检索结果-内蒙古大学图书馆

A fault diagnosis method for electric vehicle power lithium battery based on wavelet packet decomposition

JOURNAL OF ENERGY STORAGE 2022年 56卷

作者： Jiang, Jiuchun Zhang, Ruhang Wu, Yutong Chang, Chun Jiang, Yan Hubei Univ Technol Hubei Key Lab High efficiency Utilizat Solar Energ Wuhan 430068 Peoples R China Sunwoda Elect Co Ltd Shenzhen 518108 Peoples R China

This paper proposes a fault diagnosis method for electric vehicle power lithium battery based on wavelet packet decomposition. Firstly, the original voltage signal is decomposed into the low-frequency part and high-frequency part based on wavelet packet decomposition. For the high-frequency part, after filtering the noise using wavelet packet energy noise reduction method, the time domain voltage signal is obtained by wavelet packet recon-struction, and the characteristic parameters reflecting the battery fault are extracted by using sparse autoen-coder;for the low-frequency part, the characteristic parameters reflecting the battery inconsistency are obtained by using singular value decomposition. The similarity between each individual cell and the average cell is then measured using the discrete Fre ' chet distance algorithm. Finally, the outlier detection method based on the Chauvenet criterion is used to detect the faulty cells using the obtained curve similarity. The effectiveness of the proposed method is verified by the data of two thermal runaway vehicles.

关键词： Battery fault diagnosis Wavelet packet decomposition and reconstruction sparse autoencoder Singular value decomposition Discrete Fre ?chet distance Chauvenet criterion

来源：评论

学校读者我要写书评

暂无评论

Unsupervised rotating machinery fault diagnosis method based on integrated SAE-DBN and a binary processor

引用

JOURNAL OF INTELLIGENT MANUFACTURING 2020年第8期31卷 1899-1916页

作者： Li, Jialin Li, Xueyi He, David Qu, Yongzhi Northeastern Univ Sch Mech Engn & Automat Shenyang 110000 Peoples R China Univ Illinois Dept Mech & Ind Engn Chicago IL 60607 USA Univ Minnesota Dept Mech & Ind Engn Duluth MN 55812 USA

In recent years, deep learning based diagnostic approaches have become more attractive. However, most of these methods are supervised diagnostic approaches. Developing a supervised diagnostic model requires a large number of labeled training data. And it is time consuming and labor intensive to obtain labeled data for a variety of systems and working conditions. Therefore, an unsupervised diagnostic model that does not require labeled training data is more desirable. This paper proposes an unsupervised diagnostic model by integrating a sparse autoencoder, a deep belief network, and a binary processor. In comparison with the existing unsupervised methods, the proposed method does not need to perform statistical features extraction, and directly uses the normalized frequency domain signals as the inputs. Moreover, in the proposed diagnostic model, the input data is passed through layer by layer without fine-tuning, which is completely unsupervised process. The proposed methods have been validated with bearing fault datasets and gear pitting fault datasets. The validation results show that the proposed method has a higher accuracy for both bearing and gear pitting fault diagnosis.

关键词： Fault diagnosis sparse autoencoder Deep belief network Bearing fault Gear pitting fault

来源：评论

学校读者我要写书评

暂无评论

A mixed intelligent condition monitoring method for nuclear power plant

引用

ANNALS OF NUCLEAR ENERGY 2020年 140卷 107307-107307页

作者： Peng, Binsen Xia, Hong Ma, Xintong Zhu, Shaomin Wang, Zhichao Zhang, Jiyu Harbin Engn Univ Fundamental Sci Nucl Safety & Simulat Technol Lab Harbin 150001 Peoples R China

