Wasserstein Generative Adversarial Network Research Articles

English Vocabulary Learning Aid System Using Digital Twin Wasserstein Generative Adversarial Network Optimized With Jelly Fish Optimization Algorithm

ABSTRACT Natural Language Processing (NLP) is a technology that permits computers to recognize human languages. Words are the fundamental unit of analysis in deep-level grammatical and semantic analysis. The main goal of NLP is typically word segmentation. Since the machine learning techniques cannot be directly applied to the practical issue of significant structural disparities between various data modalities in a multi-modal context. In this paper, English Vocabulary Learning Aid System Using Digital Twin Wasserstein Generative Adversarial Network Optimized using Jelly Fish Optimization Algorithm is proposed. The problematic of multiple modal data heterogeneity is handled by the feature extraction of Parameterized Local Maximum Synchro squeezing Transform and extract the features such as Phonetic features, sentence length, word embedding’s, part of speech tags, word frequencies, N-grams. Then, the Digital twin Wasserstein generative adversarial network classifies the English vocabulary to easy words, intermediate words, and difficult words. The performance of the proposed EVLS-DtwinWGAN-NLP approach attains 3.101%, 7.12%, 7.73% higher accuracy, 24.13%, 13.04%, 29.51% lower computation Time and 2.292%, 5.365%, 1.551% higher AUC compared with existing methods like Feature extraction and analysis of natural language processing for deep learning English language (EVLS-BiLSTM-NLP), State of art for semantic analysis of natural language processing (EVLS-SA-NLP) respectively.

Research on fault diagnosis of industrial robots based on generative adversarial network

Abstract-In today's industrial production, companies have to introduce various types of industrial robots in order to reduce labor costs, shorten product processing time, and obtain greater profits. This move has caused the installed capacity of industrial robots to increase year by year. However, this also makes industrial robots have more and more frequent failures and an increasing amount of failures in actual production. The occurrence of industrial robot failures is unavoidable, and the amount of data in the healthy state and the amount of data in the fault state are extremely unbalanced. Whether the fault diagnosis model is efficient and accurate is the key to providing reliable theoretical and technical support for the health management of industrial robots. Therefore, this paper constructs an imbalanced data fault diagnosis model based on Wasserstein Generative Adversarial Network (WGAN) for fault diagnosis of industrial robots in data balanced and unbalanced states. We evaluate the quality of generated data through the following three aspects: the change in loss values ​​of the discriminator and generator, the degree of overlap between the generated data and real data samples, and the classification accuracy of the classification algorithm. The results show that the data generated by the WGAN model is of high quality and can be used as extended data for the fault data set. Next, we used the deep residual network designed in this article to perform fault diagnosis on the balanced data set expanded with the generated data. The experimental results confirmed the high quality of the generated data and the outstanding expressive ability of the deep residual network. In order to measure the performance of the model in this paper, we used 7 types of generative adversarial networks to generate fault data. The quality of the generated data samples is still analyzed and evaluated through the three aspects mentioned above. The results show that only the conditional Wasserstein generative adversarial network model generates data of high quality, which can be used as extended data for fault data and has good results in actual applications.

An oil wear particle identification method based on Wasserstein generative adversarial network and improved CNN using a custom-built optical imaging sensor

The accurate classification of wear particles in lubricating oil holds significant importance for understanding the wear characteristics of lubricated components. However, there are prominent issues, such as blurred particle images, limited identification efficiency, and low generalization capabilities. To solve the problems, this research initially devises an exceptional online monitoring sensor to collect particle images based on the optical method. Subsequently, an improved Wasserstein Generative Adversarial Network (WGAN) is developed to ameliorate the categorization performance, which is hampered by data imbalance. Lastly, a MobileNetV2-SENet-based Convolutional Neural Network (MSCNN) is proposed to autonomously discover the associations between images and types of wear particles. Experimental results illustrate that our method achieves a recognition accuracy rate of 92.5%. The analysis outcomes between several comparative networks show that our approach can effectively improve recognition performance under conditions of limited samples. This work offers an effective solution for automatically identifying wear particles in oil and can be a powerful predictive maintenance tool for rotating mechanical equipment.

