检索结果-内蒙古大学图书馆

Unsupervised domain adversarial network for few-sample fault detection in industrial processes

ADVANCED ENGINEERING INFORMATICS 2024年 61卷

作者： Fang, Ruiyi Wang, Kai Li, Jing Yuan, Xiaofeng Wang, Yalin Cent South Univ Sch Automat Changsha 410083 Peoples R China Agcy Sci Technol & Res Inst High Performance Comp Singapore Singapore Agcy Sci Technol & Res Ctr Frontier AI Res Singapore Singapore

Industrial processes are evolving to become larger and more integrated, resulting in frequent transitions between different operating conditions. When performing fault detection for processes under new operation conditions, the scarcity of samples poses a significant challenge in constructing effective monitoring models. To address the issue of fault detection with few samples, we propose a method called DASAE. This method is based on a stacked autoencoder (SAE) and incorporates domain adversarial (DA) techniques to model the data-poor target domain (new working mode) by transferring valuable information from a data-rich source domain (historical working mode). DASAE involves a new unsupervised knowledge transfer paradigm that relies on domain similarity without label guidance. In tackling the challenge of data imbalance during adversarial training, we introduce a domain-imbalance-aware-margin Loss (DIAM), which alleviates the problem by encouraging a larger margin for the minority domain. The proposed method is evaluated using both a numerical case and a real-world industry case, the continuous stirred tank reactor (CSTR). The results demonstrate that in few-sample scenarios, the proposed method generally exhibits the best performance compared to other state-of-the-art approaches, showing enhanced detection effectiveness in both T2 and SPE metrics.

关键词： Domain adversarial training Imbalanced data stacked autoencoder Fault detection Few samples

来源：评论

学校读者我要写书评

暂无评论

Forecast the electricity price of US using a wavelet transform-based hybrid model

引用

ENERGY 2020年第0期193卷 511-530页

作者： Qiao, Weibiao Yang, Zhe North China Univ Water Resources & Elect Power Sch Environm & Municipal Engn 136 Jinshui East Rd Zhengzhou 450046 Henan Peoples R China Sinopec Petr Engn Zhongyuan Co Ltd Zhengzhou 450046 Peoples R China Univ Manchester Sch Comp Sci Manchester M13 9PL Lancs England

Wavelet transform (WT), as a data preprocessing algorithm, has been widely applied in electricity price forecasting. However, this deterministic-based algorithm does not present stable performance owing to the experiential selection of its orders and layers. For determining the selection of WTs orders and layers in U.S. electricity prices forecasting, this paper designs a crossover experiment with 240 schemes of WT parameter selection and forecasts each scheme with stacked autoencoder (SAE) and long short-term memory (LSTM), generating a novel hybrid model WT-SAE-LSTM. The results show that the proposed model outperforms other AI models, such as back propagation neural network et al., in forecasting accuracy. The best performance of WT-SAE-LSTM in residential, commercial, and industrial electricity price cases obtained by five order four layers, five order four layers, and four order seven layers, where the MAPE is 0.8606%, 0.4719%, and 0.4956%, respectively. Additionally, the difference between the proposed forecasting model and the forecasting result of Energy Information Administration (U.S.) is small. This paper determines the optimal orders and layers of WT in U.S. electricity prices forecasting, which provides an effective reference for the application of WT in other forecasting scenarios and for electricity market participants. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Electricity price Wavelet transform stacked autoencoder Long short-term memory Forecasting Energy information administration

来源：评论

学校读者我要写书评

暂无评论

Image Co-Saliency Detection: Novel Approaches with Convex Optimization and Deep Neural Networks

Image Co-Saliency Detection: Novel Approaches with Convex Op...

引用

作者： Tsai, Chung-Chi Texas A&M University

The advance of digital technologies has endowed people with easier access to massive collections of image or video data than ever before. For its capability to borrow signal strengths across images or video frames, image co-saliency detection has become an active research topic to help address many advanced computer vision applications, such as image retrieval and object tracking. Co-saliency detection is to distill the essential content of an image group by locating the eye-catching objects commonly present in multiple images. In this dissertation, we present several novel approaches based on convex optimization and deep neural networks for accurate image co-saliency detection. First, we introduce a region-wise saliency map fusion approach to amend the inherent flaw of traditional map-wise fusion methods. The effectiveness of region-wise fusion motivates us to the improved model by integrating segmentation revealed objectness in the following work. Second, we explore the complementary relationship between image co-saliency detection and co-segmentation for higher quality performance on both tasks with scalability to multiple input images. Third, we improved our region-wise fusion scheme by exploring the power of unsupervised deep learning methods by stacked auto-encoder to relax the underlying foreground consistency assumption in most state-of-the-art fusion models. To achieve the desired practical significance, we further combine our stacked autoencoder-enabled fusion with the convolutional neural networks (CNNs). Our proposed two-stage co-saliency detection model can retain the highly discriminative power from the CNNs without the requirement of massive human labeling. Comprehensive experimental results demonstrate its state-of-the-art performance on the publicly available benchmark data sets. We expect solving these issues in image co-saliency detection can lead to significant contributions to the computer vision community for better image understanding and cons

