Load and risk based maintenance management of wind turbines
Doctoral thesis, 2016

Wind power has proven to be an important source of renewable energy in the modern electric power systems. Low profit margins due to falling electricity prices and high maintenance costs, over the past few years, have led to a focus on research in the area of maintenance management of wind turbines. The main aim of maintenance management is to find the optimal balance between Preventive Maintenance (PM) and Corrective Maintenance (CM), such that the overall life cycle cost of the asset is minimized. This thesis proposes a maintenance management framework called Self Evolving Maintenance Scheduler (SEMS), which provides guidelines for improving reliability and optimizing maintenance of wind turbines, by focusing on critical components. The thesis introduces an Artificial Intelligence (AI) based condition monitoring method, which uses Artificial Neural Network (ANN) models together with Supervisory Control And Data Acquisition (SCADA) data for the early detection of failures in wind turbine components. The procedure for creating robust and reliable ANN models for condition monitoring applications is presented. The ANN based Condition Monitoring System (CMS) procedure focuses on issues like the selection of configuration of ANN models, the filtering of SCADA data for the selection of correct data set for ANN model training, and an approach to overcome the issue of randomness in the training of ANN models. Furthermore, an anomaly detection approach, which ensures an accuracy of 99% in the anomaly detection process is presented. The ANN based condition monitoring method is validated through case studies using real data from wind turbines of different types and ratings. The results from the case studies indicate that the ANN based CMS method can detect a failure in the wind turbine gearbox components as early as three months before the replacement of the damaged component is required. An early information about an impending failure can then be utilized for optimizing the maintenance schedule in order to avoid expensive unscheduled corrective maintenance. The final part of the thesis presents a mathematical optimization model, called the Preventive Maintenance Scheduling Problem with Interval Costs (PMSPIC), for optimal maintenance decision making. The PMSPIC model provides an Age Based Preventive Maintenance (ABPM) schedule, which gives an initial estimate of the number of replacements, and an optimal ABPM schedule for the critical components during the life of the wind turbine, based on the failure rate models created using the historical failure times. Modifications in the PMSPIC model are presented, which enable an update of the maintenance decisions following an indication of deterioration from the CMS, providing a Condition Based Preventive Maintenance (CBPM) schedule. A hypothetical but realistic case study utilizing the Proportional Hazards Model (PHM) and output from the ANN based CMS method, is presented. The results from the case study demonstrate the possibility of updating the maintenance decisions in continuous time considering the changing conditions of the damaged components. Unlike the previously published mathematical models for maintenance optimization, the PMSPIC based scheduler provides an optimal decision considering the effect of an early replacement of the damaged component on the entire lives of all the critical components in the wind turbine system.

condition monitoring system (CMS)

optimization

supervisory control and data acquisition (SCADA)

maintenance planning

Artificial neural network (ANN)

life cycle cost

maintenance management

maintenance strategy

wind energy.

EB, Hörsalsvägen 11, 41296 Gothenburg.
Opponent: Prof. Miguel A. Sanz Bobi, Intelligent Systems Research Group, Comillas Pontifical University, Madrid, Spain

Author

Pramod Bangalore

Swedish Wind Power Technology Center (SWPTC)

Chalmers, Energy and Environment

Chalmers, Energy and Environment, Electric Power Engineering

Cost Efficient Maintenance Strategies for Wind Power Systems Using LCC

2014 International Conference on Probabilistic Methods Applied to Power Systems, PMAPS 2014; Durham; United Kingdom; 7 July 2014 through 10 July 2014,;(2014)p. Art. no. 6960591-

Paper in proceeding

An Artificial Neural Network Approach for Early Fault Detection of Gearbox Bearings

IEEE Transactions on Smart Grid,;Vol. 6(2015)p. 980-987

Journal article

Self Evolving Neural Network Based Algorithm for Fault Prognosis in Wind Turbines : A Case Study

2014 International Conference on Probabilistic Methods Applied to Power Systems (Pmaps),;(2014)

Paper in proceeding

An Approach for Self Evolving Neural Network Based Algorithm for Fault Prognosis in Wind Turbine

IEEE Grenoble Conference PowerTech, POWERTECH 2013; Grenoble; France,;(2013)p. (article no 6652218)-

Paper in proceeding

För att vindkraften ska bli en konkurrenskraftig energikälla krävs att dess tillförlitlighet är mycket hög. Målet med våra projekt inom området är att bistå med planeringsmodeller, baserade på matematisk optimering, vars indata inkluderar information om kritiska komponenters status, rådande vindförhållanden och tillgängliga resurser. Våra planeringsmodeller utnyttjar denna information, framför allt för att ge beslutsstöd i närtid med avseende speciellt på lämpliga utbyten, men de kan också användas för att ge förslag på produktutveckling av de komponenter som bidrar mest till en hög driftkostnad.

Areas of Advance

Energy

Subject Categories

Other Electrical Engineering, Electronic Engineering, Information Engineering

ISBN

978-91-7597-451-4

Doktorsavhandlingar vid Chalmers tekniska högskola. Ny serie: 4132

EB, Hörsalsvägen 11, 41296 Gothenburg.

Opponent: Prof. Miguel A. Sanz Bobi, Intelligent Systems Research Group, Comillas Pontifical University, Madrid, Spain

More information

Latest update

3/19/2018