WSBCV: A data-driven cross-version defect model via multi-objective optimization and incremental representation learning

Cross-version defect prediction (CVDP) refers to training an excellent model on tagged defect data in a previously released project version, and then performing defect prediction on an unlabeled instance module in the current version. Nevertheless, the complicated internal intrinsic construction hidden behind the code defects makes it difficult for the previous cross-version defect models to capture more discriminative software features, and seriously restrains the CVDP performance. In this study, we propose an intelligent data-driven CVDP model named WSBCV based on multi-objective optimization and incremental representation learning. We firstly leverage an advanced deep generation adversarial network – WGAN-GP (Wasserstein GAN with Gradient Penalty) to perform data augmentation, including balancing defect classes and synthesizing abundant training instances. Secondly, a multi-objective SPEA/R (Strength Pareto-based Evolutionary Algorithm / Reference) feature selection optimization method is built to effectively search the fewest representative feature subsets while achieving the minimum error. Finally, a powerful defect predictor for CVDP based on the BLS (Broad Learning System) with incremental learning is built to learn excellent feature representations and achieve incremental online model update quickly. Experimental results across 32 cross-version pairs from 45 version demonstrate that the proposed SPEA/R, BLS and WSBCV all have statistically significant difference advantages compared to ten multi-objective feature selection approaches, six defect predictors and two CVDP models, respectively.

Ultra-fast generation of air shower images for Imaging Air Cherenkov Telescopes using Generative Adversarial Networks

For the analysis of data taken by Imaging Air Cherenkov Telescopes (IACTs), a large number of air shower simulations are needed to derive the instrument response. The simulations are very complex, involving computational and memory-intensive calculations, and are usually performed repeatedly for different observation intervals to take into account the varying optical sensitivity of the instrument. The use of generative models based on deep neural networks offers the prospect for memory-efficient storing of huge simulation libraries and cost-effective generation of a large number of simulations in an extremely short time. In this work, we use Wasserstein Generative Adversarial Networks to generate photon showers for an IACT equipped with the FlashCam design, which has more than 1,500 pixels. Using simulations of the H.E.S.S. experiment, we demonstrate the successful generation of high-quality IACT images. The analysis includes a comprehensive study of the generated image quality based on low-level observables and the well-known Hillas parameters that describe the shower shape. We demonstrate for the first time that the generated images have high fidelity with respect to low-level observables, the Hillas parameters, their physical properties, as well as their correlations. The found increase in generation speed in the order of 105 yields promising prospects for fast and memory-efficient simulations of air showers for IACTs.

Gan-based data augmentation to improve breast ultrasound and mammography mass classification

Data imbalance is a common problem in breast cancer diagnosis, to address this challenge, the research explores the use of Generative Adversarial Networks (GANs) to generate synthetic medical data. Various GAN methods, including Wasserstein GAN with Gradient Penalty (WGAN-GP), Cycle GAN, Conditional GAN, and Spectral Normalization GAN (SNGAN), were tested for data augmentation in breast regions of interest (ROIs) using mammography and ultrasound databases. The study employed real, synthetic, and hybrid ROIs (128x128 pixels) to train a Resnet network for classifying as benign (B) or malignant (M) classes. The quality and diversity of the synthetic data were assessed using several metrics: Fréchet Inception Distance (FID), Kernel Inception Distance (KID), Structural Similarity Index (SSIM), Multi-Scale SSIM (MS-SSIM), Blind Reference Image Spatial Quality Evaluator (BRISQUE), Naturalness Image Quality Evaluator (NIQE), and Perception-based Image Quality Evaluator (PIQE).Results revealed that the SNGAN model (FID = 52.89) was most effective for augmenting mammography data, while CGAN (FID = 116.03) excelled with ultrasound data. Cycle GAN and WGAN-GP, though demonstrating lower KID values, did not perform better than SNGAN and CGAN. The lower average MS-SSIM values suggested that SNGAN and CGAN produced a high diversity of synthetic images. However, lower SSIM, BRISQUE, NIQE, and PIQE values indicated poor quality in both real and synthetic images. Classification results showed high accuracy without data augmentation in both US (93.1 %B/94.9 %M) and mammography (80.9 %B/76.9 %M). The research concludes that preprocessing and characterizing ROIs by abnormality type is crucial to generate diverse synthetic data and improve accuracy in the classification process using combined GANs and CNN models.

