Stacked sparse autoencoder based fault detection and location method for modular five-level converters

Yin, Qiaoxuan; Duan, Bin; Shen, Mowei; Qu, Xiangshuai

doi:10.1109/iecon.2017.8216268

Cited by 3 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In such a case, the k-NN, GLM, SVM, and NN are chosen as a suitable method. Nowadays, the RL and deep AE are strived to be utilized for the failure diagnosis and detection of motors [46]- [48], and for the failure detection of switching power supplies [49], however, the number of publications concerned with this application is still few.…”

Section: Detection or Prediction Of Degradation Failure And Abnormalitymentioning

confidence: 99%

“…iii) [60] iv) [46] Auto-encoder -Unsupervised learning is possible -Application is limited iv) [47]- [49] Intelligent Optimization Algorithms GA -Ability to deal with non-linear, non-differentiable, multimodal, combinatorial optimization -Concerns about initial convergence -Strong problem dependence i) [17], [20], [21], [64] ii) [10] iii) [11], [62], [63] PSO -Ability to deal with non-linear, non-differentiable -Concerns about initial convergence -Strong problem dependence ii) [67] iii) [43], [65], [66] Ant Colony Optimization -Ability to deal with non-linear, non-differentiable -Concerns about initial convergence -Strong problem dependence i) [19] Multi-Objective Optimization -Ability to deal with non-linear, non-differentiable, multimodal, combinatorial optimization -Concerns about initial convergence -Strong problem dependence -High calculation cost i) [18] ii) [69] iii) [57], [68] INTERNATIONAL JOURNAL of RENEWABLE ENERGY RESEARCH F. Kurokawa…”

Section: Detection or Prediction Of Degradation Failure And Abnormalitymentioning

confidence: 99%

See 1 more Smart Citation

Recent Research Trends of Artificial Intelligence Applications in Power Electronics

Kurokawa

Tanaka

Furukawa

et al. 2021

IJRER

View full text Add to dashboard Cite

The artificial intelligence (AI) is one of the most significant topics to obtain an optimal solution in various applications. Focusing on the AI applications to the power electronics, this paper presents their tendency and future trend systematically and exhaustively. In the process, IEEE Xplore is chosen for the paper investigation and the result is arranged chronologically. Furthermore, several considerable AI methods for the power electronics, such as the neural network, deep learning, genetic algorithm, particle swarm optimization, and multi-objective optimization, are explained. Several published papers with respect to AI applications to the power electronics in the renewable energy system are also introduced.

show abstract

Section: Detection or Prediction Of Degradation Failure And Abnormalitymentioning

confidence: 99%

Section: Detection or Prediction Of Degradation Failure And Abnormalitymentioning

confidence: 99%

Recent Research Trends of Artificial Intelligence Applications in Power Electronics

Kurokawa

Tanaka

Furukawa

et al. 2021

IJRER

View full text Add to dashboard Cite

show abstract

“…By training the network to disregard inconsequential input ("noise"), the autoencoder establishes a pattern (encoding) for a collection of data, generally for feature extraction. Stacked autoencoders could be used to learn the features of standard samples, and then a support vector machine (SVM) classifier could be used to make the method more accurate [8]. Mahajan et al [9] used a deep neural network to learn about the features of input data and then used an autoencoder to look for anomalies in the data.…”

Section: Introductionmentioning

confidence: 99%

A Metaheuristic Autoencoder Deep Learning Model for Intrusion Detector System

Pandey

Kumar

Lamin

et al. 2022

Mathematical Problems in Engineering

View full text Add to dashboard Cite

A multichannel autoencoder deep learning approach is developed to address the present intrusion detection systems’ detection accuracy and false alarm rate. First, two separate autoencoders are trained with average traffic and assault traffic. The original samples and the two additional feature vectors comprise a multichannel feature vector. Next, a one-dimensional convolution neural network (CNN) learns probable relationships across channels to better discriminate between ordinary and attack traffic. Unaided multichannel characteristic learning and supervised cross-channel characteristic dependency are used to develop an effective intrusion detection model. The scope of this research is that the method described in this study may significantly minimize false positives while also improving the detection accuracy of unknown attacks, which is the focus of this paper. This research was done in order to improve intrusion detection prediction performance. The autoencoder can successfully reduce the number of features while also allowing for easy integration with different neural networks; it can reduce the time it takes to train a model while also improving its detection accuracy. An evolutionary algorithm is utilized to discover the ideal topology set of the CNN model to maximize the hyperparameters and improve the network’s capacity to recognize interchannel dependencies. This paper is based on the multichannel autoencoder’s effectiveness; the fourth experiment is a comparative analysis, which proves the benefits of the approach in this article by correlating it to the findings of various different intrusion detection methods. This technique outperforms previous intrusion detection algorithms in several datasets and has superior forecast accuracy.

show abstract

Fault Diagnosis for Multilevel Converters Based on an Affine-Invariant Riemannian Metric Autoencoder

Zhang

Gao

Zhou

et al. 2023

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Stacked sparse autoencoder based fault detection and location method for modular five-level converters

Cited by 3 publications

References 20 publications

Recent Research Trends of Artificial Intelligence Applications in Power Electronics

Recent Research Trends of Artificial Intelligence Applications in Power Electronics

A Metaheuristic Autoencoder Deep Learning Model for Intrusion Detector System

Fault Diagnosis for Multilevel Converters Based on an Affine-Invariant Riemannian Metric Autoencoder

Contact Info

Product

Resources

About