Predictive maintenance is an integral part of the power sector, helping to enhance productivity and reduce costs. Predictive maintenance tools examine the condition of operational equipment and help to foresee its maintenance needs to attain optimum performance and avert any equipment failure, according to GlobalData.
Power utilities have to deal with the crucial task of monitoring and maintaining their assets, while functioning with increased efficiency and reliability levels. Through the use of predictive maintenance technologies, power utilities can detect underperforming assets and enable the operating staff or personnel to understand the factors leading to abnormal operations, and accordingly schedule maintenance activities.
Listed below are some of the leading predictive maintenance service providers in the predictive maintenance space, as well as power utilities that are using predictive maintenance services, as identified by GlobalData’s latest report: Thematic Research: Predictive Maintenance in Power.
Maximo Asset Performance Management (APM) forms a key segment of IBM’s APM suite. Its main key area is to enable maintenance managers to pin down and manage asset reliability risks that could critically affect damage plant or business operations. It can set out actions according to predictive scoring, pinpoint factors, which can impact asset health, and provide a comprehensive comparison of historical factors having an effect on asset performance.
SAP serves as a key predictive maintenance player. Through its SAP Predictive Maintenance and Service solution, it offers deep understanding of asset history and trends, hence enabling predictive maintenance and service requirements.
The Microsoft Corp. develops, licenses and supports software, services, devices and solutions globally. With its Microsoft Azure, the company is setting itself up itself as a major public cloud platform for industrial Internet of Things (IoT) solutions along with predictive maintenance.
Agder Energi, a Norwegian energy group, is using Azure Digital Twins to determine ways to efficiently operate its electricity grid via distributed energy resources (DER), device controls, along with predictive forecasting to avoid costly and tedious energy upgrades.
Through its cloud-based, open IoT operating system MindSphere, Siemens’ predictive learning platform offers early notifications of asset defects, enabling companies to avoid unscheduled equipment downtime.
GE’s Predix platform has been used by Enel for examining, predicting and enhancing Enel’s power plant reliability. GE uses its advanced predictive analytics to monitor data, detect and identify any equipment-related problems, and schedule maintenance activities to help decrease equipment downtime.
EDF Energy has used Schneider’s EcoStruxure Maintenance Advisor solution to save over $1m by preventing equipment damage and lost production. The company has also chosen Emerson’s AMS Suite predictive maintenance software to enable optimisation of maintenance strategies at one of its EDF’s combined cycle gas turbine (CCGT) power stations in West Burton, UK.
Duke Energy has made use of Schneider Electric’s Avantis PRiSM technology to save over $7.5m through the early detection of a crack in a turbine rotor. The utility has utilised Genpact’s Lean Digital approach to deal with cost over-runs predictability, as well as for asset optimisation.
E.ON is using artificial intelligence to warn of any faults or issues in the electricity grid. This solution has been used by Schleswig-Holstein Netz, a German grid operator offering utility services, on its medium voltage (MV) grids.
American Electric Power (AEP)
AEP’s monitoring and diagnostics (M&D) center has helped undertake repair works of a gas turbine blade before breakdown. This helped the company save around $19 million.
Southern Co. has used Schneider Electric’s Avantis PRiSM (Predictive Analytics) technology to continuously examine around 2,200 models (across gas and biomass power stations. This helped the utility save around $4.5 million in performance efficiencies by decreasing unexpected maintenance and maintaining maximum data quality reliability.
Image by Pete Linforth from Pixabay