Diffusion-based Wasserstein generative adversarial network for blood cell image augmentation

White blood cells (WBC) are vital elements of the immune system, and their number and differential count are crucial for diagnosing blood-related disorders. While existing research has primarily focused on classifying easily distinguishable major WBC types, our study delves into a model encompassing up to 19 WBC classes, some of which exhibit irregular shapes and are challenging to differentiate manually. Convolutional Neural Networks (CNNs) have shown remarkable progress in accurately classifying these intricate WBC classes. However, the accuracy of these models depends mainly on the availability of enough appropriate datasets, which can be challenging to obtain for rare WBC classes. To address this, we introduce a generative model, the diffusion-based Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP). This model innovatively combines the Denoising Diffusion Probabilistic Model (DDPM) forward diffusion process with the WGAN-GP, leveraging DDPM’s noisy vectors as inputs for WGAN-GP’s generator. This fusion accelerates the generative process and significantly enhances the output’s fidelity, particularly for complex WBC images. Our model demonstrated its effectiveness on a dataset comprising 4,503 images across 19 WBC classes from Soonchunhyang University Bucheon Hospital, Korea, showing significant improvement in generating high-quality images for rare WBC classes and addressing data imbalance. We further combined pre-trained CNNs with Support Vector Machines (SVM) for classification, where our augmentation strategy led to the ResNet50-SVM model achieving an average accuracy of 95% in classifying the 19 WBC classes. This study not only addresses the data imbalance but also sets a new benchmark in WBC image analysis, demonstrating our model’s efficacy in generating high-quality data for rare classes.

Optimizing GAN parameters for efficient and accurate image generation: A study of WGAN-GP in brain tumor dataset

In this era of unprecedented rapid development of artificial intelligence, researchers are moving forward to develop new neural networks. Nevertheless, few have considered optimizing the extant generative adversarial network (GAN) to achieve the most effective and accurate solutions to provide optimal results for the challenges. This study aims to investigate the critical role of parameter optimization in GAN neural networks, with a particular focus on the Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP) architecture applied to the generation of medical images, especially images depicting brain tumors. Therefore, the project used Kaggles brain tumor data set as a canvas to conduct an in-depth study of the impact of these parameters on the training model and generated results. For the starter, to investigate how alterations in the learning rate impact the model, this article selects a series of values for meticulous analysis to determine the most effective configuration. Then, evaluate and find a better and more suitable choice between Adam and SGD optimizers through comparison, focusing on their impact on training dynamics. As the last one, this study examines how the Tanh activation function constrains pixel values and shapes image realism through comparative results. By dissecting and understanding the interaction of these parameters in detail, we lay the foundation for optimizing GAN neural networks, increasing their efficiency, and producing accurate solutions for accurate diagnostics and healthcare applications. The journey through the labyrinth of GAN parameter tuning ultimately provided valuable insights into seamlessly synthesizing medical images.

Comparative assessment of generative models for transformer- and consumer-level load profiles generation

Residential load profiles (RLPs) play an increasingly important role in the optimal operation and planning of distribution systems, particularly with the rising integration of low-carbon energy resources such as PV systems, electric vehicles, small-scale batteries, etc. Despite the prevalence of various data-driven models for generating consumption profiles, there is a lack of clear conclusions about their relative strengths and weaknesses. This study undertakes a comprehensive comparison of frequently used data-driven models in recent research, including Generative Adversarial Networks (GANs), Variational Autoencoders (VAE), Wasserstein GANs (WGAN), WGANs with Gradient Penalty (WGANGP), Gaussian Mixture Models (GMMs), and Gaussian Mixture Copulas (GMC). The presented comparison explores the effectiveness of the above-mentioned models on transformer- and consumer-level consumption profiles, as well as for different time resolutions (15-min, 30-min, and 60-min). The objective of this research is to elucidate the respective advantages and drawbacks of these models, thereby providing valuable insights for subsequent research in this field.

Rotating Machinery Fault Diagnosis with Limited Multisensor Fusion Samples by Fused Attention-Guided Wasserstein GAN