关键词： Co-saliency detection co-segmentation saliency detection image segmentation stacked autoencoder reconstruction residual adaptive fusion optimization self-paced learning CNNs Thesis

来源：评论

学校读者我要写书评

暂无评论

A Novel Algorithm for High-Resolution Magnetic Induction Tomography Based on stacked Auto-Encoder for Biological Tissue Imaging

引用

IEEE ACCESS 2019年 7卷 185597-185606页

作者： Chen, Ruijuan Huang, Juan Wang, Huiquan Li, Bingnan Zhao, Zhe Wang, Jinhai Wang, Yao Tianjin Polytech Univ Sch Life Sci Tianjin 300387 Peoples R China Tianjin Key Lab Optoelect Detect Technol & Syst Tianjin 300387 Peoples R China

Magnetic induction tomography (MIT) is a non-invasive and non-contact imaging method that uses an excitation coil to generate time-varying magnetic fields in space and reconstruct the internal conductivity distribution based on the phase difference. In this study, a new MIT reconstruction algorithm was proposed for non-contact measurement and monitoring of the location of the anomaly in the biomedical object of interest. To reconstruct the distribution of electrical characteristics inside the biological tissue, this technique uses a stacked auto-encoder (SAE) neural network composed of a multi-layer automatic encoder. The location and reconstruction accuracy of the anomaly based on SAE and back-projection were compared, and a hemorrhagic stroke was simulated to verify the practicability of the proposed algorithm. The results showed that the relative error of reconstruction based on the SAE network algorithm reached 0.29%, which improved anomaly reconstruction accuracy and reduced the prediction time to 0.02 s. At the same time, the network was used for the reconstruction of hemorrhagic stroke in different locations, amounts, and shapes. Accordingly, the SAE neural network reconstruction algorithm proposed in this study, which can autonomously learn the non-linear relationship between input and output, can solve the defects of the traditional reconstruction algorithm, such as serious artifacts and complex calculations.

关键词： Electrical conductivity eddy current magnetic induction tomography stacked autoencoder reconstruction algorithm

来源：评论

学校读者我要写书评

暂无评论

SN-SAE: a new damage diagnosis method for CFRP using Lamb wave

引用

MEASUREMENT SCIENCE AND TECHNOLOGY 2023年第9期34卷 095020-095020页

作者： Li, Zhiyong Wang, Zhiyong Li, Yong Han, Shanling Shandong Univ Sci & Technol Coll Mech & Elect Engn Qingdao Peoples R China Binzhou Univ Coll Mech & Elect Engn Binzhou Peoples R China

The damage diagnosis of carbon fiber reinforced polymer (CFRP) using Lamb wave has been widely developed, but it is still a challenging task to obtain reliable damage diagnosis results by analysis of Lamb wave, the emergence of deep learning models provides an effective solution for this work. However, the internal covariate shift and overfitting exist in traditional deep networks. The SN-SAE (stochastic normalization-stacked autoencoder) deep neural network model is proposed by introducing stochastic normalization (SN) into stacked autoencoder (SAE). The signals of 28 different damage locations in the CFRP plate provided by the open platform were processed by SN-SAE, and the damage diagnosis at different locations was achieved. The validity of SN-SAE was further verified by data obtained through building an experimental platform. The results demonstrated that the SN-SAE model can achieve high test accuracy with only 15% of the data samples as training with limited data sample, which provides a simple and effective solution for damage diagnosis of composite plates.

