personnel. The vibration step change had not been significant enough to alert the operations staff of this impending condition through standard monitoring practices. The early warning notification and the following staff action resulted in a potential estimated savings of more than $4 million in lost revenue and repair costs with this one catch alone, in addition to maintaining the safety of the operating engineers.

Conclusion

Predictive asset analytics solutions help grid operators, systems engineers, controllers and many other plant personnel take advantage of the massive amounts of data and use it to make real-time decisions that have a significantly positive impact on equipment maintenance and reliability.

Early warning detection and diagnosis of equipment problems help personnel work more effectively by increasing lead time to plan necessary maintenance and avoid potential equipment failure.

Power utilities can transform their maintenance strategies by leveraging predictive asset analytics solutions to spend less time looking for potential issues and more time taking actions to get the most out of every asset. Using predictive asset analytics software, power utilities can monitor critical assets to identify, diagnose and prioritize impending equipment problems continuously and in real time.


Author

Mike Reed is the manager of analytical services for Avantis PRiSM at Schneider Electric. Reach him at [email protected].