As vital equipment in modern industry, the health state of rotating machinery influences the production process and equipment safety. However, rotating machinery generally operates in a normal state most of the time, which results in limited fault data, thus greatly constraining the performance of intelligent fault diagnosis methods. To solve this problem, this paper proposes a novel fault diagnosis method for rotating machinery with limited multisensor fusion samples based on the fused attention-guided Wasserstein generative adversarial network (WGAN). Firstly, the dimensionality of collected multisensor data is reduced to three channels by principal component analysis, and then the one-dimensional data of each channel are converted into a two-dimensional pixel matrix, of which the RGB images are obtained by fusing the three-channel two-dimensional images. Subsequently, the limited RGB samples are augmented to obtain sufficient samples utilizing the fused attention-guided WGAN combined with the gradient penalty (FAWGAN-GP) method. Lastly, the augmented samples are applied to train a residual convolutional neural network for fault diagnosis. The effectiveness of the proposed method is demonstrated by two case studies. When training samples per class are 50, 35, 25, and 15 on the KAT-bearing dataset, the average classification accuracy is 99.9%, 99.65%, 99.6%, and 98.7%, respectively. Meanwhile, the methods of multisensor fusion and the fused attention mechanism have an average improvement of 1.51% and 1.09%, respectively, by ablation experiments on the WT gearbox dataset.

Differential-Critic GAN: Generating What You Want by a Cue of Preferences.

This article proposes differential-critic generative adversarial network (DiCGAN) to learn the distribution of user-desired data when only partial instead of the entire dataset possesses the desired property. DiCGAN generates desired data that meet the user's expectations and can assist in designing biological products with desired properties. Existing approaches select the desired samples first and train regular GANs on the selected samples to derive the user-desired data distribution. However, the selection of the desired data relies on global knowledge and supervision over the entire dataset. DiCGAN introduces a differential critic that learns from pairwise preferences, which are local knowledge and can be defined on a part of training data. The critic is built by defining an additional ranking loss over the Wasserstein GAN's critic. It endows the difference of critic values between each pair of samples with the user preference and guides the generation of the desired data instead of the whole data. For a more efficient solution to ensure data quality, we further reformulate DiCGAN as a constrained optimization problem, based on which we theoretically prove the convergence of our DiCGAN. Extensive experiments on a diverse set of datasets with various applications demonstrate that our DiCGAN achieves state-of-the-art performance in learning the user-desired data distributions, especially in the cases of insufficient desired data and limited supervision.

Generative adversarial networks for data-scarce radiative heat transfer applications

Abstract Generative adversarial networks (GANs) are one of the most robust and versatile techniques in the field of generative artificial intelligence. In this work, we report on an application of GANs in the domain of synthetic spectral data generation for data-scarce radiative heat transfer applications, an area where their use has not been previously reported. We demonstrate the proposed approach by applying it to an illustrative problem within the realm of near-field radiative heat transfer involving a multilayered hyperbolic metamaterial. We find that a successful generation of spectral data requires two modifications to conventional GANs: (i) the introduction of Wasserstein GANs (WGANs) to avoid mode collapse, and, (ii) the conditioning of WGANs to obtain accurate labels for the generated data. We show that a simple feed-forward neural network (FFNN), when augmented with data generated by a CWGAN, enhances significantly its performance under conditions of limited data availability. In addition, we show that CWGANs can act as a surrogate model with improved performance in the low-data regime with respect to simple FFNNs. Overall, this work contributes to highlight the potential of generative machine learning algorithms in scientific applications beyond image generation and optimization.

A framework for demonstrating practical quantum advantage: comparing quantum against classical generative models

Generative modeling has seen a rising interest in both classical and quantum machine learning, and it represents a promising candidate to obtain a practical quantum advantage in the near term. In this study, we build over an existing framework for evaluating the generalization performance of generative models, and we establish the first quantitative comparative race towards practical quantum advantage (PQA) between classical and quantum generative models, namely Quantum Circuit Born Machines (QCBMs), Transformers (TFs), Recurrent Neural Networks (RNNs), Variational Autoencoders (VAEs), and Wasserstein Generative Adversarial Networks (WGANs). After defining four types of PQAs scenarios, we focus on what we refer to as potential PQA, aiming to compare quantum models with the best-known classical algorithms for the task at hand. We let the models race on a well-defined and application-relevant competition setting, where we illustrate and demonstrate our framework on 20 variables (qubits) generative modeling task. Our results suggest that QCBMs are more efficient in the data-limited regime than the other state-of-the-art classical generative models. Such a feature is highly desirable in a wide range of real-world applications where the available data is scarce.