关键词： damage diagnosis carbon fiber reinforced polymer Lamb wave stochastic normalization stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Learning Method for Emotion Charting Using Multimodal Physiological Signals

引用

SENSORS 2022年第23期22卷 9480-9480页

作者： Awan, Amna Waheed Usman, Syed Muhammad Khalid, Shehzad Anwar, Aamir Alroobaea, Roobaea Hussain, Saddam Almotiri, Jasem Ullah, Syed Sajid Akram, Muhammad Usman Bahria Univ Dept Comp Engn Islamabad 44000 Pakistan Air Univ Fac Comp & AI Dept Creat Technol Islamabad 44000 Pakistan Univ West London Sch Comp & Engn London W5 5RF England Taif Univ Coll Comp & Informat Technol Dept Comp Sci POB 11099 Taif 21944 Saudi Arabia Univ Brunei Darussalam Sch Digital Sci Jalan Tungku Link Gadong BE1410 Brunei Univ Agder UiA Dept Informat & Commun Technol N-4898 Grimstad Norway Villanova Univ Dept Elect & Comp Engn Villanova PA 19085 USA Natl Univ Sci & Technol NUST Coll Eletr & Mech Engn E & ME Islamabad 44000 Pakistan

Emotion charting using multimodal signals has gained great demand for stroke-affected patients, for psychiatrists while examining patients, and for neuromarketing applications. Multimodal signals for emotion charting include electrocardiogram (ECG) signals, electroencephalogram (EEG) signals, and galvanic skin response (GSR) signals. EEG, ECG, and GSR are also known as physiological signals, which can be used for identification of human emotions. Due to the unbiased nature of physiological signals, this field has become a great motivation in recent research as physiological signals are generated autonomously from human central nervous system. Researchers have developed multiple methods for the classification of these signals for emotion detection. However, due to the non-linear nature of these signals and the inclusion of noise, while recording, accurate classification of physiological signals is a challenge for emotion charting. Valence and arousal are two important states for emotion detection;therefore, this paper presents a novel ensemble learning method based on deep learning for the classification of four different emotional states including high valence and high arousal (HVHA), low valence and low arousal (LVLA), high valence and low arousal (HVLA) and low valence high arousal (LVHA). In the proposed method, multimodal signals (EEG, ECG, and GSR) are preprocessed using bandpass filtering and independent components analysis (ICA) for noise removal in EEG signals followed by discrete wavelet transform for time domain to frequency domain conversion. Discrete wavelet transform results in spectrograms of the physiological signal and then features are extracted using stacked autoencoders from those spectrograms. A feature vector is obtained from the bottleneck layer of the autoencoder and is fed to three classifiers SVM (support vector machine), RF (random forest), and LSTM (long short-term memory) followed by majority voting as ensemble classification. The propose

关键词： emotion charting EEG signals physiological signals ECG signals ICA stacked autoencoder ensemble classifier

来源：评论

学校读者我要写书评

暂无评论

A Novel Method of Building Functional Brain Network Using Deep Learning Algorithm with Application in Proficiency Detection

引用

INTERNATIONAL JOURNAL OF NEURAL SYSTEMS 2019年第1期29卷 1850015-1850015页

作者： Hua, Chengcheng Wang, Hong Wang, Hong Lu, Shaowen Liu, Chong Khalid, Syed Madiha Northeastern Univ Dept Mech Engn & Automat Shenyang 110819 Liaoning Peoples R China Univ Manchester Control Syst Ctr Manchester Lancs England Northeastern Univ State Key Lab Synthet Automat Proc Ind Shenyang 110189 Liaoning Peoples R China

Functional brain network (FBN) has become very popular to analyze the interaction between cortical regions in the last decade. But researchers always spend a long time to search the best way to compute FBN for their specific studies. The purpose of this study is to detect the proficiency of operators during their mineral grinding process controlling based on FBN. To save the search time, a novel semi-datadriven method of computing functional brain connection based on stacked autoencoder (BCSAE) is proposed in this paper. This method uses stacked autoencoder (SAE) to encode the multi-channel EEG data into codes and then computes the dissimilarity between the codes from every pair of electrodes to build FBN. The highlight of this method is that the SAE has a multi-layered structure and is semi-supervised, which means it can dig deeper information and generate better features. Then an experiment was performed, the EEG of the operators were collected while they were operating and analyzed to detect their proficiency. The results show that the BCSAE method generated more number of separable features with less redundancy, and the average accuracy of classification (96.18%) is higher than that of the control methods: PLV (92.19%) and PLI (78.39%).