Nuclear power plant is a highly safety required system which has multi- operating condition in different power mode, and it requires a more advanced technology to realize condition monitoring. To improve the condition monitoring techniques, a mixed condition monitoring method based on sparse autoencoder and isolation forest is proposed to realize the condition monitoring of nuclear power plant, where sparse autoencoder is responsible for data feature extraction and dimensionality reduction, and isolation forest is responsible for the anomaly monitoring of nuclear power plant. The proposed method can transform high-dimensional data into a low-dimensional space, remove the redundancy of the data, and then identify the state through a high-performance monitoring model, thereby improving monitoring efficiency and accuracy. In order to expound the performance of the condition monitoring model proposed in this paper, we select one operating condition and two operating conditions for testing. We also obtained the condition monitoring results of local outlier factor and one-class support vector machine to compare with our method. From the results, it can be known that sparse autoencoder can extract the nature of operating data, and monitoring accuracy of 100% and 98% can be achieved under one operating condition and two operating conditions by isolation forest method, respectively. Compared with other methods, the proposed method has obvious advantages. This research has important implications for the condition monitoring of nuclear power plant and the system with multi-operating conditions. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： Nuclear power plant Intelligent Condition monitoring sparse autoencoder Isolation forest

来源：评论

学校读者我要写书评

暂无评论

An SAE -based resampling SVM ensemble learning paradigm for pipeline leakage detection

引用

NEUROCOMPUTING 2020年 403卷 237-246页

作者： Wang, Chuang Han, Fei Zhang, Yong Lu, Jingyi Northeast Petr Univ Inst Complex Syst & Adv Control Daqing 163318 Peoples R China Northeast Petr Univ Heilongjiang Prov Key Lab Networking & Intelligen Daqing 163318 Peoples R China Northeast Petr Univ Coll Elect Sci Daqing 163318 Peoples R China

In this paper, an ensemble learning framework combining the sparse autoencoder (SAE) network with an improved support vector machine (SVM) is established to enhance the accuracy of classification in detecting the pipeline leakage. First of all, the SAE network is introduced to extract the discriminative and robust features of the pipeline leakage data. Then, a kind of leader-follower particle swarm optimization (LFPSO) algorithm is put forward to optimize the parameters of the SVM algorithm such that the probability trapping into the local optimum is effectively reduced. Next, the proposed LFPSO-SVM approach is employed to further classify and recognize the features extracted from the pipeline leakage data via the SAE network. Moreover, the performance of the SAE-LFPSO-SVM approach is quantitatively evaluated by three performance indicators, i.e., sensitivity, positive predictive value and total classification accuracy. Finally, some simulation examples are given to demonstrate the effectiveness of the proposed SAE-LFPSO-SVM approach, which exhibits a higher classification accuracy than that of the other traditional classification algorithms. (C) 2020 Published by Elsevier B.V.

关键词： Deep learning Pipeline leakage detection sparse autoencoder Leader-follower Particle swarm optimization Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Enhancing the reliability of protection scheme for PV integrated microgrid by discriminating between array faults and symmetrical line faults using sparse auto encoder

引用

IET RENEWABLE POWER GENERATION 2019年第2期13卷 308-317页

作者： Manohar, Murli Koley, Ebha Ghosh, Subhojit Natl Inst Technol Dept Elect Engn Raipur CG India

The ever increasing power demand and stress on reducing carbon footprint have paved the way for widespread use of photovoltaic (PV) integrated microgrid. However, the development of a reliable protection scheme for PV integrated microgrid is challenging because of the similar voltage-current profile of PV array faults and symmetrical line faults. Conventional protection schemes based on pre-defined threshold setting are not able to distinguish between PV array and symmetrical faults, and hence fail to provide separate controlling actions for the two cases. In this regard, a protection scheme based on sparse autoencoder (SAE) and deep neural network has been proposed to discriminate between array faults and symmetrical line faults in addition to perform mode detection, fault detection, classification and section identification. The voltage-current signals retrieved from relaying buses are converted into grey-scale images and further fed as input to the SAE to perform unsupervised feature learning. The performance of the proposed scheme has been evaluated through reliability analysis and compared with artificial neural network, support vector machine and decision tree based techniques under both islanding and grid-connected mode of the microgrid. The scheme has been also validated for field applications by performing real-time simulations on OPAL-RT digital simulator.

