An official website of the United States government
Abstract While preventive maintenance is crucial in wind turbine operation, conventional condition monitoring systems face limitations in terms of cost and complexity when compared to innovative signal processing techniques and artificial intelligence. In this paper, a cascading deep learning framework is proposed for the monitoring of generator winding conditions, specifically to promptly detect and identify inter-turn short circuit faults and estimate their severity in real time. This framework encompasses the processing of high-resolution current signal samples, coupled with the extraction of current signal features in both time and frequency domains, achieved through discrete wavelet transform. By leveraging long short-term memory recurrent neural networks, our aim is to establish a cost-efficient and reliable condition monitoring system for wind turbine generators. Numeral experiments show an over 97% accuracy for fault diagnosis and severity estimation. More specifically, with the intrinsic feature provided by wavelet transform, the faults can be 100% identified by the diagnosis model.
more »
« less
This content will become publicly available on April 1, 2026
Bi-Level Interturn Short-Circuit Fault Monitoring for Wind Turbine Generators With Benchmark Dataset Development
Abstract Flourished wind energy market pushes the latest wind turbines (WTs) to further and harsher inland and offshore environment. Increased operation and maintenance cost calls for more reliable and cost effective condition monitoring systems. In this article, a bi-level condition monitoring framework for interturn short-circuit faults (ITSCFs) in WT generators is proposed. A benchmark dataset, consisting of 75 ITSCF scenarios and generator current signals of a specific WT, has been created and made publicly available on Zenodo. The data are simulated at a rate of 4 kHz. Based on the time and frequency features extracted from data processing, machine learning-based severity estimation and faulty phase identification modules can provide valuable diagnostic information for wind farm operators. Specifically, the performance of long short-term memory (LSTM) networks, gated recurrent unit (GRU) networks, and convolutional neural networks (CNNs) are analyzed and compared for severity estimation and faulty phase identification. For test-bed experimental reference, various numbers of scenarios for training the models are analyzed. Numerical experiments demonstrate the computational efficiency and robust denoising capability of the CNN algorithm. The GRU network, however, achieves the highest accuracy. The overall system performance improves significantly, from 87.76% with 16 training scenarios to 99.95% with 52 training scenarios, when tested on a set containing all 76 scenarios from an unforeseen period.
more »
« less
- Award ID(s):
- 1916776
- PAR ID:
- 10658230
- Publisher / Repository:
- ASME
- Date Published:
- Journal Name:
- Journal of Mechanical Design
- Volume:
- 147
- Issue:
- 4
- ISSN:
- 1050-0472
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Milling is a critical manufacturing process to produce high-value components in aerospace, tooling, and automotive industries. However, milling is prone to chatter, a severe vibration that damages surface quality, cutting tools, and machines. Traditional experimental and mechanistic methods of chatter prediction have significant limitations. This study presents a data-driven machine learning (ML) model to predict and quantify milling chatter directly based on time-series vibration data. Three ML models, including hybrid long short-term memory (LSTM)—fully convolutional network (FCN) model, gated recurrent unit (GRU)—FCN model, and temporal convolutional network (TCN) models, have been developed and verified by incorporating milling parameters to enhance prediction accuracy and stability. Among the proposed models, the best-performing ML model (GRU-FCN) demonstrates strong performance in chatter prediction and severity quantification, providing actionable insights with improved computational efficiency. The integration of milling parameters into the ML model notably enhances the prediction accuracy and stability, proving particularly effective in real-time monitoring scenarios.more » « less
-
ABSTRACT Traditional software reliability growth models (SRGM) characterize defect discovery with the Non‐Homogeneous Poisson Process (NHPP) as a function of testing time or effort. More recently, covariate NHPP SRGM models have substantially improved tracking and prediction of the defect discovery process by explicitly incorporating discrete multivariate time series on the amount of each underlying testing activity performed in successive intervals. Both classes of NHPP models with and without covariates are parametric in nature, imposing assumptions on the defect discovery process, and, while neural networks have been applied to SRGM models without covariates, no such studies have been applied in the context of covariate SRGM models. Therefore, this paper assesses the effectiveness of neural networks in predicting the software defect discovery process, incorporating covariates. Three types of neural networks are considered, including (i) recurrent neural networks (RNNs), (ii) long short‐term memory (LSTM), and (iii) gated recurrent unit (GRU), which are then compared with covariate models to validate tracking and predictive accuracy. Our results suggest that GRU achieved better overall goodness‐of‐fit, such as approximately 3.22 and 1.10 times smaller predictive mean square error, and 5.33 and 1.22 times smaller predictive ratio risk in DS1G and DS2G data sets, respectively, compared to covariate models when of the data is used for training. Moreover, to provide an objective comparison, three different proportions for training data splits were employed to illustrate the advancements between the top‐performing covariate NHPP model and the neural network, in which GRU illustrated a better performance over most of the scenarios. Thus, the neural network model with gated recurrent units may be a suitable alternative to track and predict the number of defects based on covariates associated with the software testing process.more » « less
-
The nature of wave resources usually requires wave energy converter (WEC) components to handle peak loads (i.e., torques, forces, and powers) that are many times greater than their average loads, accelerating equipment degradation. Moreover, due to their isolated nature and harsh operating environment, WEC systems are projected to possess high operations and maintenance (O&M) cost, i.e., around 27% of their leveled cost of energy. As such, developing techniques to mitigate these costs through the application of condition monitoring and fault tolerant control will significantly impact the economic feasibility of grid connected WEC power. Toward this goal, models of faulty components are developed in the open source modeling platform, WEC‐Sim, to estimate the performance and measurable states of a WEC operating with likely device and sensor failures. Two types of faulty component models are then applied to a point absorber WEC model with basic controller damping and spring forces. Resulting changes in device behavior are recorded as a benchmark, and a graph‐theoretic approach is proposed for fault detection and identification utilizing multivariate time series. Simulation results demonstrate that these faults can greatly affect the WEC performance, and that the proposed method can effectively detect and classify different types of faults.more » « less
-
In recent years, using orthogonal matrices has been shown to be a promising approach to improving recurrent neural networks (RNNs) with training, stability, and convergence, particularly to control gradients. While gated recurrent unit (GRU) and long short-term memory (LSTM) architectures address the vanishing gradient problem by using a variety of gates and memory cells, they are still prone to the exploding gradient problem. In this work, we analyze the gradients in GRU and propose the use of orthogonal matrices to prevent exploding gradient problems and enhance long-term memory. We study where to use orthogonal matrices and propose a Neumann series–based scaled Cayley transformation for training orthogonal matrices in GRU, which we call Neumann-Cayley orthogonal GRU (NC-GRU). We present detailed experiments of our model on several synthetic and real-world tasks, which show that NC-GRU significantly outperforms GRU and several other RNNs.more » « less
