Mario Augusto Caetano dos Santos – Maintenance Engineer, Itaipu Binacional, Brazil
“Many power generation companies and utilities face the same challenge: providing energy and services with quality and competitive costs while managing aging assets. It’s not an easy task! Predictive maintenance as an approach within the asset managment strategy has the ability to drive efforts (especially budget) based on risk analysis nd KPIs. Today, the growth of data science and associated technologies has taken predictive maintenance to a new level.”
Luiz André Moysés Lima – Senior Renewable Resources Analyst, Voltalia, Brazil
Luiz André Moysés Lima – Senior Renewable Resources Analyst, Voltalia, Brazil“Large fleets that span multiple wind farms may include turbines of different models, brands and characteristics. The same principle applies for solar plants. One of the greatest challenges related to Predictive Maintenance is to create and automatize accurate prediction processes while still keeping them general enough, so that they work properly for different equipment, locations and weather conditions.“
Kristofer Jakobson – Senior Data Scientist, Fortum, Sweden
“AI tools show great potential in improving both the operation and maintenance of energy assets, but there are many obstacles on the way from proof-of-concepts to a scalable, robust and maintainable system. Fortum’s ongoing digitalization journey for the hydropower fleet provides concrete examples of both such obstacles and possible solutions“
Teemu Vekkeli – O&M Technical Manager, Eurus Energy Europe, The Netherlands
Teemu Vekkeli – O&M Technical Manager, Eurus Energy Europe, The Netherlands“The biggest challenge for predictive maintenance is the required change in mindset. Operations and Maintenance organizations will need to adapt their daily operations to generate real benefits from a predictive approach. Asset owners will need to be the drivers of this change. The industry as a whole will benefit from collaboration of owners and operators.”
Anne-Marie Giroux – Research Scientist, Hydro-Quebec, Canada
Anne-Marie Giroux – Research Scientist, Hydro-Quebec, Canada“Availability of data from sensors connected to assets and the development of AI capabilities and other analytic tools make possible the transformation of classic systematic maintenance to one that is adjusted to the actual condition and risk of failure of a specific equipment. The implementation of early anomaly detection, which helps in adapting inspection frequencies, remains challenging for assets that are not serial made and which behaviour changes with the natural conditions (water levels, water and air temperat…res, …) like hydropower units.
Physics-based digital twins may not only detect anomalies, but also identify their cause (diagnostic) and ultimately do some prognosis, helping the asset owner to plan the right maintenance action at the right time, and thus minimize maintenance costs while preventing outages. The development of digital twins of such complex equipment is a very challenging task that we started to address by splitting the whole unit in smaller parts: turbine, generator, shaft and bearings, speed governor and excitation system.
“
João Fontes Machado – Data Analytics & Automation, EDP, Portugal
“The main goal for predictive maintenance is the same it has always been: maximizing the success rate of problem detection, while providing the exact cause. Being able to remotely tackle as many issues as possible is also of tremendous importance – given that it will reduce costs for both the client and the service provider, whenever it is the case.”
Martina Tamburini – Head of Datalab Upstream & Staff, Edision Spa, Italy
Martina Tamburini – Head of Datalab Upstream & Staff, Edision Spa, Italy“The fast development of renewables in the coming years brings a big challenge to energy companies on O&M activities because plants will become more and more numerous and geographically distributed. Companies have to create a flexible infrastructure that could easily scale up by leveraging digital tools and advanced use of data from a predictive point of view: this represents both a technological and cultural tra”sformation.”