关键词： support vector machines learning (artificial intelligence) decision trees power generation protection power engineering computing neural nets photovoltaic power systems fault diagnosis power generation faults distributed power generation power grids unsupervised learning PV integrated microgrid symmetrical line faults sparse auto encoder photovoltaic integrated microgrid reliable protection scheme similar voltage-current profile PV array faults conventional protection schemes sparse autoencoder fault detection SAE deep neural network approach array faults fault classification fault section identification grey-scale image dataset unsupervised feature learning reliability analysis artificial neural network support vector machine decision tree-based techniques grid-connected mode islanding mode OPAL-RT digital simulator

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Architecture for P300 Detection with Brain-Computer Interface Application

引用

IRBM 2020年第1期41卷 31-38页

作者： Kundu, S. Ari, S. Natl Inst Technol Rourkela Dept Elect & Commun Engn Rourkela 769008 Odisha India

In this paper, a brain-cdmputer interface (BCI) system for character recognition is proposed based on the P300 signal. A P300 speller is used to spell the word or character without any muscle movement. P300 detection is the first step to detect the character from the electroencephalogram (EEG) signal. The character is recognized from the detected P300 signal. In this paper, sparse autoencoder (SAE) and stacked sparse autoencoder (SSAE) based feature extraction methods are proposed for P300 detection. This work also proposes a fusion of deep-features with the temporal features for P300 detection. A SSAE technique extracts high-level information about input data. The combination of SSAE features with the temporal features provides abstract and temporal information about the signal. An ensemble of weighted artificial neural network (EWANN) is proposed for P300 detection to minimize the variation among different classifiers. To provide more importance to the good classifier for final classification, a higher weightage is assigned to the better performing classifier. These weights are calculated from the cross-validation test. The model is tested on two different publicly available datasets, and the proposed method provides better or comparable character recognition performance than the state-of-the-art methods. (C) 2019 AGBM. Published by Elsevier Masson SAS. All rights reserved.

关键词： Brain-computer interface Deep learning P300 sparse autoencoder Stacked sparse autoencoder

来源：评论

学校读者我要写书评

暂无评论

Learning the Structure of Auto-Encoding Recommenders 20

Learning the Structure of Auto-Encoding Recommenders

引用

29th World Wide Web Conference (WWW)

作者： Khawar, Farhan Poon, Leonard Zhang, Nevin L. Hong Kong Univ Sci & Technol Hong Kong Peoples R China Educ Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9781450370233

autoencoder recommenders have recently shown state-of-the-art performance in the recommendation task due to their ability to model non-linear item relationships effectively. However, existing autoencoder recommenders use fully-connected neural network layers and do not employ structure learning. This can lead to inefficient training, especially when the data is sparse as commonly found in collaborative filtering. The aforementioned results in lower generalization ability and reduced performance. In this paper, we introduce structure learning for autoencoder recommenders by taking advantage of the inherent item groups present in the collaborative filtering domain. Due to the nature of items in general, we know that certain items are more related to each other than to other items. Based on this, we propose a method that first learns groups of related items and then uses this information to determine the connectivity structure of an auto-encoding neural network. This results in a network that is sparsely connected. This sparse structure can be viewed as a prior that guides the network training. Empirically we demonstrate that the proposed structure learning enables the autoencoder to converge to a local optimum with a much smaller spectral norm and generalization error bound than the fully-connected network. The resultant sparse network considerably outperforms the state-of-the-art methods like MULT-VAE/MULT-DAE on multiple benchmarked datasets even when the same number of parameters and flops are used. It also has a better cold-start performance.

关键词： Structure Learning Collaborative Filtering sparse autoencoder Wide autoencoder Shallow Networks

来源：评论

学校读者我要写书评

暂无评论

Open-Circuit Fault Diagnosis of Z-Source Inverter via Deep Neural Network

Open-Circuit Fault Diagnosis of Z-Source Inverter via Deep N...

引用

Chinese Automation Congress (CAC)

作者： Song, Baoye Nie, Shiju Li, Xuewen Xu, Lin Shandong Univ Sci & Technol Coll Elect Engn & Automat Qingdao 266590 Shandong Peoples R China

ISBN: (纸本)9781728176871

In this paper, issues of open-circuit fault diagnosis are solved for Z-source-inverter via the deep-sparse-autoencoder, which is one type of the various deep neural networks. Firstly, the preliminary of Z-source-inverter is introduced briefly. On the basis of the introduction of Z-source inverter, MATLAB/Simulink is utilized for the development of the open-circuit fault model of the Z-source inverter, and the output voltages of diverse fault cases are recorded for the training and test of the deep neural network based fault diagnosis. In the end, the superiority and effectiveness of the presented fault diagnosis approach can be verified by several comparisons with other methods on simulation experiments.