An Image Classification Method of Unbalanced Ship Coating Defects Based on DCCVAE-ACWGAN-GP

Affected by the improper operation of the workers, environmental changes during drying and curing or the quality of the paint itself, diverse defects are produced during the process of ship painting. The traditional defect recognition method relies on expert knowledge or experience to detect defects, which is not conducive to ensuring the effectiveness of defect recognition. Therefore, this paper proposes an image generation and recognition model which is suitable for small samples. Based on a deep convolutional neural network (DCNN), the model combines a conditional variational autoencoder (DCCVAE) and auxiliary conditional Wasserstein GAN with gradient penalty (ACWGAN-GP) to gradually expand and generate various coating defect images for solving the overfitting problem due to unbalanced data. The DCNN model is trained based on newly generated image data and original image data so as to build a coating defect image classification model suitable for small samples, which is conducive to improving classification performance. The experimental results showed that our proposed model can achieve up to 92.54% accuracy, an F-score of 88.33%, and a G mean value of 91.93%. Compared with traditional data enhancement methods and classification algorithms, our proposed model can identify various defects in the ship painting process more accurately and consistently, which can provide effective theoretical and technical support for ship painting defect detection and has significant engineering research value and application prospects.

Robust stochastic optimal dispatching of integrated electricity-gas-heat system considering generation-network-load uncertainties

Integrated energy systems with the deep coupling of electric power, natural gas, and heat have attracted much interest lately. In the modeling of such an integrated electric-gas-heat system (IEGHS), there is the problem of generation–load uncertainty. The literature has not yet addressed the uncertainties related to pipeline parameters and buried temperature in a natural gas network. To fill this gap, a robust stochastic optimal dispatching model has been proposed in this paper, which can effectively solve the IEGHS dispatching problem under multiple uncertainties. A robust adjustable uncertain set is adopted to deal with the uncertainties of wind power generation and pipeline parameters. The Wasserstein generative adversarial network based on gradient normalization is proposed to generate load-side demand scenarios. Then, a column and constraint generation algorithm is adopted to solve the proposed model. The simulation analysis successfully demonstrates the efficacy of the proposed model and algorithm. By utilizing this approach, the system can obtain a scheduling scheme with the lowest operating cost even under worst-case scenarios.

Comparison of three recent discrete stochastic inversion methods and influence of the prior choice

Groundwater flow depends on subsurface heterogeneity, which often calls for categorical fields to represent different geological facies. The knowledge about subsurface is however limited and often provided indirectly by state variables, such as hydraulic heads of contaminant concentrations. In such cases, solving a categorical inverse problem is an important step in subsurface modeling. In this work, we present and compare three recent inverse frameworks: Posterior Population Expansion (PoPEx), Ensemble Smoother with Multiple Data Assimilation (ESMDA), and DREAM-ZS (a Markov chain Monte Carlo sampler). PoPEx and ESDMA are used with Multiple-point statistics (MPS) as geostatistical engines, and DREAM-ZS is used with a Wasserstein generative adversarial network (WGAN). The three inversion methods are tested on a synthetic example of a pumping test in a fluvial channelized aquifer. Moreover, the inverse problem is solved three times with each method, each time using a different training image to check the performance of the methods with different geological priors. To assess the quality of the results, we propose a framework based on continuous ranked probability score (CRPS), which compares single true values with predictive distributions. All methods performed well when using the training image used to create the reference, but their performances were degraded with the alternative training images. PoPEx produced the least geological artifacts but presented a rather slow convergence. ESMDA showed initially a very fast convergence which reaches a plateau, contrary to the remaining methods. DREAM-ZS was overly confident in placing some incorrect geological features but outperformed the other methods in terms of convergence.

Bad Data Repair for New Energy Stations in Power System Based on Multi-Model Parallel Integration Approach

The accurate and reliable acquisition of measurement information is very important for the stable operation of power systems, especially the operation status information of new energy stations. With the increasing proportion of new energy stations in power systems, the quality issues of data from these stations, caused by communication congestion, interference, and network attacks, become more pronounced. In this paper, to deal with the issue of low accuracy and poor performance of bad data restoration in new energy stations, a novel deep learning approach by combining the modified long short-term memory (LSTM) neural network and Wasserstein generative adversarial network with gradient penalty (WGAN-GP) is proposed. The proposed method can be implemented in a parallel ensemble way. First, the normal data set acquired from multiple sections of new energy stations is utilized to train the modified LSTM and WGAN-GP model. Secondly, according to the data characteristics and rules captured by each model, the two models are systematically integrated and the bad data repair model pool is constructed. Subsequently, the results of model repair are screened and merged twice by the parallel integration framework to obtain the final repair result. Finally, the extensive experiments are carried out to verify the proposed method. The simulative results of energy stations in a real provincial power grid demonstrate that the proposed method can effectively repair bad data, thereby enhancing the data quality of new energy stations.

