Wind Turbine Mechanical Load Estimation Based On Adaptive Network-based Fuzzy Inference System

Abstract

Estimating accumulated mechanical load of operating wind turbines (WT) is important to the operation security and lowering operation and maintenance (O&M) costs. This paper aims to estimate the mechanical load of a WT using data from its Supervisory Control And Data Acquisition (SCADA) system. Firstly, input parameters are determined by calculating the correlation coefficients between SCADA data and mechanical loads of the WT. Moreover, the Adaptive Network-based Fuzzy Inference System (ANFIS) is applied to establish the relationship between input parameters and mechanical loads. In order to prove the validity of proposed method, SCADA data and load measurements on seven crucial locations of a 2.5MW WT are collected to compare estimated and measured loads. Results show that the estimated loads are in good agreement with measurements. The coefficients of determination (R2) on different locations of the WT is between 88% and 97%. Using the proposed method, the R2 increases nearly 2%. This method can be used to optimise and lower the cost of operation & maintenance (O&M), for example by prioritising inspections and replacements.