The effect of intelligent fault diagnosis of mechanical equipment based on data-driven is often premised on big data and class-balance.However,due to the limitation of working environment,operating conditions and equi...The effect of intelligent fault diagnosis of mechanical equipment based on data-driven is often premised on big data and class-balance.However,due to the limitation of working environment,operating conditions and equipment status,the fault data collected by mechanical equipment are often small and imbalanced with normal samples.Therefore,in order to solve the abovementioned dilemma faced by the fault diagnosis of practical mechanical equipment,an auxiliary generative mutual adversarial network(AGMAN)is proposed.Firstly,the generator combined with the auto-encoder(AE)constructs the decoder reconstruction feature loss to assist it to complete the accurate mapping between noise distribution and real data distribution,generate highquality fake samples,supplement the imbalanced dataset to improve the accuracy of small sample class-imbalanced fault diagnosis.Secondly,the discriminator introduces a structure with unshared dual discriminators.Realize the mutual adversarial between the dual discriminator by setting the scoring criteria that the dual discriminator are completely opposite to the real and fake samples,thus improving the quality and diversity of generated samples to avoid mode collapse.Finally,the auxiliary generator and the dual discriminator are updated alternately.The auxiliary generator can generate fake samples that deceive both discriminators at the same time.Meanwhile,the dual discriminator cannot give correct scores to the real and fake samples according to their respective scoring criteria,so as to achieve Nash equilibrium.Using three different test-bed datasets for verification,the experimental results show that the proposed method can explicitly generate highquality fake samples,which greatly improves the accuracy of class-unbalanced fault diagnosis under small sample,especially when it is extremely imbalanced,after using this method to supplement fake samples,the fault diagnosis accuracy of DCNN and SAE are relatively big improvements.So,the proposed method provides an effective solution for small sample class-unbalanced fault diagnosis.展开更多
Improving the generative and representational capabilities of auto-encoders is a hot research topic. However, it is a challenge to jointly and simultaneously optimize the bidirectional mapping between the encoder and ...Improving the generative and representational capabilities of auto-encoders is a hot research topic. However, it is a challenge to jointly and simultaneously optimize the bidirectional mapping between the encoder and the decoder/generator while ensuing convergence. Most existing auto-encoders cannot automatically trade off bidirectional mapping. In this work, we propose Bi-GAE, an unsupervised bidirectional generative auto-encoder based on bidirectional generative adversarial network (BiGAN). First, we introduce two terms that enhance information expansion in decoding to follow human visual models and to improve semantic-relevant feature representation capability in encoding. Furthermore, we embed a generative adversarial network (GAN) to improve representation while ensuring convergence. The experimental results show that Bi-GAE achieves competitive results in both generation and representation with stable convergence. Compared with its counterparts, the representational power of Bi-GAE improves the classification accuracy of high-resolution images by about 8.09%. In addition, Bi-GAE increases structural similarity index measure (SSIM) by 0.045, and decreases Fréchet inception distance (FID) by in the reconstruction of 512*512 images.展开更多
Single-image super-resolution(SISR)typically focuses on restoring various degraded low-resolution(LR)images to a single high-resolution(HR)image.However,during SISR tasks,it is often challenging for models to simultan...Single-image super-resolution(SISR)typically focuses on restoring various degraded low-resolution(LR)images to a single high-resolution(HR)image.However,during SISR tasks,it is often challenging for models to simultaneously maintain high quality and rapid sampling while preserving diversity in details and texture features.This challenge can lead to issues such as model collapse,lack of rich details and texture features in the reconstructed HR images,and excessive time consumption for model sampling.To address these problems,this paper proposes a Latent Feature-oriented Diffusion Probability Model(LDDPM).First,we designed a conditional encoder capable of effectively encoding LR images,reducing the solution space for model image reconstruction and thereby improving the quality of the reconstructed images.We then employed a normalized flow and multimodal adversarial training,learning from complex multimodal distributions,to model the denoising distribution.Doing so boosts the generative modeling capabilities within a minimal number of sampling steps.Experimental comparisons of our proposed model with existing SISR methods on mainstream datasets demonstrate that our model reconstructs more realistic HR images and achieves better performance on multiple evaluation metrics,providing a fresh perspective for tackling SISR tasks.展开更多
