A Small-Sample Wind Turbine Fault Detection Method With Synthetic Fault Data Using Generative Adversarial Nets

Liu, Jinhai; Qu, Fuming; Hong, Xiaowei; Zhang, Huaguang

doi:10.1109/tii.2018.2885365

Cited by 150 publications

(36 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where B (n) is the upper bound of the grid size. This paper uses B (n) = n 0.6 because it has better performance in practice [43], [44], [46], [47].…”

Section: Maximum Information Coefficientmentioning

confidence: 99%

Unsupervised Detection of Abnormal Electricity Consumption Behavior Based on Feature Engineering

Zhang¹,

Dong²,

Li³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The detection of abnormal electricity consumption behavior has been of great importance in recent years. However, existing research often focuses on algorithm improvement and ignores the process of obtaining features. The optimal feature set, which reflects customers' electricity consumption behavior, has a significant influence on the final detection results. Moreover, it is not straightforward to obtain datasets with label information. In this paper, a method based on feature engineering for unsupervised detection of abnormal electricity consumption behavior is proposed. First, the original feature set is constructed by brainstorming in the feature engineering step. Then, the optimal feature set, which reflects the customers' electricity consumption behavior, is obtained by features selected based on the variance and similarity between them. After that, in the abnormal detection step, a density-based clustering algorithm, in which the best clustering parameters are selected through iteration and evaluation, combined with unsupervised clustering evaluation indexes, is used to detect abnormal electricity consumption behaviors. Finally, using the load dataset of an industrial park, several typical feature strategies are applied for comparison with the feature engineering proposed in this paper. To perform the evaluation, the label information of abnormal behaviors is obtained by combining the original electricity consumption behavior detection results with abnormal data injections. The abnormal detection method proposed has given good results and outperformed typical feature strategies in an effective and generalizable way.

show abstract

“…where B (n) is the upper bound of the grid size. This paper uses B (n) = n 0.6 because it has better performance in practice [43], [44], [46], [47].…”

Section: Maximum Information Coefficientmentioning

confidence: 99%

Unsupervised Detection of Abnormal Electricity Consumption Behavior Based on Feature Engineering

Zhang¹,

Dong²,

Li³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

show abstract

“…(2) Error cause identification If the effects of the factors in each layer on the contour error are different, the error cause identification of machine tool dynamic accuracy can be carried out. (45,46) The error cause identification is similar to the evaluation, i.e., the final result is derived from the results of each layer of the evaluation model. The specific process is shown in Fig.…”

Section: Evaluation Of Machine Tool Dynamic Accuracymentioning

confidence: 99%

Method of Evaluating Dynamic Accuracy of Five-axis Machine Tool Based on Test Piece and Comprehensive Evaluation System

Song¹,

Dai²,

Li³

et al. 2020

Sensors and Materials

View full text Add to dashboard Cite

To improve the dynamic accuracy of a five-axis machine tool, an evaluation method based on a test piece and a comprehensive evaluation (CE) system is proposed in this paper. The test pieces, namely, cone frustum and S test piece, in ISO 10791-7 are compared to show their ability to reflect the dynamic accuracy. After the comparison, the S test piece is selected owing to its various changes in contour error under different dynamic accuracies. The kinematic and dynamic simulation model is established to affect the effects of the various dynamic factors on the S test piece. The relationship between the dynamic factors and the S test piece is applied to the construction of a CE system. Then, the evaluation of the dynamic accuracy of the fiveaxis machine tool can be completed. On the basis of the evaluation result, the error is identified to determine the factors that must be adjusted. Thus, the dynamic accuracy of the fiveaxis machine tool can be improved by the adjustment. The proposed method is validated by experiments.

show abstract

“…Generative Adversarial Nets (GANs) have recently attracted a lot of attention in the machine learning area for generating new synthetic data with the same statistics as the training set [10]. It has a capability to learn and mimic any distribution of data and has been widely applied in image generation, video generation, etc [11], [12].…”

Section: Introductionmentioning

confidence: 99%

A Gans-Based Deep Learning Framework for Automatic Subsurface Object Recognition From Ground Penetrating Radar Data

Xin

Han²,

Robinson³

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Ground penetrating radar (GPR) is a well-known useful tool for subsurface exploration. GPR data can be recorded at a relatively high speed in a continuous way with hyperbolas being artifacts and evidence of disturbances in the soil. Automatic and accurate detection and interpretation of hyperbolas in GPR remains an open challenge. Recently deep learning techniques have achieved remarkable success in image recognition tasks and this has potential for interpretation of GPR data. However, training reliable deep learning models requires massive labeled data, which is challenging. To address the challenges, this work proposes a Generative Adversarial Nets (GANs)-based deep learning framework, which generates new training data to address the scarcity of GPR data, automatically learns features and detects subsurface objects (via hyperbola) through an end-to-end solution. We have evaluated our proposed approach using real GPR B-scan images from rail infrastructure monitoring applications and compared this with the stateof-the-art methods for object detection (i.e. Faster-RCNN, Cascade R-CNN, SSD and YOLO V2). The proposed approach outperforms the existing methods with high accuracy of 97% being the mean Average Precision (mAP). Moreover, the proposed approach also demonstrates the good generalizability through cross-validation on independent datasets. INDEX TERMS Generative Adversarial Nets (GANs), Deep learning, Ground penetrating radar (GPR)

show abstract

A Small-Sample Wind Turbine Fault Detection Method With Synthetic Fault Data Using Generative Adversarial Nets

Cited by 150 publications

References 34 publications

Unsupervised Detection of Abnormal Electricity Consumption Behavior Based on Feature Engineering

Unsupervised Detection of Abnormal Electricity Consumption Behavior Based on Feature Engineering

Method of Evaluating Dynamic Accuracy of Five-axis Machine Tool Based on Test Piece and Comprehensive Evaluation System

A Gans-Based Deep Learning Framework for Automatic Subsurface Object Recognition From Ground Penetrating Radar Data

Contact Info

Product

Resources

About