Deep Learning-based predictive maintenance for improving wind turbines reliability - F. Bertoni

preview_player
Показать описание

Based on the forecasted growth of wind power in the upcoming years, asset managers are expected to adapt their O&M strategies improving asset reliability and operation, whilst reducing high maintenance costs and downtimes. Data science, and especially predictive maintenance algorithms for early fault detection are key to improving asset reliability. This seminar will explore the use of machine learning techniques for predicting faults for several wind turbine components simultaneously, allowing for a more adaptive and scalable system and for the localisation of faults.

Federica Bertoni, Falck Renewables SpA
Federica graduated in Environmental Engineering at Politecnico di Milano in 2016, where she also obtained a PhD in Information Technology in 2020. During her academic years, she has been a visiting research fellow at the Technical University of Denmark (DTU) and Cornell University. She is specialized in the renewable energy sector with a strong background in optimization and machine learning techniques. She is also experienced with all the steps of the lifecycle of data science projects. Since January 2020, Federica is a digital data scientist at Falck Renewables, where she is currently applying the knowledge gained during her academic career to the performance monitoring, improvement and forecast of renewable energy assets.
  1. Machine Learning Milan
  2. MLMilan
  3. predictive maintenance
  4. deep learning
Рекомендации по теме
How to Use 0:05:33

How to Use Machine Learning for Predictive Maintenance

Deep Learning-based predictive 0:21:53

Deep Learning-based predictive maintenance for improving wind turbines reliability - F. Bertoni

AI-Based Predictive Maintenance 0:09:16

AI-Based Predictive Maintenance in 4 Steps

Predictive Maintenance using 0:14:17

Predictive Maintenance using Deep Learning || LSTM based fault diagnosis

How to Use 0:02:03

How to Use Machine Learning for Predictive Maintenance

Deep Learning for 0:47:04

Deep Learning for Predictive Quality And Predictive Maintenance

Predictive Maintenance Explained 0:07:26

Predictive Maintenance Explained

Deep Learning for 0:06:03

Deep Learning for Predictive Maintenance and Health Management

No Deep Learning 0:04:04

No Deep Learning predictive maintenance

Kyklos 4.0 - 0:02:29

Kyklos 4.0 - Predictive Maintenance via Deep Learning

Predictive Maintenance Using 0:55:02

Predictive Maintenance Using Deep Learning and Reliability Engineering with Shayan Mortazavi - #540

Deep Reinforcement Learning 0:00:30

Deep Reinforcement Learning Based Predictive Maintenance Model for Effective Resource Management in

DESSERT'2023 Conference. S1.2. 0:26:46

DESSERT'2023 Conference. S1.2. Machine Learning-Based Predictive Maintenance...

Deep learning for 0:02:55

Deep learning for sounds recognition with IoT and cloud ( demo predictive maintenance ) EP1

Predictive Maintenance and 0:11:32

Predictive Maintenance and More: How to Use Machine Learning Without Being a Data Scientist

Predictive Maintenance: Common 0:08:07

Predictive Maintenance: Common Challenges & How to Overcome Them

Deep Learning-Based Predictive 0:01:33

Deep Learning-Based Predictive Maintenance for Indian Railways Using IoT Data || ANN || Python

Deep Reinforcement Learning 0:00:58

Deep Reinforcement Learning Based Predictive Maintenance Model for Effective Resource Management

SHAPLY values for 0:19:29

SHAPLY values for Explaining Machine Learning based Predictive Maintenance

Azure Sphere AI 0:02:26

Azure Sphere AI Powered Predictive Maintenance

AMiMO PhDs Workshop: 0:15:10

AMiMO PhDs Workshop: AI-based Machine Learning and Reasoning for Predictive Maintenance

Deep Reinforcement Learning 0:00:40

Deep Reinforcement Learning Based Predictive Maintenance Model for Effective Resource Management

Predictive Maintenance with 0:34:47

Predictive Maintenance with MATLAB: A Data-Based Approach

Deep Learning für 0:29:30

Deep Learning für die Industrie – Qualitätskontrolle, Prozessoptimierung und Predictive Maintenance...

Комментарии
Автор

Thank you so much for the awesome session.

malekmoursi
Автор

At 19:20, the explanation "update of SCADA system" is weird to me. Physically the update would not change real measurement value of PT100 temperature sensors. The bearing temperature does not change according to SCADA, SCADA only collects data.

ruanjiayang
Автор

This is a very insightful presentation, a lot of takeaways for someone like me who is quite naive in renewable energy domain. I have a question - You had mentioned about configuring false alarm threshold for temperature when software was upgraded at the wind site? Could you throw more insight on this? Thanks!

eswarbabu