False data injection attack(FDIA)is a typical cyber-attack aiming at falsifying measurement data for state estimation(SE),which may incur catastrophic consequences on cyber-physical system operation.In this paper,we d...False data injection attack(FDIA)is a typical cyber-attack aiming at falsifying measurement data for state estimation(SE),which may incur catastrophic consequences on cyber-physical system operation.In this paper,we develop a deep learning based methodology for detection,localization,and data recovery of FDIA on power systems in a coherent and holistic manner.However,the multi-modal probability distributions of both measurements and state variables in SE due to ever-changing operating points and structural/topological changes pose great challenges in detecting and localizing FDIA.To address this challenge,we first propose an enhanced attack model to launch massive FDIA on limited access points.Second,we train an auto-encoder(AE)with a Bayesian change verification(BCV)classifier using N-1 contingencies to detect FDIA with unseen N-k operational topologies.Third,to avoid model collapse caused by multi-modal measurement distribution,an AE-based generative adversarial network(GAN)is derived to generate a diverse candidate set of normal measurement vectors with various operational topologies.Finally,we develop a pattern match algorithm to localize and recover the falsified measurements and state variables by comparing the falsified measurement vectors with the normal measurement vectors in the candidate set.Case studies with IEEE benchmark systems and a modified 415-bus China Southern Grid system are provided to validate the proposed methodology.It shows that the proposed methodology achieves an average 95%accuracy for detection,over 80%accuracy for localization of FDIA,and recovers the measurement and state variables close to their true values.展开更多
基金co-supported by the Special Project of the National Key Research and Development Program of China (No. 2020YFB1709801)the Postgraduate Research and Practice Innovation Program of Jiangsu Province (No. KYCX21_0230)+1 种基金the National Natural Science Foundation of China (No. 51975276)the National Science and Technology Major Project (No. 2017-Ⅳ-0008-0045).
文摘The effect of intelligent fault diagnosis of mechanical equipment based on data-driven is often premised on big data and class-balance.However,due to the limitation of working environment,operating conditions and equipment status,the fault data collected by mechanical equipment are often small and imbalanced with normal samples.Therefore,in order to solve the abovementioned dilemma faced by the fault diagnosis of practical mechanical equipment,an auxiliary generative mutual adversarial network(AGMAN)is proposed.Firstly,the generator combined with the auto-encoder(AE)constructs the decoder reconstruction feature loss to assist it to complete the accurate mapping between noise distribution and real data distribution,generate highquality fake samples,supplement the imbalanced dataset to improve the accuracy of small sample class-imbalanced fault diagnosis.Secondly,the discriminator introduces a structure with unshared dual discriminators.Realize the mutual adversarial between the dual discriminator by setting the scoring criteria that the dual discriminator are completely opposite to the real and fake samples,thus improving the quality and diversity of generated samples to avoid mode collapse.Finally,the auxiliary generator and the dual discriminator are updated alternately.The auxiliary generator can generate fake samples that deceive both discriminators at the same time.Meanwhile,the dual discriminator cannot give correct scores to the real and fake samples according to their respective scoring criteria,so as to achieve Nash equilibrium.Using three different test-bed datasets for verification,the experimental results show that the proposed method can explicitly generate highquality fake samples,which greatly improves the accuracy of class-unbalanced fault diagnosis under small sample,especially when it is extremely imbalanced,after using this method to supplement fake samples,the fault diagnosis accuracy of DCNN and SAE are relatively big improvements.So,the proposed method provides an effective solution for small sample class-unbalanced fault diagnosis.