关键词： deep neural network sparse autoencoder Z-source inverter open-circuit fault fault diagnosis

来源：评论

学校读者我要写书评

暂无评论

Diabetes detection using deep learning techniques with oversampling and feature augmentation

引用

COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2021年 202卷 105968-105968页

作者： Garcia-Ordas, Maria Teresa Benavides, Carmen Benitez-Andrades, Jose Alberto Alaiz-Moreton, Hector Garcia-Rodriguez, Isaias Univ Leon Escuela Ingenierias Ind & Informat SECOMUCI Res Grp Campus Vegazana S-N Leon 24071 Spain Univ Leon SALBIS Res Grp Dept Elect Syst & Automat Engn Campus Vegazana S-N Leon 24071 Spain

Background and objective : Diabetes is a chronic pathology which is affecting more and more people over the years. It gives rise to a large number of deaths each year. Furthermore, many people living with the disease do not realize the seriousness of their health status early enough. Late diagnosis brings about numerous health problems and a large number of deaths each year so the development of methods for the early diagnosis of this pathology is essential.& nbsp;& nbsp;Methods: In this paper, a pipeline based on deep learning techniques is proposed to predict diabetic peo-ple. It includes data augmentation using a variational autoencoder (VAE), feature augmentation using an sparse autoencoder (SAE) and a convolutional neural network for classification. Pima Indians Diabetes Database, which takes into account information on the patients such as the number of pregnancies, glu-cose or insulin level, blood pressure or age, has been evaluated.& nbsp;Results: A 92 . 31% of accuracy was obtained when CNN classifier is trained jointly the SAE for featuring augmentation over a well balanced dataset. This means an increment of 3.17% of accuracy with respect the state-of-the-art.& nbsp;Conclusions : Using a full deep learning pipeline for data preprocessing and classification has demonstrate to be very promising in the diabetes detection field outperforming the state-of-the-art proposals.& nbsp;(c) 2021 Elsevier B.V. All rights reserved.

关键词： Diabetes Detection Deep learning sparse autoencoder Variational autoencoder Oversampling

来源：评论

学校读者我要写书评

暂无评论

An extreme rainfall-induced landslide susceptibility assessment using autoencoder combined with random forest in Shimane Prefecture, Japan

引用

GEOENVIRONMENTAL DISASTERS 2020年第1期7卷 1-16页

作者： Nam, Kounghoon Wang, Fawu Shimane Univ Dept Earth Sci 1060 Nishikawatsu Cho Matsue Shimane 6908504 Japan

BackgroundLandslide-affecting factors are uncorrelated or non-linearly correlated, limiting the predictive performance of traditional machine learning methods for landslide susceptibility assessment. Deep learning methods can take advantage of the high-level representation and reconstruction of information from landslide-affecting factors. In this paper, a novel deep learning-based algorithm that combine classifiers of both deep learning and machine learning is proposed for landslide susceptibility assessment. A stacked autoencoder (StAE) and a sparse autoencoder (SpAE) both consist of an input layer for raw data, hidden layer for feature extraction, and output layer for classification and prediction. As a study case, Oda City and Gotsu City in Shimane Prefecture, southwestern Japan, were used for susceptibility assessment and prediction of landslides triggered by extreme *** prediction performance was compared by analyzing real landslide and non-landslide data. The prediction performance of random forest (RF) was evaluated as better than that of a support vector machine (SVM) in traditional machine learning, so RF was combined with both StAE and SpAE. The results show that the prediction ratio of the combined classifiers was 93.2% for StAE combined with RF model and 92.5% for SpAE combined with RF model, which were higher than those of the SVM (87.4%), RF (89.7%), StAE (84.2%), and SpAE (88.2%).ConclusionsThis study provides an example of combined classifiers giving a better predictive ratio than a single classifier. The asymmetric and unsupervised autoencoder combined with RF can exploit optimal non-linear features from landslide-affecting factors successfully, outperforms some conventional machine learning methods, and is promising for landslide susceptibility assessment.

关键词： Stacked autoencoder sparse autoencoder Support vector machine Random forest Landslide susceptibility

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：