Condition monitoring of wind turbines based on analysis of temperature-related parameters in supervisory control and data acquisition data

Xian, Wang; Zhao, Qiancheng; Yang, Xiaoliang; Zeng, Bing

doi:10.1177/0020294019888239

Cited by 15 publications

(12 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A scatter plot that visualizes the relationship between the temperature values in certain key locations of the WTs and active power is given in Wang et al, 26 from which it is known that there is a complex relationship between the temperature in the key locations of the WT and the active power. The relationship between temperature rise and active power is also very similar to the above situation, yet the scatter plot is too complex to analyze and it is necessary to process the data by a single-valued processing method.…”

Section: Methodsmentioning

confidence: 99%

“…The temperature data collected by the SCADA system was used in the application cases. Based on the framework of the nonlinear autoregressive with exogenous inputs (NARX) neural network, Wang et al 26 established a predictive time-sequence regression model, based on the key temperature signals of WTs. The vague information on the condition of WTs contained in the individual variation prediction residuals is clearly presented through the health index from the perspective of the temperature-related parameters (HIPT) established in the paper.…”

Section: Introductionmentioning

confidence: 99%

“…The vague information on the condition of WTs contained in the individual variation prediction residuals is clearly presented through the health index from the perspective of the temperature-related parameters (HIPT) established in the paper. Many studies have shown that there is significant individual variation and temporal variation in WT SCADA data, 13,26,[27][28][29] but the extent of variation is relatively unknown. Therefore, most of the above-mentioned methods (especially model-based methods) are flawed with limited applicability and onesided assessment because they use recent local data as a reference for condition assessment.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis of long-term temperature monitoring of multiple wind turbines

Wang

Zhao

Yang

et al. 2021

Measurement and Control

Self Cite

View full text Add to dashboard Cite

The historical temperature data logged in the supervisory control and data acquisition (SCADA) system contains a wealth of information that can assist with the performance optimization of wind turbines (WTs). However, mining and using these long-term data is difficult and time-consuming due to their complexity, volume, etc. In this study, we tracked and analyzed the 5-year trends of major SCADA temperature rise variables in relation to the active power of four WTs in a real wind farm. To uncover useful information, an extended version of the bins method, which calculates the standard deviation (SD) as well as the average, is proposed and adopted. The implications of the analysis for engineering practice are discussed from multiple perspectives. The research results demonstrate a change in the patterns of the main temperature rise variables in a real wind farm, completeness of the monitoring of the WT internal temperature state, influence of wind turbine aging on temperature signals, a correlation between different measurement points, and a correlation between signals from different years. The knowledge gained from this research provides a reference for the development of more practical and comprehensive condition monitoring systems and methods, as well as better operation maintenance strategies.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of long-term temperature monitoring of multiple wind turbines

Wang

Zhao

Yang

et al. 2021

Measurement and Control

Self Cite

View full text Add to dashboard Cite

show abstract

“…This showed a novel design of analysis using SCADA data. In Wang et al, 7 the use of the temperature parameter from the SCADA was emphasized by the author resulting in a condition monitoring using health index. These health indexes can effectively reflect early problems in wind turbines.…”

Section: Literature Reviewmentioning

confidence: 99%

Performance analysis of different predictive models for condition monitoring of direct drive wind turbine generator

Liu

Corbita

2021

Measurement and Control

View full text Add to dashboard Cite

This paper presents a performance analysis of predictive models for the generator module which can be used as a reference for improvement in the condition monitoring system using wind turbines in a wind farm in Taiwan. With the generator being a critical component prone to failures, it is important to perform data analysis on its parameters that could be used for condition monitoring. The main innovative feature in this framework is the conduct of performance analysis before the development of the condition monitoring system. Also, the consistency of the performance between the different wind turbines in the wind farm is evaluated. The predictive models are generated using the neural network algorithm with a different combination of parameters from the SCADA system. The correlation of the parameters as well as the mean square error of the predictive models were then computed for analysis. Results showed that pairing of input parameters with a higher correlation to the output parameter would give better performance for the predictive model. Furthermore, the performance of the different models was consistent throughout the different wind turbines in the wind farm which indicates that the same model can be developed and used for wind turbines belonging to the same wind farm. Employing a preliminary performance analysis of different combinations of component parameters could help in optimizing predictive models for condition monitoring.

show abstract

“…In reference [21], bearing temperature was also selected as the prediction target variable, abnormal level index (ALI) was defined to quantify the abnormal level of prediction error of each selected model, and a fuzzy synthetic evaluation method was used to integrate the identification results. In [22], A kind of health index from the perspective of temperature-related parameters was developed by separating the statistics concerning the conformity of the predicted values of key temperature parameters within a certain time window from the measured values.…”

Section: Introductionmentioning

confidence: 99%

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

Luo

Liu

2020

IEEE Access

View full text Add to dashboard Cite

Among the various maintenance technologies of wind turbines, online fault prediction technology is a kind of more cost-effective and reliable method. It may also be the most promising method for wind turbines with potential mechanical faults. SCADA data-based online condition monitoring technology has become a hot spot in current researches. Therefore, a novel fault prediction method based on the Pair-Copula model is proposed in this study. First, the conditional mutual information method is introduced to screen out useful variables from a number of variables. Then aiming at the limitation that the conventional Copula model can only deal with two-dimensional variables, the Pair-Copula model is introduced. In addition, the complexity of the prediction model and the dimension of the input variables are greatly reduced by the Pair-Copula model. So, the BP neural network is selected to complete the prediction model. A combined model based on BP neural network and Pair-Copula model is proposed. In order to solve the problem that the conventional Pair-Copula model cannot process real-time data which must be required in fault prediction, a kind of improved Pair-Copula model combined with the kernel density estimation is used to calculate the real-time data. Finally, the proposed method is validated with real data from a 1.5 MW wind turbine, and the effectiveness is confirmed.

show abstract

Condition monitoring of wind turbines based on analysis of temperature-related parameters in supervisory control and data acquisition data

Cited by 15 publications

References 44 publications

Analysis of long-term temperature monitoring of multiple wind turbines

Analysis of long-term temperature monitoring of multiple wind turbines

Performance analysis of different predictive models for condition monitoring of direct drive wind turbine generator

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

Contact Info

Product

Resources

About