A Scalable Predictive Maintenance Model for Detecting Wind Turbine Component Failures Based on SCADA Data

Gigoni, Lorenzo; Betti, Alessandro; Tucci, Mauro; Crisostomi, Emanuele

doi:10.1109/pesgm40551.2019.8973898

Cited by 11 publications

(7 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The methodologies presented in this paper allowed to improve the input data quality and to model accurately an hydroelectric basin. As a future development, the author intend to integrate the model presented in this work with the condition monitoring model previously proposed in [24], also applied to photovoltaic plants [35], in order to improve the performance of the model based on SCADA (Supervisory Control And Data Acquisition) data [37] and selforganizing maps [36]. As a second future development we shall investigate the application of sensitivity analysis techniques, such as [38,39] to estimate the influence of the input variables to the performance of the model.…”

Section: Discussionmentioning

confidence: 99%

Hourly Water Level Forecasting in an Hydroelectric Basin Using Spatial Interpolation and Artificial Intelligence

Tucci¹

2022

Preprint

View full text Add to dashboard Cite

In this work a new hydroelectric basin modelling approach is described and applied to the Pontecosi basin, Italy. Several types of data sources were used to learn the model: a number of weather stations, satellite observations, Reanalysis dataset and basin data. With the goal of predicting the water level of the basin, the model was composed by three cascade modules. Firstly, different spatial interpolation methods, such as Kriging, Radial Basis Function and Natural Neighbours, were compared and applied to interpolate the weather stations data nearby the basin area to infer the main environmental variables (air temperature, air humidity, precipitation and wind speed) in the basin area. Then, using these variables as inputs, a neural network was trained to predict the mean soil moisture concentration over the area, also to improve the low availability due to satellite orbits. Finally, a non-linear auto regressive exogenous input (NARX) model was trained to simulate the basin level with different prediction horizons, using the data from the previous modules and past basin data (water level, discharge flow rate, turbine flow rate). Accurate predictions of the basin water level were achieved within 1 to 6 hours ahead, with mean absolute errors (MAE) between 2cm and 10cm respectively.

show abstract

Section: Discussionmentioning

confidence: 99%

Hourly Water Level Forecasting in an Hydroelectric Basin Using Spatial Interpolation and Artificial Intelligence

Tucci¹

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…The methodologies presented in this paper allowed to improve the input data quality and to model accurately an hydroelectric basin. As a future development, the author intend to integrate the model presented in this work with the condition monitoring model previously proposed in [ 25 ], also applied to photovoltaic plants [ 35 ], in order to improve the performance of the model based on SCADA (Supervisory Control And Data Acquisition) data [ 36 ] and self-organizing maps. As a second future development, we shall investigate the application of sensitivity analysis techniques, such as [ 37 , 38 ] to estimate the influence of the input variables to the performance of the model.…”

Section: Discussionmentioning

confidence: 99%

Hourly Water Level Forecasting in an Hydroelectric Basin Using Spatial Interpolation and Artificial Intelligence

Tucci

2022

Sensors

Self Cite

View full text Add to dashboard Cite

In this work, a new hydroelectric basin modelling approach is described and applied to the Pontecosi basin, Italy. Several types of data sources were used to learn the model: a number of weather stations, satellite observations, the reanalysis dataset, and basin data. With the goal of predicting the water level of the basin, the model was composed by three cascade modules. Firstly, different spatial interpolation methods, such as Kriging, Radial Basis Function, and Natural Neighbours, were compared and applied to interpolate the weather stations data nearby the basin area to infer the main environmental variables (air temperature, air humidity, precipitation, and wind speed) in the basin area. Then, using these variables as inputs, a neural network was trained to predict the mean soil moisture concentration over the area, also to improve the low availability due to satellite orbits. Finally, a non-linear auto regressive exogenous input (NARX) model was trained to simulate the basin level with different prediction horizons, using the data from the previous modules and past basin data (water level, discharge flow rate, and turbine flow rate). Accurate predictions of the basin water level were achieved within 1 to 6 h ahead, with mean absolute errors (MAE) between 2 cm and 10 cm, respectively.

show abstract

“…Nisi et al (2019) and Renga et al (2020) built a prognostic-diagnostic model based on several years of SCADA data from the electricity distribution network. Gigoni et al (2019) proposed predictive maintenance on wind turbines with SCADA data. Almost similar to Gigoni et al (2019), the SCADA data has been proposed (Colone et al, 2019;Leahy et al, 2018).…”

Section: Electricity Gas Steam and Air Conditioning Supplymentioning

confidence: 99%

“…Gigoni et al (2019) proposed predictive maintenance on wind turbines with SCADA data. Almost similar to Gigoni et al (2019), the SCADA data has been proposed (Colone et al, 2019;Leahy et al, 2018). The difference with Colone et al (2019) and Leahy et al (2018) proposed classification techniques, De La Hermosa González-Carrato et al (2013) proposed a new algorithm for conducting predictive maintenance on wind turbines.…”

Section: Electricity Gas Steam and Air Conditioning Supplymentioning

confidence: 99%

Predictive Maintenance in SCADA-Based Industries: A literature review

Suryadarma

2020

IJIEEM

View full text Add to dashboard Cite

The purpose of this paper is to mapping and review what has been done on the topic of research on predictive maintenance in SCADA (Supervisory Control and Data Acquisition) based industries. In the research area of predictive maintenance, various methods for predicting damage or time to failure of a machine have been proposed and applied in various industries. This paper systematically categorizes predictive maintenance in SCADA-based industries research based on industry classifications according to ISIC (International Standard Industrial Classification of All Economic Activities). Furthermore, the research scope is explored its connection to the topics of Internet of Things (IoT), Artificial Intelligence (AI), Machine Learning (ML), and Supervisory Control and Data Acquisition (SCADA). It is found that 81.5% of the research was conducted on the electricity, gas, steam, and air conditioning supply industries, 11.1% of research was conducted on the mining and quarrying industry, and 7.4% of the research conducted in the manufacturing industry. It is also found that 85.2% of studies used AI and ML, 18.5% of the studies used IoT, and 18.5% of research used AI/ML and IoT technology together.

show abstract

A Scalable Predictive Maintenance Model for Detecting Wind Turbine Component Failures Based on SCADA Data

Cited by 11 publications

References 7 publications

Hourly Water Level Forecasting in an Hydroelectric Basin Using Spatial Interpolation and Artificial Intelligence

Hourly Water Level Forecasting in an Hydroelectric Basin Using Spatial Interpolation and Artificial Intelligence

Hourly Water Level Forecasting in an Hydroelectric Basin Using Spatial Interpolation and Artificial Intelligence

Predictive Maintenance in SCADA-Based Industries: A literature review

Contact Info

Product

Resources

About