Fault detection and diagnosis for rotating machinery: A model based on convolutional LSTM, Fast Fourier and continuous wavelet transforms

Wind turbine fault diagnosis based on transfer learning and convolutional autoencoder with small-scale data

Operation and maintenance (O&M) activities represent a significant share of the total expenditure of a wind farm Of these expenses, costs associated with unexpected failures account for the highest percentage Therefore, it is clear that early detection of wind turbine (WT) failures, which can be achieved through appropriate condition monitoring (CM), is critical to reduce O&M costs The use of Supervisory Control and Data Acquisition (SCADA) data has recently been recognized as an effective solution for CM since most modern WTs record large amounts of parameters using their SCADA systems Artificial intelligence (AI) techniques can convert SCADA data into information that can be used for early detection of WT failures This work presents a systematic literature review (SLR) with the aim to assess the use of SCADA data and AI for CM of WTs To this end, we formulated four research questions as follows: (i) What are the current challenges of WT CM? (ii) What are the WT components to which CM has been applied? (iii) What are the SCADA variables used? and (iv) What AI techniques are currently under research? Further to answering the research questions, we identify the lack of accessible WT SCADA data towards research and the need for its standardization Our SLR was developed by reviewing more than 95 scientific articles published in the last three years

https://www.mdpi.com/1996-1073/13/12/3132/pdf

Using SCADA Data for Wind Turbine Condition Monitoring: A Systematic Literature Review

An adversarial denoising convolutional neural network for fault diagnosis of rotating machinery under noisy environment and limited sample size case

Tidal current turbine, as an effective technical means to contribute to all around the world achieving targets for reducing greenhouse gas emissions and the production of renewable energy, has obtained great concern. It was established that more than 94 TWh per year could be generated in the developable sea area. Many types of tidal current turbine structures and control methods have been proposed, however, the possible increase in power generation must consider parameters such as reliability, cost, and complexity of the control system. The paper presents a review on configuration and control methods of tidal current turbines. The configuration and control methods of tidal current turbines are classified, described and compared, especially for horizontal axis tidal current turbines. Horizontal axis tidal current turbine is more widely used, due to high energy conversion efficiency. Different configuration and corresponding control methods have their advantages and disadvantages, which affect efficiency, maintenance requirements, and the cost of electricity from tidal current.

Review on configuration and control methods of tidal current turbines

A novel wind turbine condition monitoring method based on cloud computing

Effective intelligent condition monitoring, as an effective technique to enhance the reliability of wind turbines and implement cost-effective maintenance, has been the object of extensive research and development to improve defect detection from supervisory control and data acquisition (SCADA) data, relying on perspective signal processing and statistical algorithms. The development of sophisticated machine learning now allows improvements in defect detection from historic data. This paper proposes a novel condition monitoring method for wind turbines based on Long Short-Term Memory (LSTM) algorithms. LSTM algorithms have the capability of capturing long-term dependencies hidden within a sequence of measurements, which can be exploited to increase the prediction accuracy. LSTM algorithms are therefore suitable for application in many diverse fields. The residual signal obtained by comparing the predicted values from a prediction model and the actual measurements from SCADA data can be used for condition monitoring. The effectiveness of the proposed method is validated in the case study. The proposed method can increase the economic benefits and reliability of wind farms.

https://www.mdpi.com/1996-1073/12/18/3411/pdf

A Novel Condition Monitoring Method of Wind Turbines Based on Long Short-Term Memory Neural Network

Accurate and reliable fault detecting plays a key role in application of grid-connected wave power generation systems. This study presents a novel IoT-based approach to condition monitoring of the wave power generation system, which has faster operating rate and lower hardware requirement. The compressed sensing (CS) method is adopted to compress the data, which aims to reduce the data uploaded to cloud platform; and then, the extreme learning machine (ELM) algorithm is used to achieve the condition monitoring of wave power generation system in cloud platform. In order to validate the effectiveness of the proposed method, the IoT-based wave power generation condition monitoring system test platform is established. The experiment results illustrate the high efficiency and reliability of proposed method. The proposed method has a potential of practical applications.

IoT-based approach to condition monitoring of the wave power generation system

A reliable condition monitoring system can help improve the reliability of wind turbines and reduce cost. Condition monitoring method based on supervisory control and data acquisition (SCADA) data has been improved an effective method to achieve fault detection. With the development of machine learning technology, higher accuracy condition monitoring model can be established by using historic data. This paper proposes a novel condition monitoring method for wind turbines based on Long ShortTerm Memory (LSTM) algorithms. In terms of time series data, LSTM model can construct the correlation between the prior-known information and the current environment. The residual signals acquired by comparing the predicted data in a prediction model and the actual measurements from SCADA data can be used to achieve condition monitoring. The effectiveness of the proposed method is validated in the case study.

/pdf/a-condition-monitoring-method-of-wind-turbines-based-on-long-2p8qswet4p.pdf

Xiange Tian

Papers

Review on configuration and control methods of tidal current turbines

A novel wind turbine condition monitoring method based on cloud computing

A Novel Condition Monitoring Method of Wind Turbines Based on Long Short-Term Memory Neural Network

IoT-based approach to condition monitoring of the wave power generation system

A condition monitoring method of wind turbines based on Long Short-Term Memory neural network