关键词： Functional brain connection EEG stacked autoencoder supervised fine-tuning proficiency detection

来源：评论

学校读者我要写书评

暂无评论

A deep neural network approach to QRS detection using autoencoders*,**

引用

EXPERT SYSTEMS WITH APPLICATIONS 2021年 184卷 115528-115528页

作者： Belkadi, Mohamed Amine Daamouche, Abdelhamid Melgani, Farid Univ MHamed Bougara Inst Elect & Elect Engn Signals & Syst Lab Boumerdes 35000 Algeria Univ Trento Dept Informat Engn & Comp Sci I-38123 Trento Italy

Objective: In this paper, a stacked autoencoder deep neural network is proposed to extract the QRS complex from raw ECG signals without any conventional feature extraction phase. Methods: A simple architecture has been deeply trained on many datasets to ensure the generalization of the network at inference. Results: The proposed method achieved a QRS detection accuracy of 99.6% using more than 1042000 beats which is competitive with all state-of-the-art QRS detectors. Moreover, the proposed method produced only 0.82% of Detection Error Rate using six unseen datasets containing more than 1470000 beats. Thus confirms the high performance of our method to detect QRSs. Conclusion: stacked autoencoder neural networks are very effective in QRS detection. At inference, our algorithm processes 1042309 beats in less than 25.32 s. Thus, it is favorably comparable with state-of-the-art deep learning methods. Significance: The stacked autoencoder is an efficient tool for QRS detection, which could replace conventional systems to help practitioners make fast and accurate decisions.

关键词： ECG Deep learning stacked autoencoder QRS detection

来源：评论

学校读者我要写书评

暂无评论

Dynamic historical information incorporated attention deep learning model for industrial soft sensor modeling

引用

ADVANCED ENGINEERING INFORMATICS 2022年 52卷

作者： Wang, Yalin Liu, Diju Liu, Chenliang Yuan, Xiaofeng Wang, Kai Yang, Chunhua Cent South Univ Sch Automat Changsha 410083 Hunan Peoples R China

Due to the limitations of sampling conditions and sampling techniques in many real industrial processes, the process data under different sampling conditions subject to different sampling frequencies, which leads to irregular interval sampling characteristics of the entire process data. The dynamic historical data information reflecting the production status under irregular sampling frequency has an important influence on the performance of data feature extraction. However, the existing soft sensor modeling methods based on deep learning do not consider introducing dynamic historical information into the feature extraction process. To combat this issue, a novel attention-based dynamic stacked autoencoder networks (AD-SAE) for soft sensor modeling is proposed in this paper. First, the sliding window technology and attention mechanism based on position coding are introduced to select dynamic historical samples and calculate the contribution of different historical samples to the current sample, respectively. Then, AD-SAE combines obtained historical sample information and current sample information as the input of the network for deep feature extraction and industrial soft sensor modeling. The experimental results on the actual hydrocracking process data set show that the proposed method has better performance than traditional methods.

关键词： Soft sensor Deep learning stacked autoencoder Attention mechanism AD-SAE

来源：评论

学校读者我要写书评

暂无评论

Explainable and interpretable bearing fault classification and diagnosis under limited data

引用

ADVANCED ENGINEERING INFORMATICS 2024年 62卷

作者： Magadan, L. Ruiz-Carcel, C. Granda, J. C. Suarez, F. J. Starr, A. Univ Oviedo Dept Comp Sci & Engn Gijon 33204 Spain Univ Cranfield Sch Aerosp Transport & Mfg Bedford MK43 0AL England

Rotating machinery plays an essential role in various industrial processes such as manufacturing, power generation, and transportation. These machines, which include turbines, pumps, motors, compressors, and many others, are the heartbeats of numerous industries. The seamless operation of these machines is critical for the efficiency and productivity of these sectors. However, over time, these machines degrade and can suffer faults. One of the most critical components are bearings, which can suffer different types of faults. This paper presents a novel approach for bearing fault classification and diagnosis under limited data. A Monotonic Smoothed stacked autoencoder (MS2AE) is used to infer a smoothed monotonic health index from raw bearing acceleration data. The MS2AE is trained using only healthy data, so this approach can also be used with recently comisioned equipment that has not failed yet. Then, using the evolution of the health index, a first faulty point is computed, so two stages are identified in the lifespan of the rotating machinery: healthy and faulty. Correlation matrices are computed to show the relationship of the health index with time-domain and frequency-domain features in order to provide explainability and validate the health index construction process. When the health index is classified as faulty, Dynamic Time Warping is applied between healthy samples and faulty samples to extract differences. Finally, based on a 1/3-binary tree 3 level kurtogram, these differences are filtered using a bandpass filter and converted to the frequency domain, where characteristic harmonics are used to identify the type of bearing fault. The explainability provided in the health index construction process makes the system useful in certain industries where black-box AI models cannot be trusted due to strict regulations. The classification and diagnosis system achieves robustness in fault classification under different working conditions by utilizing multiple be

关键词： Industry 4.0 Fault diagnosis Fault classification Rotating machinery Dynamic time warping stacked autoencoder Explainable AI

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

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：