A novel multi-information fusion grey model and its application in wear trend prediction of wind turbines

Abstract The small and fluctuating samples of lubricating oil data render the wear trend prediction a challenging task in operation and maintenance management of wind turbine gearboxes. To deal with this problem, this paper puts forward a method to enhance the prediction accuracy and robustness of the grey prediction model by introducing multi-source information into traditional grey models. Multi-source information is applied by creating a mapping sequence according to the sequence to be predicted. The significance of the key parameters in the proposed model was investigated by numerical experiments. Based on the results from the numerical experiments, the effectiveness of the proposed method was demonstrated using lubricating oil data captured from industrial wind turbine gearboxes. A comparative analysis was also conducted with a number of selected other models to illustrate the superiority of the proposed model in dealing with small and fluctuating data. Prediction results show that the proposed model is able to relax the quasi-smooth requirement of data sequence and is much more robust in comparison to exponential regression, linear regression and non-equidistance GM(1,1) models.

[1]  Sifeng Liu,et al.  An approach to increase prediction precision of GM(1, 1) model based on optimization of the initial condition , 2010, Expert Syst. Appl..

[2]  Xinping Xiao,et al.  Research on generalized non-equidistance GM(1, 1) model based on matrix analysis , 2011, Grey Syst. Theory Appl..

[3]  Liu Si-feng,et al.  The GM models that x(n) be taken as initial value , 2004 .

[4]  Fouad Slaoui-Hasnaoui,et al.  Wind Turbine Condition Monitoring: State-of-the-Art Review, New Trends, and Future Challenges , 2014 .

[5]  Tan Guan-jun,et al.  The Structure Method and Application of Background Value in Grey System GM(1,1) Model (II) , 2000 .

[6]  Yingjie Yang,et al.  Using a novel multi-variable grey model to forecast the electricity consumption of Shandong Province in China , 2018 .

[7]  Wang Zheng-xin.  The Optimization of Background Value in Non-Equidistant GM(1,1) Model , 2008 .

[8]  Jeffrey Forrest,et al.  Grey Data Analysis - Methods, Models and Applications , 2017, Computational Risk Management.

[9]  Wei Zhou,et al.  Generalized GM (1, 1) model and its application in forecasting of fuel production , 2013 .

[10]  Liu Si-feng.  Study on morbidity of NGM(1,1,k) model based on conditions of matrix , 2010 .

[11]  David W. Lewis,et al.  Matrix theory , 1991 .

[12]  Wei Qiao,et al.  A Survey on Wind Turbine Condition Monitoring and Fault Diagnosis—Part I: Components and Subsystems , 2015, IEEE Transactions on Industrial Electronics.

[13]  C. P. Hung,et al.  Novel grey model for the prediction of trend of dissolved gases in oil-filled power apparatus , 2003 .

[14]  Sifeng Liu,et al.  Using fractional order accumulation to reduce errors from inverse accumulated generating operator of grey model , 2014, Soft Computing.

[15]  Hong Zhang,et al.  Application of grey modeling method to fitting and forecasting wear trend of marine diesel engines , 2003 .

[16]  Chun-I Chen,et al.  The development of discriminants to prevent erroneous prediction by GM(1, 1) , 2016 .

[17]  Liu Si-feng,et al.  Research on Extension of Discrete Grey Model and Its Optimize Formula , 2006 .

[18]  Dongmei Fu,et al.  Non-equidistant GM(1,1) model based on GCHM_WBO and its application to corrosion rate prediction , 2015, 2015 IEEE International Conference on Grey Systems and Intelligent Services (GSIS).

[19]  Czesław Cempel,et al.  Using a set of GM(1,1) models to predict values of diagnostic symptoms , 2015 .

[20]  Shi-wei Chen,et al.  Application of non-equal interval GM(1,1) model in oil monitoring of internal combustion engine , 2005 .