A combined mono- and multi-turbine approach for fault indicator synthesis and wind turbine monitoring using SCADA data

Design of Fire Risk Estimation Method Based on Facility Data for Thermal Power Plants

In this paper, we propose a data classification and analysis method to estimate fire risk using facility data of thermal power plants. To estimate fire risk based on facility data, we divided facilities into three states-Steady, Transient, and Anomaly-categorized by their purposes and operational conditions. This method is designed to satisfy three requirements of fire protection systems for thermal power plants. For example, areas with fire risk must be identified, and fire risks should be classified and integrated into existing systems. We classified thermal power plants into turbine, boiler, and indoor coal shed zones. Each zone was subdivided into small pieces of equipment. The turbine, generator, oil-related equipment, hydrogen (H2), and boiler feed pump (BFP) were selected for the turbine zone, while the pulverizer and ignition oil were chosen for the boiler zone. We selected fire-related tags from Supervisory Control and Data Acquisition (SCADA) data and acquired sample data during a specific period for two thermal power plants based on inspection of fire and explosion scenarios in thermal power plants over many years. We focused on crucial fire cases such as pool fires, 3D fires, and jet fires and organized three fire hazard levels for each zone. Experimental analysis was conducted with these data set by the proposed method for 500 MW and 100 MW thermal power plants. The data classification and analysis methods presented in this paper can provide indirect experience for data analysts who do not have domain knowledge about power plant fires and can also offer good inspiration for data analysts who need to understand power plant facilities.

A deep capsule neural network with data augmentation generative adversarial networks for single and simultaneous fault diagnosis of wind turbine gearbox

The fault diagnosis (FD) of wind turbine gearbox (WTG) is of special importance for keeping the wind turbine drivetrain working normally and safely. However, owing to the limited training data and the mutual interference of various mechanical parts, it is of great difficulty to realize the simultaneous-fault monitoring task of WTG using existing intelligent FD methods or manual inspection-based approaches. To tackle the issue, a deep capsule neural network with data augmentation generative adversarial networks, named ST-DAGANs-CapNet, is developed for the single and simultaneous FD of WTG by integrating capsule neural network (CapsNet) with Stockwell transform (ST) and data augmentation generative adversarial networks (DAGANs). The proposed ST-DAGANs-CapNet method mainly consists of three steps. First of all, ST is adopted to extract two-dimension (2-d) image features of time-frequency domain from raw time-domain vibration signals of WTG. Then, DAGANs are employed for generating more fake image samples to address the problem of lacking training data. At last, the built CapsNet model is utilized to diagnose the single and compound faults of WTG by the primary 2-d feature images and the made fake 2-d feature images in training set. Two experimental studies are implemented to prove the effectiveness of the proposed method, and the result is compared with some existing intelligent FD of WTG. It indicates that DAGANs are effective in helping to tackle the issue of limited and unbalanced training samples in real FD of WTG, and the diagnosis result of the proposed approach in test sample set is better than that of several commonly used FD methods in literatures.

Correlation Investigation of Wind Turbine Multiple Operating Parameters Based on SCADA Data

The primary wind turbines’ in-service performance evaluation method is mining and analyzing the SCADA data. However, there are complex mathematical and physical relationships between multiple operating parameters, and so far, there is a lack of systematic understanding. To solve this issue, the distribution of wind turbines’ operating parameters was first analyzed according to the characteristics of the energy flow of wind turbines. Then, the correlation calculation was performed using the Spearman correlation coefficient method based on the minute-level data and second-level data. According to the numerical characteristics of the nacelle vibration acceleration, the data preprocessing technology sliding window maximum (SWM) was proposed during the calculation. In addition, taking temperature correlation as an example, two-dimensional scatter (including single-valued scatter) and three-dimensional scatter features were combined with numerical analysis and physical mechanism analysis to understand the correlation characteristics better. On this basis, a quantitative description model of the temperature characteristics of the gearbox oil pool was constructed. Through this research work, the complex mathematical and physical relationships among the multi-parameters of the wind turbines were comprehensively obtained, which provides data and theoretical support for the design, operation, and maintenance.

A Multi-Turbine Approach for Improving Performance of Wind Turbine Power-Based Fault Detection Methods

The relationship between wind speed and the power produced by a wind turbine is expressed by its power curve. Power curves are commonly used to monitor the production performance of a wind turbine by asset managers to ensure optimal production. They can also be used as a tool to detect faults occurring on a wind turbine when the fault causes a decrease in performance. However, the wide dispersion of data generally observed around the reference power curve limits the detection performance of power curve-based techniques. Fault indicators, such as residuals, which measure the difference between the actual power produced and the expected power, are largely affected by this dispersion. To increase the detection performance of power-based fault detection methods, a hybrid solution of mono-multi-turbine residual generation is proposed in this paper to reduce the influence of the power curve dispersion. A new simulation framework, modeling the effect of wind nature (turbulent/laminar) on the wind turbine performance, is also proposed. This allows us to evaluate and compare the performances of two fault detection methods in their multi-turbine implementation. The results show that the application of a multi-turbine approach to a basic residual generation method significantly improves its detection performance and makes it as efficient as a more complex method.

Exploring Quantum Machine Learning and Feature Reduction Techniques for Wind Turbine Pitch Fault Detection

Driven by the development of machine learning (ML) and deep learning techniques, prognostics and health management (PHM) has become a key aspect of reliability engineering research. With the recent rise in popularity of quantum computing algorithms and public availability of first-generation quantum hardware, it is of interest to assess their potential for efficiently handling large quantities of operational data for PHM purposes. This paper addresses the application of quantum kernel classification models for fault detection in wind turbine systems (WTSs). The analyzed data correspond to low-frequency SCADA sensor measurements and recorded SCADA alarm logs, focused on the early detection of pitch fault failures. This work aims to explore potential advantages of quantum kernel methods, such as quantum support vector machines (Q-SVMs), over traditional ML approaches and compare principal component analysis (PCA) and autoencoders (AE) as feature reduction tools. Results show that the proposed quantum approach is comparable to conventional ML models in terms of performance and can outperform traditional models (random forest, k-nearest neighbors) for the selected reduced dimensionality of 19 features for both PCA and AE. The overall highest mean accuracies obtained are 0.945 for Gaussian SVM and 0.925 for Q-SVM models.

An Ensemble Learning Solution for Predictive Maintenance of Wind Turbines Main Bearing

A novel and innovative solution addressing wind turbines’ main bearing failure predictions using SCADA data is presented. This methodology enables to cut setup times and has more flexible requirements when compared to the current predictive algorithms. The proposed solution is entirely unsupervised as it does not require the labeling of data through work orders logs. Results of interpretable algorithms, which are tailored to capture specific aspects of main bearing failures, are merged into a combined health status indicator making use of Ensemble Learning principles. Based on multiple specialized indicators, the interpretability of the results is greater compared to black-box solutions that try to address the problem with a single complex algorithm. The proposed methodology has been tested on a dataset covering more than two year of operations from two onshore wind farms, counting a total of 84 turbines. All four main bearing failures are anticipated at least one month of time in advance. Combining individual indicators into a composed one proved effective with regard to all the tracked metrics. Accuracy of 95.1%, precision of 24.5% and F1 score of 38.5% are obtained averaging the values across the two windfarms. The encouraging results, the unsupervised nature and the flexibility and scalability of the proposed solution are appealing, making it particularly attractive for any online monitoring system used on single wind farms as well as entire wind turbine fleets.