Comparative analysis of Gaussian Process power curve models based on different stationary covariance functions for the purpose of improving model accuracy

Abstract

Gaussian Process (GP) models are increasingly finding application in wind turbine condition monitoring and in particular early fault detection. GP model accuracy is greatly influenced by the choice and type of the covariance functions (used to describe the similarity between two given data points). Hence, the appropriate selection and composition of covariance functions is essential for accurate GP modelling. In this study, an in-depth analysis of commonly used stationary covariance functions is presented in which wind turbine power curve used where GP based power curve has been constructed using different stationary covariance functions, and after that, a comparative analysis has been carried out in order to identify the most effective covariance function. The commonly used squared exponential covariance function is taken as the benchmark, against which other covariance functions are assessed. The results show that the performance (in terms of model accuracy and uncertainty) of GP fitted power curve models based on rational quadratic covariance functions is almost the same as for the most commonly used squared exponential function. Thus, rational quadratic covariance functions can be used instead of squared exponential covariance functions. In this paper, strength and weakness of stationary covariance functions would be highlighted for effective condition monitoring.

A Novel Fault Prediction Method of Wind Turbine Gearbox Based on Pair-Copula Construction and BP Neural Network

“…It is the follow-up work to further explore the application of the proposed method in other faults. In addition, the research results of reference [43]- [48] show that air density has a significant effect on the output power of WTs. So, the SCADA data processing method which takes into account the influence of air density is also one of the future research directions.…”

Fault early warning of wind turbine gearbox based on multi‐input support vector regression and improved ant lion optimization

“…Analyzing the power curve, it is easy to find that some power values will be close to 0 when the wind speed meets the requirements of the grid connection. [39][40][41] In fact, the main reason for this part of the abnormal data is the shutdown status caused by wind abandonment of the wind turbine or other reasons and interference data due to the brake pads not being locked. Therefore, in this paper, when the SCADA data of the wind turbine standby state is excluded, in addition to the wind speed and active power, the active power set value is also added.…”

A Novel GPR-Based Prediction Model for Strip Crown in Hot Rolling by Using the Improved Local Outlier Factor

“…Compared with traditional covariance functions, it proves that rational quadratic functions are equal to the adding some various kinds of square exponential covariance functions with different length scale . Thus, according to the theory, rational quadratic covariance function can fit the data smoothly across different length scales [36], which is defined below:…”