Dynamic Fault Monitoring of Pitch System in Wind Turbines using Selective Ensemble Small-World Neural Networks

Li, Meng; Wang, Shuangxin

doi:10.3390/en12173256

Cited by 9 publications

(9 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method of Ref. [4] and the method of Ref. [5] are used as control methods, and the test results are shown in Figure 7.…”

Section: Analysis On Matching Degree Of User Complaint Labelsmentioning

confidence: 99%

Power user portrait model based on random forest

Yang

et al. 2023

IET Cyber-Phy Sys Theory & Ap

View full text Add to dashboard Cite

With the vigorous development of the energy Internet, all kinds of user information data are increasing day by day. How to comprehensively and deeply mine the effective information of users, develop a model to predict the behaviour characteristics of big data users, distinguish customer relationships, and provide an accurate basis for the next behaviour of users for various platforms have become one of the research hotspots of big data analysis of user behaviour. The data is sampled according to the feature vector of power user. The portrait mining of power user is conducted, and the user screening and analysis are conducted by using the measure of decision tree node purity in the model. The decision tree variable of the up–down stopping rule is generated. Then the results of the model and the Logistics model are tested and analysed, which can effectively predict the behaviour of power user. The proposed user strategy based on the characteristics of power consumption behaviour is analysed to verify the effectiveness of the scheme. The example shows that the model has a strong ability to distinguish and good stability than the traditional Logistics model, which can effectively predict the user's behaviour in advance, reduce user complaints, and help enterprises and users to form a long‐term mechanism of mutual benefit and reciprocity, which has a strong practical significance. This paper analyses the panorama of users through power big data technology and proposes a maturity model to evaluate the priority of users' electricity consumption. It emphasises the use of resources and methods provided in the power big data technology package to solve the practical problems of users' electricity consumption, and helps power companies to avoid market risks and improve service levels, which has strong practical significance.

show abstract

“…The method of Ref. [4] and the method of Ref. [5] are used as control methods, and the test results are shown in Figure 7.…”

Section: Analysis On Matching Degree Of User Complaint Labelsmentioning

confidence: 99%

Power user portrait model based on random forest

Yang

et al. 2023

IET Cyber-Phy Sys Theory & Ap

View full text Add to dashboard Cite

show abstract

“…A small-world network is an intermediate network between completely random and completely regular, which was originally proposed by Watts in 1998 to describe the natural distribution of biological, technological and social networks [26]. After that, various researches began to apply the characteristics of a small-world network to the structural improvement of artificial neural networks (ANNs) [21,22,27]. We summarize the current researches and consider that the small-world transformation has two ways (see Figure 3): reconstruct-edge transformation and add-edge transformation.…”

Section: Small-world Transformation Of Dswnnmentioning

confidence: 99%

“…The authors of this paper have improved a BP neural network into a small-world one and then used it to predict the wind power [20]. On this basis, a selective ensemble strategy combining multiple small-world neural networks has been proposed to diagnose and detect the WT pitch failures [21]. Combined with the characteristics of wind turbines' SCADA data, this paper proposed a deep small-world neural network (DSWNN) for anomaly detection of wind turbines.…”

Section: Introductionmentioning

confidence: 99%

Anomaly Detection of Wind Turbines Based on Deep Small-World Neural Network

Wang

Fang

et al. 2020

Applied Sciences

Self Cite

View full text Add to dashboard Cite

Accurate and efficient condition monitoring is the key to enhance the reliability and security of wind turbines. In recent years, an intelligent anomaly detection method based on deep learning networks has been receiving increasing attention. Since accurately labeled data are usually difficult to obtain in real industries, this paper proposes a novel Deep Small-World Neural Network (DSWNN) on the basis of unsupervised learning to detect the early failures of wind turbines. During network construction, a regular auto-encoder network with multiple restricted Boltzmann machines is first constructed and pre-trained by using unlabeled data of wind turbines. After that, the trained network is transformed into a DSWNN model by randomly add-edges method, where the network parameters are fine-tuned by using minimal amounts of labeled data. In order to guard against the changes and disturbances of wind speed and reduce false alarms, an adaptive threshold based on extreme value theory is presented as the criterion of anomaly judgment. The DSWNN model is excellent in depth mining data characteristics and accurate measurement error. Last, two failure cases of wind turbine anomaly detection are given to demonstrate its validity and accuracy of the proposed methodology contrasted with the deep belief network and deep neural network.

show abstract

“…During ensemble stage, only the learners with better performance are selected to avoid the impact of the basic learners with poor performance on the ensemble model. The process of selective ensemble learning is shown in The main idea of selective ensemble learning [13] is to select only a part of the learners with better performance among many base learners, so as to obtain the better effect than that of ensemble all base learners [14]. In the search process of the basic learner, the method used is very important, which has a great impact on the ensemble results.…”

Section: Related Workmentioning

confidence: 99%

Household Power Consumption Prediction Method Based on Selective Ensemble Learning

2020

View full text Add to dashboard Cite

In the context power big data, the household power consumption data on the user side has the characteristics of large quantity, wide distribution and many types. Ensemble learning is very excellent in the analysis and mining of power data with large amount of data, strong timeliness and many influencing factors. Based on the data of household power consumption, this paper analyzes and predicts the power consumption of some users in a city by using selective ensemble learning technology and combining with meteorological factors. In this paper, K-means algorithm is used to cluster the household power consumption, and then the clustering results are combined with the meteorological information. In the stage of power consumption prediction, a Filter Iterative Optimization Ensemble Strategy (FIOES) is proposed to selectively ensemble the basic learners and get the final prediction model. Experimental results show that the FIOES algorithm has better performance in time cost and prediction accuracy than the traditional ensemble learning algorithm. INDEX TERMS Power big data, ensemble learning, power consumption, iterative optimization.

show abstract

Dynamic Fault Monitoring of Pitch System in Wind Turbines using Selective Ensemble Small-World Neural Networks

Cited by 9 publications

References 38 publications

Power user portrait model based on random forest

Power user portrait model based on random forest

Anomaly Detection of Wind Turbines Based on Deep Small-World Neural Network

Household Power Consumption Prediction Method Based on Selective Ensemble Learning

Contact Info

Product

Resources

About