A generative adaptive convolutional neural network with attention mechanism for driver fatigue detection with class-imbalanced and insufficient data

Over the past few years, fatigue driving has emerged as one of the main causes of traffic accidents, necessitating the development of driver fatigue detection systems. However, many existing methods involves tedious manual parameter tunings, a process that is both time-consuming and results in task-specific models. On the other hand, most of the researches on fatigue recognition are based on class-balanced and sufficient data, and effectively “mine” meaningful information from class-imbalanced and insufficient data for fatigue recognition is still a challenge. In this paper, we proposed two novel models, the attention-based residual adaptive multiscale fully convolutional network-long short term memory network (ARMFCN-LSTM), and the Generative ARMFCN-LSTM (GARMFCN-LSTM) aiming to address this issue. ARMFCN-LSTM excels at automatically extracting multiscale representations through adaptive multiscale temporal convolutions, while capturing temporal dependency features through LSTM. GARMFCN-LSTM integrates Wasserstein GAN with gradient penalty (WGAN-GP) into ARMFCN-LSTM to improve driver fatigue detection performance by alleviating data scarcity and addressing class imbalances. Experimental results show that ARMFCN-LSTM achieves the highest classification accuracy of 95.84% in driver fatigue detection on the class-balanced EEG dataset (binary classification), and GARMFCN-LSTM attained an improved classification accuracy of 84.70% on the class-imbalanced EOG dataset (triple classification), surpassing the competing methods. Therefore, the proposed models are promising for further implementations in online driver fatigue detection systems.

Dual interactive Wasserstein generative adversarial networks optimized with hybrid Archimedes optimization and chimp optimization algorithm‐based channel estimation in OFDM

SummaryDual interactive Wasserstein generative adversarial networks optimized with hybrid Archimedes optimization and chimp optimization algorithm‐based channel estimation in OFDM (DiWGAN‐Hyb AOA‐COA‐MIMO‐OFDM) is proposed in this manuscript. In OFDM, there is a non‐stationary channel physical appearance during channel estimation (CE). Therefore in this work, Hyb AOA‐COA is employed to enhance the DiWGAN weight parameters. The proposed DiWGAN‐Hyb AOA‐COA‐MIMO‐OFDM technique is executed in network simulator (NS2) tool. The proposed technique attains lower computational cost 99.67%, 92.34%, and 97.45%; lesser bit error rate 98.33%, 83.12%, and 88.96%; and lesser mean square error 93.15%, 79.90%, and 92.88% compared with existing methods, like MIMO‐OFDM system using deep neural network and MN‐based improved AMO model (DNN‐IAMO‐MIMO‐OFDM), MIMO‐OFDM systems using the deep learning and optimization (RBFNN‐PSO‐MIMO‐OFDM), and MIMO‐OFDM systems using hybrid neural network (HNN‐CSI‐MIMO‐OFDM) respectively.

Application of generative AI-based data augmentation technique in transformer winding deformation fault diagnosis

Accurately diagnosing various winding deformation faults is significant in power transformer maintenance. Among the different fault diagnosis methods, frequency response analysis (FRA) is widely used but still poses challenges. Artificial intelligence (AI)-based methods have recently been proposed to interpret FRA data. Nevertheless, these approaches are either complicated or exhibit limited generalization performance due to real-world FRA fault data scarcity. Inspired by AI-generated content (AIGC), this study proposes a data augmentation technique named conditional Wasserstein generative adversarial network with gradient penalty (Conditional-WGAN-GP) combined with fault diagnosis model. Numerous FRA-based data are automatically generated using the proposed data augmentation technique based on real FRA data obtained from a specially designed 10 kV transformer. The augmented dataset is then used to train fault diagnosis models to detect winding deformation faults. The trained fault diagnosis model is subsequently applied to assess two actual transformers. Experimental results demonstrate that when combined with the proposed method, even simpler fault diagnosis models can achieve high accuracy, exhibiting an improvement of approximately 5 % compared to the previous baseline model. The fault diagnosis models combined with the proposed data augmentation technique demonstrate improved generalization and robustness. (GitHub code: https://github.com/cy1034429432/Diagnosing-Transformer-Winding-Deformation-Fault-Types-from-FRA-Based-on-Conditional-WGAN-GP-/tree/main).