基金supported by the Program of Technology Innovation of the Science and Technology Commission of Shanghai Municipality under Grant No.21511104700the Artificial Intelligence Technology Support Project of the Science and Technology Commission of Shanghai Municipality under Grant No.22DZ1100103the Shanghai Informatization Development Special Project under Grant No.202001030.
文摘Improving the generative and representational capabilities of auto-encoders is a hot research topic. However, it is a challenge to jointly and simultaneously optimize the bidirectional mapping between the encoder and the decoder/generator while ensuing convergence. Most existing auto-encoders cannot automatically trade off bidirectional mapping. In this work, we propose Bi-GAE, an unsupervised bidirectional generative auto-encoder based on bidirectional generative adversarial network (BiGAN). First, we introduce two terms that enhance information expansion in decoding to follow human visual models and to improve semantic-relevant feature representation capability in encoding. Furthermore, we embed a generative adversarial network (GAN) to improve representation while ensuring convergence. The experimental results show that Bi-GAE achieves competitive results in both generation and representation with stable convergence. Compared with its counterparts, the representational power of Bi-GAE improves the classification accuracy of high-resolution images by about 8.09%. In addition, Bi-GAE increases structural similarity index measure (SSIM) by 0.045, and decreases Fréchet inception distance (FID) by in the reconstruction of 512*512 images.
基金supported by General Project of Guangxi Science and Technology Major Project(AA19254016)Beihai City Science and Technology Planning Project(202082033)+1 种基金Beihai City Science and Technology Planning Project(202082023)Guangxi Graduate Student Innovation Project(YCSW2021174)。
文摘Single-image super-resolution(SISR)typically focuses on restoring various degraded low-resolution(LR)images to a single high-resolution(HR)image.However,during SISR tasks,it is often challenging for models to simultaneously maintain high quality and rapid sampling while preserving diversity in details and texture features.This challenge can lead to issues such as model collapse,lack of rich details and texture features in the reconstructed HR images,and excessive time consumption for model sampling.To address these problems,this paper proposes a Latent Feature-oriented Diffusion Probability Model(LDDPM).First,we designed a conditional encoder capable of effectively encoding LR images,reducing the solution space for model image reconstruction and thereby improving the quality of the reconstructed images.We then employed a normalized flow and multimodal adversarial training,learning from complex multimodal distributions,to model the denoising distribution.Doing so boosts the generative modeling capabilities within a minimal number of sampling steps.Experimental comparisons of our proposed model with existing SISR methods on mainstream datasets demonstrate that our model reconstructs more realistic HR images and achieves better performance on multiple evaluation metrics,providing a fresh perspective for tackling SISR tasks.
基金supported in part by the National Natural Science Foundation of China(No.51767001).
文摘False data injection attack(FDIA)is a typical cyber-attack aiming at falsifying measurement data for state estimation(SE),which may incur catastrophic consequences on cyber-physical system operation.In this paper,we develop a deep learning based methodology for detection,localization,and data recovery of FDIA on power systems in a coherent and holistic manner.However,the multi-modal probability distributions of both measurements and state variables in SE due to ever-changing operating points and structural/topological changes pose great challenges in detecting and localizing FDIA.To address this challenge,we first propose an enhanced attack model to launch massive FDIA on limited access points.Second,we train an auto-encoder(AE)with a Bayesian change verification(BCV)classifier using N-1 contingencies to detect FDIA with unseen N-k operational topologies.Third,to avoid model collapse caused by multi-modal measurement distribution,an AE-based generative adversarial network(GAN)is derived to generate a diverse candidate set of normal measurement vectors with various operational topologies.Finally,we develop a pattern match algorithm to localize and recover the falsified measurements and state variables by comparing the falsified measurement vectors with the normal measurement vectors in the candidate set.Case studies with IEEE benchmark systems and a modified 415-bus China Southern Grid system are provided to validate the proposed methodology.It shows that the proposed methodology achieves an average 95%accuracy for detection,over 80%accuracy for localization of FDIA,and recovers the measurement and state variables close to their true values.
